Fault prediction method, device, readable storage medium and computer equipment

By building a knowledge graph, comparing the attribute information of user's home appliances with fault attribute information, predicting electrical appliances or components that may have failed, solving the problems of high fault prediction costs and insufficient fault prediction capabilities in the existing technology, and achieving high efficiency , accurate failure prediction.

CN112101666BActive Publication Date: 2024-11-15GREE ELECTRIC APPLIANCE INC OF ZHUHAI +1
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202010977152.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-09-16
Publication Date
2024-11-15
Estimated Expiration
2040-09-16

AI Technical Summary

Technical Problem

In the prior art, the failure prediction cost of household appliances such as air conditioners is high and it is impossible to predict multiple types of failures.

Method used

By constructing a knowledge graph, using a user-centered fault knowledge graph, we compare the similarity between the attribute information of the user's home appliance and the fault attribute information, and predict the electrical appliances or components that may fail.

Benefits of technology

It realizes the prediction of the fault location and cause in advance before the fault occurs, reduces the cost of troubleshooting, and improves the accuracy and efficiency of fault prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112101666B_ABST
    Figure CN112101666B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of fault prediction technology, and in particular to a fault prediction method, apparatus, readable storage medium and computer equipment, the method comprising: constructing a knowledge graph, wherein the knowledge graph comprises a master node and slave nodes connected to the master node, the master node is a user, the slave nodes comprise objects, the objects comprise an electrical appliance corresponding to the user and components corresponding to the electrical appliance; when a first object of the current user fails, obtaining fault attribute information of the first object; calculating a first similarity between attribute information of a first object of a user to be predicted in the knowledge graph and the fault attribute information of the first object; and determining that a first object of a user to be predicted whose first similarity is greater than a first object similarity threshold may fail.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of fault prediction, and in particular to a fault prediction method, device, readable storage medium and computer equipment. Background Art

[0002] Fault prediction is a very important aspect in the failure of home appliances such as air conditioners. Fault prediction means that before a certain part or component fails, it can be predicted that this part may fail in the future, so that consumers or back-end customer service personnel and fault maintenance personnel can be reminded in time, so that technical support can be provided to customers in advance.

[0003] Household appliances such as air conditioners are composed of multiple components. Therefore, in order to ensure the normal operation of household appliances such as air conditioners, it is necessary to monitor and judge the air conditioners and their components to facilitate the detection of possible faults that may occur during the operation of the air conditioners.

[0004] In some technical solutions, the changing trend of the working parameters of the refrigerator within a predetermined time is obtained; and the fault occurrence time corresponding to the changing trend of the working parameters is determined according to a fault time prediction model, wherein the fault time prediction model is obtained through machine learning training using multiple sets of training data, and each set of data in the multiple sets of training data includes: the changing trend of the working parameters and the fault occurrence time corresponding to the changing trend of the working parameters.

[0005] In some technical solutions, a predicted loss curve of a component of an air conditioner whose failure is to be predicted is obtained; loss change data of the component is obtained, and the predicted loss curve is corrected according to the loss change data to obtain a corrected loss curve; and the component failure is predicted according to the corrected loss curve.

[0006] Some technical solutions include basic data modules, big data technology platform layer modules, fault analysis model layer modules and information real-time reflection application layer modules. Based on knowledge graph technology, big data technology is integrated and utilized to diagnose power equipment faults. By adopting open and advanced Internet, big data technology, and Internet of Things technology, a big data power grid library information management application system is constructed to bring professional, intelligent, and intuitive data analysis and mining to fault diagnosis, thereby locating the fault location, determining the cause of the fault, and intelligently generating solutions. This can realize real-time monitoring of the power grid, prediction and early warning analysis, shorten the troubleshooting time, greatly improve the efficiency of troubleshooting power equipment faults, and ensure that the power quickly resumes normal operation.

[0007] However, the technical solutions based on machine learning require a lot of calculations and calibrations, so the cost of this type of solution is relatively high; the method of calculating the predicted loss curve of components is essentially to calculate the running time. This solution can predict the aging of components, but component aging is only one type of component failure, that is, this solution cannot predict other types of component failures.

[0008] Based on the above discussion, it can be seen that the art is in urgent need of a simple technical solution that can predict failures of electrical appliances such as air conditioners and their components. Summary of the invention

[0009] The present invention provides a fault prediction method, device, readable storage medium and computer equipment to solve the technical problems of high cost and inability to predict faults of various causes in the prior art.

[0010] In a first aspect, the present invention provides a fault prediction method, comprising:

[0011] Constructing a knowledge graph, wherein the knowledge graph includes a master node and slave nodes connected to the master node, the master node is a user, the slave nodes include objects, and the objects include an electrical appliance corresponding to the user and components corresponding to the electrical appliance;

[0012] When a first object of the current user fails, obtaining failure attribute information of the first object;

[0013] Calculating a first similarity between attribute information of a first object of a user to be predicted in the knowledge graph and fault attribute information of the first object;

[0014] It is determined that the first object of the to-be-predicted user whose first similarity is greater than a first object similarity threshold may fail.

[0015] In some embodiments, the knowledge graph includes multiple master nodes corresponding to multiple users, and the multiple master nodes are interconnected;

[0016] Each master node is connected to one or more slave nodes corresponding to electrical appliances;

[0017] Each slave node corresponding to an electrical appliance is connected to one or more slave nodes corresponding to components;

[0018] Each slave node corresponding to an object is connected to a slave node corresponding to the attribute information of the object.

[0019] In some embodiments, the electrical appliances include air conditioners, washing machines and refrigerators; the components include resistors, inductors, capacitors, motors and circuit boards.

[0020] In some embodiments, the attribute information includes one or more of voltage, current, temperature, and power on / off times.

[0021] In some embodiments, the method further comprises:

[0022] Fault reminder information is generated and sent to a user corresponding to the first object that may have a fault.

[0023] In some embodiments, calculating a first similarity between attribute information of a first object of a user to be predicted in the knowledge graph and fault attribute information of the first object includes:

[0024] Compare each attribute information of the first object of the user to be predicted in the knowledge graph with each fault attribute information of the first object, and determine whether each attribute information is the same as each fault attribute information;

[0025] Calculate the proportion of the number of attribute information that is the same as the fault attribute information in the total number of attribute information, and use the proportion as the first similarity between the attribute information of the first object of the user to be predicted in the knowledge graph and the fault attribute information of the first object.

[0026] In some embodiments, the method further includes: determining a first object similarity threshold; the first object similarity threshold is determined as follows:

[0027] Collecting historical fault attribute information of the first object in the knowledge graph;

[0028] The second similarity between the historical fault attribute information of every two first objects in the knowledge graph is calculated, and the average value of all the second similarities is taken as the similarity threshold of the first object.

[0029] In a second aspect, the present invention further provides a fault prediction device, comprising:

[0030] A knowledge graph construction module, which is used to construct a knowledge graph, wherein the knowledge graph includes a master node and slave nodes connected to the master node, the master node is a user, the slave nodes include objects, and the objects include electrical appliances corresponding to the users and components corresponding to the electrical appliances;

[0031] A fault prediction module is used to obtain fault attribute information of the first object when a fault occurs in the first object of the current user; calculate the first similarity between the attribute information of the first object of the user to be predicted in the knowledge graph and the fault attribute information of the first object; and determine that the first object of the user to be predicted whose first similarity is greater than the first object similarity threshold may have a fault.

[0032] In a third aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method described in the first aspect.

[0033] In a fourth aspect, the present invention further provides a computer device, comprising a processor and a memory, wherein a computer program is stored in the memory, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0034] The present invention provides a fault prediction method, device, readable storage medium and computer equipment, which construct a fault knowledge graph and perform fault prediction based on the fault knowledge graph, so that the location and cause of the fault can be known in advance before the fault occurs. That is, by constructing a user-centric fault knowledge graph and comparing the similarity of the relationship between each user's home electrical appliance in the knowledge graph, the problem of electrical appliance fault prediction in the user's home is solved, and the following beneficial effects are achieved: customer service personnel or users can predict the electrical appliances or components that may fail in advance before the electrical appliances fail. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The present invention will be described in more detail below based on embodiments and with reference to the accompanying drawings:

[0036] Figure 1 A schematic diagram of a flow chart of a fault prediction method provided by an embodiment of the present invention;

[0037] Figure 2 A schematic diagram of a knowledge graph provided by an embodiment of the present invention;

[0038] Figure 3 A structural block diagram of a fault prediction device provided by an embodiment of the present invention;

[0039] Figure 4 A structural block diagram of a computer device provided in an embodiment of the present invention.

[0040] In the drawings, the same reference numerals are used for the same components, and the drawings are not drawn to scale. DETAILED DESCRIPTION

[0041] In order to enable those skilled in the art to better understand the scheme of the present invention, and to fully understand and implement how the present invention applies technical means to solve technical problems and achieve the corresponding technical effects, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only an embodiment of a part of the present invention, not all of the embodiments. The embodiments of the present invention and the various features in the embodiments can be combined with each other without conflict, and the technical schemes formed are all within the scope of protection of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present invention.

[0042] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0043] According to an embodiment of the present invention, a method embodiment of a fault prediction method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0044] Embodiment 1

[0045] This embodiment provides a fault prediction method. Figure 1 A schematic diagram of a fault prediction method provided by an embodiment of the present invention. Figure 1 As shown, a fault prediction method includes:

[0046] Step S100, constructing a knowledge graph, wherein the knowledge graph includes a master node and slave nodes connected to the master node, the master node is a user, the slave nodes include objects, and the objects include an electrical appliance corresponding to the user and components corresponding to the electrical appliance;

[0047] Step S200, when a first object of the current user fails, the failure attribute information of the first object of the current user is obtained; it can be understood that the first object is any electrical appliance corresponding to the current user.

[0048] Step S300, calculate the first similarity between the attribute information of the first object of the user to be predicted in the knowledge graph and the fault attribute information of the first object of the current user; wherein, the user to be predicted is any user other than the current user in the knowledge graph, and by comparing the attribute information of the same object of the user to be predicted with the fault attribute, the possibility of failure of the same object in the knowledge graph can be determined.

[0049] Step S400: Determine that a first object of a user to be predicted whose first similarity is greater than a first object similarity threshold may fail.

[0050] This embodiment solves the problem of predicting electrical appliance failures in users' homes by constructing a knowledge graph with users as main nodes and users' electrical appliances and components of electrical appliances as slave nodes, and performing fault prediction based on the knowledge graph, so that customer service personnel or users can predict electrical appliances or components that may fail in advance before the appliances fail.

[0051] Specifically, when the attribute information of the first object of one or several users to be predicted in the knowledge graph reaches a certain degree of similarity with the fault attribute information corresponding to the fault of the first object of the current user, it means that the attribute information meets the characteristics of the fault information, and the first object corresponding to the attribute information also has the risk of failure, and it is predicted that the first object may fail.

[0052] Specifically, when the first object of the current user, such as an air conditioner, fails, the attribute information of the air conditioner is obtained and updated to the knowledge graph. On this basis, the air conditioners of other users are predicted, that is, the similarity between the attribute information of the air conditioner of the user to be predicted in the knowledge graph and the fault attribute information of the faulty air conditioner is calculated as the first similarity, and it is determined that the air conditioner whose first similarity is greater than the first object similarity threshold is about to fail.

[0053] Embodiment 2

[0054] Figure 2 A schematic diagram of a knowledge graph provided by an embodiment of the present invention. Figure 2 As shown, the knowledge graph includes multiple main nodes corresponding to multiple users, and the multiple main nodes are connected to each other;

[0055] Each master node is connected to one or more slave nodes corresponding to electrical appliances;

[0056] Each slave node corresponding to an electrical appliance is connected to one or more slave nodes corresponding to components;

[0057] Each slave node corresponding to an object is connected to a slave node corresponding to the attribute information of the object.

[0058] The electrical appliances include air conditioners, washing machines and refrigerators; the components include resistors, inductors, capacitors, motors and circuit boards. The attribute information includes one or more of voltage, current, temperature and power on / off times.

[0059] The knowledge graph is a user-centric knowledge graph, that is, for each additional user, there will be an additional user node as the master node, and the appliances in the user's home will also be slave nodes of this node. Users can be connected to each other (for example, user 1, user 2, and user 3 are connected), and the appliances corresponding to the users can be connected to the components corresponding to the appliances. There is no need to connect appliances of different users, different appliances of the same user, and different components of the same appliance. The attribute information of appliances and components is connected to the appliances and components respectively.

[0060] This embodiment constructs the skeleton of the knowledge graph by setting a main node for each user, and connects one or more appliances to the main node as the skeleton based on the relationship between the user and his / her home appliances, connects one or more components to the appliances, and connects one or more attributes to the appliances or components as slave nodes.

[0061] In this embodiment, the construction process of the knowledge graph is as follows:

[0062] First, each user is included in the knowledge graph as a master node, and then all the appliances in the user's home are included in the knowledge graph as slave nodes. The appliances may include but are not limited to air conditioners, washing machines and refrigerators; the components may include but are not limited to resistors, inductors, capacitors, motors and circuit boards. The attribute information may include but is not limited to one or more of voltage, current, temperature and the number of times the machine is turned on and off. Figure 2 In the example above, only the air conditioner is used as an electrical appliance. In actual applications, the electrical appliance can also be a washing machine, a refrigerator or other household appliances. Similar to building a knowledge graph based on air conditioners, you can just replace "air conditioner" with "washing machine" and other household appliances when building the knowledge graph.

[0063] Then, the current and voltage corresponding to the air conditioner are written into the knowledge graph as the attribute information of the air conditioner as a slave node. For example, the current and voltage corresponding to the air conditioner are expressed in ranges, with a current range of 10A to 12A and a voltage range of 220V to 230V. Each component in the air conditioner (for example, component 1, component 2) is a slave node corresponding to the air conditioner, and the current and voltage corresponding to the component are also written into the knowledge graph as the attribute information of the component. On this basis, the attribute information of "damage time" can be recorded by electricians or after-sales service personnel. Each time the appliance or the component corresponding to the appliance is damaged, it is recorded once in the attribute information of "damage time", for example: "Damage on 2020-1-1". It is understandable that the attribute information of "damage time" can also be recorded by the appliance itself.

[0064] Through the knowledge graph constructed in this embodiment, when an object (electrical appliance or component) of any user in the knowledge graph fails, the attribute information of the same object in the knowledge graph can be compared with the attribute information of the faulty object, and the same objects in the knowledge graph that may fail can be identified, and then the user corresponding to the object that may fail can be determined based on the correspondence between users and objects determined by the knowledge graph.

[0065] Embodiment 3

[0066] Based on the above embodiment, the method further includes:

[0067] Step S500: Generate fault reminder information, which is sent to a user corresponding to the first object that may have a fault. The fault reminder information may be in text form or in voice broadcast form, which is not limited in this embodiment.

[0068] Taking the air conditioner as an example, when the current user's air conditioner breaks down, the attribute information of the air conditioner is obtained, and the attribute information of the air conditioner is updated in the knowledge graph. On this basis, fault prediction is performed on the air conditioners of other users, that is, the similarity between the attribute information of the air conditioner of the user to be predicted in the knowledge graph and the fault attribute information of the faulty air conditioner is calculated as the first similarity, and it is determined that the air conditioner whose first similarity is greater than the first object similarity threshold may break down. At this time, fault reminder information is generated, and the fault reminder information is sent to the terminal device of the user corresponding to the air conditioner that may break down, so that the customer service staff or the user can predict the appliances or components that may break down in advance before the appliances or components break down.

[0069] Embodiment 4

[0070] Based on the above embodiment, the step S300 of calculating the first similarity between the attribute information of the first object of the user to be predicted in the knowledge graph and the fault attribute information of the first object may further include the following sub-steps:

[0071] Step S301, comparing each attribute information of the first object of the user to be predicted in the knowledge graph with each fault attribute information of the first object, and determining whether each attribute information is the same as each fault attribute information;

[0072] Step S302, calculate the proportion of the number of attribute information that is the same as the fault attribute information in the total number of attribute information, and use the proportion as the first similarity between the attribute information of the first object of the user to be predicted in the knowledge graph and the fault attribute information of the first object.

[0073] For example, assuming that the first component of the first user's air conditioner is damaged, the maintenance personnel repairs the first component of the first user's air conditioner and records the fault attribute information. At this time, the background server obtains the attribute information of the first component of the first user's air conditioner when it is damaged, including: the current range is 15A~17A, the voltage range is 180V~190V, the temperature is 30 degrees~40 degrees, and the number of times the machine is turned on and off in a day is 38 times. Based on the solution of the present invention, the knowledge graph is searched and the similarity of the attributes of the first component of the air conditioner of each user to be predicted and the first component of the air conditioner of the first user is analyzed. If the similarity exceeds the component similarity threshold, it is predicted that the first component of the air conditioner of the user to be predicted may be damaged, the corresponding user is reminded, and relevant maintenance personnel can be arranged to visit for re-inspection.

[0074] As to how to quantitatively measure the similarity of the attribute information of the first components of the air conditioners of two users, this embodiment is described as follows based on the above example.

[0075] Assume that the same attributes of the first components of the air conditioners of two users are: attribute A, attribute B, attribute C and attribute D, and the different attributes are: attribute E and attribute F, then the first similarity of the first components of the air conditioners of the two users is (1+1+1+1) / (1+1+1+1+1+1+1)=4 / 6. In this case, the similarity of the attributes of the first components of the air conditioners of the two users can be measured by setting a threshold for the first components. If the similarity of the two first components is greater than the threshold, it means that the attributes of the first components of the air conditioners of the two users are highly similar, that is, if the first component of the air conditioner of one user is damaged, the first component of the air conditioner of the other user may also be damaged soon.

[0076] Regarding how to determine whether two attributes are the same, this embodiment provides the following description based on the above example.

[0077] Since electrical appliances such as air conditioners have multiple attributes, voltage is used as an example for explanation. When determining whether the attribute information of each item is the same, the following method can be used in this embodiment:

[0078] Method 1, record the voltage value of the air conditioner, and divide the voltage value into the range to which it belongs. If the voltage values ​​of the two air conditioners fall into the same range, the voltage values ​​of the two air conditioners are considered to be the same. For example, the range can be divided with 220V as the center and 5V as the step unit on both sides, that is, 210V to 215V is a voltage range, 215V to 220V is a voltage range, 220V to 225V is a voltage range, and 225V to 230V is a voltage range. If the voltage value of air conditioner A is 221V and the voltage value of air conditioner B is 224V, the voltage values ​​of the two air conditioners are considered to be the same; if the voltage value of air conditioner A is 224V and the voltage value of air conditioner B is 226V, the voltage values ​​of the two air conditioners are considered to be different. In this method, by judging whether the attribute value of the object (electrical appliance or component) is within the numerical range determined according to the fault attribute information, it is judged whether the attribute information is the same, which not only takes into account the value fluctuation or error of the attribute information, but also can accurately judge whether the attribute information between the two objects is the same.

[0079] Method 2, whether the ratio of the absolute value of the difference between the two attribute information and the smaller value of the two attribute information is less than a threshold value, such as 0.01, to determine whether the two attribute information are the same. If the ratio is less than the threshold value, the two attribute information are judged to be the same, and if the ratio is not less than the threshold value, the two attribute information are judged to be different. For example, if the voltage value of air conditioner A is 221V and the voltage value of air conditioner B is 224V, since (224-221) / 221=0.013, this value is greater than the threshold value 0.01, it is considered that the voltage values ​​of the two air conditioners are different, that is, it is judged that the voltage attribute information of the two air conditioners is different; if the voltage value of air conditioner A is 224V and the voltage value of air conditioner B is 226V, since (226-224) / 224=0.009, this value is less than the threshold value 0.01, it is considered that the voltage values ​​of the two air conditioners are the same, that is, it is judged that the voltage attribute information of the two air conditioners is the same. In this method, whether the voltage attributes of the two air conditioners are the same is determined by judging whether the absolute value of the difference between the voltage attribute values ​​of the two air conditioners and the ratio of the smaller value of the two voltage attribute values ​​is less than a threshold value, such as 0.01, thereby avoiding the technical problem that voltage attribute values ​​with similar values ​​are judged as different while voltage attribute values ​​with different values ​​are judged as the same, thereby achieving the technical effect of improving the accuracy of judgment.

[0080] In addition, the present invention may also adopt a method of directly rounding and comparing the numerical values ​​of the attribute information, thereby avoiding the calculation and storage of floating point numbers in the computer, thereby saving computing resources and storage resources.

[0081] Embodiment 5

[0082] Based on the above embodiment, a first object similarity threshold is determined; the first object similarity threshold is determined as follows:

[0083] Collecting historical fault attribute information of the first object in the knowledge graph;

[0084] The second similarity between the historical fault attribute information of every two first objects in the knowledge graph is calculated, and the average value of all the second similarities is taken as the similarity threshold of the first object.

[0085] Specifically, taking the first object as an example, the attribute information of the air conditioners that have failed for each user in the knowledge graph is counted, that is, the historical fault attribute information of the air conditioners that have failed in the knowledge graph is counted, and the first similarity between the attribute information of every two air conditioners that have failed is calculated as the second similarity, and the average of all second similarities is used as the similarity threshold of the air conditioner. That is, the attributes of the air conditioners of all users in the entire knowledge graph when they are damaged (that is, the historical fault attribute information) are calculated. Assuming that there are 10 users whose air conditioners are damaged, the similarities between the attribute information of the 10 air conditioners are calculated, and then these similarities are averaged. The average similarity is the similarity threshold of the air conditioner. The similarity thresholds of other objects in the knowledge graph can be determined in this way.

[0086] In addition, if the number of faulty air conditioners in the knowledge graph is large, for example, more than 100, the attribute information of 100 faulty air conditioners is selected to obtain the similarity threshold of the air conditioners, thereby achieving the technical effect of saving computing resources.

[0087] Embodiment 6

[0088] This embodiment provides a fault prediction device. Figure 3 A structural block diagram of a fault prediction device provided in an embodiment of the present invention.

[0089] like Figure 3 As shown, a fault prediction device comprises:

[0090] A knowledge graph construction module, which is used to construct a knowledge graph, wherein the knowledge graph includes a master node and slave nodes connected to the master node, the master node is a user, the slave nodes include objects, and the objects include electrical appliances corresponding to the users and components corresponding to the electrical appliances;

[0091] A fault prediction module is used to obtain fault attribute information of the first object when a fault occurs in the first object of the current user; calculate the first similarity between the attribute information of the first object of the user to be predicted in the knowledge graph and the fault attribute information of the first object; and determine that the first object of the user to be predicted whose first similarity is greater than the first object similarity threshold may have a fault.

[0092] The present invention constructs a knowledge graph with users as main nodes and users' electrical appliances and components of electrical appliances as slave nodes through a knowledge graph construction module, and then uses a fault prediction module to perform fault prediction based on the knowledge graph, thereby solving the problem of electrical appliance fault prediction in users' homes, allowing customer service personnel or users to predict electrical appliances or components that may fail in advance before the electrical appliances fail.

[0093] Specifically, when the first object of the current user, such as an air conditioner, fails, the attribute information of the air conditioner is obtained and updated to the knowledge graph. On this basis, the air conditioners of other users are predicted, that is, the similarity between the attribute information of the air conditioner of the user to be predicted in the knowledge graph and the fault attribute information of the faulty air conditioner is calculated as the first similarity, and it is determined that the air conditioner whose first similarity is greater than the first object similarity threshold may fail.

[0094] Embodiment 7

[0095] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method described in the above embodiment is implemented.

[0096] The above-mentioned storage media can be flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, CD, server, App application store, etc.

[0097] Embodiment 8

[0098] This embodiment provides a computer device, Figure 4 A structural block diagram of a computer device provided in an embodiment of the present invention.

[0099] like Figure 4 As shown, this embodiment provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor implements the method described in the above embodiment when executing the computer program.

[0100] The processor can be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components, and is used to execute the electric kettle water level detection method in the above-mentioned embodiment 1.

[0101] The memory can be implemented by any type of volatile or non-volatile storage device or a combination of them, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0102] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0103] It should be noted that, in the present invention, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0104] Although the embodiments disclosed in the present invention are as above, the above contents are only embodiments adopted for facilitating the understanding of the present invention and are not intended to limit the present invention. Any technician in the technical field to which the present invention belongs can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present invention, but the patent protection scope of the present invention shall still be subject to the scope defined in the attached claims.

Claims

1. A fault prediction method, It is characterized in that include: Constructing a knowledge graph including a user master node and object slave nodes connected to the user master node, wherein the user master nodes are connected to each other, wherein the object slave nodes include an electrical appliance slave node corresponding to the user and a component slave node corresponding to the electrical appliance; When a first object of the current user's primary node in the knowledge graph fails, obtaining fault attribute information of the first object; Searching for a user main node to be predicted connected to the current user main node in the knowledge graph, comparing each attribute information of the first object of the user to be predicted in the knowledge graph with each fault attribute information of the first object, and determining whether each attribute information is the same as each fault attribute information; calculating the proportion of the number of attribute information that is the same as the fault attribute information in the total number of attribute information, and using the proportion as the first similarity between the attribute information of the first object of the user to be predicted in the knowledge graph and the fault attribute information of the first object; Determine that a first object of the to-be-predicted user master node whose first similarity is greater than a first object similarity threshold may fail; Fault reminder information is generated and sent to a user corresponding to the first object that may have a fault.

2. The method according to claim 1, It is characterized in that Each user master node is connected to one or more electrical slave nodes; Each electrical slave node is connected to one or more component slave nodes; Each object slave node is connected to an attribute slave node corresponding to the attribute information of the object.

3. The method according to claim 1, It is characterized in that The electrical appliances include air conditioners, washing machines and refrigerators; the components include resistors, inductors, capacitors, motors and circuit boards.

4. The method according to claim 1, It is characterized in that The attribute information includes one or more of voltage, current, temperature, and power on / off times.

5. The method according to claim 1, It is characterized in that The method further includes: determining a first object similarity threshold; the first object similarity threshold is determined as follows: Collecting historical fault attribute information of the first object in the knowledge graph; The second similarity between the historical fault attribute information of every two first objects in the knowledge graph is calculated, and the average value of all the second similarities is taken as the similarity threshold of the first object.

6. A fault prediction device based on any one of the fault prediction methods of claims 1 to 5, It is characterized in that include: A knowledge graph construction module, which is used to construct a knowledge graph including a user master node and object slave nodes connected to the user master node, wherein the user master nodes are connected to each other, wherein the object slave nodes include an electrical appliance slave node corresponding to the user and a component slave node corresponding to the electrical appliance; A fault prediction module is used to obtain fault attribute information of the first object of the current user main node in the knowledge graph when the first object of the first object fails; find the user main node to be predicted connected to the current user main node in the knowledge graph, calculate the first similarity between the attribute information of the first object of the user main node to be predicted in the knowledge graph and the fault attribute information of the first object; determine that the first object of the user main node to be predicted whose first similarity is greater than the first object similarity threshold may fail; generate fault reminder information, and send the fault reminder information to the user corresponding to the first object that may fail.

7. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the fault prediction method according to any one of claims 1 to 5 is implemented.

8. A computer device comprising a processor and a memory, It is characterized in that The memory stores a computer program, and the processor implements the fault prediction method according to any one of claims 1 to 5 when executing the computer program.

Citation Information

Patent Citations

  • Fault prediction method and device, storage medium and electronic equipment

    CN110349289A

  • Household appliance fault prediction method and prediction device, refrigerator and storage medium

    CN111126632A

  • Equipment predictive maintenance method and device

    CN111563606A

  • Operation management system, monitoring server, method and program

    JP2019057139A

  • Artificial intelligence based risk and knowledge management

    US20190197442A1