Detection Method for Trend Issues of Air Conditioners and Electronic Devices

Abstract

The present disclosure provides a method for detecting trending problems of an air conditioner and an electronic device. The method includes: for any air conditioner to be detected, obtaining multiple sets of air conditioner status data of the air conditioner to be detected at specified time intervals, where the multiple sets of status data are air conditioner status data corresponding to different times; and obtaining target air conditioner status data of the air conditioner to be detected based on the multiple sets of air conditioner status data; determining each target recalled air conditioner among the detected air conditioners and the confidence level of each target recalled air conditioner according to the target air conditioner status data of each air conditioner to be detected; and performing clustering analysis on the target recalled air conditioners through the confidence levels of the target recalled air conditioners to obtain the level of the trending problems of the target recalled air conditioners. Therefore, by determining the level of the trending problems of the air conditioner, the present disclosure avoids the situation where an alarm is triggered only when a very serious problem occurs in the air conditioner, and improves the accuracy of detecting the trending problems of the air conditioner.

Description

Background Art

[0002] The trending problems of air conditioners refer to the problems that will inevitably occur gradually as the usage time of air conditioners increases. Among them, the trending problems of air conditioners include refrigerant leakage, dirt blockage, etc. Trending problems do not belong to air conditioner failures, and it is difficult to formulate a unified evaluation standard. When such trending problems are serious, they not only affect the service life of air conditioner equipment, increase power consumption, but also affect the user experience, and may even affect the physical and mental health of users.

[0003] Currently, the methods for detecting the trending problems of air conditioners are mainly completed by detecting the status of the air conditioner equipment end. When analyzing whether the air conditioner equipment reaches a certain critical value through the compressor frequency and exhaust temperature of the air conditioner equipment, it is only when the critical value is reached that it can be determined that the air conditioner has trending problems. For example, when the refrigerant retention reaches 20%, a fault is reported. This solution needs to set the critical value low enough to ensure that the detection method has high accuracy. However, a low critical value means that the user's air conditioner equipment has been working in a "sub-healthy" state for a period of time, that is, the existing status detection method only alarms when the problem is very serious. Therefore, the accuracy of the detection method for the trending problems of air conditioners in the prior art is low. Summary of the Invention

[0004] In an exemplary embodiment of the present disclosure, a method for detecting the trending problems of an air conditioner and an electronic device are provided, which avoid the situation of alarming only when very serious problems occur in the air conditioner by determining the level of the trending problems of the air conditioner, and improve the accuracy of detecting the trending problems of the air conditioner.

[0005] A first aspect of the present disclosure provides a method for detecting the trending problems of an air conditioner, the method comprising:

[0006] For any air conditioner to be detected, at regular intervals, obtain multiple groups of air conditioner status data of the air conditioner to be detected, where the multiple groups of status data are air conditioner status data corresponding to different times; and,

[0007] Based on the multiple groups of air conditioner status data, obtain the target air conditioner status data of the air conditioner to be detected;

[0008] According to the target air conditioner status data of each air conditioner to be detected, determine each target recalled air conditioner among the detected air conditioners and the confidence level of each target recalled air conditioner;

[0009] Perform cluster analysis on each target recalled air conditioner through the confidence level of each target recalled air conditioner to obtain the level of the trending problems of each target recalled air conditioner.

[0010] In this embodiment, the target air conditioner state data of the air conditioner to be detected is determined through multiple groups of air conditioner state data of the air conditioner to be detected. Then, according to the target air conditioner state data of each air conditioner to be detected, each target recalled air conditioner among the detected air conditioners and the confidence level of each target recalled air conditioner are determined. Finally, cluster analysis is performed on each target recalled air conditioner through the confidence level of each target recalled air conditioner to obtain the level of the trending problem of each target recalled air conditioner. Thus, in this embodiment, the level of the trending problem of the air conditioner can be determined, avoiding the situation where an alarm is issued only when a very serious problem occurs with the air conditioner, and improving the accuracy of detecting the trending problem of the air conditioner.

[0011] In one embodiment, any group of air conditioner state data includes time, on / off state, compressor discharge temperature, outdoor condenser temperature, indoor pipe temperature value, indoor temperature, outdoor temperature, indoor set temperature, compressor set power, and compressor actual power.

[0012] Obtaining the target air conditioner state data of the air conditioner to be detected based on the multiple groups of air conditioner state data includes:

[0013] For any air conditioner to be detected, based on the multiple groups of on / off states of the air conditioner to be detected and the time corresponding to the multiple groups of on / off states, the total usage duration of the air conditioner to be detected is obtained, where the total usage duration is used to represent the total usage duration of the air conditioner to be detected within a specified time period; and,

[0014] When the air conditioner to be detected is in the cooling mode, then based on multiple groups of the compressor discharge temperature and multiple groups of the outdoor condenser temperature, target superheat data is obtained; or, when the air conditioner to be detected is in the heating mode, then based on multiple groups of the compressor discharge temperature and multiple groups of the indoor pipe temperature, the target superheat data is obtained; and,

[0015] Based on multiple groups of the indoor temperature and multiple groups of the indoor pipe temperature values, target indoor heat exchange temperature difference data is obtained; and,

[0016] Through multiple groups of the outdoor condenser temperature and multiple groups of the outdoor temperature, target outdoor heat exchange temperature difference data is obtained; and,

[0017] Using multiple groups of the indoor temperature and multiple groups of the indoor set temperature, target set temperature difference data is obtained; and,

[0018] Based on multiple groups of the compressor set power and multiple groups of the compressor actual power, target power gap data is obtained;

[0019] Determine the total usage duration, the target exhaust superheat data, the target indoor heat exchange temperature difference data, the target outdoor heat exchange temperature difference data, the target set temperature difference data, and the target power gap data as the target air conditioner state data.

[0020] In this embodiment, the target air conditioner state data is determined based on multiple sets of air conditioner state data of each air conditioner to be detected. Since the usage durations of different air conditioners to be detected are different, the recorded quantities of the air conditioner state data of each air conditioner to be detected vary greatly. Therefore, in this embodiment, the multiple sets of air conditioner state data of each air conditioner to be detected are processed to make the formats of the air conditioner state data of each air conditioner to be detected unified, which is convenient for subsequent processing and calculation, and further improves the detection efficiency of the trend problems of the air conditioner.

[0021] In one embodiment, the obtaining of the total usage duration of the air conditioner to be detected based on multiple sets of on / off states of the air conditioner to be detected and the times corresponding to the multiple sets of on / off states includes:

[0022] Traverse each time in ascending order of time. For any traversed time, perform the following steps:

[0023] If the on / off state corresponding to the time is the on state and the on / off state of the time immediately following the time is the on state, then determine the difference between the time and the time immediately following the time as the intermediate on duration;

[0024] Otherwise, determine the intermediate on duration corresponding to the time as the preset duration;

[0025] Add up the determined intermediate on durations to obtain the total usage duration of the air conditioner to be detected.

[0026] In this embodiment, the total usage duration of the air conditioner to be detected is determined based on the on state and the corresponding time, thereby ensuring the accuracy of the determined total usage duration of the air conditioner to be detected.

[0027] In one embodiment, when the air conditioner to be detected is in the cooling mode, the obtaining of the target exhaust superheat data based on multiple sets of the compressor exhaust temperature and multiple sets of the outdoor condenser temperature includes:

[0028] For any set of air conditioner state data, subtract the outdoor condenser temperature from the compressor exhaust temperature in the air conditioner state data to obtain the exhaust superheat data, and determine the variance, mean, and quantity of the multiple sets of exhaust superheat data of the air conditioner to be detected as the target exhaust superheat data;

[0029] When the air conditioner to be detected is in the heating mode, the target superheat data is obtained according to multiple groups of the compressor exhaust temperature and multiple groups of the indoor pipe temperature, including:

[0030] For any group of air conditioner status data, subtract the compressor exhaust temperature in the air conditioner status data from the indoor pipe temperature to obtain the superheat data, and determine the variance, mean, and the number of multiple groups of the superheat data of the air conditioner to be detected as the target superheat data;

[0031] The target indoor heat exchange temperature difference data is obtained according to multiple groups of the indoor temperature and multiple groups of the indoor pipe temperature values, including:

[0032] For any group of air conditioner status data, determine the difference between the indoor temperature and the indoor pipe temperature value in the air conditioner status data as the indoor heat exchange temperature difference data, and determine the variance, mean, and the number of multiple groups of the indoor heat exchange temperature difference as the target indoor heat exchange temperature difference data;

[0033] The target outdoor heat exchange temperature difference data is obtained through multiple groups of the outdoor condenser temperature and multiple groups of the outdoor temperature, including:

[0034] For any group of air conditioner status data, determine the difference between the outdoor condenser temperature and the outdoor temperature in the air conditioner status data as the outdoor heat exchange temperature difference data, and determine the variance, mean, and the number of multiple groups of the outdoor heat exchange temperature difference as the target outdoor heat exchange temperature difference data;

[0035] The target set temperature difference data is obtained by using multiple groups of the indoor temperature and multiple groups of the indoor set temperature, including:

[0036] For any group of air conditioner status data, determine the difference between the indoor temperature and the indoor set temperature in the air conditioner status data as the set temperature difference data, and determine the variance, mean, and the number of multiple groups of the set temperature difference data as the target set temperature difference data;

[0037] The target power gap data is obtained according to multiple groups of the compressor set power and multiple groups of the compressor actual power, including:

[0038] For any group of air conditioner status data, determine the difference between the compressor set power and the compressor actual power in the air conditioner status data as the power gap data, and determine the variance, mean, and the number of multiple groups of the power gap data as the target power gap data.

[0039] In this embodiment, by performing corresponding processing on multiple groups of air conditioner status data of each air conditioner to be detected, the formats of the air conditioner status data of each air conditioner to be detected are unified, which facilitates subsequent processing and calculation, and further improves the detection efficiency of the trending problems of the air conditioner.

[0040] In one embodiment, determining each target recalled air conditioner and the confidence level of each target recalled air conditioner in each detected air conditioner according to the target air conditioner status data of each air conditioner to be detected includes:

[0041] Using a preset single-classification algorithm and the target air conditioner status data of each air conditioner to be detected to classify each air conditioner to be detected, obtaining the categories of each air conditioner to be detected and the confidence levels of each air conditioner to be detected, where the categories include a recalled air conditioner category and a non-recalled air conditioner category;

[0042] Determining each air conditioner to be detected with the category of recalled air conditioner category as the target recalled air conditioner, and determining the confidence level of each air conditioner to be detected as the confidence level of each target recalled air conditioner.

[0043] In this embodiment, the categories of each air conditioner to be detected are determined through the target air conditioner status data of each air conditioner to be detected, and then the target recalled air conditioners are determined based on the categories of each air conditioner to be detected. Thus, in this embodiment, the target recalled air conditioners are determined based on the status data of the air conditioners to be detected themselves, which improves the accuracy of the determined target recalled air conditioners.

[0044] In one embodiment, performing clustering analysis on each target recalled air conditioner through the confidence level of each target recalled air conditioner to obtain the level of the trending problem of each target recalled air conditioner includes:

[0045] Using a preset clustering algorithm to cluster each target recalled air conditioner to obtain multiple clustering sets;

[0046] For any one clustering set, determining the confidence level of the target recalled air conditioner that is the clustering center in the clustering set as the clustering value of the clustering set;

[0047] Based on the clustering values of each clustering set, respectively determine the level of the trending problem of each target recalled air conditioner in each clustering set.

[0048] In this embodiment, each target recalled air conditioner is clustered through a preset clustering algorithm to obtain multiple clustering sets, and then the level of the trending problem of each target recalled air conditioner in each clustering set is determined through the confidence level of the clustering center of each clustering set. Thus, the accuracy of the trending problem detection is further improved.

[0049] The second aspect of the present disclosure provides an electronic device, including a storage unit and a processor, where:

[0050] The storage unit is configured to store multiple groups of air conditioner status data of each air conditioner to be detected, where the multiple groups of status data are air conditioner status data corresponding to different times;

[0051] The processor is configured to:

[0052] For any air conditioner to be detected, at specified intervals, obtain multiple groups of air conditioner status data of the air conditioner to be detected, where the multiple groups of status data are air conditioner status data corresponding to different times; and,

[0053] Based on the multiple groups of air conditioner status data, obtain the target air conditioner status data of the air conditioner to be detected;

[0054] According to the target air conditioner status data of each air conditioner to be detected, determine each target recalled air conditioner among the detected air conditioners and the confidence level of each target recalled air conditioner;

[0055] Perform clustering analysis on each target recalled air conditioner through the confidence level of each target recalled air conditioner to obtain the level of the trending problem of each target recalled air conditioner.

[0056] In one embodiment, any group of air conditioner status data includes time, on / off state, compressor discharge temperature, outdoor condenser temperature, indoor pipe temperature value, indoor temperature, outdoor temperature, indoor set temperature, compressor set power, and compressor actual power;

[0057] When the processor executes obtaining the target air conditioner status data of the air conditioner to be detected based on the multiple groups of air conditioner status data, it is specifically configured to:

[0058] For any air conditioner to be detected, based on the multiple groups of on / off states of the air conditioner to be detected and the times corresponding to the multiple groups of on / off states, obtain the total usage duration of the air conditioner to be detected, where the total usage duration is used to represent the total usage duration of the air conditioner to be detected within a specified time period; and,

[0059] When the air conditioner to be detected is in the cooling mode, then obtain the target superheat data based on multiple groups of the compressor discharge temperature and multiple groups of the outdoor condenser temperature; or, when the air conditioner to be detected is in the heating mode, then obtain the target superheat data based on multiple groups of the compressor discharge temperature and multiple groups of the indoor pipe temperature; and,

[0060] Obtain the target indoor heat exchange temperature difference data based on multiple groups of the indoor temperature and multiple groups of the indoor pipe temperature values; and,

[0061] Obtain target outdoor heat exchange temperature difference data based on multiple groups of the outdoor condenser temperature and multiple groups of the outdoor temperature; and,

[0062] Obtain target set temperature difference data by using multiple groups of the indoor temperature and multiple groups of the indoor set temperature; and,

[0063] Obtain target power gap data according to multiple groups of the compressor set power and multiple groups of the compressor actual power;

[0064] Determine the total usage duration, the target exhaust superheat data, the target indoor heat exchange temperature difference data, the target outdoor heat exchange temperature difference data, the target set temperature difference data, and the target power gap data as the target air conditioner state data.

[0065] In one embodiment, when the processor executes to obtain the total usage duration of the air conditioner to be detected based on multiple groups of the on / off states of the air conditioner to be detected and the time corresponding to the multiple groups of on / off states, it is specifically configured as follows:

[0066] Traverse each time in ascending order of time. For any traversed time, perform the following steps:

[0067] If the on / off state corresponding to the time is the on state and the on / off state of the time immediately following the time is the on state, then determine the difference between the time and the time immediately following the time as the intermediate on duration;

[0068] Otherwise, determine the intermediate on duration corresponding to the time as the preset duration;

[0069] Add up the determined intermediate on durations to obtain the total usage duration of the air conditioner to be detected.

[0070] In one embodiment, when the processor executes to obtain the target exhaust superheat data according to multiple groups of the compressor exhaust temperature and multiple groups of the outdoor condenser temperature when the air conditioner to be detected is in the cooling mode, it is specifically configured as follows:

[0071] For any set of air conditioner state data, subtract the outdoor condenser temperature from the compressor exhaust temperature in the air conditioner state data to obtain the exhaust superheat data, and determine the variance, mean, and the number of multiple groups of the exhaust superheat data of the air conditioner to be detected as the target exhaust superheat data;

[0072] When the processor executes to obtain the target exhaust superheat data according to multiple groups of the compressor exhaust temperature and multiple groups of the indoor pipe temperature when the air conditioner to be detected is in the heating mode, it is specifically configured as follows:

[0073] For any set of air conditioner status data, subtract the compressor discharge temperature in the air conditioner status data from the indoor pipe temperature to obtain the superheat degree data of the exhaust gas, and determine the variance, mean value, and the number of multiple sets of the superheat degree data of the exhaust gas of the air conditioner to be detected as the target superheat degree data of the exhaust gas;

[0074] The processor executes to obtain the target indoor heat exchange temperature difference data according to multiple sets of the indoor temperature and multiple sets of the indoor pipe temperature values, and is specifically configured as:

[0075] For any set of air conditioner status data, determine the difference between the indoor temperature and the indoor pipe temperature value in the air conditioner status data as the indoor heat exchange temperature difference data, and determine the variance, mean value, and the number of multiple sets of the indoor heat exchange temperature difference as the target indoor heat exchange temperature difference data;

[0076] The processor executes to obtain the target outdoor heat exchange temperature difference data through multiple sets of the outdoor condenser temperature and multiple sets of the outdoor temperature, and is specifically configured as:

[0077] For any set of air conditioner status data, determine the difference between the outdoor condenser temperature and the outdoor temperature in the air conditioner status data as the outdoor heat exchange temperature difference data, and determine the variance, mean value, and the number of multiple sets of the outdoor heat exchange temperature difference as the target outdoor heat exchange temperature difference data;

[0078] The processor executes to obtain the target set temperature difference data by using multiple sets of the indoor temperature and multiple sets of the indoor set temperature, and is specifically configured as:

[0079] For any set of air conditioner status data, determine the difference between the indoor temperature and the indoor set temperature in the air conditioner status data as the set temperature difference data, and determine the variance, mean value, and the number of multiple sets of the set temperature difference data as the target set temperature difference data;

[0080] The processor executes to obtain the target power gap data according to multiple sets of the compressor set power and multiple sets of the compressor actual power, and is specifically configured as:

[0081] For any set of air conditioner status data, determine the difference between the compressor set power and the compressor actual power in the air conditioner status data as the power gap data, and determine the variance, mean value, and the number of multiple sets of the power gap data as the target power gap data.

[0082] In one embodiment, the processor executes to determine, according to the target air conditioner state data of each air conditioner to be detected, each target recalled air conditioner among the detected air conditioners and the confidence level of each target recalled air conditioner, and is specifically configured as follows:

[0083] Classify each air conditioner to be detected by using a preset single-classification algorithm and the target air conditioner state data of each air conditioner to be detected, to obtain the category of each air conditioner to be detected and the confidence level of each air conditioner to be detected, where the category includes a recalled air conditioner category and a non-recalled air conditioner category;

[0084] Determine each air conditioner to be detected with the category of recalled air conditioner category as the target recalled air conditioner, and determine the confidence level of each air conditioner to be detected as the confidence level of each target recalled air conditioner.

[0085] In one embodiment, the processor executes to perform clustering analysis on each target recalled air conditioner through the confidence level of each target recalled air conditioner, to obtain the level of the trending problem of each target recalled air conditioner, and is specifically configured as follows:

[0086] Cluster each target recalled air conditioner by using a preset clustering algorithm, to obtain a plurality of clustering sets;

[0087] For any one clustering set, determine the confidence level of the target recalled air conditioner that is the clustering center in the clustering set as the clustering value of the clustering set;

[0088] Based on the clustering values of each clustering set, respectively determine the level of the trending problem of each target recalled air conditioner in each clustering set.

[0089] According to the third aspect provided by the embodiments of the present disclosure, there is provided a computer storage medium storing a computer program for executing the method as described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] To more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for description in the embodiments. Obviously, the following drawings are only some embodiments of the present disclosure, and those of ordinary skill in the art can also obtain other drawings without creative efforts based on these drawings.

[0091] Figure 1 FIG. is one of the schematic diagrams of the applicable scenarios in an embodiment of the present disclosure;

[0092] Figure 2 FIG. is another schematic diagram of the applicable scenarios in an embodiment of the present disclosure;

[0093] Figure 3 It is the third schematic diagram of an applicable scenario according to an embodiment of the present disclosure;

[0094] Figure 4 It is one of the schematic flowcharts of a method for detecting trend problems of an air conditioner according to an embodiment of the present disclosure;

[0095] Figure 5 It is the schematic flowchart of a process for determining the total usage duration according to an embodiment of the present disclosure;

[0096] Figure 6 It is the schematic flowchart of a process for determining target recalled air conditioners according to an embodiment of the present disclosure;

[0097] Figure 7 It is the schematic flowchart of a process for determining the levels of trend problems of each target recalled air conditioner according to an embodiment of the present disclosure;

[0098] Figure 8 It is the schematic diagram of a clustering set according to an embodiment of the present disclosure;

[0099] Figure 9 It is the second schematic flowchart of a method for detecting trend problems of an air conditioner according to an embodiment of the present disclosure;

[0100] Figure 10 It is a device for detecting trend problems of an air conditioner according to an embodiment of the present disclosure;

[0101] Figure 11 It is the schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. Detailed implementation manners

[0102] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are some, but not all, of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts shall fall within the protection scope of the present disclosure.

[0103] In the embodiments of the present disclosure, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after.

[0104] The application scenarios described in the embodiments of the present disclosure are for more clearly illustrating the technical solutions of the embodiments of the present disclosure, and do not constitute a limitation on the technical solutions provided by the embodiments of the present disclosure. Those of ordinary skill in the art will know that with the emergence of new application scenarios, the technical solutions provided by the embodiments of the present disclosure are equally applicable to similar technical problems. Among them, in the description of the present disclosure, unless otherwise specified, the meaning of "a plurality" is two or more.

[0105] In the prior art, when analyzing whether an air-conditioning device reaches a certain critical value through the compressor frequency and exhaust temperature of the air-conditioning device, it is only when the critical value is reached that it can be determined that there is a trending problem with the air conditioner. However, a low critical value means that the user's air-conditioning device has been operating in a "sub-healthy" state for a period of time, that is, in the existing state detection method, an alarm will only be issued when the problem is very serious. Therefore, the accuracy rate of the method for detecting the trending problems of air conditioners in the prior art is relatively low.

[0106] Therefore, the present disclosure provides a method for detecting the trending problems of an air conditioner. By obtaining multiple groups of air-conditioning state data of the air conditioner to be detected, the target air-conditioning state data of the air conditioner to be detected is determined. Then, according to the target air-conditioning state data of each air conditioner to be detected, each target recalled air conditioner in each of the detected air conditioners and the confidence level of each target recalled air conditioner are determined; finally, clustering analysis is performed on each target recalled air conditioner through the confidence level of each target recalled air conditioner to obtain the level of the trending problem of each target recalled air conditioner. Thus, in this embodiment, the level of the trending problem of the air conditioner can be determined, avoiding the situation where an alarm is issued only when a very serious problem occurs with the air conditioner, and improving the accuracy rate of detecting the trending problems of the air conditioner. Next, the solution of the present disclosure will be introduced in detail with reference to the accompanying drawings.

[0107] As Figure 1 shown, it is a schematic diagram of the application scenario of the method for detecting the trending problems of an air conditioner provided by an embodiment of the present application. In this application scenario, an electronic device is taken as an example of a server for illustration. This application scenario includes an air conditioner 110 and a server 120. The server 120 can be implemented by a single server or by multiple servers. The server 120 can be implemented by a physical server or by a virtual server.

[0108] In a possible application scenario, for any air conditioner 110, the server 120 obtains multiple sets of air conditioner status data of the air conditioner 110 at specified intervals, where the multiple sets of status data are air conditioner status data corresponding to different times; and the server 120 obtains the target air conditioner status data of the air conditioner 110 based on the multiple sets of air conditioner status data; then the server 120 determines the target recalled air conditioners in each of the air conditioners 110 and the confidence levels of the target recalled air conditioners according to the target air conditioner status data of each air conditioner 110, and finally the server 120 performs cluster analysis on the target recalled air conditioners through the confidence levels of the target recalled air conditioners to obtain the levels of the trending problems of the target recalled air conditioners.

[0109] As Figure 2 shown, this application scenario includes an air conditioner 110, a server 120, and a memory 130. In a possible application scenario, for any air conditioner 110, the server 120 obtains multiple sets of air conditioner status data stored in the same memory 130 of the air conditioner 110 at specified intervals, where the multiple sets of status data are air conditioner status data corresponding to different times; and the server 120 obtains the target air conditioner status data of the air conditioner 110 based on the multiple sets of air conditioner status data; then the server 120 determines the target recalled air conditioners in each of the air conditioners 110 and the confidence levels of the target recalled air conditioners according to the target air conditioner status data of each air conditioner 110, and finally the server 120 performs cluster analysis on the target recalled air conditioners through the confidence levels of the target recalled air conditioners to obtain the levels of the trending problems of the target recalled air conditioners.

[0110] As Figure 3 shown, this application scenario includes an air conditioner 110, a server 120, and a memory 130. In a possible application scenario, for any air conditioner 110, the server 120 obtains multiple sets of air conditioner status data stored in their respective memories 130 of the air conditioner 110 at specified intervals, where the multiple sets of status data are air conditioner status data corresponding to different times; and the server 120 obtains the target air conditioner status data of the air conditioner 110 based on the multiple sets of air conditioner status data; then the server 120 determines the target recalled air conditioners in each of the air conditioners 110 and the confidence levels of the target recalled air conditioners according to the target air conditioner status data of each air conditioner 110, and finally the server 120 performs cluster analysis on the target recalled air conditioners through the confidence levels of the target recalled air conditioners to obtain the levels of the trending problems of the target recalled air conditioners.

[0111] Among them, Figure 1 information interaction can be carried out between the server 120 and the air conditioner 110 through a communication network, where the communication method adopted by the communication network can be divided into a wireless communication method or a wired communication method.

[0112] Exemplarily, the server 120 can access the network through cellular mobile communication technology and communicate with the air conditioner 110. Among them, the cellular mobile communication technology, for example, includes the fifth generation mobile communication (5th Generation Mobile Networks, 5G) technology.

[0113] Optionally, the server 120 can access the network through short-range wireless communication and communicate with the air conditioner 110. Among them, the short-range wireless communication, for example, includes Wireless Fidelity (Wi-Fi) technology.

[0114] Moreover, in the description of the present application, only three air conditioners 110, a single server 120, and a single memory 130 are described in detail. However, those skilled in the art should understand that the illustrated air conditioners 110, server 120, and memory 130 are intended to represent the operations of the air conditioners 110, server 120, and memory 130 involved in the technical solution of the present application. Instead of implying any limitations on the quantity, type, or location of the air conditioners 110, server 120, and memory 130. It should be noted that if additional modules are added to or individual modules are removed from the illustrated environment, the underlying concept of the exemplary embodiments of the present application will not be changed.

[0115] It should be noted that the method for detecting the trending problems of the air conditioner proposed in the present application is not only applicable to Figure 1 , Figure 2 and Figure 3 the application scenarios shown, but also applicable to any device for detecting the trending problems of the air conditioner.

[0116] Next, in combination with the above-described application scenarios, the method for detecting the trending problems of the air conditioner according to the exemplary embodiments of the present application will be described with reference to the accompanying drawings. It should be noted that the above application scenarios are only shown for the convenience of understanding the method and principle of the present application, and the embodiments of the present application are not limited in this regard.

[0117] As Figure 4 shown, it is a schematic flowchart of the method for detecting the trending problems of the air conditioner of the present disclosure, which may include the following steps:

[0118] Step 401: For any air conditioner to be detected, at regular intervals, obtain multiple sets of air conditioner status data of the air conditioner to be detected, where the multiple sets of status data are air conditioner status data corresponding to different times;

[0119] Among them, any set of air conditioner status data includes time, on / off status, compressor discharge temperature, outdoor condenser temperature, indoor pipe temperature value, indoor temperature, outdoor temperature, indoor set temperature, compressor set power, and compressor actual power.

[0120] It should be noted that: the specified duration in this embodiment can be set according to the actual situation, and the specific value of the specified duration is not limited in this embodiment.

[0121] Step 402: Based on the multiple sets of air conditioner status data, obtain the target air conditioner status data of the air conditioner to be detected;

[0122] Among them, the target air conditioner status data includes total usage duration, target exhaust superheat data, target indoor heat exchange temperature difference data, target outdoor heat exchange temperature difference data, target set temperature difference data, and target power gap data. Among them, the total usage duration is used to represent the total usage duration of the air conditioner to be detected within the specified time period.

[0123] It should be noted that: the specified time period in this embodiment is 00:00~24:00, but this embodiment does not limit the specified time period, and the specified time period in this embodiment can be set according to the actual situation. Next, the determination method of the target air conditioner status data will be introduced in detail:

[0124] 1. Total usage duration:

[0125] Based on the multiple on / off statuses of the air conditioner to be detected and the time corresponding to the multiple on / off statuses, obtain the total usage duration of the air conditioner to be detected, where the total usage duration is used to represent the total usage duration of the air conditioner to be detected within the specified time period.

[0126] In one embodiment, as Figure 5 shown, is a flow diagram for determining the total usage duration, including the following steps:

[0127] Step 501: Traverse each time in ascending order of time;

[0128] Step 502: For any traversed time, determine whether the on / off status corresponding to the time is the on state and whether the on / off status of the time immediately following the time is the on state. If so, execute Step 503; if not, execute Step 504;

[0129] Step 503: Determine the difference between the time and the time immediately following the time as the intermediate on duration;

[0130] Step 504: Determine the intermediate on duration corresponding to the time as the preset duration;

[0131] Among them, the preset duration in this embodiment is 0. However, the preset duration in this embodiment is not limited, and the preset duration in this embodiment can be set according to the actual situation.

[0132] Step 505: Add up the determined intermediate startup durations to obtain the total usage duration of the air conditioner to be detected.

[0133] For example, the times of the air conditioner 1 to be detected include: 10:00, 10:05, 10:10, 10:15, 10:20. If it is determined that the on-off state corresponding to 10:00 is the on state, the on-off state corresponding to 10:05 is the on state, the on-off state corresponding to 10:10 is the off state, the on-off state corresponding to 10:15 is the on state, and the on-off state corresponding to 10:20 is the on state. Then it is determined that the intermediate startup duration between 10:00 and 10:05 is 5 minutes, the intermediate startup duration between 10:05 and 10:10 is the preset duration of 0 minutes, the intermediate startup duration between 10:10 and 10:15 is the preset duration of 0 minutes. The intermediate startup duration between 10:15 and 10:20 is 5 minutes. Then add up the determined intermediate startup durations to obtain the total usage duration of the air conditioner 1 to be detected as 10 minutes.

[0134] 2. Target superheat data at the exhaust:

[0135] Method 1: When the air conditioner to be detected is in the cooling mode, the target superheat data at the exhaust is obtained according to multiple groups of the compressor exhaust temperature and multiple groups of the outdoor condenser temperature.

[0136] In one embodiment, the target superheat data at the exhaust is specifically determined by the following method:

[0137] For any group of air conditioner state data, subtract the outdoor condenser temperature from the compressor exhaust temperature in the air conditioner state data to obtain the superheat data at the exhaust, and determine the variance, mean value of multiple groups of the superheat data at the exhaust of the air conditioner to be detected, and the number of multiple groups of the superheat data at the exhaust as the target superheat data at the exhaust. Among them, the number of multiple groups of the superheat data at the exhaust is the number of groups of the superheat data at the exhaust.

[0138] In one embodiment, the superheat data at the exhaust can be determined by formula (1):

[0139] S 1 =W 压 -W 1 ……(1);

[0140] Among them, S 1 is the superheat data at the exhaust, W 压 is the compressor exhaust temperature, W1 is the outdoor condenser temperature.

[0141] Next, a detailed introduction is given to the method of determining the variance and mean of multiple sets of exhaust superheat data of the air conditioner to be detected:

[0142] 1. Mean:

[0143] Add up the multiple sets of exhaust superheat data of the air conditioner to be detected and divide by the number of the multiple sets of exhaust superheat data to obtain the mean.

[0144] 2. Variance:

[0145] For any set of exhaust superheat data among the multiple sets of exhaust superheat data, subtract the mean of the multiple sets of exhaust superheat data from the exhaust superheat data to obtain a first difference. Add up the squares of the first differences corresponding to the multiple sets of exhaust superheat data to obtain a first total difference. Divide the first total difference by the number of the multiple sets of exhaust superheat data to obtain the variance of the exhaust superheat data. Among them, the variance of the exhaust superheat data can be obtained through formula (2):

[0146]

[0147] Among them, is the variance of the exhaust superheat data, x 1i is the i-th exhaust superheat data among the multiple sets of exhaust superheat data, is the mean of the multiple sets of exhaust superheat data, and n is the number of the multiple sets of exhaust superheat data.

[0148] Method 2: When the air conditioner to be detected is in the heating mode, the target exhaust superheat data is obtained according to multiple sets of the compressor exhaust temperature and multiple sets of the indoor pipe temperature.

[0149] In one embodiment, the target exhaust superheat data is specifically obtained through the following method:

[0150] For any set of air conditioner state data, subtract the indoor pipe temperature from the compressor exhaust temperature in the air conditioner state data to obtain the exhaust superheat data, and determine the variance, mean, and number of the multiple sets of exhaust superheat data of the air conditioner to be detected as the target exhaust superheat data. Among them, the exhaust superheat data can be determined through formula (3):

[0151] S 1 =W 压 -W 2 ……(3);

[0152] Among them, S is the exhaust superheat data, and W 压 is the compressor exhaust temperature, and W 2 is the indoor pipe temperature.

[0153] It should be noted that: In this embodiment, the method for determining the variance and mean of multiple sets of exhaust superheat data is the same as the method described above, and this embodiment will not elaborate here.

[0154] 3. Target indoor heat exchange temperature difference data:

[0155] Based on multiple sets of the indoor temperature and multiple sets of the indoor pipe temperature values, the target indoor heat exchange temperature difference data is obtained.

[0156] In one embodiment, the target indoor heat exchange temperature difference data is determined by the following method:

[0157] For any set of air conditioner state data, the difference between the indoor temperature and the indoor pipe temperature value in the air conditioner state data is determined as the indoor heat exchange temperature difference data, and the variance, mean, and the number of multiple sets of the indoor heat exchange temperature differences of the multiple sets of the indoor heat exchange temperature difference data are determined as the target indoor heat exchange temperature difference data.

[0158] Among them, the method for determining the indoor heat exchange temperature difference data specifically includes the following two:

[0159] Method 1: When the air conditioner to be detected is in the cooling mode, subtract the indoor pipe temperature value from the indoor temperature to obtain the indoor heat exchange temperature difference data. Among them, the indoor heat exchange temperature difference data can be obtained through formula (4):

[0160] S 2 =W s -W 2 ……(4);

[0161] Among them, S 2 is the indoor heat exchange temperature difference data, W s is the indoor temperature, and W 2 is the indoor pipe temperature value.

[0162] Method 2: When the air conditioner to be detected is in the heating mode, subtract the indoor temperature from the indoor pipe temperature value to obtain the indoor heat exchange temperature difference data. Among them, the indoor heat exchange temperature difference data can be obtained through formula (5):

[0163] S 2 =W 2 -W s ……(5);

[0164] Among them, S 2 is the indoor heat exchange temperature difference data, and Ws is the indoor temperature, W 2 is the indoor pipe temperature.

[0165] Next, a detailed introduction is given to the method of determining the variance and mean of multiple groups of the indoor heat exchange temperature difference data of the air conditioner to be detected:

[0166] 1. Mean:

[0167] Add up multiple groups of the indoor heat exchange temperature difference data of the air conditioner to be detected and divide by the number of multiple groups of the indoor heat exchange temperature difference data to obtain the mean.

[0168] 2. Variance:

[0169] For any group of the indoor heat exchange temperature difference data among multiple groups of the indoor heat exchange temperature difference data, subtract the mean of multiple groups of the indoor heat exchange temperature difference data from the indoor heat exchange temperature difference data to obtain a second difference. Add up the squares of the second differences corresponding to multiple groups of the indoor heat exchange temperature difference data to obtain a second total difference. Divide the second total difference by the number of multiple groups of the indoor heat exchange temperature difference data to obtain the variance of the indoor heat exchange temperature difference data. Among them, the variance of the indoor heat exchange temperature difference data can be obtained through formula (6):

[0170]

[0171] Among them, is the variance of the indoor heat exchange temperature difference data, x 2i is the i-th indoor heat exchange temperature difference data among multiple groups of the indoor heat exchange temperature difference data, is the mean of multiple groups of the indoor heat exchange temperature difference data, and n is the number of multiple groups of the indoor heat exchange temperature difference data.

[0172] 4. Target outdoor heat exchange temperature difference data:

[0173] Obtain the target outdoor heat exchange temperature difference data through multiple groups of the outdoor condenser temperature and multiple groups of the outdoor temperature.

[0174] In one embodiment, the target outdoor heat exchange temperature difference data is specifically determined by the following method:

[0175] For any group of air conditioner state data, determine the difference between the outdoor condenser temperature and the outdoor temperature in the air conditioner state data as the outdoor heat exchange temperature difference data, and determine the variance, mean, and number of multiple groups of the outdoor heat exchange temperature difference data as the target outdoor heat exchange temperature difference data.

[0176] Among them, the method of determining the outdoor heat exchange temperature difference data specifically includes the following two:

[0177] Method 1: When the air conditioner to be detected is in the cooling mode, subtract the outdoor condenser temperature from the outdoor temperature to obtain the outdoor heat exchange temperature difference data. Among them, the outdoor heat exchange temperature difference data can be determined by formula (7):

[0178] S 3 = W 1 - W w ……(7);

[0179] Among them, S 3 is the outdoor heat exchange temperature difference data, W 1 is the outdoor condenser temperature, and W w is the outdoor temperature.

[0180] Method 2: When the air conditioner to be detected is in the heating mode, subtract the outdoor condenser temperature from the outdoor temperature to obtain the outdoor heat exchange temperature difference data. Among them, the outdoor heat exchange temperature difference data can be determined by formula (8):

[0181] S 3 = W w - W 1 ……(8);

[0182] Among them, S 3 is the outdoor heat exchange temperature difference data, W 1 is the outdoor condenser temperature, and W w is the outdoor temperature.

[0183] Next, a detailed introduction will be given to the method of determining the variance and mean of multiple groups of outdoor heat exchange temperature difference data of the air conditioner to be detected:

[0184] 1. Mean:

[0185] Add the multiple groups of outdoor heat exchange temperature difference data of the air conditioner to be detected and divide by the number of the multiple groups of outdoor heat exchange temperature difference data to obtain the mean.

[0186] 2. Variance:

[0187] For any group of outdoor heat exchange temperature difference data among the multiple groups of outdoor heat exchange temperature difference data, subtract the mean of the multiple groups of outdoor heat exchange temperature difference data from the outdoor heat exchange temperature difference data to obtain a third difference. Square the third differences corresponding to the multiple groups of outdoor heat exchange temperature difference data and add them up to obtain a third total difference. Divide the third total difference by the number of the multiple groups of outdoor heat exchange temperature difference data to obtain the variance of the outdoor heat exchange temperature difference data. Among them, the variance of the outdoor heat exchange temperature difference data can be obtained by formula (9):

[0188]

[0189] Among them, is the variance of the outdoor heat exchange temperature difference data, x 3i is the i-th outdoor heat exchange temperature difference data in the multiple groups of outdoor heat exchange temperature difference data, is the mean value of the multiple groups of outdoor heat exchange temperature difference data, and n is the number of the multiple groups of outdoor heat exchange temperature difference data.

[0190] 5. Target set temperature difference data:

[0191] Using the multiple groups of indoor temperatures and the multiple groups of indoor set temperatures, target set temperature difference data is obtained.

[0192] In one embodiment, the target set temperature difference data is specifically determined by the following method:

[0193] For any group of air conditioner state data, the difference between the indoor temperature and the indoor set temperature in the air conditioner state data is determined as the set temperature difference data, and the variance, mean value, and number of the multiple groups of set temperature difference data are determined as the target set temperature difference data. Among them, the set temperature difference data can be determined by the following two methods:

[0194] Method 1: When the air conditioner to be detected is in the cooling mode, subtract the indoor set temperature from the indoor temperature to obtain the set temperature difference. Among them, the set temperature difference can be determined by formula (10):

[0195] S 4 = W s - W 3 ……(10);

[0196] Among them, S 4 is the set temperature difference, W s is the indoor temperature, and W 3 is the indoor set temperature.

[0197] Method 2: When the air conditioner to be detected is in the heating mode, subtract the indoor temperature from the indoor set temperature to obtain the set temperature difference. Among them, the set temperature difference can be determined by formula (11):

[0198] S 4 = W 3 - W s ……(11);

[0199] Among them, S 4 is the set temperature difference, W s is the indoor temperature, and W 3 is the indoor set temperature.

[0200] Next, a detailed introduction will be given to the method of determining the variance and mean of multiple groups of set temperature difference data of the air conditioner to be detected:

[0201] 1. Mean:

[0202] Add the multiple groups of set temperature difference data of the air conditioner to be detected and divide the sum by the number of the multiple groups of set temperature difference data to obtain the mean.

[0203] 2. Variance:

[0204] For any group of set temperature difference data among the multiple groups of set temperature difference data, subtract the mean of the multiple groups of set temperature difference data from the set temperature difference data to obtain a fourth difference. Add the squares of the fourth differences corresponding to the multiple groups of set temperature difference data to obtain a fourth total difference. Divide the fourth total difference by the number of the multiple groups of set temperature difference data to obtain the variance of the set temperature difference data. Among them, the variance of the set temperature difference data can be obtained through formula (12):

[0205]

[0206] Among them, is the variance of the set temperature difference data, x 4i is the i-th set temperature difference data among the multiple groups of set temperature difference data, is the mean of the multiple groups of set temperature difference data, and n is the number of the multiple groups of set temperature difference data.

[0207] 6. Target power gap data:

[0208] Obtain the target power gap data according to multiple groups of the set power of the compressor and multiple groups of the actual power of the compressor.

[0209] In one embodiment, the target power gap data is specifically determined by the following method:

[0210] For any group of air conditioner state data, determine the difference between the set power of the compressor and the actual power of the compressor in the air conditioner state data as the power gap data, and determine the variance, mean, and number of the multiple groups of power gap data as the target power gap data. Among them, the power gap data can be obtained through formula (13):

[0211] Δw = w 设 - w 实 ……(13);

[0212] Among them, Δw is the power gap data, w 设 is the set power of the compressor, and w 实 is the actual power of the compressor.

[0213] Next, a detailed introduction is given to the method of determining the variance and mean of multiple groups of power gap data of the air conditioner to be detected:

[0214] 1. Mean:

[0215] Add the multiple groups of power gap data of the air conditioner to be detected and divide by the number of the multiple groups of power gap data to obtain the mean.

[0216] 2. Variance:

[0217] For any group of power gap data among the multiple groups of power gap data, subtract the mean of the multiple groups of power gap data from the power gap data to obtain a fifth difference. Add the squares of the fifth differences corresponding to the multiple groups of power gap data to obtain a fifth total difference. Divide the fifth total difference by the number of the multiple groups of power gap data to obtain the variance of the power gap data. Among them, the variance of the power gap data can be obtained through formula (14):

[0218]

[0219] Among them, is the variance of the power gap data, x 5i is the i-th power gap data among the multiple groups of power gap data, is the mean of the multiple groups of power gap data, and n is the number of the multiple groups of power gap data.

[0220] Step 403: Determine each target recalled air conditioner and the confidence level of each target recalled air conditioner among the detected air conditioners according to the target air conditioner state data of each air conditioner to be detected;

[0221] As Figure 6 shown, it is a schematic flow chart for determining the target recalled air conditioner, including the following steps:

[0222] Step 601: Classify each air conditioner to be detected by using a preset single-classification algorithm and the target air conditioner state data of each air conditioner to be detected to obtain the category and confidence level of each air conditioner to be detected. Among them, the category includes the recalled air conditioner category and the non-recalled air conditioner category;

[0223] In one embodiment, input the target air conditioner state data of each air conditioner to be detected into the preset single-classification algorithm to obtain the category and confidence level of each air conditioner to be detected.

[0224] It should be noted that: the single-classification algorithm in this embodiment uses the one-class support vector machine algorithm, but the specific single-classification algorithm can be set according to the actual situation, and this embodiment does not limit the single-classification algorithm here.

[0225] Step 602: Determine each air conditioner to be detected with the category of recalled air conditioners as the target recalled air conditioners, and determine the confidence levels of the air conditioners to be detected as the confidence levels of the target recalled air conditioners.

[0226] Among them, the categories of the air conditioners to be detected in this embodiment include the recalled air conditioner category and the non-recalled air conditioner category.

[0227] Step 404: Perform clustering analysis on the target recalled air conditioners through the confidence levels of the target recalled air conditioners to obtain the levels of the trending problems of the target recalled air conditioners.

[0228] Thus, in this disclosure, the target air conditioner state data of the air conditioners to be detected is determined by obtaining multiple groups of air conditioner state data of the air conditioners to be detected, and then, according to the target air conditioner state data of each air conditioner to be detected, each target recalled air conditioner among the detected air conditioners and the confidence levels of the target recalled air conditioners are determined; finally, clustering analysis is performed on the target recalled air conditioners through the confidence levels of the target recalled air conditioners to obtain the levels of the trending problems of the target recalled air conditioners. Thus, the level of the trending problem of the air conditioner can be determined in this disclosure, avoiding the situation where an alarm is triggered only when a very serious problem occurs with the air conditioner, and improving the accuracy of detecting the trending problems of the air conditioner.

[0229] Next, a detailed description of determining the levels of the trending problems of the target recalled air conditioners is as follows Figure 7 As shown, it is a schematic flowchart of the process for specifically determining the levels of the trending problems of the target recalled air conditioners, including the following steps:

[0230] Step 701: Cluster the target recalled air conditioners using a preset clustering algorithm to obtain multiple clustering sets;

[0231] It should be noted that: the clustering algorithm in this embodiment uses k-means (k-means clustering algorithm, K-means clustering algorithm), but the clustering algorithm in this embodiment is not limited, and the clustering algorithm in this embodiment can be set according to the actual situation.

[0232] Next, the clustering process in this embodiment is described by taking the k-means algorithm as an example:

[0233] First, randomly select a specified number of target recalled air conditioners as the initial clustering centers. Then, calculate the distance between each of the other target recalled air conditioners and each of the initial clustering centers. Then assign each target recalled air conditioner to the clustering center closest to it. The clustering centers and the target recalled air conditioners assigned to them represent a clustering set. Once all the target recalled air conditioners have been assigned, the clustering centers of each clustering set will be recalculated based on the existing target recalled air conditioners in the clustering set. This process will be repeated continuously until a certain termination condition is met. The termination condition can be any of the following:

[0234] (1) No object is reassigned to a different cluster.

[0235] (2) No clustering center changes anymore.

[0236] Among them, the distance between any target recalled air conditioner and the clustering center is determined based on the confidence level of the target recalled air conditioner and the confidence level of the clustering center. The distance between the target recalled air conditioner and the clustering center can be determined by formula (15):

[0237]

[0238] where C 1 is the confidence level of the target recalled air conditioner, C 2 is the confidence level of the clustering center, and d is the distance between the target recalled air conditioner and the clustering center.

[0239] Step 702: For any clustering set, determine the confidence level of the target recalled air conditioner that is the clustering center in the clustering set as the clustering value of the clustering set;

[0240] For example, clustering set 1 includes target recalled air conditioner 1, target recalled air conditioner 2, target recalled air conditioner 3, and target recalled air conditioner 4. Among them, target recalled air conditioner 1 is the clustering center of clustering set 1, then determine the confidence level of target recalled air conditioner 1 as the clustering value of clustering set 1.

[0241] Step 703: Based on the clustering values of each clustering set, determine the level of the trend problem of each target recalled air conditioner in each clustering set.

[0242] In one embodiment, specifically determine the level of the trend problem of each target recalled air conditioner in the clustering set in the following way:

[0243] For any clustering set, use the corresponding relationship between the preset clustering value and the level of the trend problem to determine the level of the trend problem corresponding to the clustering value of each clustering set, and determine the level of the trend problem as the level of the trend problem of each target recalled air conditioner in the clustering set.

[0244] Among them, Table 1 shows the correspondence between clustering values and trending problems:

[0245]

[0246]

[0247] Table 1

[0248] For example, as Figure 8 shown, there are three clustering sets in the figure, namely clustering set 1, clustering set 2, and clustering set 3. Among them, if the clustering value of clustering set 1 is A, the clustering value of clustering set 2 is D, and the clustering value of clustering set 3 is M, then using the corresponding relationship in Table 1, it is determined that the level of the trending problems of each target recalled air conditioner (i.e., recalled air conditioner 1, recalled air conditioner 2, and recalled air conditioner 3) in clustering set 1 is low. And it is determined that the level of the trending problems of each target recalled air conditioner (i.e., recalled air conditioner 4, recalled air conditioner 5, and recalled air conditioner 6) in clustering set 2 is medium. And it is determined that the level of the trending problems of each target recalled air conditioner (i.e., recalled air conditioner 7, recalled air conditioner 8, and recalled air conditioner 9) in clustering set 3 is extremely high.

[0249] To further understand the technical solution of the present disclosure, the following is described in detail in conjunction with Figure 9 and may include the following steps:

[0250] Step 901: For any air conditioner to be detected, at regular intervals, obtain multiple groups of air conditioner status data of the air conditioner to be detected, where the multiple groups of status data are air conditioner status data corresponding to different times, and any group of air conditioner status data includes time, on / off state, compressor discharge temperature, outdoor condenser temperature, indoor pipe temperature value, indoor temperature, outdoor temperature, indoor set temperature, compressor set power, and compressor actual power;

[0251] Step 902: For any air conditioner to be detected, traverse each time in chronological order;

[0252] Step 903: For any traversed time, determine whether the on / off state corresponding to the time is the on state and the on / off state of the subsequent time of the time is the on state. If so, execute Step 904; if not, execute Step 905;

[0253] Step 904: Determine the difference between the time and the subsequent time of the time as the intermediate on time;

[0254] Step 905: Determine the intermediate on time corresponding to the time as the preset time;

[0255] Step 906: Add up the determined intermediate startup durations to obtain the total usage duration of the air conditioner to be detected, where the total usage duration is used to represent the total usage duration of the air conditioner to be detected within a specified time period;

[0256] Step 907: Obtain target discharge superheat data based on multiple sets of the compressor discharge temperatures;

[0257] Step 908: For any set of air conditioner status data, determine the difference between the indoor temperature and the indoor pipe temperature value in the air conditioner status data as the indoor heat exchange temperature difference data, and determine the variance, mean, and the number of multiple sets of the indoor heat exchange temperature differences as the target indoor heat exchange temperature difference data;

[0258] Step 909: For any set of air conditioner status data, determine the difference between the outdoor condenser temperature and the outdoor temperature in the air conditioner status data as the outdoor heat exchange temperature difference data, and determine the variance, mean, and the number of multiple sets of the outdoor heat exchange temperature differences as the target outdoor heat exchange temperature difference data;

[0259] Step 910: For any set of air conditioner status data, determine the difference between the indoor temperature and the indoor set temperature in the air conditioner status data as the set temperature difference data, and determine the variance, mean, and the number of multiple sets of the set temperature difference data as the target set temperature difference data;

[0260] Step 911: For any set of air conditioner status data, determine the difference between the compressor set power and the compressor actual power in the air conditioner status data as the power gap data, and determine the variance, mean, and the number of multiple sets of the power gap data as the target power gap data;

[0261] Among them, the execution order of Steps 907 to 911 is not limited in this embodiment and can be executed successively or simultaneously.

[0262] Step 912: Determine the total usage duration, the target discharge superheat data, the target indoor heat exchange temperature difference data, the target outdoor heat exchange temperature difference data, the target set temperature difference data, and the target power gap data as the target air conditioner status data;

[0263] Step 913: Use a preset single-classification algorithm and the target air conditioner status data of each air conditioner to be detected to classify each air conditioner to be detected, and obtain the categories of each air conditioner to be detected and the confidence levels of each air conditioner to be detected, where the categories include recalled air conditioner categories and non-recalled air conditioner categories;

[0264] Step 914: Determine each to-be-detected air conditioner with the category of recalled air conditioners as the target recalled air conditioner, and determine the confidence level of each to-be-detected air conditioner as the confidence level of each target recalled air conditioner;

[0265] Step 915: Cluster each of the target recalled air conditioners by using a preset clustering algorithm to obtain a plurality of clustering sets;

[0266] Step 916: For any one of the clustering sets, determine the confidence level of the target recalled air conditioner that is the clustering center in the clustering set as the clustering value of the clustering set;

[0267] Step 917: Based on the clustering values of each clustering set, respectively determine the levels of the trending problems of each target recalled air conditioner in each clustering set.

[0268] Based on the same inventive concept, the method for detecting the trending problem of the air conditioner as described above in the present disclosure can also be implemented by a device for detecting the trending problem of the air conditioner. The effect of the device for detecting the trending problem of the air conditioner is similar to the effect of the foregoing method, and will not be elaborated herein.

[0269] Figure 10 FIG. is a schematic structural diagram of a device for detecting the trending problem of an air conditioner according to an embodiment of the present disclosure.

[0270] As Figure 10 shown, the device 1000 for detecting the trending problem of the air conditioner of the present disclosure may include an acquisition module 1010, a target air conditioner status data determination module 1020, a target recalled air conditioner determination module 1030, and a clustering analysis module 1040.

[0271] The acquisition module 1010 is configured to, for any one of the to-be-detected air conditioners, acquire multiple groups of air conditioner status data of the to-be-detected air conditioner at intervals of a specified duration, where the multiple groups of status data are air conditioner status data corresponding to different times;

[0272] The target air conditioner status data determination module 1020 is configured to obtain the target air conditioner status data of the to-be-detected air conditioner based on the multiple groups of air conditioner status data;

[0273] The target recalled air conditioner determination module 1030 is configured to determine each target recalled air conditioner among the to-be-detected air conditioners and the confidence level of each target recalled air conditioner according to the target air conditioner status data of each to-be-detected air conditioner;

[0274] The clustering analysis module 1040 is configured to perform clustering analysis on each of the target recalled air conditioners through the confidence levels of each of the target recalled air conditioners to obtain the levels of the trending problems of each of the target recalled air conditioners.

[0275] In one embodiment, any set of air conditioner status data includes time, on / off status, compressor discharge temperature, outdoor condenser temperature, indoor pipe temperature value, indoor temperature, outdoor temperature, indoor set temperature, compressor set power, and compressor actual power;

[0276] The target air conditioner status data determination module 1020 is specifically configured to:

[0277] For any air conditioner to be detected, based on multiple sets of on / off statuses of the air conditioner to be detected and the times corresponding to the multiple sets of on / off statuses, obtain the total usage duration of the air conditioner to be detected, where the total usage duration is used to represent the total usage duration of the air conditioner to be detected within a specified time period; and,

[0278] When the air conditioner to be detected is in the cooling mode, then based on multiple sets of the compressor discharge temperature and multiple sets of the outdoor condenser temperature, obtain the target superheat data; or, when the air conditioner to be detected is in the heating mode, then based on multiple sets of the compressor discharge temperature and multiple sets of the indoor pipe temperature, obtain the target superheat data; and,

[0279] Based on multiple sets of the indoor temperature and multiple sets of the indoor pipe temperature values, obtain the target indoor heat exchange temperature difference data; and,

[0280] Through multiple sets of the outdoor condenser temperature and multiple sets of the outdoor temperature, obtain the target outdoor heat exchange temperature difference data; and,

[0281] Utilize multiple sets of the indoor temperature and multiple sets of the indoor set temperature to obtain the target set temperature difference data; and,

[0282] Based on multiple sets of the compressor set power and multiple sets of the compressor actual power, obtain the target power gap data;

[0283] Determine the total usage duration, the target superheat data, the target indoor heat exchange temperature difference data, the target outdoor heat exchange temperature difference data, the target set temperature difference data, and the target power gap data as the target air conditioner status data.

[0284] In one embodiment, when the target air conditioner status data determination module 1020 executes obtaining the total usage duration of the air conditioner to be detected based on multiple sets of on / off statuses of the air conditioner to be detected and the times corresponding to the multiple sets of on / off statuses, it is specifically configured to:

[0285] Traverse each time in ascending order, and for any traversed time, perform the following steps:

[0286] If the on / off state corresponding to the time is the on state, and the on / off state at the time immediately following the time is the on state, then determine the difference between the time and the time immediately following the time as the intermediate on duration;

[0287] Otherwise, determine the intermediate on duration corresponding to the time as the preset duration;

[0288] Add up the determined intermediate on durations to obtain the total usage duration of the air conditioner to be detected.

[0289] In one embodiment, when the air conditioner to be detected is in the cooling mode, the target air conditioner state data determination module 1020 obtains target superheat data according to multiple sets of the compressor discharge temperature and multiple sets of the outdoor condenser temperature, and specifically is used for:

[0290] For any set of air conditioner state data, subtract the compressor discharge temperature in the air conditioner state data from the outdoor condenser temperature to obtain superheat data, and determine the variance, mean, and the number of multiple sets of the superheat data of the air conditioner to be detected as the target superheat data;

[0291] When the air conditioner to be detected is in the heating mode, the target air conditioner state data determination module 1020 obtains the target superheat data according to multiple sets of the compressor discharge temperature and multiple sets of the indoor pipe temperature, and specifically is used for:

[0292] For any set of air conditioner state data, subtract the indoor pipe temperature in the air conditioner state data from the compressor discharge temperature to obtain superheat data, and determine the variance, mean, and the number of multiple sets of the superheat data of the air conditioner to be detected as the target superheat data;

[0293] The target air conditioner state data determination module 1020 obtains target indoor heat exchange temperature difference data according to multiple sets of the indoor temperature and multiple sets of the indoor pipe temperature values, and specifically is used for:

[0294] For any set of air conditioner state data, determine the difference between the indoor temperature and the indoor pipe temperature value in the air conditioner state data as the indoor heat exchange temperature difference data, and determine the variance, mean, and the number of multiple sets of the indoor heat exchange temperature differences as the target indoor heat exchange temperature difference data;

[0295] The target air conditioner state data determination module 1020 obtains target outdoor heat exchange temperature difference data through multiple sets of the outdoor condenser temperature and multiple sets of the outdoor temperature, and specifically is used for:

[0296] For any set of air conditioner status data, the difference between the outdoor condenser temperature and the outdoor temperature in the air conditioner status data is determined as the outdoor heat exchange temperature difference data, and the variance, mean, and the number of multiple sets of the outdoor heat exchange temperature difference data are determined as the target outdoor heat exchange temperature difference data;

[0297] The target air conditioner status data determination module 1020 executes obtaining the target set temperature difference data by using multiple sets of the indoor temperature and multiple sets of the indoor set temperature, specifically for:

[0298] For any set of air conditioner status data, the difference between the indoor temperature and the indoor set temperature in the air conditioner status data is determined as the set temperature difference data, and the variance, mean, and the number of multiple sets of the set temperature difference data are determined as the target set temperature difference data;

[0299] The target air conditioner status data determination module 1020 executes obtaining the target power gap data according to multiple sets of the compressor set power and multiple sets of the compressor actual power, specifically for:

[0300] For any set of air conditioner status data, the difference between the compressor set power and the compressor actual power in the air conditioner status data is determined as the power gap data, and the variance, mean, and the number of multiple sets of the power gap data are determined as the target power gap data.

[0301] In one embodiment, the target recalled air conditioner determination module 1030 is specifically for:

[0302] Using a preset single-classification algorithm and the target air conditioner status data of each air conditioner to be detected to classify each air conditioner to be detected, obtaining the category of each air conditioner to be detected and the confidence level of each air conditioner to be detected, where the category includes the recalled air conditioner category and the non-recalled air conditioner category;

[0303] Each air conditioner to be detected with the category of the recalled air conditioner category is determined as the target recalled air conditioner, and the confidence level of each air conditioner to be detected is determined as the confidence level of each target recalled air conditioner.

[0304] In one embodiment, the clustering analysis module 1040 is specifically for:

[0305] Using a preset clustering algorithm to cluster each target recalled air conditioner to obtain multiple clustering sets;

[0306] For any one clustering set, the confidence level of the target recalled air conditioner that is the clustering center in the clustering set is determined as the clustering value of the clustering set;

[0307] Based on the clustering values of each clustering set, determine the level of the trending problems of each target recalled air conditioner in each of the clustering sets respectively.

[0308] After introducing a method and device for detecting the trending problems of an air conditioner according to an exemplary embodiment of the present disclosure, next, an electronic device according to another exemplary embodiment of the present disclosure will be introduced.

[0309] Those skilled in the art to which the present disclosure pertains can understand that various aspects of the present disclosure can be implemented as a system, a method, or a program product. Therefore, various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to herein as "circuitry", "module", or "system".

[0310] In some possible embodiments, the electronic device according to the present disclosure may at least include at least one processor and at least one computer storage medium. Among them, the computer storage medium stores program code, and when the program code is executed by the processor, the processor executes the steps in the method for detecting the trending problems of the air conditioner according to various exemplary embodiments of the present disclosure described above in this specification. For example, the processor may execute steps 401 - 404 as shown in Figure 4 shown in.

[0311] Next, refer to Figure 11 to describe the electronic device 1100 according to this embodiment of the present disclosure. Figure 11 The electronic device 1100 shown is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present disclosure.

[0312] As Figure 11 shown, the electronic device 1100 is presented in the form of a general-purpose electronic device. The components of the electronic device 1100 may include but are not limited to: the above-mentioned at least one processor 1101, the above-mentioned at least one computer storage medium 1102, and a bus 1103 connecting different system components (including the computer storage medium 1102 and the processor 1101).

[0313] The bus 1103 represents one or more of several types of bus structures, including a computer storage medium bus or a computer storage medium controller, a peripheral bus, a processor, or a local bus using any bus structure in a variety of bus structures.

[0314] The computer storage medium 1102 may include a readable medium in the form of a volatile computer storage medium, such as a random access computer storage medium (RAM) 1121 and / or a cache storage medium 1122, and may further include a read-only computer storage medium (ROM) 1123.

[0315] The computer storage medium 1102 may also include a program / utilities 1125 having a set (at least one) of program modules 1124. Such program modules 1124 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment.

[0316] The electronic device 1100 may also communicate with one or more external devices 1104 (such as a keyboard, a pointing device, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 1100, and / or may communicate with any device that enables the electronic device 1100 to communicate with one or more other electronic devices (such as a router, a modem, etc.). Such communication may be carried out through an input / output (I / O) interface 1105. And, the electronic device 1100 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 1106. As shown in the figure, the network adapter 1106 communicates with other modules for the electronic device 1100 through a bus 1103. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 1100, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0317] In some possible implementation manners, various aspects of a method for detecting a trending problem of an air conditioner provided by the present disclosure may also be implemented in the form of a program product, which includes program code. When the program product runs on a computer device, the program code is used to cause the computer device to execute the steps in the method for detecting a trending problem of an air conditioner according to various exemplary implementation manners of the present disclosure described above in this specification.

[0318] The program product may employ any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access computer storage medium (RAM), a read-only computer storage medium (ROM), an erasable programmable read-only computer storage medium (EPROM or flash memory), an optical fiber, a portable compact disk read-only computer storage medium (CD-ROM), an optical computer storage medium, a magnetic computer storage medium, or any suitable combination of the foregoing.

[0319] The program product for detecting trend problems of the air conditioner according to the embodiments of the present disclosure may employ a portable compact disk read-only computer storage medium (CD-ROM) and include program code, and may run on an electronic device. However, the program product of the present disclosure is not limited thereto. In this document, the readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0320] The readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal may take various forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the foregoing. The readable signal medium may also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0321] The program code contained on the readable medium may be transmitted by any appropriate medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination of the foregoing.

[0322] The program code for performing the operations of the present disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's electronic device, partially on the user's device, executed as a stand-alone software package, partially on the user's electronic device and partially on a remote electronic device, or entirely on a remote electronic device or server. In the case of a remote electronic device, the remote electronic device can be connected to the user's electronic device through any type of network including a local area network (LAN) or a wide area network (WAN), or, alternatively, can be connected to an external electronic device (e.g., by connecting through the Internet using an Internet service provider).

[0323] It should be noted that although several modules of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more of the above-described modules can be embodied in one module. Conversely, the features and functions of one module described above can be further divided and embodied by multiple modules.

[0324] In addition, although the operations of the method of the present disclosure are described in a specific order in the drawings, this does not require or imply that the operations must be performed in that specific order, or that all of the shown operations must be performed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution.

[0325] Those skilled in the art should understand that the embodiments of the present disclosure can be provided as a method, a system, or a computer program product. Therefore, the present disclosure can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present disclosure can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic computer storage media, CD-ROM, optical computer storage media, etc.) containing computer-usable program code.

[0326] This disclosure is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to the disclosure. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to produce a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 or means for implementing the functions specified in a block or multiple blocks.

[0327] These computer program instructions can also be stored in a computer-readable computer storage medium that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable computer storage medium produce a manufactured article including instruction means that implement the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 or means for implementing the functions specified in a block or multiple blocks.

[0328] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are performed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 or means for implementing the functions specified in a block or multiple blocks.

[0329] Obviously, those skilled in the art can make various changes and modifications to this disclosure without departing from the spirit and scope of this disclosure. Thus, if these modifications and variations of this disclosure fall within the scope of the claims of this disclosure and their equivalent technologies, this disclosure is also intended to include these changes and modifications.

Claims

1. A method for detecting trend problems of an air conditioner, characterized in that, the method includes: For any air conditioner to be detected, at regular intervals, obtain multiple groups of air conditioner state data of the air conditioner to be detected, where the multiple groups of state data are air conditioner state data corresponding to different times; and, Based on the multiple groups of air conditioner state data, obtain the target air conditioner state data of the air conditioner to be detected; According to the target air conditioner state data of each air conditioner to be detected, determine each target recalled air conditioner among the detected air conditioners and the confidence level of each target recalled air conditioner; Perform clustering analysis on each target recalled air conditioner through the confidence level of each target recalled air conditioner to obtain the level of trend problems of each target recalled air conditioner.

2. The method according to claim 1, characterized in that, Any group of air conditioner state data includes time, on / off state, compressor exhaust temperature, outdoor condenser temperature, indoor pipe temperature value, indoor temperature, outdoor temperature, indoor set temperature, compressor set power, and compressor actual power; The obtaining the target air conditioner state data of the air conditioner to be detected based on the multiple groups of air conditioner state data includes: For any air conditioner to be detected, based on the multiple groups of on / off states of the air conditioner to be detected and the times corresponding to the multiple groups of on / off states, obtain the total usage duration of the air conditioner to be detected, where the total usage duration is used to represent the total usage duration of the air conditioner to be detected within a specified time period; and, When the air conditioner to be detected is in the cooling mode, then obtain the target superheat data based on multiple groups of the compressor exhaust temperature and multiple groups of the outdoor condenser temperature; or, when the air conditioner to be detected is in the heating mode, then obtain the target superheat data based on multiple groups of the compressor exhaust temperature and multiple groups of the indoor pipe temperature; and, Obtain the target indoor heat exchange temperature difference data based on multiple groups of the indoor temperature and multiple groups of the indoor pipe temperature values; and, Obtain the target outdoor heat exchange temperature difference data through multiple groups of the outdoor condenser temperature and multiple groups of the outdoor temperature; and, Utilize multiple groups of the indoor temperature and multiple groups of the indoor set temperature to obtain the target set temperature difference data; and, Obtain the target power gap data according to multiple groups of the compressor set power and multiple groups of the compressor actual power; Determine the total usage duration, the target superheat data, the target indoor heat exchange temperature difference data, the target outdoor heat exchange temperature difference data, the target set temperature difference data, and the target power gap data as the target air conditioner state data.

3. The method according to claim 2, characterized in that, The obtaining the total usage duration of the air conditioner to be detected based on the multiple groups of on / off states of the air conditioner to be detected and the times corresponding to the multiple groups of on / off states includes: Traverse each time in ascending order of time, and for any traversed time, perform the following steps: If the on-off state corresponding to the time is the on state and the on-off state at the next time after the time is the on state, then the difference between the time and the next time after the time is determined as the intermediate on-time duration; Otherwise, the intermediate on-time duration corresponding to the time is determined as the preset duration; The determined intermediate on-time durations are added together to obtain the total usage duration of the air conditioner to be detected.

4. The method according to claim 2, wherein, when the air conditioner to be detected is in the cooling mode, the target superheat degree data is obtained according to multiple groups of the compressor discharge temperature and multiple groups of the outdoor condenser temperature, including: For any group of air conditioner state data, the difference between the compressor discharge temperature and the outdoor condenser temperature in the air conditioner state data is obtained as the superheat degree data, and the variance, mean value of the multiple groups of superheat degree data of the air conditioner to be detected, and the number of the multiple groups of superheat degree data are determined as the target superheat degree data; when the air conditioner to be detected is in the heating mode, the target superheat degree data is obtained according to multiple groups of the compressor discharge temperature and multiple groups of the indoor pipe temperature, including: For any group of air conditioner state data, the difference between the compressor discharge temperature and the indoor pipe temperature in the air conditioner state data is obtained as the superheat degree data, and the variance, mean value of the multiple groups of superheat degree data of the air conditioner to be detected, and the number of the multiple groups of superheat degree data are determined as the target superheat degree data; The target indoor heat exchange temperature difference data is obtained according to multiple groups of the indoor temperature and multiple groups of the indoor pipe temperature values, including: For any group of air conditioner state data, the difference between the indoor temperature and the indoor pipe temperature value in the air conditioner state data is determined as the indoor heat exchange temperature difference data, and the variance, mean value of the multiple groups of indoor heat exchange temperature difference data, and the number of the multiple groups of indoor heat exchanges are determined as the target indoor heat exchange temperature difference data; The target outdoor heat exchange temperature difference data is obtained through multiple groups of the outdoor condenser temperature and multiple groups of the outdoor temperature, including: For any group of air conditioner state data, the difference between the outdoor condenser temperature and the outdoor temperature in the air conditioner state data is determined as the outdoor heat exchange temperature difference data, and the variance, mean value of the multiple groups of outdoor heat exchange temperature difference data, and the number of the multiple groups of outdoor heat exchanges are determined as the target outdoor heat exchange temperature difference data; The target set temperature difference data is obtained by using multiple groups of the indoor temperature and multiple groups of the indoor set temperature, including: For any group of air conditioner state data, the difference between the indoor temperature and the indoor set temperature in the air conditioner state data is determined as the set temperature difference data, and the variance, mean value of the multiple groups of set temperature difference data, and the number of the multiple groups of set temperature difference data are determined as the target set temperature difference data; The target power gap data is obtained according to multiple groups of the compressor set power and multiple groups of the compressor actual power, including: For any set of air conditioner status data, the difference between the set power of the compressor and the actual power of the compressor in the air conditioner status data is determined as the power gap data, and the variance, mean value of multiple sets of the power gap data, and the number of multiple sets of the power gap data are determined as the target power gap data.

5. The method according to claim 1, wherein, the determining of the target recalled air conditioners in each of the detected air conditioners and the confidence levels of the target recalled air conditioners according to the target air conditioner status data of each of the air conditioners to be detected includes: classifying each of the air conditioners to be detected by using a preset single-classification algorithm and the target air conditioner status data of each of the air conditioners to be detected, to obtain the categories of each of the air conditioners to be detected and the confidence levels of each of the air conditioners to be detected, wherein the categories include a recalled air conditioner category and a non-recalled air conditioner category; determining each of the air conditioners to be detected with the category of the recalled air conditioner category as the target recalled air conditioners, and determining the confidence levels of each of the air conditioners to be detected as the confidence levels of the target recalled air conditioners.

6. The method according to claim 1, wherein, the obtaining of the levels of the trending problems of the target recalled air conditioners by performing cluster analysis on the target recalled air conditioners through the confidence levels of the target recalled air conditioners includes: performing clustering on the target recalled air conditioners by using a preset clustering algorithm to obtain multiple clustering sets; for any one of the clustering sets, determining the confidence level of the target recalled air conditioner that is the clustering center in the clustering set as the clustering value of the clustering set; respectively determining the levels of the trending problems of each of the target recalled air conditioners in each of the clustering sets based on the clustering values of the clustering sets.

7. An electronic device, wherein, it includes a storage unit and a processor, wherein: the storage unit is configured to store multiple sets of air conditioner status data of each of the air conditioners to be detected, wherein the multiple sets of status data are air conditioner status data corresponding to different times; the processor is configured to: for any one of the air conditioners to be detected, acquire multiple sets of air conditioner status data of the air conditioner to be detected at intervals of a specified duration, wherein the multiple sets of status data are air conditioner status data corresponding to different times; and, obtain the target air conditioner status data of the air conditioner to be detected based on the multiple sets of air conditioner status data; determine the target recalled air conditioners in each of the detected air conditioners and the confidence levels of the target recalled air conditioners according to the target air conditioner status data of each of the air conditioners to be detected; perform cluster analysis on the target recalled air conditioners through the confidence levels of the target recalled air conditioners to obtain the levels of the trending problems of the target recalled air conditioners.

8. The electronic device according to claim 7, wherein, any set of air conditioner status data includes time, on / off state, compressor discharge temperature, outdoor condenser temperature, indoor pipe temperature value, indoor temperature, outdoor temperature, indoor set temperature, compressor set power, compressor actual power; when the processor executes the obtaining of the target air conditioner status data of the air conditioner to be detected based on the multiple sets of air conditioner status data, it is specifically configured to: For any air conditioner to be detected, based on multiple groups of on / off states of the air conditioner to be detected and the time corresponding to the multiple groups of on / off states, obtain the total usage duration of the air conditioner to be detected, where the total usage duration is used to represent the total usage duration of the air conditioner to be detected within a specified time period; and, When the air conditioner to be detected is in the cooling mode, then based on multiple groups of the compressor discharge temperature and multiple groups of the outdoor condenser temperature, obtain the target superheat degree data; or, when the air conditioner to be detected is in the heating mode, then based on multiple groups of the compressor discharge temperature and multiple groups of the indoor pipe temperature, obtain the target superheat degree data; and, Based on multiple groups of the indoor temperature and multiple groups of the indoor pipe temperature values, obtain the target indoor heat exchange temperature difference data; and, Through multiple groups of the outdoor condenser temperature and multiple groups of the outdoor temperature, obtain the target outdoor heat exchange temperature difference data; and, Utilize multiple groups of the indoor temperature and multiple groups of the indoor set temperature to obtain the target set temperature difference data; and, Based on multiple groups of the compressor set power and multiple groups of the compressor actual power, obtain the target power gap data; Determine the total usage duration, the target superheat degree data, the target indoor heat exchange temperature difference data, the target outdoor heat exchange temperature difference data, the target set temperature difference data, and the target power gap data as the target air conditioner state data.

9. The electronic device according to claim 7, wherein, The processor executes to determine the target recalled air conditioners and the confidence levels of the target recalled air conditioners in each of the detected air conditioners according to the target air conditioner state data of each air conditioner to be detected, and is specifically configured as: Use a preset single-classification algorithm and the target air conditioner state data of each air conditioner to be detected to classify each air conditioner to be detected, obtaining the categories of each air conditioner to be detected and the confidence levels of each air conditioner to be detected, where the categories include the recalled air conditioner category and the non-recalled air conditioner category; Determine the air conditioners to be detected with the category of the recalled air conditioner category as the target recalled air conditioners, and determine the confidence levels of each air conditioner to be detected as the confidence levels of each target recalled air conditioner.

10. The electronic device according to claim 7, wherein, The processor executes to perform a clustering analysis on each of the target recalled air conditioners through the confidence levels of each of the target recalled air conditioners to obtain the levels of the trending problems of each of the target recalled air conditioners, and is specifically configured as: Use a preset clustering algorithm to cluster each of the target recalled air conditioners, obtaining multiple clustering sets; For any one clustering set, determine the confidence level of the target recalled air conditioner that is the clustering center in the clustering set as the clustering value of the clustering set; Based on the clustering values of each clustering set, respectively determine the levels of the trending problems of each of the target recalled air conditioners in each clustering set.

Images