CN117824068A

CN117824068A - Air conditioner maintenance resource allocation method, device and equipment

Info

Publication number: CN117824068A
Application number: CN202211195122.1A
Authority: CN
Inventors: 卫立炜; 曲文武; 王宁; 李承志
Original assignee: Qingdao Hisense Smart Life Technology Co Ltd
Current assignee: Qingdao Hisense Smart Life Technology Co Ltd
Priority date: 2022-09-27
Filing date: 2022-09-27
Publication date: 2024-04-05

Abstract

The application provides a method, a device and equipment for distributing air conditioner maintenance resources, wherein the method comprises the following steps: analyzing historical operation data of each air conditioner in a preset area in a historical preset period to obtain historical characteristic data corresponding to each air conditioner; for any one air conditioner, determining whether any one air conditioner has faults in the history preset period according to history characteristic data corresponding to the any one air conditioner; inputting the counted number of the air conditioners with faults in a history preset period into a prediction model, and outputting the counted number of the air conditioners with faults in the preset period after the preset area; and distributing maintenance resources for the preset area according to the number of the air conditioners which fail in the subsequent preset period. By the method, corresponding maintenance resources can be timely and reasonably allocated for the preset area.

Description

Air conditioner maintenance resource allocation method, device and equipment

Technical Field

The application relates to the field of intelligent service of household appliances, in particular to a method, a device and equipment for distributing maintenance resources of an air conditioner.

Background

The air conditioner has obvious seasonal characteristics, and the air conditioner is used in the spring and autumn in the light season and in the summer and winter in the vigorous season. Air conditioners can experience a variety of problems and malfunctions during the life cycle of the air conditioner, such as: refrigerant leakage, dirt blockage, sensor faults, communication faults and the like. When these problems and malfunctions occur, a user needs to repair the air conditioner through an after-sales repair service.

The after-sales maintenance service of the air conditioner correspondingly has similar seasonal features, on one hand, when the user is in a busy season, the air conditioner in the user family can be switched from a 'dead' state to a 'frequently used' state for a plurality of months, and the number of the problematic air conditioners can show an explosion trend; on the other hand, the long use time of the air conditioner in the busy season also causes a large number of problematic air conditioners. The maintenance business of going up of the air conditioner in the busy season is busy, and the requirement of a user is often difficult to respond in time under the condition that the number of maintenance personnel is limited and maintenance resources are not reasonably and effectively distributed.

Disclosure of Invention

The embodiment of the application provides an air conditioner maintenance resource allocation method, device and equipment, which can reasonably and timely allocate air conditioner maintenance resources.

In a first aspect, an embodiment of the present application provides a method for allocating air conditioner maintenance resources, where the method includes:

Analyzing historical operation data of each air conditioner in a preset area in a historical preset period to obtain historical characteristic data corresponding to each air conditioner;

inputting historical characteristic data of any air conditioner into a fault diagnosis model to obtain a fault number for identifying the fault category of the any air conditioner, and if the fault number comprises a preset fault category identification, determining that the any air conditioner has a fault;

inputting the counted number of the air conditioners with faults in a preset period of the history into a prediction model, and outputting the counted number of the air conditioners with faults in the preset period after the preset region, wherein the prediction model is obtained by taking the number of the air conditioners with faults in a first preset period of the history in sample data as input, taking the number of the air conditioners with faults in a second preset period of the history in the sample data as output, and training the prediction model, wherein the second preset period of the history is a period after the first preset period of the history;

and distributing maintenance resources for the preset area according to the number of the air conditioners which fail in the subsequent preset period.

In the embodiment, through analyzing the historical data, determining the fault type through the fault diagnosis model and determining that the air conditioner with the specified fault type is the fault equipment, the air conditioner which does not need to be maintained can be screened out, and the situation that a large amount of maintenance resources are blindly distributed to the same area is avoided; and then counting the number of failed air conditioners in a history preset period according to a preset area, inputting the number of failed air conditioners in the history preset period into a prediction model to determine the number of air conditioners which possibly fail in the future prediction period, and predicting the peak time of the failure of the air conditioners in advance by predicting the number of air conditioners which possibly fail in a future prediction period, so that corresponding maintenance resources can be timely and reasonably distributed for the preset area, wherein the maintenance resources comprise maintenance equipment, maintenance personnel and the like.

In one possible implementation manner, the fault number includes a preset fault category identifier by the following manner:

if a fault state value for identifying a preset fault class exists in the output fault number, and the accumulated existence time of the fault state value is longer than a preset time length, determining that at least one fault class comprises a preset first fault class;

if the output fault number has a fault state value for identifying a preset fault category, and the ratio of the accumulated duration of the fault state value to the total starting duration is greater than a preset ratio, determining that at least one fault category comprises a preset second fault category.

In the above embodiment, a plurality of methods for judging fault types are provided, and appropriate judging methods can be used corresponding to faults of different types, so that the judging result of the fault type is more accurate.

In one possible implementation manner, the analyzing the historical operation data of each air conditioner in the preset area in the historical preset period to obtain the historical feature data corresponding to each air conditioner includes:

analyzing the historical operation data of any air conditioner in a preset unit time of the history aiming at any air conditioner in a preset area to obtain single historical feature data of at least one feature class corresponding to the any air conditioner;

Normalizing a plurality of single historical characteristic data of the same characteristic category in a continuous plurality of historical preset unit time;

respectively calculating the mean value and the variance of the normalized single historical feature data, and taking the mean value and the variance as the historical feature data corresponding to the feature class;

combining the historical characteristic data of the at least one characteristic category to obtain the historical characteristic data corresponding to any air conditioner in a plurality of continuous historical preset unit time;

the history preset period comprises a plurality of history preset unit time.

In the above embodiment, a plurality of single pieces of historical characteristic data of the same characteristic category in a plurality of historical preset unit time are normalized, and the data are normalized to the same numerical range, so that the subsequent calculation process is facilitated; the calculated normalized mean value and variance are used as the historical characteristic data corresponding to the characteristic category, so that the characteristic data can more clearly embody the running characteristic of the air conditioner.

In a possible implementation manner, the analyzing the historical operation data of the any one air conditioner within the preset unit time of the history to obtain single historical feature data of at least one feature class corresponding to the any one air conditioner includes the following part or all:

Taking the difference value between the exhaust temperature value of the compressor in any air conditioner refrigeration mode and the temperature value of the outdoor condenser in a history preset unit time or the difference value between the exhaust temperature value of the compressor in a heating mode and the temperature value of the indoor pipe as single piece of history exhaust superheat characteristic data corresponding to any air conditioner;

taking the difference value between the indoor temperature value and the indoor tube temperature value in any air conditioner refrigeration mode in a history preset unit time or the difference value between the indoor tube temperature value and the indoor temperature value in a heating mode as single piece of history indoor heat exchange temperature difference characteristic data corresponding to any air conditioner;

taking the difference value between the temperature value of an indoor condenser and the temperature value of an outdoor condenser in any air conditioner refrigerating mode in a history preset unit time or the difference value between the temperature value of the outdoor condenser and the temperature value of the indoor condenser in a heating mode as single piece of history outdoor heat exchange temperature difference characteristic data corresponding to any air conditioner;

taking the difference value between the indoor temperature value and the air conditioner set temperature value in any air conditioner refrigeration mode in the history preset unit time or the difference value between the preset temperature value and the indoor temperature value in the heating mode as single history set temperature difference characteristic data corresponding to any air conditioner;

And taking the difference value between the preset running power of any air conditioner compressor and the actual running power of the compressor in the history preset unit time as single history compressor frequency characteristic data corresponding to any air conditioner.

In the embodiment, by analyzing the historical operation data in the historical preset unit time, the operation condition of each air conditioner in the preset area can be monitored in real time, and whether the air conditioner has faults or not can be timely found; and the historical characteristic data is divided into a refrigerating mode and a heating mode, so that the distribution of maintenance resources in different seasons can be realized.

In one possible implementation manner, the calculating the mean and the variance of the normalized plurality of single historical feature data respectively, and taking the mean and the variance as the historical feature data corresponding to the feature class includes some or all of the following:

taking the average value and the variance of the single normalized historical exhaust superheat characteristic data as the historical exhaust superheat characteristic data corresponding to any air conditioner;

taking the average value and the variance of the respectively calculated normalized multiple single historical indoor heat exchange temperature difference characteristic data as the historical indoor heat exchange temperature difference characteristic data corresponding to any air conditioner;

Taking the average value and the variance of the respectively calculated normalized plurality of single historical outdoor heat exchange temperature difference characteristic data as the historical outdoor heat exchange temperature difference characteristic data corresponding to any air conditioner;

taking the average value and the variance of the respectively calculated normalized single historical set temperature difference characteristic data as the historical set temperature difference characteristic data corresponding to any air conditioner;

and taking the average value and the variance of the normalized frequency characteristic data of the plurality of single historical compressors calculated respectively as the frequency characteristic data of the historical compressor corresponding to any air conditioner.

In a possible implementation manner, the combining the historical feature data of the at least one feature class to obtain the historical feature data corresponding to the any one air conditioner in a continuous plurality of historical preset unit time includes:

and combining part or all of the historical exhaust superheat degree characteristic data, the historical indoor heat exchange temperature difference characteristic data, the historical outdoor heat exchange temperature difference characteristic data, the historical set temperature difference characteristic data and the historical compressor frequency characteristic data to obtain historical characteristic data corresponding to any one air conditioner in a plurality of continuous historical preset unit time.

In the above embodiment, the historical feature data of the plurality of feature categories of any one air conditioner are combined together to obtain the historical feature data corresponding to any one air conditioner, that is, when the fault category diagnosis is performed, different fault diagnosis models do not need to be trained for the historical feature data of different fault categories.

In one possible implementation manner, after determining that the any air conditioner has a fault, the method further includes:

and sending alarm information to a user corresponding to any air conditioner, wherein the alarm information comprises fault types and maintenance resource information.

In the above embodiment, when any air conditioner is found to possibly fail in the future use process, the user is timely reminded of overhauling before the failure peak period of the air conditioner comes, so that the problem of long waiting time of the user caused by accumulation of repair time in the failure peak period of the preset area is effectively avoided.

In a second aspect, an embodiment of the present application provides an air conditioner maintenance resource allocation device, where the device includes:

the analysis module is used for analyzing the historical operation data of each air conditioner in the preset area in the historical preset period to obtain the historical characteristic data corresponding to each air conditioner;

The determining module is used for inputting the historical characteristic data of any air conditioner into the fault diagnosis model to obtain a fault number for identifying the fault category of the any air conditioner, and if the fault number comprises a preset fault category identification, determining that the any air conditioner has a fault;

the prediction module is used for inputting the counted number of the air conditioners with faults in the history preset period into a prediction model and outputting the counted number of the air conditioners with faults in the preset period after the preset area, wherein the prediction model is obtained by taking the number of the air conditioners with faults in the first history preset period in sample data as input and the number of the air conditioners with faults in the second history preset period in the sample data as output, and the second history preset period is a period after the first history preset period;

and the distribution module is used for distributing maintenance resources for the preset area according to the number of the air conditioners which fail in the preset period.

In a third aspect, an embodiment of the present application provides an air conditioner maintenance resource allocation apparatus, including:

At least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect described above.

In a fourth aspect, embodiments of the present application provide a computer storage medium storing a computer program for causing a computer to perform the method of the first aspect.

Drawings

Fig. 1 is a schematic application scenario diagram of an air conditioner maintenance resource allocation method according to an embodiment of the present application;

fig. 2 is a schematic flow chart of a method for distributing air conditioner maintenance resources according to an embodiment of the present application;

FIG. 3 is a flowchart of a method for analyzing historical operating data according to an embodiment of the present application;

fig. 4 is a flowchart of a normalization method according to an embodiment of the present application;

fig. 5 is a schematic flow chart of a fault judging method according to an embodiment of the present application;

fig. 6 is a specific flowchart of a first fault determining method provided in the embodiment of the present application;

Fig. 7 is a specific flowchart of a second fault determining method provided in the embodiment of the present application;

fig. 8 is a schematic diagram of a number change trend of air conditioners with failures in 2019 according to an embodiment of the present application;

fig. 9 is a schematic diagram of a quantity change trend of an air conditioner that fails in 2020 according to an embodiment of the present application;

fig. 10 is a schematic diagram of a number change trend of air conditioners with a fault in 2021 provided in an embodiment of the present application;

fig. 11 is a schematic diagram of a number change trend of air conditioners with a fault in 2022 according to an embodiment of the present application;

FIG. 12 is a schematic flow chart of a trend method of fault equipment according to an embodiment of the present application;

fig. 13 is a schematic flow chart of a feature analysis method according to an embodiment of the present application;

fig. 14 is a flowchart of a fault diagnosis model training method according to an embodiment of the present application;

fig. 15 is a schematic diagram of an air conditioner fault determination flow provided in an embodiment of the present application;

fig. 16 is a schematic diagram of an air conditioner maintenance resource allocation device according to an embodiment of the present application;

fig. 17 is a schematic diagram of an air conditioner maintenance resource allocation device according to an embodiment of the present application;

fig. 18 is a schematic diagram of a storage medium according to an embodiment of the present application.

Detailed Description

For the purposes of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure. Embodiments and features of embodiments in this application may be combined with each other arbitrarily without conflict. Also, while a logical order of illustration is depicted in the flowchart, in some cases the steps shown or described may be performed in a different order than presented.

The terms first and second in the description and claims of the present application and in the above-described figures are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the term "include" and any variations thereof is intended to cover non-exclusive protection. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus. The term "plurality" in the present application may mean at least two, for example, two, three or more, and embodiments of the present application are not limited.

Fig. 1 is a schematic application scenario diagram of an air conditioner maintenance resource allocation method according to an embodiment of the present application, where the application scenario includes: server 101, database 102, and at least one air conditioner (air conditioner 103_1, air conditioner 103_2, and air conditioner 103_n in the example in the figure). Each air conditioning device communicates with the server 101, that is, each air conditioning device uploads historical operation data to the server 101, the server 101 analyzes the historical operation data uploaded by each air conditioning device to determine whether each air conditioner has a fault, and the database 102 stores data and programs required by the server 101 to execute the air conditioning maintenance resource allocation method.

Aiming at the problem that maintenance resources cannot be reasonably distributed in the air conditioner maintenance peak period at present, the embodiment of the application provides an air conditioner maintenance resource distribution method, the flow of which is shown in figure 2, and the method comprises the following steps:

s201: analyzing historical operation data of each air conditioner in a preset area in a historical preset period to obtain historical characteristic data corresponding to each air conditioner.

Firstly, all air conditioners are divided according to different areas, and the operation conditions of the air conditioners in different areas are different, for example, the peak period of the air conditioner in the north is mostly in summer, and for the south without heating, the peak period of the air conditioner in winter and summer can be the peak period of the air conditioner.

When the air conditioner is started, the operation data of the air conditioner can be uploaded to the server, and the server can analyze when receiving the operation data of the air conditioner.

In a possible implementation manner, the historical operation data of each air conditioner in the preset area in the historical preset period is analyzed to obtain the historical feature data corresponding to each air conditioner, as shown in fig. 3, and the method includes:

s301: analyzing the historical operation data of any air conditioner in a preset unit time of the history aiming at any air conditioner in a preset area to obtain single historical characteristic data of at least one characteristic category corresponding to the any air conditioner.

In order to realize real-time monitoring of the operation condition of the air conditioner, a piece of historical operation data is uploaded every unit time, and because the embodiment of the application needs to predict the number of the air conditioners which fail in the future, the operation data of the historical time relative to the future moment needs to be obtained, that is, the operation data of the air conditioner at the current moment also belongs to the historical operation data for the future moment.

For any air conditioner, various operation data can be generated in the operation process, and single historical characteristic data with different characteristic categories can be obtained according to different analyses of different operation data.

S302: and normalizing the plurality of single pieces of historical characteristic data of the same characteristic category in the continuous plurality of historical preset unit time.

In order to limit the preprocessed data within a certain range and eliminate adverse effects caused by singular sample data, a plurality of single pieces of historical characteristic data of the same characteristic category in a continuous plurality of historical preset unit time are normalized. After the data normalization processing, in the subsequent process of determining the fault type and the number prediction, the speed of gradient descent to solve the optimal solution can be increased, and the prediction precision can be improved.

In the embodiment of the present application, a normalization method is provided, as shown in fig. 4, and a specific flow includes:

s401: according to the characteristic values of a plurality of single pieces of historical characteristic data of different characteristic categories, determining the numerical upper limit and the numerical lower limit of the characteristic values;

s402: normalizing each characteristic value of the plurality of single pieces of historical characteristic data by adopting the following formula:

(eigenvalue-lower numerical limit)/(upper numerical limit-lower numerical limit);

and if the characteristic value is smaller than the lower limit, replacing the characteristic value by using the numerical lower limit. The normalization method may be other methods than the above embodiments, and is not specifically limited herein.

S303: and respectively calculating the mean and the variance of the normalized single historical characteristic data, and taking the mean and the variance as the historical characteristic data corresponding to the characteristic category.

After normalization, the data has statistical distribution, in the embodiment of the present application, the mean and variance are used as the historical feature data corresponding to the feature class, and other features may be extracted as the historical feature data, for example, covariance of a plurality of single historical feature data, which is not specifically limited herein.

S304: and combining the historical characteristic data of the at least one characteristic category to obtain the historical characteristic data corresponding to any air conditioner in a plurality of continuous historical preset unit time.

For example, the historical feature data of the first feature class is as [0.2,0.15,0.32,0.2 ]]The one-dimensional row vectors, one-dimensional column vectors, and other formats are shown, the format of the historical feature data is not specifically limited, and the historical feature data of the second feature class is as follows [0.7,0.52,0.47,0.8 ]]Combining the historical feature data of the first feature class with the historical feature data of the second feature class to obtain, for example The shown 2 x 4 multidimensional matrix may also be e.g. [0.2 0.15 0.32 0.2 0.7 0.52 0.47 0.48 ]]The form of the one-dimensional vector is shown, and the embodiments of the present application are not limited to a specific combination.

S202: and inputting the historical characteristic data of any air conditioner into a fault diagnosis model to obtain a fault number for identifying the fault category of the any air conditioner, and if the fault number comprises a preset fault category identification, determining that the any air conditioner has faults.

In order to predict the number of failed air conditioners in a preset period by using the number of failed air conditioners in the preset period, it is first required to determine whether each air conditioner fails in the preset period, and if so, the air conditioners are counted.

The specific steps for determining whether the any air conditioner has a fault in the history preset period are shown in fig. 5:

s501: and inputting the historical characteristic data of any air conditioner into a fault diagnosis model to obtain a fault number for identifying any air conditioner fault category.

S502: and judging whether the fault number comprises a preset fault type identifier, if so, executing S503, otherwise, executing S504.

S503: determining that any air conditioner has a fault;

s504: and determining that any air conditioner has no fault.

Through the analysis process in S201, the historical feature data corresponding to any air conditioner can be obtained, where the historical feature data includes data of multiple feature types, so that multiple fault types can be obtained after a fault diagnosis model is obtained, where the fault diagnosis model is obtained by training sample historical feature data and sample fault types corresponding to the sample historical feature data.

The fault categories of the air conditioner include various kinds, for example: refrigerant leakage, dirt blockage, sensor failure, communication failure, etc., but for some relatively light failures, temporary use may not be affected and maintenance may not be required, and it may not be necessary to allocate maintenance resources thereto. For example, the air conditioner is not used as fault equipment under the condition that the normal operation of the air conditioner is not affected by lighter dirt blocking.

Inputting a plurality of continuous historical characteristic data of any air conditioner in a preset unit time into the fault diagnosis model for fault diagnosis to obtain a fault number for identifying any air conditioner fault category, wherein the fault category number comprises identification bits of a plurality of fault categories, for example: 0100 contains four kinds of fault category identifiers, if a fault of the fault category is not identified by 0, a fault of the fault category is identified by 1 (a fault of the fault category is also not identified by 1, a fault of the fault category is identified by 0), then 0100 indicates that a fault of a first fault category, a fault of a third fault category and a fault of a fourth fault category is not occurred, a fault of a second fault category is occurred, each identification bit can be numbered according to a left-to-right order, and each identification bit can be numbered according to a right-to-left order, which is not particularly limited herein. When judging that at least one fault class comprises the preset fault class, training by using the preset fault class and the historical characteristic data corresponding to the preset fault class as a data set when training the fault class diagnosis model, namely, screening out the characteristic data which does not accord with the preset fault class in advance, and finally obtaining the fault diagnosis model which can only identify the preset fault class; the historical feature data may not be screened in advance, and then it may be determined whether a predetermined fault class exists after the result is output, for example, 00001 is output finally, where the first fault class, the second fault class, the third fault class, and the fourth fault class are predetermined fault classes, and the fifth fault class is not a predetermined fault class, so that even if the air conditioner fails in the fifth fault class, it is determined that the air conditioner does not have a fault.

In order to ensure the accuracy of fault class determination, a fault class determination method adapted to a fault class may be selected for different fault classes.

(1) Indoor and outdoor communication failure

For indoor and outdoor communication faults, the specific flow of the fault type judging method is shown in fig. 6:

s601: judging whether a fault state value for identifying a preset fault class exists in the output fault numbers, if so, executing S602, otherwise, executing S603;

s602: judging whether the accumulated existence duration of the fault state value is longer than a preset duration, if so, executing S604, otherwise, executing S603;

s603: no fault exists;

s604: there is a fault.

For example, if the failure numbers outputted within 5 seconds are 0100, 0101, 0100, 0000 and 0100, respectively, and if the preset time period is 2 seconds, the identification bits are numbered in the order from left to right, then for the second failure type (indoor and outdoor communication failure), the indoor and outdoor communication failure occurs in the first second, the second, the third second and the fifth seconds, respectively, and the indoor and outdoor communication failure occurs in 3 seconds in succession, which indicates that the air conditioner is a device of the indoor and outdoor communication failure, and the air conditioner is counted when the number of failed air conditioners is counted.

(2) Indoor and outdoor temperature sensor failure

For faults of indoor and outdoor temperature sensors, the specific flow of the fault type judging method is shown in fig. 7:

s701: judging whether a fault state value for identifying a preset fault class exists in the output fault numbers, if so, executing S702, otherwise, executing S703;

s702: judging whether the ratio of the accumulated duration of the fault state value to the total starting duration is larger than a preset ratio, if so, executing S704, otherwise, executing S703;

s703: no fault exists;

s704: there is a fault.

For example, in units of each second, the starting time is 5 seconds, the fault numbers outputted per second are 0100, 0101, 0100, 0000 and 0100 respectively, if the preset ratio is 50%, the identification bits are numbered in the sequence from left to right, for the second fault type (the faults of the indoor and outdoor temperature sensors), the faults of the indoor and outdoor temperature sensors occur in the first second, the second, the third second and the fifth seconds respectively, and the faults of the indoor and outdoor temperature sensors occur in 3 seconds continuously, the ratio of the fault state value accumulated time length to the total starting time length is 3/5=60% >50%, which indicates that the air conditioner is the equipment of the faults of the indoor and outdoor temperature sensors, and the air conditioner is counted when counting the number of the faulty air conditioners.

S203: inputting the counted number of the air conditioners with faults in a preset period of the history into a prediction model, and outputting the counted number of the air conditioners with faults in the preset period after the preset region, wherein the prediction model is obtained by taking the number of the air conditioners with faults in a preset period of a first history in sample data as input, taking the number of the air conditioners with faults in a preset period of a second history in the sample data as output, and training the prediction model, wherein the preset period of the second history is a period after the preset period of the first history.

After determining whether each air conditioner in the preset area has a fault, the number of the air conditioners with faults in the history preset period can be counted, wherein the history can be used for 3 months as the history preset period, and the history can be used for 1 month as the history preset period, and the method is not particularly limited in the embodiment of the application.

Any air conditioner fails on any one of the days in the history preset period, the air conditioner is judged to fail in the history period, or any air conditioner fails on any 10 hours in the history preset period, the air conditioner is judged to fail in the history period, and specific time of the air conditioner failure is not limited, so long as the air conditioner failure is in the history period.

The method for predicting the number of air conditioners that fail within a preset period after prediction provided in the embodiment of the present application is to use a prediction model, for example, bi-directional Long Short-Term Memory (Bi-LSTM) neural network, and may also be a logistic regression model or other prediction models, which are not specifically limited herein.

Since the same trend is given to the number of failed air conditioners each year, the trend of the number of failed air conditioners in the current year can be predicted using the trend of the number of failed air conditioners in the historical year.

For example, the trend of the number of failed air conditioners 2022 is predicted from the trend of the number of failed air conditioners in a certain area 2019, 2020, 2021.

The number of failed air conditioners corresponding to the above-described years for 4, 5, 6 and 7 months is shown in table 1.

TABLE 1

	4 months of	5 months of	6 months of	7 months of
					2019	25	35	40	150
2020, 2020	20	32	44	167
					2021	19	28	42	142
2022 years	24	36	39	？

As shown in fig. 8, the number of failed air conditioners in 2019 for 4, 5, 6 and 7 months is changed to gradually rise, and the number of air conditioners in 6 to 7 months is greatly increased; as shown in fig. 9, the number of failed air conditioners in 2020 for 4, 5, 6 and 7 months is changed to gradually increase, and the number of air conditioners from 6 to 7 months is greatly increased; as shown in fig. 10, the number of failed air conditioners in 2021 years 4, 5, 6 and 7 is changed to gradually rise, and the number of 6 to 7 months is greatly increased. For some areas, 7 months and 8 months are peak periods of air conditioner usage, so the number of air conditioners that fail in 7 months is large, and based on the trend of the change in the number of air conditioners that fail in 2019, 2020 and 2021, 4, 5, 6 and 7 months, the number of air conditioners that fail in 2022, 7 months, can be predicted from the number of air conditioners that fail in 2022, 4, 5 and 6 months, as shown in fig. 11, exhibiting a tendency of a large increase in the number of air conditioners that fail. Moreover, according to the trend diagrams shown in fig. 8-10, the time of occurrence of a large number of faulty air conditioners can be predicted, for example, 7 months, so that the required maintenance resources can be distributed well before 7 months come, and the maintenance resources can be scheduled timely when the user has a demand.

In addition, after determining that any one of the air conditioners has a fault, the method further comprises:

If a fault occurs in one air conditioner in 4 months, 5 months and 6 months, an alarm can be timely sent to a user to remind the user to start up and overhaul the air conditioner so as to stagger the peak time of the fault occurrence of the air conditioner, reduce or avoid the waiting time of the user for maintenance in a busy season, and further improve the use experience of the user.

S204: and distributing maintenance resources for the preset area according to the number of the air conditioners which fail in the subsequent preset period.

The embodiment of the application provides an air conditioner maintenance resource allocation method, which is used for presetting the number of failed air conditioners in a certain time period in the future through statistical analysis of the number of air conditioners with historical failures, so that the time of maintenance peaks can be predicted in advance, and maintenance resources can be allocated more reasonably. In addition, through the analysis of the historical characteristic data of the air conditioner, a fault characteristic model is generated, so that the problem of the air conditioner in the home of which users is predicted, the users are reminded to start up and overhaul the air conditioner in advance before the maintenance peak arrives, the waiting time of the users in the busy season is reduced or avoided, and the use experience of the users is improved.

An embodiment of predicting the number of failed air conditioners will be described below by way of example, with the overall flow shown in fig. 12:

(1) Firstly, combining historical operation data with service data of an air conditioner to perform feature analysis to obtain historical feature data containing service features, wherein the service data comprises but is not limited to: air conditioner model and region information.

Taking the difference value between the exhaust temperature value of the compressor in any air conditioner refrigeration mode and the temperature value of the outdoor condenser in a history preset unit time or the difference value between the exhaust temperature value of the compressor in a heating mode and the temperature value of the indoor pipe as single piece of history exhaust superheat characteristic data corresponding to any air conditioner; normalizing the single piece of historical exhaust superheat characteristic data according to the normalization mode in the step S402; and taking the average value and the variance of the single normalized historical exhaust superheat characteristic data as the historical exhaust superheat characteristic data corresponding to any air conditioner.

Taking the difference value between the indoor temperature value and the indoor tube temperature value in any air conditioner refrigeration mode in a history preset unit time or the difference value between the indoor tube temperature value and the indoor temperature value in a heating mode as single piece of history indoor heat exchange temperature difference characteristic data corresponding to any air conditioner; normalizing the single piece of historical indoor heat exchange temperature difference characteristic data according to the normalization mode in the step S402; taking the average value and the variance of the respectively calculated normalized multiple single historical indoor heat exchange temperature difference characteristic data as the historical indoor heat exchange temperature difference characteristic data corresponding to any air conditioner;

Taking the difference value between the temperature value of an indoor condenser and the temperature value of an outdoor condenser in any air conditioner refrigerating mode in a history preset unit time or the difference value between the temperature value of the outdoor condenser and the temperature value of the indoor condenser in a heating mode as single piece of history outdoor heat exchange temperature difference characteristic data corresponding to any air conditioner; normalizing the single piece of historical outdoor heat exchange temperature difference characteristic data according to the normalization mode in the step S402; taking the average value and the variance of the respectively calculated normalized plurality of single historical outdoor heat exchange temperature difference characteristic data as the historical outdoor heat exchange temperature difference characteristic data corresponding to any air conditioner;

taking the difference value between the indoor temperature value and the air conditioner set temperature value in any air conditioner refrigeration mode in the history preset unit time or the difference value between the preset temperature value and the indoor temperature value in the heating mode as single history set temperature difference characteristic data corresponding to any air conditioner; normalizing the single piece of historical set temperature difference characteristic data according to the normalization mode in the step S402; taking the average value and the variance of the respectively calculated normalized single historical set temperature difference characteristic data as the historical set temperature difference characteristic data corresponding to any air conditioner;

Taking the difference value between the preset running power of any air conditioner compressor and the actual running power of the compressor in the history preset unit time as single history compressor frequency characteristic data corresponding to any air conditioner; normalizing the single piece of historical compressor characteristic data according to the normalization mode in the step S402; and taking the average value and the variance of the normalized frequency characteristic data of the plurality of single historical compressors calculated respectively as the frequency characteristic data of the historical compressor corresponding to any air conditioner.

In the embodiment of the present application, the historical feature data of the feature class is listed, and part or all of the historical feature data can be selected as the historical feature data of any air conditioner, or the feature data of other feature classes can be added, which is not particularly limited herein.

After the history feature data of any air conditioner is obtained, further processing is performed on the history feature data, and specific steps are shown in fig. 13:

s1301: mapping the characteristics of the air conditioner model and the regional information character string in any air conditioner service data into numerical values; wherein the mapping method includes, but is not limited to, tag encoding and one-hot encoding.

S1302: screening the historical characteristic data of any air conditioner, and screening the historical characteristic data which accords with the preset fault category to obtain a characteristic subset.

S1303: and correlating the numerical value and the feature subset corresponding to any one air conditioner business data with the equipment identifier of any one air conditioner to obtain a correlation feature vector corresponding to any one air conditioner.

S1304: and selecting by a fault feature method based on the associated feature vector, and reducing the dimension of the high-dimension feature vector of the fault. In order to convert the high-dimensional feature vector into a low-dimensional feature vector or sensitive feature with better discrimination performance, the high-dimensional feature vector can be subjected to dimension reduction operation by adopting principal component analysis or other feature selection methods.

(2) And then, carrying out fault category identification based on the historical characteristic data to obtain the air conditioner with faults in the historical preset period.

The fault class determination is based on a fault diagnosis model, and a specific flow of generating the fault diagnosis model is shown in fig. 14:

s1401: constructing a data set based on the low-dimensional feature vector in the S1304 and the corresponding fault class number;

s1402: training a classification algorithm based on the data set to obtain a fault diagnosis model.

The specific flow of obtaining the fault class according to the fault diagnosis model is shown in fig. 15:

s1501: inputting the associated feature vector into a fault diagnosis model, outputting to obtain a fault class corresponding to the associated feature vector, and judging whether a fault exists in the corresponding air conditioner;

s1502: when the air conditioner is determined to be faulty, a corresponding user is associated according to the equipment identifier of the air conditioner, and a startup maintenance prompt is carried out on the user.

(3) And finally, counting the number of the failed air conditioners in the history preset period, inputting a prediction model, outputting the number of the failed air conditioners in the preset period after the preset area, and further realizing trend prediction of the failed equipment.

The specific embodiments of the number of failed air conditioners within the preset period are described above, and will not be repeated here.

Based on the same inventive concept, the embodiment of the present application further provides an air conditioner maintenance resource allocation device 1600, as shown in fig. 16, where the device includes:

The analyzing module 1601 is configured to analyze historical operation data of each air conditioner located in the preset area in a historical preset period to obtain historical feature data corresponding to each air conditioner;

a determining module 1602, configured to input historical feature data of any one air conditioner into a fault diagnosis model to obtain a fault number for identifying a fault class of the any one air conditioner, and determine that the any one air conditioner has a fault if the fault number includes a preset fault class identifier;

the prediction module 1603 is configured to input the counted number of failed air conditioners in a preset period of history into a prediction model, and output the counted number of failed air conditioners in a preset period after the preset region, where the prediction model is obtained by training the prediction model with the number of failed air conditioners in a first preset period of history in sample data as input and the number of failed air conditioners in a second preset period of history in sample data as output, where the second preset period of history is a period after the first preset period of history;

an allocation module 1604 allocates maintenance resources to the preset area according to the number of failed air conditioners within the subsequent preset period.

In a possible implementation manner, the determining module 1602 is configured to determine that the fault number includes a preset fault category identifier in the following manner:

In a possible implementation manner, the analyzing module 1601 is configured to analyze historical operation data of each air conditioner located in a preset area in a historical preset period to obtain historical feature data corresponding to each air conditioner, and includes:

the history preset period comprises a plurality of history preset unit time.

In a possible implementation manner, the analyzing module 1601 is configured to analyze the historical operation data of the any one air conditioner within a preset unit time of the history to obtain single historical feature data of at least one feature class corresponding to the any one air conditioner, where the single historical feature data includes part or all of the following:

In one possible implementation, the parsing module 1601 is configured to calculate a mean and a variance of the normalized plurality of single pieces of historical feature data, and take the mean and the variance as the historical feature data corresponding to the feature class, where the historical feature data includes some or all of the following:

In a possible implementation manner, the analyzing module 1601 is configured to combine the historical feature data of the at least one feature class to obtain historical feature data corresponding to the any one air conditioner within a plurality of continuous historical preset unit times, where the analyzing module includes:

In a possible implementation manner, the determining module 1602 is configured to determine that the any air conditioner has a fault, and further includes:

Based on the same inventive concept, the embodiment of the present application further provides an air conditioner maintenance resource allocation device, where the device includes:

the apparatus includes at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the intelligent cooking method of the above embodiment as applied to a cloud server.

An electronic device 130 according to this embodiment of the present application is described below with reference to fig. 17. The electronic device 130 shown in fig. 17 is merely an example, and should not be construed to limit the functionality and scope of use of the embodiments herein.

As shown in fig. 17, the electronic device 130 is embodied in the form of a general-purpose electronic device. Components of electronic device 130 may include, but are not limited to: the at least one processor 131, the at least one memory 132, and a bus 133 connecting the various system components, including the memory 132 and the processor 131.

The processor 131 is configured to read and execute the instructions in the memory 132, so that the at least one processor can execute the intelligent cooking method applied to the cloud server provided in the foregoing embodiment.

Bus 133 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a processor, and a local bus using any of a variety of bus architectures.

The electronic device 130 may also communicate with one or more external devices 134 (e.g., keyboard, pointing device, etc.), one or more devices that enable a user to interact with the electronic device 130, and/or any device (e.g., router, modem, etc.) that enables the electronic device 130 to communicate with one or more other electronic devices. Such communication may occur through an input/output (I/O) interface 135. Also, electronic device 130 may 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 network adapter 136. As shown, network adapter 136 communicates with other modules for electronic device 130 over bus 133. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 130, including, but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.

In some possible embodiments, aspects of an intelligent cooking method applied to a cloud server provided herein may also be implemented in the form of a program product comprising program code for causing a computer device to perform the steps of an intelligent cooking method applied to a cloud server according to various exemplary embodiments of the present application as described herein above, when the program product is run on the computer device.

In addition, the present application also provides a computer-readable storage medium, as shown in fig. 18, in which a computer program for causing a computer to execute the method according to any one of the above embodiments is stored.

Storage media may include readable media in the form of volatile memory, such as Random Access Memory (RAM) 1321 and/or cache memory 1322, and may further include Read Only Memory (ROM) 1323; may also include a program/utility 1325 having a set (at least one) of program modules 1324, such program modules 1324 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 which may include an implementation of a network environment.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to cover such modifications and variations.

Claims

1. An air conditioner maintenance resource allocation method, which is characterized by comprising the following steps:

2. The method of claim 1, wherein the fault number is determined to include a predetermined fault category identification by:

3. The method according to claim 1, wherein the analyzing the historical operation data of each air conditioner in the preset area in the historical preset period to obtain the corresponding historical feature data of each air conditioner includes:

combining the historical characteristic data of the at least one characteristic category to obtain the historical characteristic data corresponding to any one air conditioner in a continuous plurality of historical preset unit time _。

4. The method of claim 3, wherein the analyzing the historical operation data of the any one air conditioner within the preset unit time of the history to obtain the single historical feature data of at least one feature class corresponding to the any one air conditioner includes the following part or all:

5. A method according to claim 3, wherein the calculating means and variances of the normalized plurality of single pieces of historical feature data, respectively, and taking the means and variances as the historical feature data corresponding to the feature class includes some or all of:

6. The method of claim 3, wherein the combining the historical feature data of the at least one feature class to obtain the historical feature data corresponding to the any one air conditioner in a continuous plurality of historical preset unit time includes:

7. The method of claim 1, wherein after determining that the any one of the air conditioners has a failure, further comprising:

8. An air conditioner maintenance resource allocation device, characterized in that the device comprises:

9. An air conditioner maintenance resource allocation apparatus, characterized by comprising:

at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A computer storage medium, characterized in that the computer storage medium stores a computer program for causing a computer to perform the method according to any one of claims 1-7.