Abnormal alarm method, system, intelligent gardening weeding equipment and storage medium

Abstract

The present application provides an abnormal alarm method, system, intelligent gardening weeding equipment and storage medium, which obtains historical freezing records; presets multiple freezing risk levels, and determines the pressure abnormality domain, temperature abnormality domain and flow rate abnormality domain of each freezing risk level based on the historical freezing records; determines the abnormal response of each pressure abnormality domain based on the coupling characteristics of each pressure abnormality domain, and continues to obtain the abnormal response of each temperature abnormality domain and the abnormal response of each flow rate abnormality domain in the manner of the above steps; obtains the state data set of the target gardening weeding equipment at the current moment, and determines the risk response value of each freezing risk level based on all abnormal responses and state data sets; and performs risk abnormality alarm based on all risk response values. The above scheme combines the coupling between the indicators related to the freezing of the herbicide to perform multi-dimensional alarm on the freezing risk, thereby improving the reliability of the abnormal alarm of the intelligent gardening weeding equipment.

Description

Technical Field

[0001] The present application relates to the technical field of abnormal alarm, and more specifically, to an abnormal alarm method, system, intelligent gardening weeding equipment and storage medium. Background Art

[0002] Smart gardening weeding equipment is a device that uses advanced technology and artificial intelligence to automate and optimize the weeding process. It can adjust the spraying time and amount of herbicides in real time through artificial intelligence algorithms. The abnormal alarm of smart gardening weeding equipment is mainly through monitoring the freezing of herbicides inside the storage tank, and issuing an freezing risk alarm when the herbicide is frozen or about to freeze.

[0003] The icing risk alarm of existing intelligent gardening weeding equipment generally monitors the temperature in the liquid storage tank in real time through a temperature sensor, and responds to excessively low temperature values ​​to issue an alarm. However, this method ignores the coupling between the temperature value in the liquid storage tank and other indicators related to the freezing of the herbicide. For example, when the herbicide flow rate in the liquid storage tank is fast, the herbicide will not freeze even if the temperature is low. This coupling situation will cause the abnormal alarm of the intelligent gardening weeding equipment to respond incorrectly. Therefore, how to combine the coupling between the indicators related to the freezing of the herbicide to issue a multi-dimensional alarm for the icing risk, and thereby improve the reliability of the abnormal alarm of the intelligent gardening weeding equipment, is a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides an abnormal alarm method, system, intelligent gardening weeding equipment and storage medium, which can perform multi-dimensional alarm on the risk of freezing in combination with the coupling between indicators related to herbicide freezing, thereby improving the reliability of abnormal alarm of intelligent gardening weeding equipment.

[0005] In a first aspect, the present application provides an abnormality alarm method, comprising:

[0006] Get historical freezing records of smart gardening weeding equipment;

[0007] Preset multiple icing risk levels, and determine the pressure anomaly domain, temperature anomaly domain and flow velocity anomaly domain of each icing risk level according to the historical icing records;

[0008] Based on the coupling characteristics of each pressure anomaly domain, a boundary correction factor of the corresponding pressure anomaly domain is determined, and the boundary of the corresponding pressure anomaly domain is corrected according to each boundary correction factor, thereby obtaining the abnormal response of each pressure anomaly domain, and the abnormal response of each temperature anomaly domain and the abnormal response of each flow velocity anomaly domain are further obtained by adopting the above steps;

[0009] Acquire a state data set of the herbicide in the target gardening weeding equipment at the current moment, determine an abnormal response matrix according to all abnormal responses and the state data set, and determine a risk response value for each freezing risk level through the abnormal response matrix;

[0010] The alarm level of the target gardening weeding equipment at the current moment is determined according to all risk response values, and a risk abnormality alarm is performed based on the alarm level.

[0011] In some embodiments, determining the pressure anomaly domain, temperature anomaly domain, and flow rate anomaly domain for each icing risk level according to the historical icing records specifically includes:

[0012] Obtaining the freezing risk level, temperature value, flow rate value and pressure value at each freezing in the historical freezing record;

[0013] For each icing risk level, determine the pressure anomaly domain of the icing risk level according to all pressure values ​​corresponding to the icing risk level;

[0014] For each icing risk level, determine the temperature anomaly domain of the icing risk level according to all temperature values ​​corresponding to the icing risk level;

[0015] For each icing risk level, a flow rate anomaly domain of the icing risk level is determined according to all flow rate values ​​corresponding to the icing risk level.

[0016] In some embodiments, determining the boundary correction factor of the corresponding pressure anomaly domain based on the coupling characteristics of each pressure anomaly domain specifically includes:

[0017] Select a pressure anomaly domain and determine the pressure center of the pressure anomaly domain;

[0018] Determine the pressure coupling amount of the pressure anomaly domain according to the pressure center, wherein the pressure coupling amount is the coupling feature;

[0019] Determine the pressure distribution entropy of all pressure values ​​in the pressure anomaly domain according to the pressure center;

[0020] Determining a boundary correction factor of the pressure anomaly domain according to the pressure distribution entropy and the pressure coupling amount;

[0021] Repeat the above steps to obtain the boundary correction factor of the residual pressure anomaly domain.

[0022] In some embodiments, determining the pressure coupling amount of the pressure anomaly domain according to the pressure center specifically includes:

[0023] Determining the amount of overlap between the pressure anomaly domain and an adjacent pressure anomaly domain according to the pressure center and the boundary of the pressure anomaly domain;

[0024] The pressure coupling amount of the pressure anomaly domain is determined according to the interval overlap amount.

[0025] In some embodiments, the boundary of the corresponding pressure anomaly domain is corrected according to each boundary correction factor, and then the abnormal response of each pressure anomaly domain is obtained, which specifically includes:

[0026] A pressure anomaly domain is selected, and an anomaly domain span of the pressure anomaly domain is determined according to a boundary correction factor of the pressure anomaly domain;

[0027] Acquire the pressure center of the pressure anomaly domain, determine the corrected boundary of the pressure anomaly domain according to the anomaly domain span and the pressure center of the pressure anomaly domain, and then obtain the corrected pressure domain of the pressure anomaly domain;

[0028] Determine the pressure ambiguity rate of the modified pressure domain;

[0029] Determine a plurality of basic pressure values ​​of the modified pressure domain according to the expected distribution entropy and the pressure fuzziness rate;

[0030] Determine the abnormal response of the modified pressure domain according to all the basic pressure values ​​in the modified pressure domain;

[0031] Repeat the above steps to obtain the abnormal response of the remaining pressure abnormal domain.

[0032] In some embodiments, determining the abnormal response matrix according to all abnormal responses and the state data set specifically includes:

[0033] Obtain the temperature value, water flow value and pressure value at the current moment in the state data set;

[0034] Determine the anomaly probability between the pressure value at the current moment and the anomaly response of each pressure anomaly domain;

[0035] Repeat the above steps to obtain the abnormal probability between the flow velocity value at the current moment and the abnormal response of each flow velocity abnormal domain and the abnormal probability between the temperature value at the current moment and the abnormal response of each temperature abnormal domain;

[0036] Convert all anomaly probabilities into an anomaly response matrix.

[0037] In some embodiments, performing risk abnormality alarm based on the alarm level specifically includes:

[0038] A preset risk threshold is set, and if the alarm level is greater than the risk threshold, an alarm is issued;

[0039] If the alarm level is less than or equal to the risk threshold, no alarm is issued.

[0040] In a second aspect, the present application provides an abnormality alarm system, the abnormality alarm system comprising:

[0041] A collection module, used to obtain historical freezing records of smart gardening weeding equipment;

[0042] A processing module, used for presetting a plurality of icing risk levels, and determining a pressure anomaly domain, a temperature anomaly domain and a flow rate anomaly domain for each icing risk level according to the historical icing records;

[0043] The processing module is also used to determine the boundary correction factor of the corresponding pressure anomaly domain based on the coupling characteristics of each pressure anomaly domain, and correct the boundary of the corresponding pressure anomaly domain according to each boundary correction factor, so as to obtain the abnormal response of each pressure anomaly domain, and continue to obtain the abnormal response of each temperature anomaly domain and the abnormal response of each flow velocity anomaly domain in the manner of the above steps;

[0044] The processing module is also used to obtain a state data set of the herbicide in the target gardening weeding equipment at the current moment, determine an abnormal response matrix according to all abnormal responses and the state data set, and determine a risk response value for each freezing risk level through the abnormal response matrix;

[0045] The execution module is used to determine the alarm level of the target gardening weeding equipment at the current moment according to all risk response values, and to issue a risk abnormality alarm based on the alarm level.

[0046] In a third aspect, the present application provides an intelligent gardening weeding device, wherein the execution system of the intelligent gardening weeding device includes an abnormality alarm system.

[0047] In a fourth aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned abnormal alarm method.

[0048] In a fifth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above-mentioned abnormal alarm method when executed by a processor.

[0049] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0050] In the abnormal alarm method, system, intelligent gardening weeding equipment and storage medium provided by the present application, first, the historical freezing records of the intelligent gardening weeding equipment are obtained; multiple freezing risk levels are preset, and the pressure abnormality domain, temperature abnormality domain and flow rate abnormality domain of each freezing risk level are determined according to the historical freezing records; the boundary correction factor of the corresponding pressure abnormality domain is determined based on the coupling characteristics of each pressure abnormality domain, and the boundary of the corresponding pressure abnormality domain is corrected according to each boundary correction factor, so as to obtain the abnormal response of each pressure abnormality domain, and the abnormal response of each temperature abnormality domain and the abnormal response of each flow rate abnormality domain are continuously obtained by adopting the above steps; the state data set of the herbicide in the target gardening weeding equipment at the current moment is obtained, the abnormal response matrix is ​​determined according to all the abnormal responses and the state data set, and the risk response value of each freezing risk level is determined by the abnormal response matrix; the alarm level of the target gardening weeding equipment at the current moment is determined according to all the risk response values, and a risk abnormality alarm is performed based on the alarm level.

[0051] It can be seen that the present application divides the range of three indicators (i.e., temperature value, flow rate value, and pressure value) corresponding to multiple icing risk levels through historical icing records, i.e., the three abnormal domains of pressure anomaly domain, temperature anomaly domain, and flow rate anomaly domain. For the pressure anomaly domain, the distribution of pressure values ​​in each pressure anomaly domain is extracted to determine the degree to which the distribution of pressure values ​​is affected by the temperature value and the flow rate value, i.e., the pressure coupling amount, and the pressure value range corresponding to each icing risk level is re-corrected based on the pressure coupling amount, and an abnormal response of the pressure value is generated, i.e., the basic data for judging whether there is an icing risk at the current moment is obtained, and the abnormal response of the temperature value and the abnormal response of the flow rate value are obtained by the same method, and all abnormal responses are compared with the state data set of the herbicide in the target horticultural weeding equipment at the current moment (the pressure value, temperature value, and flow rate value at the current moment), and then an alarm is issued based on the comparison result. In summary, the present application can combine the coupling between the indicators related to the icing of the herbicide to perform multi-dimensional alarms on the icing risk, thereby improving the reliability of the abnormal alarm of the intelligent horticultural weeding equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is an exemplary flow chart of an abnormality alarm method according to some embodiments of the present application;

[0053] Figure 2 is an exemplary flow chart of determining a boundary correction factor according to some embodiments of the present application;

[0054] Figure 3 is an exemplary flow chart of determining an abnormal response matrix according to some embodiments of the present application;

[0055] Figure 4is a schematic diagram of exemplary hardware and / or software of an abnormality alarm system according to some embodiments of the present application;

[0056] Figure 5 It is a structural diagram of a computer device for implementing an abnormal alarm method according to some embodiments of the present application. DETAILED DESCRIPTION

[0057] The core of this application is to obtain historical freezing records; preset multiple freezing risk levels, and determine the pressure anomaly domain, temperature anomaly domain and flow rate anomaly domain of each freezing risk level according to the historical freezing records; determine the abnormal response of each pressure anomaly domain based on the coupling characteristics of each pressure anomaly domain, and continue to obtain the abnormal response of each temperature anomaly domain and the abnormal response of each flow rate anomaly domain in the manner of the above steps; obtain the status data set of the target horticultural weeding equipment at the current moment, and determine the risk response value of each freezing risk level according to all abnormal responses and status data sets; and perform risk abnormality alarm according to all risk response values. The above scheme combines the coupling between the indicators related to the freezing of herbicides to perform multi-dimensional alarms on freezing risks, thereby improving the reliability of abnormal alarms of intelligent horticultural weeding equipment.

[0058] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of an abnormality alarm method according to some embodiments of the present application. The abnormality alarm method 100 mainly includes the following steps:

[0059] In step 101, historical freezing records of the intelligent gardening weeding equipment are obtained.

[0060] In specific implementation, the historical freezing records of all the intelligent gardening weeding equipment in the park can be obtained through the control terminal in the park. The historical freezing records include the temperature value, flow rate value, pressure value of the inner wall of the liquid storage tank and freezing value of the herbicide in the intelligent gardening weeding equipment when the intelligent gardening weeding equipment has a freezing failure. The freezing value refers to a measure of the severity of the freezing of the herbicide in the intelligent gardening weeding equipment. The freezing value is set according to the actual situation. For example, the score range can be from 0 to 5 from the herbicide not freezing to the herbicide completely freezing, where 0 indicates that the herbicide is not frozen, 1 indicates slight freezing, 2 indicates mild freezing, 3 indicates moderate freezing, 4 indicates severe freezing, and 5 indicates complete freezing.

[0061] It should be noted that the control terminal in the present application is a terminal used to control all intelligent gardening weeding equipment in the park. The control terminal is connected to all intelligent gardening weeding equipment in the park via wireless signals, and the control terminal can store historical freezing records of all intelligent gardening weeding equipment in the park.

[0062] In step 102, a plurality of icing risk levels are preset, and the pressure anomaly domain, the temperature anomaly domain and the flow velocity anomaly domain of each icing risk level are determined according to the historical icing records.

[0063] In specific implementation, the icing risk level can be preset according to the icing values ​​in the historical icing records. For example, there are 6 levels of icing values ​​in the historical icing records. In this application, the icing risk level is preset to 6 levels, where level 0 is no icing risk, level 1 is a slight icing risk, level 2 is a mild icing risk, level 3 is a moderate icing risk, level 4 is a high icing risk, and level 5 is an emergency icing risk.

[0064] In some embodiments, determining the pressure anomaly domain, temperature anomaly domain, and flow rate anomaly domain for each icing risk level according to the historical icing records can be achieved by using the following steps:

[0065] Obtaining the freezing risk level, temperature value, flow rate value and pressure value at each freezing in the historical freezing record;

[0066] For each icing risk level, determine the pressure anomaly domain of the icing risk level according to all pressure values ​​corresponding to the icing risk level;

[0067] For each icing risk level, determine the temperature anomaly domain of the icing risk level according to all temperature values ​​corresponding to the icing risk level;

[0068] For each icing risk level, a flow rate anomaly domain of the icing risk level is determined according to all flow rate values ​​corresponding to the icing risk level.

[0069] In specific implementation, the pressure anomaly domain of the icing risk level can be determined based on all pressure values ​​corresponding to the icing risk level by the following steps, namely: the smallest pressure value among all pressure values ​​corresponding to the icing risk level is taken as the lower limit of the interval, and the largest pressure value among all pressure values ​​corresponding to the icing risk level is taken as the upper limit of the interval, thereby obtaining an interval range, and taking the interval range as the pressure anomaly domain of the icing risk level.

[0070] It should be noted that the pressure anomaly domain in the present application refers to the distribution range of corresponding pressure values ​​when different degrees of abnormal freezing occur in the intelligent gardening weeding equipment in the historical freezing records.

[0071] In specific implementation, the temperature anomaly domain of the icing risk level can be determined based on all temperature values ​​corresponding to the icing risk level by the following steps, namely: taking the smallest temperature value among all temperature values ​​corresponding to the icing risk level as the lower limit of the interval, and taking the largest temperature value among all temperature values ​​corresponding to the icing risk level as the upper limit of the interval, thereby obtaining an interval range, and taking the interval range as the temperature anomaly domain of the icing risk level.

[0072] It should be noted that the temperature anomaly domain in the present application refers to the distribution range of corresponding temperature values ​​when the intelligent gardening weeding equipment has different degrees of abnormal freezing in the historical freezing records.

[0073] In specific implementation, the flow rate anomaly domain of the icing risk level can be determined based on all flow rate values ​​corresponding to the icing risk level by the following steps, namely: taking the smallest flow rate value among all flow rate values ​​corresponding to the icing risk level as the lower limit of the interval, and taking the largest flow rate value among all flow rate values ​​corresponding to the icing risk level as the upper limit of the interval, thereby obtaining an interval range, and taking the interval range as the flow rate anomaly domain of the icing risk level.

[0074] It should be noted that the abnormal flow rate domain in the present application refers to the distribution range of the corresponding flow rate values ​​when the intelligent gardening weeding equipment has different degrees of abnormal freezing in the historical freezing records.

[0075] In step 103, the boundary correction factor of the corresponding pressure anomaly domain is determined based on the coupling characteristics of each pressure anomaly domain, and the boundary of the corresponding pressure anomaly domain is corrected according to each boundary correction factor, so as to obtain the abnormal response of each pressure anomaly domain. The abnormal response of each temperature anomaly domain and the abnormal response of each flow velocity anomaly domain are further obtained by adopting the above steps.

[0076] In some embodiments, reference Figure 2 , which is an exemplary flow chart of determining a boundary correction factor according to some embodiments of the present application. In the present application, determining the boundary correction factor of the corresponding pressure anomaly domain based on the coupling characteristics of each pressure anomaly domain can be implemented by the following steps:

[0077] In step 1031, a pressure anomaly domain is selected and the pressure center of the pressure anomaly domain is determined;

[0078] In step 1032, the pressure coupling amount of the pressure anomaly domain is determined according to the pressure center, and the pressure coupling amount is the coupling feature;

[0079] In step 1033, the pressure distribution entropy of all pressure values ​​in the pressure anomaly domain is determined according to the pressure center;

[0080] In step 1034, a boundary correction factor of the pressure anomaly domain is determined according to the pressure distribution entropy and the pressure coupling amount;

[0081] In step 1035, the above steps are repeated to obtain the boundary correction factor of the residual pressure anomaly domain.

[0082] In specific implementation, the pressure center of the pressure anomaly domain can be determined in the following manner, namely: all pressure values ​​corresponding to the icing risk level can be sorted from small to large, and the average value of all pressure values ​​within the quartile range of the obtained sequence is taken as the pressure center of the icing risk level.

[0083] It should be noted that the pressure center in this application is the pressure value that best reflects the corresponding icing risk level.

[0084] In some embodiments, determining the pressure coupling amount of the pressure anomaly domain according to the pressure center may be achieved by using the following steps:

[0085] Determining the amount of overlap between the pressure anomaly domain and an adjacent pressure anomaly domain according to the pressure center and the boundary of the pressure anomaly domain;

[0086] The pressure coupling amount of the pressure anomaly domain is determined according to the interval overlap amount.

[0087] In specific implementation, determining the interval overlap between the pressure anomaly domain and the adjacent pressure anomaly domain according to the pressure center and the boundary of the pressure anomaly domain can be achieved in the following manner, namely: first, sorting all the pressure anomaly domains according to the corresponding icing risk levels, then, for the i-th pressure anomaly domain, subtracting the corresponding pressure center from the interval upper limit of the i-th pressure anomaly domain, and using the obtained value as the right interval length of the pressure anomaly domain, then, subtracting the pressure center of the i-th pressure anomaly domain from the interval upper limit of the i+1-th pressure anomaly domain, and using the obtained value as the right overlapping interval of the i-th pressure anomaly domain, and then using the ratio between the right interval length and the right overlapping interval as the right interval overlap of the i-th pressure anomaly domain, repeating the above steps to obtain the left interval overlap of the i-th pressure anomaly domain, and finally, using the average of the right interval overlap and the left interval overlap as the interval overlap of the i-th pressure anomaly domain.

[0088] It should be noted that the interval overlap in the present application is a parameter used to measure the degree of overlap between the corresponding measured pressure anomaly domain and the adjacent measured pressure anomaly domain. The larger the interval overlap, the more overlap there is between the corresponding measured pressure anomaly domain and the adjacent measured pressure anomaly domain, that is, the greater the possibility of boundary error of the corresponding pressure anomaly domain.

[0089] In specific implementation, the pressure coupling amount of the pressure anomaly domain can be determined according to the interval overlap amount in the following manner, namely: subtract the square of the interval overlap amount from 1, set the difference obtained to a, divide the logarithm of 0.5 with the base 10 by the logarithm of a with the base 10, and use the quotient obtained as the pressure coupling amount of the pressure anomaly domain.

[0090] It should be noted that the pressure coupling amount in the present application is a parameter used to measure the coupling between the pressure value distribution in the corresponding icing risk level and other indicators. The larger the pressure coupling amount, the more coupled the pressure value distribution in the corresponding icing risk level is with other indicators, that is, the more pressure values ​​that should not exist in this icing risk level, the greater the boundary error probability of the pressure anomaly domain corresponding to this icing risk level. Among them, other indicators in the present application include temperature value and flow rate value.

[0091] In specific implementation, determining the pressure distribution entropy of all pressure values ​​in the pressure anomaly domain based on the pressure center can be achieved in the following manner, namely: the pressure center can be used as the average value of all pressure values ​​in the icing risk level, and then the variance of all pressure values ​​in the icing risk level is determined based on the average value, and the variance is used as the pressure of the icing risk level.

[0092] It should be noted that the pressure distribution entropy in the present application is a parameter used to measure the degree of disorder in the distribution of all pressure values ​​in the corresponding pressure anomaly domain. The larger the pressure distribution entropy, the more disordered the distribution of pressure values ​​in the corresponding pressure anomaly domain.

[0093] In specific implementation, determining the boundary correction factor of the pressure anomaly domain according to the pressure distribution entropy and the pressure coupling amount can be achieved in the following manner, namely: taking the pressure distribution entropy as the standard deviation, taking the pressure coupling amount as the probability density order of the normal distribution function, and then determining the three standard deviation range corresponding to the normal distribution, and taking half of the three standard deviation range as the boundary correction factor of the pressure anomaly domain. In some preferred embodiments, for example, the pressure coupling amount can be doubled and 3 can be added to the root, and then the obtained value can be multiplied by the pressure distribution entropy, and the obtained value can be used as the boundary correction factor of the pressure anomaly domain.

[0094] It should be noted that the boundary correction factor in the present application is a parameter used to correct the erroneous boundary in the corresponding pressure anomaly domain.

[0095] In some embodiments, the boundary of the corresponding pressure anomaly domain is corrected according to each boundary correction factor, and then the abnormal response of each pressure anomaly domain is obtained, which can be achieved by the following steps:

[0096] A pressure anomaly domain is selected, and an anomaly domain span of the pressure anomaly domain is determined according to a boundary correction factor of the pressure anomaly domain;

[0097] Acquire the pressure center of the pressure anomaly domain, determine the corrected boundary of the pressure anomaly domain according to the anomaly domain span and the pressure center of the pressure anomaly domain, and then obtain the corrected pressure domain of the pressure anomaly domain;

[0098] Determine the pressure ambiguity rate of the modified pressure domain;

[0099] Determine a plurality of basic pressure values ​​of the modified pressure domain according to the expected distribution entropy and the pressure fuzziness rate;

[0100] Determine the abnormal response of the modified pressure domain according to all the basic pressure values ​​in the modified pressure domain;

[0101] Repeat the above steps to obtain the abnormal response of the remaining pressure abnormal domain.

[0102] In specific implementation, the anomaly domain span refers to the distribution range of pressure values ​​in the corrected pressure domain after correction. As a preferred embodiment, determining the anomaly domain span of the pressure anomaly domain according to the boundary correction factor of the pressure anomaly domain can be implemented in the following manner, namely: taking twice the boundary correction factor as the anomaly domain span of the pressure anomaly domain. In other embodiments, other methods can also be used for determination, which is not limited here.

[0103] In specific implementation, the corrected boundary of the pressure anomaly domain is determined according to the anomaly domain span and the pressure center of the pressure anomaly domain, and then the corrected pressure domain of the pressure anomaly domain is obtained, which can be implemented in the following manner, namely: the pressure center of the pressure anomaly domain is taken as the median of the interval, the span of the anomaly domain is taken as the interval length, and then an interval is constructed, the boundary of the interval is taken as the corrected boundary of the pressure anomaly domain, and the interval is taken as the corrected pressure domain of the pressure anomaly domain.

[0104] In specific implementation, the pressure ambiguity rate of the corrected pressure domain can be determined in the following manner, namely: subtract the square of the pressure distribution entropy of the pressure anomaly domain corresponding to the corrected pressure domain from the square of the variance of all pressure values ​​in the historical icing records within the range of the corrected pressure domain, and take the root of the difference as the pressure ambiguity rate of the corrected pressure domain.

[0105] It should be noted that the pressure ambiguity rate in the present application is a parameter used to measure the ambiguity of the abnormal response corresponding to the corrected pressure domain. The smaller the pressure ambiguity rate, the closer the data distribution in the corresponding abnormal response is to a normal distribution curve. The larger the pressure ambiguity rate, the closer the data distribution in the corresponding abnormal response is to the superposition of multiple normal distribution curves with the same expectations and similar variances.

[0106] In specific implementation, determining multiple basic pressure values ​​of the corrected pressure domain according to the expected distribution entropy and the pressure fuzziness rate can be achieved in the following manner, namely: taking the expected distribution entropy as the expected value, and the pressure fuzziness rate as the standard deviation, generating N normal random numbers, and taking each of the obtained normal random numbers as the basic pressure value, wherein N is a preset value, which can be preset according to actual needs. For example, in the present application, N can be preset to 5000.

[0107] It should be noted that the basic pressure value in the present application is the basic data used to construct the abnormal response corresponding to the modified pressure domain.

[0108] In specific implementation, determining the abnormal response of the corrected pressure domain based on all the basic pressure values ​​in the corrected pressure domain can be achieved in the following manner, namely: first, randomly select a pressure value within the corrected pressure domain, square the difference between the pressure value and the pressure center of the corrected pressure domain, then divide the obtained value by 2 and divide it by the square of any basic pressure value, take the opposite of the quotient obtained as a, and finally take the ath power of the natural constant as the membership of the basic pressure value, repeat the above steps until the membership of all basic pressure values ​​is obtained, take each membership and the corresponding pressure value as a set of abnormal data, and take the set of all abnormal data as the abnormal response.

[0109] It should be noted that the abnormal response in the present application is basic data constructed based on historical freezing records and used to respond to the freezing risk level of the target gardening weeding equipment at the current moment.

[0110] In some embodiments, by adopting the above steps, the abnormal response of each temperature abnormal domain and the abnormal response of each flow rate abnormal domain can be continuously obtained by adopting the following steps:

[0111] Determine the boundary correction factor of the corresponding temperature anomaly domain based on the coupling characteristics of each temperature anomaly domain;

[0112] The boundary of the corresponding temperature anomaly domain is corrected according to the boundary correction factor of each temperature anomaly domain, thereby obtaining the abnormal response of each temperature anomaly domain;

[0113] Determine the boundary correction factor of the corresponding velocity anomaly domain based on the coupling characteristics of each velocity anomaly domain;

[0114] The boundary of each velocity anomaly domain is corrected according to the boundary correction factor of each velocity anomaly domain, thereby obtaining the abnormal response of each velocity anomaly domain.

[0115] In some embodiments, determining the boundary correction factor of the corresponding temperature anomaly domain based on the coupling characteristics of each temperature anomaly domain can be implemented by the following steps:

[0116] Select a temperature anomaly domain and determine the temperature center of the temperature anomaly domain;

[0117] Determine the temperature coupling amount of the temperature anomaly domain according to the temperature center, the temperature coupling amount is the coupling feature;

[0118] Determine the temperature distribution entropy of all temperature values ​​in the temperature anomaly domain according to the temperature center;

[0119] Determine a boundary correction factor of the temperature anomaly domain according to the temperature distribution entropy and the temperature coupling amount;

[0120] Repeat the above steps to obtain the boundary correction factors of the remaining temperature anomaly domains.

[0121] In specific implementation, the temperature center of the temperature anomaly domain can be determined in the following manner, that is, all temperature values ​​corresponding to the icing risk level can be sorted from small to large, and the average value of all temperature values ​​within the quartile range of the obtained sequence is taken as the temperature center of the icing risk level.

[0122] It should be noted that the temperature center in this application is the temperature value that best reflects the corresponding icing risk level.

[0123] In some embodiments, determining the temperature coupling amount of the temperature anomaly domain according to the temperature center may be implemented by the following steps:

[0124] Determining the interval overlap amount between the temperature anomaly domain and an adjacent temperature anomaly domain according to the temperature center and the boundary of the temperature anomaly domain;

[0125] The temperature coupling amount of the temperature anomaly domain is determined according to the interval overlap amount.

[0126] In specific implementation, determining the interval overlap between the temperature anomaly domain and the adjacent temperature anomaly domain according to the temperature center and the boundary of the temperature anomaly domain can be achieved in the following manner, namely: first, sorting all the temperature anomaly domains according to the corresponding icing risk levels, then, for the i-th temperature anomaly domain, subtracting the corresponding temperature center from the interval upper limit of the i-th temperature anomaly domain, and using the obtained value as the right interval length of the temperature anomaly domain, then, subtracting the temperature center of the i-th temperature anomaly domain from the interval upper limit of the i+1-th temperature anomaly domain, and using the obtained value as the right overlapping interval of the i-th temperature anomaly domain, and then using the ratio between the right interval length and the right overlapping interval as the right interval overlap of the i-th temperature anomaly domain, repeating the above steps to obtain the left interval overlap of the i-th temperature anomaly domain, and finally, using the average of the right interval overlap and the left interval overlap as the interval overlap of the i-th temperature anomaly domain.

[0127] It should be noted that the interval overlap in the present application is a parameter used to indicate the degree of overlap between the corresponding measured temperature anomaly domain and the adjacent measured temperature anomaly domain. The larger the interval overlap, the more overlap there is between the corresponding measured temperature anomaly domain and the adjacent measured temperature anomaly domain, that is, the greater the possibility of boundary error of the corresponding temperature anomaly domain.

[0128] In specific implementation, the temperature coupling amount of the temperature anomaly domain can be determined according to the interval overlap amount in the following manner, namely: subtract the square of the interval overlap amount from 1, set the difference obtained to a, divide the logarithm of 0.5 with the base 10 by the logarithm of a with the base 10, and use the quotient obtained as the temperature coupling amount of the temperature anomaly domain.

[0129] It should be noted that the temperature coupling amount in the present application is a parameter used to measure the coupling between the distribution of temperature values ​​in the corresponding icing risk level and other indicators. The larger the temperature coupling amount, the more coupled the distribution of temperature values ​​in the corresponding icing risk level is with other indicators, that is, the more temperature values ​​that should not exist in this icing risk level, the greater the boundary error probability of the temperature anomaly domain corresponding to this icing risk level. Among them, other indicators in the present application include pressure value and flow rate value.

[0130] In specific implementation, determining the temperature distribution entropy of all temperature values ​​in the temperature anomaly domain according to the temperature center can be achieved in the following manner, namely: the temperature center can be used as the average value of all temperature values ​​in the icing risk level, and then the variance of all temperature values ​​in the icing risk level is determined according to the average value, and the variance is used as the temperature of the icing risk level.

[0131] It should be noted that the temperature distribution entropy in the present application is a parameter used to measure the degree of disorder in the distribution of all temperature values ​​in the corresponding temperature anomaly domain. The larger the temperature distribution entropy, the more disordered the distribution of temperature values ​​in the corresponding temperature anomaly domain.

[0132] In specific implementation, determining the boundary correction factor of the temperature anomaly domain according to the temperature distribution entropy and the temperature coupling amount can be achieved in the following manner, namely: taking the temperature distribution entropy as the standard deviation, taking the temperature coupling amount as the probability density order of the normal distribution function, and then determining the three standard deviation range corresponding to the normal distribution, and taking half of the three standard deviation range as the boundary correction factor of the temperature anomaly domain. In some preferred embodiments, for example, twice the temperature coupling amount can be added to 3 and then the root can be taken, and then the obtained value can be multiplied by the temperature distribution entropy, and the obtained value can be used as the boundary correction factor of the temperature anomaly domain.

[0133] It should be noted that the boundary correction factor in the present application is a parameter used to correct the erroneous boundary in the corresponding temperature anomaly domain.

[0134] In some embodiments, the boundary of each temperature anomaly domain is corrected according to the boundary correction factor of each temperature anomaly domain, and then the abnormal response of each temperature anomaly domain is obtained, which can be achieved by the following steps:

[0135] A temperature anomaly domain is selected, and an anomaly domain span of the temperature anomaly domain is determined according to a boundary correction factor of the temperature anomaly domain;

[0136] Acquire the temperature center of the temperature anomaly domain, determine the correction boundary of the temperature anomaly domain according to the anomaly domain span and the temperature center of the temperature anomaly domain, and then obtain the correction temperature domain of the temperature anomaly domain;

[0137] Determine the temperature fuzziness rate of the corrected temperature domain;

[0138] Determine a plurality of temperature basic values ​​of the modified temperature domain according to the expected distribution entropy and the temperature fuzziness rate;

[0139] Determine the abnormal response of the corrected temperature domain according to all the basic temperature values ​​in the corrected temperature domain;

[0140] Repeat the above steps to obtain the abnormal responses of the remaining temperature anomaly domains.

[0141] In specific implementation, the anomaly domain span refers to the distribution range of temperature values ​​in the corrected temperature domain after correction. As a preferred embodiment, the anomaly domain span of the temperature anomaly domain is determined according to the boundary correction factor of the temperature anomaly domain. It can be implemented in the following way, namely: twice the boundary correction factor is used as the anomaly domain span of the temperature anomaly domain. In other embodiments, other methods can also be used for determination, which is not limited here.

[0142] In specific implementation, the corrected boundary of the temperature anomaly domain is determined according to the anomaly domain span and the temperature center of the temperature anomaly domain, and then the corrected temperature domain of the temperature anomaly domain is obtained, which can be implemented in the following manner, namely: the temperature center of the temperature anomaly domain is taken as the median of the interval, the anomaly domain span is taken as the interval length, and then an interval is constructed, the boundary of the interval is taken as the corrected boundary of the temperature anomaly domain, and the interval is taken as the corrected temperature domain of the temperature anomaly domain.

[0143] In specific implementation, the temperature fuzziness rate of the corrected temperature domain can be determined in the following manner, namely: subtract the square of the temperature distribution entropy of the temperature anomaly domain corresponding to the corrected temperature domain from the square of the variance of all temperature values ​​in the historical freezing records within the range of the corrected temperature domain, and take the root of the difference as the temperature fuzziness rate of the corrected temperature domain.

[0144] It should be noted that the temperature fuzziness rate in the present application is a parameter used to measure the fuzziness of the abnormal response corresponding to the corrected temperature domain. The smaller the temperature fuzziness rate, the closer the data distribution in the corresponding abnormal response is to a normal distribution curve. The larger the temperature fuzziness rate, the closer the data distribution in the corresponding abnormal response is to the superposition of multiple normal distribution curves with the same expectations and similar variances.

[0145] In specific implementation, determining multiple temperature basic values ​​of the corrected temperature domain according to the expected distribution entropy and the temperature fuzziness rate can be achieved in the following manner, namely: taking the expected distribution entropy as the expected value, and the temperature fuzziness rate as the standard deviation, generating N normal random numbers, and taking each of the obtained normal random numbers as the temperature basic value, wherein N is a preset value, which can be preset according to actual needs. For example, in the present application, N can be preset to 5000.

[0146] It should be noted that the basic temperature value in the present application is the basic data used to construct the abnormal response corresponding to the modified temperature domain.

[0147] In specific implementation, the abnormal response of the corrected temperature domain can be determined according to all the basic temperature values ​​in the corrected temperature domain. That is, first, a temperature value is randomly selected within the corrected temperature domain, and the difference between the temperature value and the temperature center of the corrected temperature domain is squared. Then, the obtained value is divided by 2 and then divided by the square of any basic temperature value. The opposite of the quotient is taken as a. Finally, the ath power of the natural constant is taken as the membership of the basic temperature value. The above steps are repeated until the membership of all basic temperature values ​​is obtained, and each membership and the corresponding temperature value are taken as a set of abnormal data, and the set consisting of all abnormal data is taken as the abnormal response.

[0148] It should be noted that the abnormal response in the present application is basic data constructed based on historical freezing records and used to respond to the freezing risk level of the target gardening weeding equipment at the current moment.

[0149] In some embodiments, determining the boundary correction factor of the corresponding velocity anomaly domain based on the coupling characteristics of each velocity anomaly domain can be achieved by using the following steps:

[0150] Select a velocity anomaly domain and determine the velocity center of the velocity anomaly domain;

[0151] Determine the velocity coupling amount of the velocity anomaly domain according to the velocity center, wherein the velocity coupling amount is the coupling feature;

[0152] Determine the velocity distribution entropy of all velocity values ​​in the velocity anomaly domain according to the velocity center;

[0153] Determine a boundary correction factor of the velocity anomaly domain according to the velocity distribution entropy and the velocity coupling amount;

[0154] Repeat the above steps to obtain the boundary correction factor of the remaining velocity anomaly domain.

[0155] In specific implementation, the velocity center of the velocity anomaly domain can be determined in the following manner, namely: all velocity values ​​corresponding to the icing risk level can be sorted from small to large, and the average value of all velocity values ​​within the quartile range in the obtained sequence is taken as the velocity center of the icing risk level.

[0156] It should be noted that the flow velocity center in this application is the flow velocity value that best reflects the corresponding icing risk level.

[0157] In some embodiments, determining the velocity coupling amount of the velocity anomaly domain according to the velocity center may be achieved by using the following steps:

[0158] Determine the interval overlap amount between the velocity anomaly domain and an adjacent velocity anomaly domain according to the velocity center and the boundary of the velocity anomaly domain;

[0159] The velocity coupling amount of the velocity anomaly domain is determined according to the interval overlap amount.

[0160] In specific implementation, determining the interval overlap between the velocity anomaly domain and the adjacent velocity anomaly domain according to the velocity center and the boundary of the velocity anomaly domain can be achieved in the following manner, namely: first, sorting all the velocity anomaly domains according to the corresponding icing risk levels, then, for the i-th velocity anomaly domain, subtracting the corresponding velocity center from the interval upper limit of the i-th velocity anomaly domain, and using the obtained value as the right interval length of the velocity anomaly domain, then, subtracting the velocity center of the i-th velocity anomaly domain from the interval upper limit of the i+1-th velocity anomaly domain, and using the obtained value as the right overlapping interval of the i-th velocity anomaly domain, and then using the ratio between the right interval length and the right overlapping interval as the right interval overlap of the i-th velocity anomaly domain, repeating the above steps to obtain the left interval overlap of the i-th velocity anomaly domain, and finally, using the average of the right interval overlap and the left interval overlap as the interval overlap of the i-th velocity anomaly domain.

[0161] It should be noted that the interval overlap in the present application is a parameter used to measure the degree of overlap between the corresponding measured velocity anomaly domain and the adjacent measured velocity anomaly domain. The larger the interval overlap, the more overlap there is between the corresponding measured velocity anomaly domain and the adjacent measured velocity anomaly domain, that is, the greater the possibility of boundary error of the corresponding velocity anomaly domain.

[0162] In specific implementation, the velocity coupling amount of the velocity anomaly domain can be determined according to the interval overlap amount in the following manner, namely: subtract the square of the interval overlap amount from 1, set the difference obtained to a, divide the logarithm of 0.5 with the base 10 by the logarithm of a with the base 10, and use the quotient obtained as the velocity coupling amount of the velocity anomaly domain.

[0163] It should be noted that the flow velocity coupling amount in the present application is a parameter used to measure the coupling between the flow velocity value distribution in the corresponding icing risk level and other indicators. The larger the flow velocity coupling amount, the more coupled the flow velocity value distribution in the corresponding icing risk level is with other indicators, that is, the more flow velocity values ​​that should not exist in this icing risk level, the greater the boundary error probability of the flow velocity anomaly domain corresponding to this icing risk level. Among them, other indicators in the present application include pressure value and temperature value.

[0164] In specific implementation, determining the velocity distribution entropy of all flow velocity values ​​in the velocity anomaly domain based on the flow velocity center can be achieved in the following manner, namely: the flow velocity center can be used as the average value of all flow velocity values ​​in the icing risk level, and then the variance of all flow velocity values ​​in the icing risk level is determined based on the average value, and the variance is used as the flow velocity of the icing risk level.

[0165] It should be noted that the velocity distribution entropy in the present application is a parameter used to measure the degree of disorder in the distribution of all velocity values ​​in the corresponding velocity anomaly domain. The larger the velocity distribution entropy, the more disordered the distribution of velocity values ​​in the corresponding velocity anomaly domain.

[0166] In specific implementation, determining the boundary correction factor of the velocity anomaly domain according to the velocity distribution entropy and the velocity coupling amount can be achieved in the following manner, namely: taking the velocity distribution entropy as the standard deviation, taking the velocity coupling amount as the probability density order of the normal distribution function, and then determining the three standard deviation range corresponding to the normal distribution, and taking half of the three standard deviation range as the boundary correction factor of the velocity anomaly domain. In some preferred embodiments, for example, the velocity coupling amount can be doubled and 3 can be added to the root, and then the obtained value can be multiplied by the velocity distribution entropy, and the obtained value can be used as the boundary correction factor of the velocity anomaly domain.

[0167] It should be noted that the boundary correction factor in the present application is a parameter used to correct the erroneous boundary in the corresponding velocity anomaly domain.

[0168] In some embodiments, the boundary correction factor of each abnormal velocity domain is used to correct the boundary of the corresponding abnormal velocity domain, and then the abnormal response of each abnormal velocity domain is obtained, which can be achieved by the following steps:

[0169] Select a velocity anomaly domain, and determine the anomaly domain span of the velocity anomaly domain according to the boundary correction factor of the velocity anomaly domain;

[0170] Obtaining the velocity center of the velocity anomaly domain, determining the correction boundary of the velocity anomaly domain according to the anomaly domain span and the velocity center of the velocity anomaly domain, and then obtaining the correction velocity domain of the velocity anomaly domain;

[0171] Determine the flow velocity fuzziness rate of the corrected flow velocity domain;

[0172] Determine a plurality of basic flow velocity values ​​of the modified flow velocity domain according to the expected distribution entropy and the flow velocity fuzziness rate;

[0173] Determine the abnormal response of the modified flow rate domain according to all the basic flow rate values ​​in the modified flow rate domain;

[0174] Repeat the above steps to obtain the abnormal response of the remaining velocity abnormal domain.

[0175] In specific implementation, the anomaly domain span refers to the distribution range of the flow velocity values ​​in the corrected flow velocity domain. As a preferred embodiment, the anomaly domain span of the flow velocity anomaly domain is determined according to the boundary correction factor of the flow velocity anomaly domain. It can be implemented in the following way, namely: twice the boundary correction factor is used as the anomaly domain span of the flow velocity anomaly domain. In other embodiments, other methods can also be used for determination, which is not limited here.

[0176] In specific implementation, the corrected boundary of the flow velocity anomaly domain is determined according to the anomaly domain span and the flow velocity center of the flow velocity anomaly domain, and then the corrected flow velocity domain of the flow velocity anomaly domain is obtained. This can be achieved in the following manner, namely: the flow velocity center of the flow velocity anomaly domain is taken as the median of the interval, the span of the anomaly domain is taken as the interval length, and then an interval is constructed, the boundary of the interval is taken as the corrected boundary of the flow velocity anomaly domain, and the interval is taken as the corrected flow velocity domain of the flow velocity anomaly domain.

[0177] In specific implementation, the velocity fuzziness rate of the corrected velocity domain can be determined in the following manner, namely: subtract the square of the velocity distribution entropy of the velocity anomaly domain corresponding to the corrected velocity domain from the square of the variance of all velocity values ​​in the historical freezing records within the corrected velocity domain, and take the root of the difference as the velocity fuzziness rate of the corrected velocity domain.

[0178] It should be noted that the flow velocity fuzziness rate in the present application is a parameter used to measure the fuzziness of the abnormal response of the corresponding corrected flow velocity domain. The smaller the flow velocity fuzziness rate, the closer the data distribution in the corresponding abnormal response is to a normal distribution curve. The larger the flow velocity fuzziness rate, the closer the data distribution in the corresponding abnormal response is to the superposition of multiple normal distribution curves with the same expectations and similar variances.

[0179] In specific implementation, determining multiple basic flow velocity values ​​of the corrected flow velocity domain according to the expected distribution entropy and the flow velocity fuzziness rate can be achieved in the following manner, namely: taking the expected distribution entropy as the expected value, and the flow velocity fuzziness rate as the standard deviation, generating N normal random numbers, and taking each of the obtained normal random numbers as the basic flow velocity value, wherein N is a preset value, which can be preset according to actual needs. For example, in the present application, N can be preset to 5000.

[0180] It should be noted that the basic flow rate value in the present application is the basic data used to construct the abnormal response corresponding to the modified flow rate domain.

[0181] In specific implementation, the abnormal response of the corrected flow velocity domain can be determined based on all the basic flow velocity values ​​in the corrected flow velocity domain. That is, first, a flow velocity value is randomly selected within the corrected flow velocity domain, and the difference between the flow velocity value and the flow velocity center of the corrected flow velocity domain is squared. Then, the obtained value is divided by 2 and then divided by the square of any basic flow velocity value. The opposite of the quotient is taken as a. Finally, the ath power of the natural constant is taken as the membership of the basic flow velocity value. The above steps are repeated until the membership of all basic flow velocity values ​​is obtained, and each membership and the corresponding flow velocity value are taken as a set of abnormal data, and the set of all abnormal data is taken as the abnormal response.

[0182] It should be noted that the abnormal response in the present application is basic data constructed based on historical freezing records and used to respond to the freezing risk level of the target gardening weeding equipment at the current moment.

[0183] In step 104, a state data set of the herbicide in the target gardening weeding equipment at the current moment is obtained, an abnormal response matrix is ​​determined according to all abnormal responses and the state data set, and a risk response value of each freezing risk level is determined by the abnormal response matrix.

[0184] In specific implementation, the temperature value of the herbicide in the liquid storage tank at the current moment can be collected by a temperature sensor installed on the liquid storage tank in the target horticultural weeding equipment, and then the flow rate value of the herbicide in the liquid storage tank at the current moment can be collected by a flow rate sensor installed on the liquid storage tank in the target horticultural weeding equipment, and the pressure value on the inner wall of the liquid storage tank at the current moment can be collected by a flow rate sensor installed on the liquid storage tank in the target horticultural weeding equipment, and the set of the temperature value, flow rate value and pressure value is used as the status data set of the herbicide in the target horticultural weeding equipment at the current moment.

[0185] In some embodiments, reference Figure 3 , which is an exemplary flow chart of determining an abnormal response matrix according to some embodiments of the present application. In the present application, determining the abnormal response matrix according to all abnormal responses and the state data set can be implemented by using the following steps:

[0186] In step 1041, the temperature value, the flow value and the pressure value at the current moment in the state data set are obtained;

[0187] In step 1042, the abnormal probability between the pressure value at the current moment and the abnormal response of each pressure abnormality domain is determined;

[0188] In step 1043, the above steps are repeated to obtain the abnormal probability between the flow velocity value at the current moment and the abnormal response of each flow velocity abnormal domain and the abnormal probability between the temperature value at the current moment and the abnormal response of each temperature abnormal domain;

[0189] In step 1044, all abnormal probabilities are converted into an abnormal response matrix.

[0190] In specific implementation, determining the abnormal probability between the pressure value at the current moment and the abnormal response of each pressure abnormal domain can be achieved in the following manner, namely: selecting a pressure abnormal domain, first, subtracting each pressure value in the abnormal response corresponding to the pressure abnormal domain from the pressure value at the current moment, and multiplying each difference by the corresponding membership degree, secondly, summing up all the products obtained and dividing by the total number of pressure values ​​in the abnormal response corresponding to the pressure abnormal domain, and then using the obtained quotient as the abnormal probability between the pressure value at the current moment and the abnormal response of the pressure abnormal domain, and finally, repeating the above steps to obtain the abnormal probability between the pressure value at the current moment and the abnormal response of each pressure abnormal domain.

[0191] It should be noted that the abnormal probability in this application refers to the probability that the state data set corresponding to the current moment belongs to the corresponding abnormal response.

[0192] In specific implementation, converting all abnormal probabilities into an abnormal response matrix can be achieved in the following manner, namely: first, sorting all abnormal probabilities corresponding to the pressure value at the current moment from small to large according to the corresponding icing risk level, and using the obtained sequence as the first row in the matrix; then, sorting all abnormal probabilities corresponding to the temperature value at the current moment from small to large according to the corresponding icing risk level, and using the obtained sequence as the second row in the matrix; finally, sorting all abnormal probabilities corresponding to the flow velocity value at the current moment from small to large according to the corresponding icing risk level, and using the obtained sequence as the third row in the matrix, and using the obtained matrix as the abnormal response matrix.

[0193] In some embodiments, determining the risk response value of each icing risk level through the abnormal response matrix may be implemented by the following steps:

[0194] Determine an indicator weight matrix according to the abnormal response matrix;

[0195] Determine an indicator weight vector according to the indicator weight matrix;

[0196] A risk response value for each icing risk level is determined according to the indicator weight vector.

[0197] In specific implementation, determining the indicator weight matrix according to the abnormal response matrix can be implemented in the following manner, namely: for each abnormal probability in the abnormal response matrix, the abnormal probability can be first divided by the sum of all abnormal probabilities in the row where the abnormal probability is located to obtain r, and then r is multiplied by the natural logarithm of r, and the obtained value is used as the indicator weight corresponding to the abnormal probability, and then the indicator weight of each abnormal probability in the abnormal response matrix is ​​obtained, and finally all the indicator weights are arranged according to the position of the corresponding abnormal probability in the abnormal response matrix, and the obtained matrix is ​​used as the indicator weight matrix.

[0198] It should be noted that the indicator weight matrix in the present application refers to a matrix used to determine the weights of different indicators used to predict the icing risk level.

[0199] In specific implementation, determining the indicator weight vector according to the indicator weight matrix can be achieved in the following manner, namely: adding the sum of the first row of data in the indicator weight matrix to the natural logarithm of the status data set to obtain q, multiplying the natural logarithm of the status data set by the total number of icing risk levels, adding the obtained product to the sum of all data in the indicator weight matrix to obtain p, taking the ratio of q to b as the indicator weight corresponding to the first row of data in the indicator weight matrix, repeating the above steps until the indicator weight corresponding to the last row of data in the indicator weight matrix is ​​obtained, sorting all the indicator weights in the order in which they are obtained, and taking the obtained sequence as the indicator weight vector.

[0200] In specific implementation, determining the risk response value of each state data in the state data set according to the indicator weight vector can be achieved in the following manner, namely: multiplying the indicator weight vector with the abnormal response matrix, taking the first value in the obtained vector as the risk response value of the first icing risk level, and sequentially taking the remaining values ​​in the obtained vector as the risk response values ​​of the corresponding icing risk levels.

[0201] In step 105, the alarm level of the target gardening weeding equipment at the current moment is determined according to all risk response values, and a risk abnormality alarm is performed based on the alarm level.

[0202] In some embodiments, determining the alarm level of the target gardening weeding equipment at the current moment according to all risk response values ​​can be achieved by using the following steps:

[0203] Determine the best response value based on all risk response values;

[0204] The alarm level at the current moment is determined according to the optimal response value.

[0205] In specific implementation, in this application, the best response value is the credibility between the abnormal responses that best match the status data set of the herbicide in the target horticultural weeding equipment at the current moment. As a preferred embodiment, the best response value determined according to all risk response values ​​in this application can be implemented in the following way, namely: the largest risk response value among all risk response values ​​is taken as the best response value. In other embodiments, other methods can also be used for determination, which is not limited here.

[0206] In specific implementation, determining the icing risk level at the current moment according to the optimal response value may be achieved in the following manner, namely: using the icing risk level corresponding to the optimal response value as the alarm level at the current moment.

[0207] In some embodiments, the risk abnormality alarm based on the alarm level can be implemented by the following steps:

[0208] A preset risk threshold is set, and if the alarm level is greater than the risk threshold, an alarm is issued;

[0209] If the alarm level is less than or equal to the risk threshold, no alarm is issued.

[0210] It should be noted that the icing risk threshold in the present application can be preset according to actual needs. For example, the icing risk threshold can be preset to level 3 in the present application.

[0211] In addition, in another aspect of the present application, in some embodiments, the present application provides an abnormality alarm system, referring to Figure 4 , which is a schematic diagram of exemplary hardware and / or software of an abnormality alarm system according to some embodiments of the present application, the abnormality alarm system 400 includes: a collection module 401, a processing module 402 and an execution module 403, which are described as follows:

[0212] Collection module 401, in this application, collection module 401 is mainly used to obtain historical freezing records of intelligent gardening weeding equipment;

[0213] Processing module 402, in the present application, processing module 402 is mainly used to preset multiple icing risk levels, and determine the pressure anomaly domain, temperature anomaly domain and flow rate anomaly domain of each icing risk level according to the historical icing records;

[0214] It should be noted that the processing module 402 in the present application is also used to determine the boundary correction factor of the corresponding pressure anomaly domain based on the coupling characteristics of each pressure anomaly domain, and correct the boundary of the corresponding pressure anomaly domain according to each boundary correction factor, so as to obtain the abnormal response of each pressure anomaly domain, and continue to obtain the abnormal response of each temperature anomaly domain and the abnormal response of each flow velocity anomaly domain by adopting the above steps;

[0215] In addition, it should be noted that the processing module 402 in the present application is also used to obtain a state data set of the herbicide in the target gardening weeding equipment at the current moment, determine an abnormal response matrix according to all abnormal responses and the state data set, and determine the risk response value of each freezing risk level through the abnormal response matrix;

[0216] Execution module 403, in the present application, execution module 403 is mainly used to determine the alarm level of the target gardening weeding equipment at the current moment according to all risk response values, and to perform risk abnormality alarm based on the alarm level.

[0217] In other aspects of the present application, a smart gardening weeding device is also provided, and the smart gardening weeding device includes the above-mentioned abnormal alarm system to realize abnormal alarm of the smart gardening weeding device, which will not be described in detail here.

[0218] In addition, the present application also provides a computer device, which includes a memory and a processor, the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned abnormal alarm method.

[0219] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer device according to the abnormality alarm method shown in some embodiments of the present application. The abnormality alarm method in the above embodiment can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503 and at least one communication interface 504.

[0220] The processor 501 may be a general-purpose central processing unit (CPU) or an application specific integrated circuit (ASIC).

[0221] The communication bus 502 may be used to transmit information between the above-mentioned components.

[0222] The memory 503 may be a read only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read only memory (EEPROM), a compact disc read only memory (CD ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 503 may exist independently and be connected to the processor 501 via the communication bus 502. The memory 503 may also be integrated with the processor 501.

[0223] The memory 503 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the program code stored in the memory 503. The program code may include one or more software modules. The abnormal alarm method in the above embodiment can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0224] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0225] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-core (single CPU) processor or a multi-core (multi CPU) processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0226] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0227] In addition, the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned abnormal alarm method is implemented.

[0228] In summary, in the abnormal alarm method, system, intelligent gardening weeding equipment and storage medium disclosed in the embodiments of the present application, first, the historical freezing records of the intelligent gardening weeding equipment are obtained; multiple freezing risk levels are preset, and the pressure abnormality domain, temperature abnormality domain and flow rate abnormality domain of each freezing risk level are determined according to the historical freezing records; the boundary correction factor of the corresponding pressure abnormality domain is determined based on the coupling characteristics of each pressure abnormality domain, and the boundary of the corresponding pressure abnormality domain is corrected according to each boundary correction factor, so as to obtain the abnormal response of each pressure abnormality domain, and the abnormal response of each temperature abnormality domain and the abnormal response of each flow rate abnormality domain are continuously obtained by adopting the above steps; the state data set of the herbicide in the target gardening weeding equipment at the current moment is obtained, and the abnormal response matrix is ​​determined according to all the abnormal responses and the state data set, and the risk response value of each freezing risk level is determined by the abnormal response matrix; the alarm level of the target gardening weeding equipment at the current moment is determined according to all the risk response values, and a risk abnormality alarm is performed based on the alarm level.

[0229] It can be seen that the present application divides the range of three indicators (i.e., temperature value, flow rate value, and pressure value) corresponding to multiple icing risk levels through historical icing records, i.e., the three abnormal domains of pressure anomaly domain, temperature anomaly domain, and flow rate anomaly domain. For the pressure anomaly domain, the distribution of pressure values ​​in each pressure anomaly domain is extracted to determine the degree to which the distribution of pressure values ​​is affected by the temperature value and the flow rate value, i.e., the pressure coupling amount, and the pressure value range corresponding to each icing risk level is re-corrected based on the pressure coupling amount, and an abnormal response of the pressure value is generated, i.e., the basic data for judging whether there is an icing risk at the current moment is obtained, and the abnormal response of the temperature value and the abnormal response of the flow rate value are obtained by the same method, and all abnormal responses are compared with the state data set of the herbicide in the target horticultural weeding equipment at the current moment (the pressure value, temperature value, and flow rate value at the current moment), and then an alarm is issued based on the comparison result. In summary, the present application can combine the coupling between the indicators related to the icing of the herbicide to perform multi-dimensional alarms on the icing risk, thereby improving the reliability of the abnormal alarm of the intelligent horticultural weeding equipment.

[0230] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0231] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An abnormal alarm method, characterized in that: include: Get historical freezing records of smart gardening weeding equipment; Preset multiple icing risk levels, and determine the pressure anomaly domain, temperature anomaly domain and flow velocity anomaly domain of each icing risk level according to the historical icing records; Based on the coupling characteristics of each pressure anomaly domain, a boundary correction factor of the corresponding pressure anomaly domain is determined, and the boundary of the corresponding pressure anomaly domain is corrected according to each boundary correction factor, thereby obtaining the abnormal response of each pressure anomaly domain, and the abnormal response of each temperature anomaly domain and the abnormal response of each flow velocity anomaly domain are further obtained by adopting the above steps; Acquire a state data set of the herbicide in the target gardening weeding equipment at the current moment, determine an abnormal response matrix according to all abnormal responses and the state data set, and determine a risk response value for each freezing risk level through the abnormal response matrix; Determine the alarm level of the target gardening weeding equipment at the current moment according to all risk response values, and issue a risk abnormality alarm based on the alarm level; Among them, the boundary correction factor of the corresponding pressure anomaly domain is determined based on the coupling characteristics of each pressure anomaly domain, specifically including: Select a pressure anomaly domain and determine the pressure center of the pressure anomaly domain; Determine the pressure coupling amount of the pressure anomaly domain according to the pressure center, wherein the pressure coupling amount is the coupling feature; Determine the pressure distribution entropy of all pressure values ​​in the pressure anomaly domain according to the pressure center; Determining a boundary correction factor of the pressure anomaly domain according to the pressure distribution entropy and the pressure coupling amount; Repeat the above steps to obtain the boundary correction factor of the residual pressure anomaly domain; Wherein, determining the pressure coupling amount of the pressure anomaly domain according to the pressure center specifically includes: Determining the interval overlap amount between the pressure anomaly domain and an adjacent pressure anomaly domain according to the pressure center and the boundary of the pressure anomaly domain; Determine the pressure coupling amount of the pressure anomaly domain according to the interval overlap amount; Among them, the boundary of the corresponding pressure anomaly domain is corrected according to each boundary correction factor, and then the abnormal response of each pressure anomaly domain is obtained, which specifically includes: A pressure anomaly domain is selected, and an anomaly domain span of the pressure anomaly domain is determined according to a boundary correction factor of the pressure anomaly domain; Acquire the pressure center of the pressure anomaly domain, determine the corrected boundary of the pressure anomaly domain according to the anomaly domain span and the pressure center of the pressure anomaly domain, and then obtain the corrected pressure domain of the pressure anomaly domain; Determine the pressure ambiguity rate of the modified pressure domain; Determine a plurality of basic pressure values ​​of the modified pressure domain according to the expected distribution entropy and the pressure fuzziness rate; Determine the abnormal response of the modified pressure domain according to all the basic pressure values ​​in the modified pressure domain; Repeat the above steps to obtain the abnormal response of the remaining pressure abnormal domain; The determining of the pressure fuzziness rate of the corrected pressure domain specifically includes: subtracting the square of the pressure distribution entropy of the pressure anomaly domain corresponding to the corrected pressure domain from the square of the variance of all pressure values ​​in the historical icing records within the corrected pressure domain, and taking the root of the difference obtained as the pressure fuzziness rate of the corrected pressure domain; Among them, determining the abnormal response of the corrected pressure domain according to all the basic pressure values ​​in the corrected pressure domain specifically includes: randomly selecting a pressure value within the range of the corrected pressure domain, squaring the difference between the pressure value and the pressure center of the corrected pressure domain, then dividing the obtained value by 2 and dividing it by the square of any basic pressure value, taking the opposite of the obtained quotient as the coefficient a, and finally taking the ath power of the natural constant as the membership of the basic pressure value, repeating the above steps until the membership of all basic pressure values ​​is obtained, taking each membership and the corresponding pressure value as a set of abnormal data, and taking the set consisting of all abnormal data as the abnormal response; Wherein, determining the abnormal response matrix according to all abnormal responses and the state data set specifically includes: Obtain the temperature value, flow rate value and pressure value at the current moment in the state data set; Determine the anomaly probability between the pressure value at the current moment and the anomaly response of each pressure anomaly domain; Repeat the above steps to obtain the abnormal probability between the flow velocity value at the current moment and the abnormal response of each flow velocity abnormal domain and the abnormal probability between the temperature value at the current moment and the abnormal response of each temperature abnormal domain; Convert all anomaly probabilities into an anomaly response matrix; Wherein, determining the risk response value of each icing risk level through the abnormal response matrix specifically includes: Determine an indicator weight matrix according to the abnormal response matrix; Determine an indicator weight vector according to the indicator weight matrix; A risk response value for each icing risk level is determined according to the indicator weight vector.

2. The method according to claim 1, characterized in that The pressure anomaly domain, temperature anomaly domain and velocity anomaly domain of each icing risk level determined according to the historical icing records specifically include: Obtaining the freezing risk level, temperature value, flow rate value and pressure value at each freezing in the historical freezing record; For each icing risk level, determine the pressure anomaly domain of the icing risk level according to all pressure values ​​corresponding to the icing risk level; For each icing risk level, determine the temperature anomaly domain of the icing risk level according to all temperature values ​​corresponding to the icing risk level; For each icing risk level, a flow rate anomaly domain of the icing risk level is determined according to all flow rate values ​​corresponding to the icing risk level.

3. The method according to claim 1, characterized in that The risk abnormality alarm based on the alarm level specifically includes: A preset risk threshold is set, and if the alarm level is greater than the risk threshold, an alarm is issued; If the alarm level is less than or equal to the risk threshold, no alarm is issued.

4. An abnormal alarm system, which uses the method according to any one of claims 1 to 3 to perform abnormal alarm, characterized in that: The abnormal alarm system includes: A collection module, used to obtain historical freezing records of smart gardening weeding equipment; A processing module, used for presetting a plurality of icing risk levels, and determining a pressure anomaly domain, a temperature anomaly domain and a flow rate anomaly domain for each icing risk level according to the historical icing records; The processing module is also used to determine the boundary correction factor of the corresponding pressure anomaly domain based on the coupling characteristics of each pressure anomaly domain, and correct the boundary of the corresponding pressure anomaly domain according to each boundary correction factor, so as to obtain the abnormal response of each pressure anomaly domain, and continue to obtain the abnormal response of each temperature anomaly domain and the abnormal response of each flow velocity anomaly domain in the manner of the above steps; The processing module is also used to obtain a state data set of the herbicide in the target gardening weeding equipment at the current moment, determine an abnormal response matrix according to all abnormal responses and the state data set, and determine a risk response value for each freezing risk level through the abnormal response matrix; The execution module is used to determine the alarm level of the target gardening weeding equipment at the current moment according to all risk response values, and to issue a risk abnormality alarm based on the alarm level.

5. An intelligent gardening weeding device, characterized in that: The intelligent gardening weeding device includes an abnormality alarm system as described in claim 4.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the abnormality alarm method according to any one of claims 1 to 3 is implemented.

Images