An agricultural intelligent irrigation water-saving management system and method based on big data

Abstract

The invention discloses an agricultural intelligent irrigation water-saving management system and method based on big data, and relates to the field of irrigation water-saving technology. The management method comprises the following steps: monitoring the water storage situation in a target field in a closed environment and dividing the area, and collecting the monitoring data of each monitoring device in the corresponding area in real time; evaluating the water storage capacity of the corresponding area based on the collected monitoring data; re-dividing the target field into a plurality of irrigation areas based on the difference in water storage capacity, and extracting the difference characteristics; arbitrarily selecting an irrigation area for comparison and analysis with the remaining irrigation areas, obtaining the influence degree of each difference characteristic, and analyzing the expected deviation amplitude of the irrigation area; each time after the target area is irrigated, the water storage situation of the target area is monitored in real time by the monitoring equipment, and based on the change of the water storage value of each irrigation area, it is judged in real time whether there is an abnormality.

Description

Technical Field

[0001] The present invention relates to the field of irrigation water-saving technology, and in particular to an agricultural intelligent irrigation water-saving management system and method based on big data. Background Art

[0002] As the global water shortage problem becomes increasingly serious, agricultural irrigation, as the largest freshwater consumption area, its water-saving technology innovation has become a core issue in the development of modern agriculture. Traditional irrigation systems mostly rely on manual experience or fixed cycles to allocate water resources, resulting in serious water waste. In recent years, with the continuous development of Internet of Things technology, it has been possible to monitor irrigation areas in real time to ensure irrigation when needed. However, the demand for water resources in irrigation areas changes dynamically with factors such as changes in plant species and soil composition. If the reasonable demand range of the irrigation area cannot be accurately analyzed, abnormal demand cannot be identified, resulting in frequent irrigation, which will also cause a waste of water resources. Summary of the invention

[0003] The purpose of the present invention is to provide an agricultural intelligent irrigation water-saving management system and method based on big data to solve the problems raised in the prior art.

[0004] To achieve the above object, the present invention provides the following technical solution: an agricultural intelligent irrigation water-saving management method based on big data, the management method comprising the following steps: Step S100: A number of monitoring devices are installed in the target field in a closed environment to monitor the water storage situation and divide the target field into regions. When the preset conditions are met, the corresponding region is irrigated, and the monitoring data of each monitoring device in the corresponding region is collected in real time; the water storage capacity of the corresponding region is evaluated based on the collected monitoring data, and a corresponding irrigation record is generated; the closed environment is set for the target field, which can effectively avoid external factors such as sudden rainfall or long-term drought, and the closed environment is such as a greenhouse environment; Step S200: re-dividing the target field into a number of irrigation areas based on the difference in water storage capacity between the various areas; extracting the difference features between the different irrigation areas based on the difference between the different irrigation areas; Step S300: randomly selecting an irrigation area, and comparing and analyzing the water storage conditions of the selected irrigation area with those of other irrigation areas, to obtain the influence degree of each difference feature in the selected irrigation area; analyzing the irrigation conditions presented by any irrigation record corresponding to the selected irrigation area, and analyzing the expected deviation amplitude of the selected irrigation area; Step S400: Whenever the target area is irrigated, the water storage situation of the target area is monitored in real time by the monitoring equipment to obtain the real-time water storage value of each irrigation area; based on the change of the water storage value of each irrigation area, it is determined in real time whether there is any abnormality.

[0005] Furthermore, step S100 includes the following steps: Step S101: installing a plurality of monitoring devices in the target field according to a pre-determined layout, obtaining the monitoring range of each monitoring device, and dividing the target field into a plurality of regions using the monitoring range of each monitoring device, wherein one region corresponds to the monitoring range of one monitoring device; Step S102: Preset a minimum water storage volume S th , use monitoring equipment to monitor the water storage capacity S of a certain area. If S<S th , then irrigate the certain area; when the irrigation of the certain area is completed, generate an irrigation record for the certain area, summarizing all monitoring data from the completion of irrigation to the next irrigation; Step S103: Select the irrigation record generated by the most recent irrigation of the area, read the water storage capacity when the irrigation is completed as S0 and the currently monitored water storage capacity as S1, set the time interval between the current distance to the completion of irrigation of the area as T, and obtain the water storage capacity of the area A=(S0-S1) / T.

[0006] Further, step S200 includes the following steps: Step S201: randomly select two areas, and obtain the water storage capacity of the two areas as A1 and A2 respectively, according to the formula: ; The first difference coefficient α between the two selected areas is calculated; since the water storage capacity value reflects the average change process of the water storage amount, which is equivalent to the slope in the coordinate system, the difference between the two slopes can be reflected by the angle between the two slopes; and the first difference coefficient reflects the difference in water storage capacity by the angle between the two slopes; Step S202: Establish a two-dimensional rectangular coordinate system with the time point as the horizontal coordinate and the water storage as the vertical coordinate, and present the change of the water storage in the two selected areas over time; respectively obtain the time when S=S th The time lengths of the two regions are T1 and T2, and the comparison lengths of the two regions are obtained as DT=Min(T1,T2), where Min() is the minimum value function; arbitrarily select a time point t0, and obtain the water storage capacity at the time point t0 as A1 t0 and A2 t0 , according to the formula: ; The second difference coefficient β between the two selected areas is calculated; the second difference coefficient reflects the difference in water storage capacity at the same time point, and presents the real-time difference between the two areas most directly; Step S203: Obtain the difference length between the two regions as CT=|T1-T2|, according to the formula: ; Calculate the water storage characteristic value Sim between the two areas; pre-set a characteristic threshold Sim th , if Sim<Sim th , the two selected areas are set as similar areas; the similarity of water storage capacity between the two areas can be judged more comprehensively by combining the two difference coefficients with the detection time. The longer the common time interval of the two areas in reaching the minimum water storage capacity and the shorter the difference time interval, the more intuitively the similarity between the two areas can be reflected; Step S204: if there are two areas that are similar to each other and there is a common boundary between the two areas, the two areas that are similar to each other are merged into one irrigation area, and the water storage capacity of the irrigation area is obtained by taking the average value of the water storage capacity of the two areas; the irrigation area is further compared with the remaining areas for similarity to obtain several irrigation areas of the target field; Step S205: arbitrarily select two irrigation areas, extract the monitoring data in the corresponding irrigation records of the irrigation areas, and divide the monitoring data into several dimensions according to preset monitoring indicators, wherein any dimension has only one monitoring indicator corresponding to it; arbitrarily select a dimension, and compare the monitoring data of the two irrigation areas on the selected dimension for similarity. If the obtained similarity is less than the preset similarity threshold, feature extraction is performed from the selected dimension to obtain several difference features between the two irrigation areas.

[0007] Further, step S300 includes the following steps: Step S301: setting an arbitrarily selected irrigation area as a target irrigation area, and randomly selecting an irrigation area from other irrigation areas as a reference area, obtaining all difference features between the target irrigation area and the reference area, and obtaining a difference feature set; Step S302: arbitrarily select the ith difference feature from the difference feature set, and obtain the monitoring data of the dimension corresponding to the ith difference feature. If the data type of the monitoring data is a pure value, the monitoring data of the target irrigation area is set to D1. i The monitoring data of the reference area is D2 i , calculate the offset degree pi =(D1 i -D2 i ) / D2 i If the data type of the monitoring data is not a pure value, the similarity x between the two monitoring data is obtained through the preset similarity comparison rule. i , calculate the offset degree p i =1-x i ; Step S303: Obtain the water storage capacity of the target irrigation area as A target and the water storage capacity of the reference area A refer , the difference in water storage capacity between the two areas is ΔA=A target -A refer ; According to the formula: ; Where i is a positive integer and i∈(1,m), m is the number of difference features in the difference feature set; the influence degree y of the i-th difference feature in the target irrigation area compared with the reference area is calculated. i ; Obtain the influence degree of the ith difference feature in any two irrigation areas, calculate the average value and obtain the average influence degree of the ith difference feature (y ave ) i ; Calculating the impact of each difference feature can reflect in real time the continuous impact of each difference feature on the irrigation area over time, and then effectively identify abnormal situations by comparing the real-time with the actual detected water storage; Step S304: Obtain the time interval between two irrigations in the target irrigation area as T target , according to the formula: ; Among them, S start is the water storage capacity of the target irrigation area after irrigation is completed, S th is the minimum water storage; the average water storage change per unit time ΔS of the target irrigation area is calculated t ; Randomly select a time point t0, and the theoretical water storage capacity at time point t0 is S t0 =S start -ΔS t ×t0, the water storage capacity S is obtained by monitoring the monitoring equipment at time point t0 ’ t0 , and the deviation amplitude f=|S at time point t0 is obtained t0 -S ’ t0 | / S t0 ; Step S305: Obtain the deviation amplitude of each irrigation record in the target irrigation area at each time point, and select the deviation amplitude with the largest value as the expected deviation amplitude f of the target irrigation area. ex .

[0008] Further, step S400 includes the following steps: Step S401: arbitrarily select an irrigation area from the target area, obtain the irrigation with the shortest time interval from the selected irrigation area to the current time, monitor the water storage after the irrigation is completed as S0, set the time interval from the current time to the completion of the irrigation as t now , get the theoretical water storage value S of the selected irrigation area at the current moment now =S0-ΔS ’ t ×t now , where ΔS ’ t To select the water storage change value per unit time in the irrigation area; Step S402: Using monitoring equipment to monitor the real-time water storage capacity S0 at the current moment ’ , calculate the deviation amplitude f of the currently selected irrigation area now =|S now -S0 ’ | / S now ; Set the expected deviation of the selected irrigation area to f ex , if f now >f ex , an abnormal reminder will be sent for the current water storage situation in the selected irrigation area.

[0009] In order to better implement the above method, an agricultural intelligent irrigation water-saving management system is also proposed. The management system includes a regional water storage analysis module, a regional feature analysis module, a feature impact analysis module and a real-time anomaly recognition module; The regional water storage analysis module is used to install several monitoring devices in the target field in a closed environment to monitor the water storage situation and divide the target field into regions, irrigate the corresponding area when the preset conditions are met, and collect the monitoring data of each monitoring device in the corresponding area in real time; evaluate the water storage capacity of the corresponding area based on the collected monitoring data, and generate corresponding irrigation records; The regional feature analysis module is used to re-divide the target field into several irrigation areas based on the differences in water storage capacity between the areas; based on the differences between the different irrigation areas, the difference features between the different irrigation areas are extracted; The feature impact analysis module is used to select an irrigation area at random and compare the water storage conditions of the selected irrigation area with those of other irrigation areas to obtain the influence of each difference feature in the selected irrigation area; analyze the irrigation conditions presented by any irrigation record corresponding to the selected irrigation area, and analyze the expected deviation amplitude of the selected irrigation area; The real-time anomaly recognition module is used to monitor the water storage situation of the target area in real time through monitoring equipment every time the target area is irrigated, and obtain the real-time water storage value of each irrigation area; based on the changes in the water storage value of each irrigation area, it is judged in real time whether there is an anomaly.

[0010] Further, the regional water storage analysis module includes an irrigation data collection unit and a water storage capacity analysis unit; The irrigation data acquisition unit is used to install several monitoring devices in the target field in a closed environment to monitor the water storage situation and divide the target field into areas. When the preset conditions are met, the corresponding area is irrigated and the monitoring data of each monitoring device in the corresponding area is collected in real time; the water storage capacity analysis unit is used to evaluate the water storage capacity of the corresponding area based on the collected monitoring data and generate corresponding irrigation records.

[0011] Furthermore, the regional feature analysis module includes an irrigation area division unit and a difference feature extraction unit; The irrigation area division unit is used to re-divide the target field into several irrigation areas based on the difference in water storage capacity between the areas; the difference feature extraction unit is used to extract the difference features between different irrigation areas based on the difference between the different irrigation areas.

[0012] Further, the characteristic impact analysis module includes an impact degree analysis unit and a desired irrigation analysis unit; The impact degree analysis unit is used to select an irrigation area at random and compare the water storage conditions of the selected irrigation area with those of other irrigation areas to obtain the impact degree of each difference feature in the selected irrigation area; the expected irrigation analysis unit is used to analyze the irrigation conditions presented in the selected irrigation area corresponding to any irrigation record, and analyze the expected deviation amplitude of the selected irrigation area.

[0013] Furthermore, the real-time anomaly identification module includes an actual water storage monitoring unit and a water storage anomaly determination unit; The actual water storage monitoring unit is used to monitor the water storage situation of the target area in real time through the monitoring equipment every time the target area is irrigated, so as to obtain the real-time water storage value of each irrigation area; the water storage abnormality judgment unit is used to judge whether there is an abnormality in real time based on the changes in the water storage value of each irrigation area.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention divides the target area according to the different water storage capacities of different areas, and independently analyzes the differences between the irrigation areas, so as to help the staff to effectively identify the areas that need to be irrigated during irrigation and avoid the waste of water resources; 2. The present invention extracts the difference features between irrigation areas, analyzes the influence of each difference feature, obtains the expected water storage situation of the irrigation area at any time point, and compares it with the actual water storage situation monitored to identify the abnormal situation of the irrigation area. It can more accurately identify the abnormal consumption of water resources, thereby promoting abnormal detection and avoiding the waste of water resources caused by frequent irrigation; 3. By comparing the expected water storage conditions with the theoretical water storage conditions in the irrigation area, compared with the conventional technical means of identifying anomalies based on irrigation frequency, the present invention can capture anomalies in the irrigation area in real time, identify anomalies in the shortest time, minimize the waste of water resources, and effectively improve processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of the steps of an agricultural intelligent irrigation water-saving management method based on big data; Figure 2 This is a structural diagram of an agricultural intelligent irrigation water-saving management system based on big data. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Example: Figure 1 to Figure 2 As shown, the present invention provides an agricultural intelligent irrigation water-saving management method based on big data, and the management method comprises the following steps: Step S100: a plurality of monitoring devices are installed in the target field in a closed environment to monitor the water storage situation and divide the target field into regions. When the preset conditions are met, the corresponding region is irrigated, and the monitoring data of each monitoring device in the corresponding region is collected in real time; the water storage capacity of the corresponding region is evaluated based on the collected monitoring data, and a corresponding irrigation record is generated; Wherein, step S100 includes the following steps: Step S101: installing a plurality of monitoring devices in the target field according to a pre-determined layout, obtaining the monitoring range of each monitoring device, and dividing the target field into a plurality of regions using the monitoring range of each monitoring device, wherein one region corresponds to the monitoring range of one monitoring device; Step S102: Preset a minimum water storage volume S th , use monitoring equipment to monitor the water storage capacity S of a certain area. If S<S th , then irrigate the certain area; when the irrigation of the certain area is completed, generate an irrigation record for the certain area, summarizing all monitoring data from the completion of irrigation to the next irrigation; Step S103: Select the irrigation record generated by the most recent irrigation of the area, read the water storage capacity when the irrigation is completed as S0 and the currently monitored water storage capacity as S1, set the time interval between the current distance to the completion of irrigation of the area as T, and obtain the water storage capacity of the area A=(S0-S1) / T.

[0018] Step S200: re-dividing the target field into a number of irrigation areas based on the difference in water storage capacity between the various areas; extracting the difference features between the different irrigation areas based on the difference between the different irrigation areas; Wherein, step S200 includes the following steps: Step S201: randomly select two areas, and obtain the water storage capacity of the two areas as A1 and A2 respectively, according to the formula: ; Calculate and obtain the first difference coefficient α between the two selected areas; Example 1: The water storage capacity of the two regions is set to 1 and 0.5 respectively, and α is calculated to be 0.25; Step S202: Establish a two-dimensional rectangular coordinate system with the time point as the horizontal coordinate and the water storage as the vertical coordinate, and present the change of the water storage in the two selected areas over time; respectively obtain the time when S=S th The time lengths of the two regions are T1 and T2, and the comparison lengths of the two regions are obtained as DT=Min(T1,T2), where Min() is the minimum value function; arbitrarily select a time point t0, and obtain the water storage capacity at the time point t0 as A1 t0 and A2 t0 , according to the formula: ; Calculate and obtain the second difference coefficient β between the two selected areas; Step S203: Obtain the difference length between the two regions as CT=|T1-T2|, according to the formula: ; Calculate the water storage characteristic value Sim between the two areas; pre-set a characteristic threshold Sim th , if Sim<Sim th , then the two selected areas are set as similar areas; Example 2: Set the comparison length of the two regions to 10h, the difference length to 2h, and α=0.25, β=0.5, and calculate the water storage characteristic value Sim between the two regions to be 0.25 / 10+0.5×2=1.025; set the characteristic threshold Sim th =1, then the two regions are not similar regions; Step S204: if there are two areas that are similar to each other and there is a common boundary between the two areas, the two areas that are similar to each other are merged into one irrigation area, and the water storage capacity of the irrigation area is obtained by taking the average value of the water storage capacity of the two areas; the irrigation area is further compared with the remaining areas for similarity to obtain several irrigation areas of the target field; Step S205: arbitrarily select two irrigation areas, extract the monitoring data in the corresponding irrigation records of the irrigation areas, and divide the monitoring data into several dimensions according to preset monitoring indicators, wherein any dimension has only one monitoring indicator corresponding to it; arbitrarily select a dimension, and compare the monitoring data of the two irrigation areas on the selected dimension for similarity. If the obtained similarity is less than the preset similarity threshold, feature extraction is performed from the selected dimension to obtain several difference features between the two irrigation areas.

[0019] Step S300: randomly selecting an irrigation area, and comparing and analyzing the water storage conditions of the selected irrigation area with those of other irrigation areas, to obtain the influence degree of each difference feature in the selected irrigation area; analyzing the irrigation conditions presented by any irrigation record corresponding to the selected irrigation area, and analyzing the expected deviation amplitude of the selected irrigation area; Wherein, step S300 includes the following steps: Step S301: setting an arbitrarily selected irrigation area as a target irrigation area, and randomly selecting an irrigation area from other irrigation areas as a reference area, obtaining all difference features between the target irrigation area and the reference area, and obtaining a difference feature set; Step S302: arbitrarily select the ith difference feature from the difference feature set, and obtain the monitoring data of the dimension corresponding to the ith difference feature. If the data type of the monitoring data is a pure value, the monitoring data of the target irrigation area is set to D1. iThe monitoring data of the reference area is D2 i , calculate the offset degree p i =(D1 i -D2 i ) / D2 i If the data type of the monitoring data is not a pure value, the similarity x between the two monitoring data is obtained through the preset similarity comparison rule. i , calculate the offset degree p i =1-x i ; Step S303: Obtain the water storage capacity of the target irrigation area as A target and the water storage capacity of the reference area A refer , the difference in water storage capacity between the two areas is ΔA=A target -A refer ; According to the formula: ; Where i is a positive integer and i∈(1,m), m is the number of difference features in the difference feature set; the influence degree y of the i-th difference feature in the target irrigation area compared with the reference area is calculated. i ; Obtain the influence degree of the ith difference feature in any two irrigation areas, calculate the average value and obtain the average influence degree of the ith difference feature (y ave ) i ; Step S304: Obtain the time interval between two irrigations in the target irrigation area as T target , according to the formula: ; Among them, S start is the water storage capacity of the target irrigation area after irrigation is completed, S th is the minimum water storage; the average water storage change per unit time ΔS of the target irrigation area is calculated t ; Randomly select a time point t0, and the theoretical water storage capacity at time point t0 is S t0 =S start -ΔS t ×t0, the water storage capacity S is obtained by monitoring the monitoring equipment at time point t0 ’ t0 , and the deviation amplitude f=|S at time point t0 is obtained t0 -S ’ t0 | / S t0 ; Example 3: Set the water storage capacity of the target irrigation area at the end of irrigation to 100, and the minimum water storage capacity to 20; obtain three difference characteristics in the target irrigation area, and the influence degrees are 0.2, 0.2 and 0.1 respectively, and obtain the time interval between two irrigations as 10 moments, and calculate ΔS t =80×(1+0.2)×(1+0.2)×(1+0.1) / 10=12.672; Step S305: Obtain the deviation amplitude of each irrigation record in the target irrigation area at each time point, and select the deviation amplitude with the largest value as the expected deviation amplitude f of the target irrigation area. ex .

[0020] Step S400: Whenever the target area is irrigated, the water storage situation of the target area is monitored in real time by the monitoring device to obtain the real-time water storage value of each irrigation area; based on the change of the water storage value of each irrigation area, it is determined in real time whether there is an abnormality; Wherein, step S400 includes the following steps: Step S401: arbitrarily select an irrigation area from the target area, obtain the irrigation with the shortest time interval from the selected irrigation area to the current time, monitor the water storage after the irrigation is completed as S0, set the time interval from the current time to the completion of the irrigation as t now , get the theoretical water storage value S of the selected irrigation area at the current moment now =S0-ΔS ’ t ×t now , where ΔS ’ t To select the water storage change value per unit time in the irrigation area; Step S402: Using monitoring equipment to monitor the real-time water storage capacity S0 at the current moment ’ , calculate the deviation amplitude f of the currently selected irrigation area now =|S now -S0 ’ | / S now ; Set the expected deviation of the selected irrigation area to f ex , if f now >f ex , an abnormal reminder will be sent for the current water storage situation in the selected irrigation area.

[0021] An agricultural intelligent irrigation water-saving management system, the management system includes a regional water storage analysis module, a regional feature analysis module, a feature impact analysis module and a real-time anomaly recognition module; The regional water storage analysis module is used to install several monitoring devices in the target field in a closed environment to monitor the water storage situation and divide the target field into regions, irrigate the corresponding area when the preset conditions are met, and collect the monitoring data of each monitoring device in the corresponding area in real time; evaluate the water storage capacity of the corresponding area based on the collected monitoring data, and generate corresponding irrigation records; The regional feature analysis module is used to re-divide the target field into several irrigation areas based on the differences in water storage capacity between the areas; based on the differences between the different irrigation areas, the difference features between the different irrigation areas are extracted; The feature impact analysis module is used to select an irrigation area at random and compare the water storage conditions of the selected irrigation area with those of other irrigation areas to obtain the influence of each difference feature in the selected irrigation area; analyze the irrigation conditions presented by any irrigation record corresponding to the selected irrigation area, and analyze the expected deviation amplitude of the selected irrigation area; The real-time anomaly recognition module is used to monitor the water storage situation of the target area in real time through monitoring equipment every time the target area is irrigated, and obtain the real-time water storage value of each irrigation area; based on the changes in the water storage value of each irrigation area, it is judged in real time whether there is an anomaly.

[0022] Among them, the regional water storage analysis module includes an irrigation data acquisition unit and a water storage capacity analysis unit; The irrigation data acquisition unit is used to install several monitoring devices in the target field in a closed environment to monitor the water storage situation and divide the target field into areas. When the preset conditions are met, the corresponding area is irrigated and the monitoring data of each monitoring device in the corresponding area is collected in real time; the water storage capacity analysis unit is used to evaluate the water storage capacity of the corresponding area based on the collected monitoring data and generate corresponding irrigation records.

[0023] Among them, the regional feature analysis module includes an irrigation area division unit and a difference feature extraction unit; The irrigation area division unit is used to re-divide the target field into several irrigation areas based on the difference in water storage capacity between the areas; the difference feature extraction unit is used to extract the difference features between different irrigation areas based on the difference between the different irrigation areas.

[0024] Among them, the characteristic impact analysis module includes an impact degree analysis unit and an expected irrigation analysis unit; The impact degree analysis unit is used to select an irrigation area at random and compare the water storage conditions of the selected irrigation area with those of other irrigation areas to obtain the impact degree of each difference feature in the selected irrigation area; the expected irrigation analysis unit is used to analyze the irrigation conditions presented in the selected irrigation area corresponding to any irrigation record, and analyze the expected deviation amplitude of the selected irrigation area.

[0025] Among them, the real-time abnormality identification module includes an actual water storage monitoring unit and a water storage abnormality judgment unit; The actual water storage monitoring unit is used to monitor the water storage situation of the target area in real time through the monitoring equipment every time the target area is irrigated, so as to obtain the real-time water storage value of each irrigation area; the water storage abnormality judgment unit is used to judge whether there is an abnormality in real time based on the changes in the water storage value of each irrigation area.

[0026] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An agricultural intelligent irrigation water-saving management method based on big data, characterized by: The management method comprises the following steps: Step S100: a plurality of monitoring devices are installed in the target field in a closed environment to monitor the water storage situation and divide the target field into regions. When the preset conditions are met, the corresponding region is irrigated, and the monitoring data of each monitoring device in the corresponding region is collected in real time; the water storage capacity of the corresponding region is evaluated based on the collected monitoring data, and a corresponding irrigation record is generated; Step S200: re-dividing the target field into a number of irrigation areas based on the difference in water storage capacity between the various areas; extracting the difference features between the different irrigation areas based on the difference between the different irrigation areas; Step S300: randomly selecting an irrigation area, and comparing and analyzing the water storage conditions of the selected irrigation area with those of other irrigation areas, to obtain the influence degree of each difference feature in the selected irrigation area; analyzing the irrigation conditions presented by any irrigation record corresponding to the selected irrigation area, and analyzing the expected deviation amplitude of the selected irrigation area; Step S400: Whenever the target area is irrigated, the water storage situation of the target area is monitored in real time by the monitoring equipment to obtain the real-time water storage value of each irrigation area; based on the change of the water storage value of each irrigation area, it is determined in real time whether there is any abnormality.

2. According to the big data-based agricultural intelligent irrigation water-saving management method of claim 1, it is characterized by: The step S100 includes the following steps: Step S101: installing a plurality of monitoring devices in the target field according to a pre-determined layout, obtaining the monitoring range of each monitoring device, and dividing the target field into a plurality of regions using the monitoring range of each monitoring device, wherein one region corresponds to the monitoring range of one monitoring device; Step S102: Preset a minimum water storage volume S th , use monitoring equipment to monitor the water storage capacity S of a certain area. If S<S th , then irrigate the certain area; when the irrigation of the certain area is completed, generate an irrigation record for the certain area, summarizing all monitoring data from the completion of irrigation to the next irrigation; Step S103: Select the irrigation record generated by the most recent irrigation of the area, read the water storage capacity when the irrigation is completed as S0 and the currently monitored water storage capacity as S1, set the time interval between the current distance to the completion of irrigation of the area as T, and obtain the water storage capacity of the area A=(S0-S1) / T.

3. The method for agricultural intelligent irrigation water-saving management based on big data according to claim 2 is characterized in that: The step S200 includes the following steps: Step S201: randomly select two areas, and obtain the water storage capacity of the two areas as A1 and A2 respectively, according to the formula: ； Calculate and obtain the first difference coefficient α between the two selected areas; Step S202: Establish a two-dimensional rectangular coordinate system with the time point as the horizontal coordinate and the water storage as the vertical coordinate, and present the change of the water storage in the two selected areas over time; respectively obtain the time when S=S th The time lengths of the two regions are T1 and T2, and the comparison lengths of the two regions are obtained as DT=Min(T1,T2), where Min() is the minimum value function; arbitrarily select a time point t0, and obtain the water storage capacity at the time point t0 as A1 t0 and A2 t0 , according to the formula: ； Calculate and obtain the second difference coefficient β between the two selected areas; Step S203: Obtain the difference length between the two regions as CT=|T1-T2|, according to the formula: ； Calculate the water storage characteristic value Sim between the two areas; pre-set a characteristic threshold Sim th , if Sim<Sim th , then the two selected areas are set as similar areas; Step S204: if there are two areas that are similar to each other and there is a common boundary between the two areas, the two areas that are similar to each other are merged into one irrigation area, and the water storage capacity of the irrigation area is obtained by taking the average value of the water storage capacity of the two areas; the irrigation area is further compared with the remaining areas for similarity to obtain several irrigation areas of the target field; Step S205: arbitrarily select two irrigation areas, extract the monitoring data in the corresponding irrigation records of the irrigation areas, and divide the monitoring data into several dimensions according to preset monitoring indicators, wherein any dimension has only one monitoring indicator corresponding to it; arbitrarily select a dimension, and compare the monitoring data of the two irrigation areas on the selected dimension for similarity. If the obtained similarity is less than the preset similarity threshold, feature extraction is performed from the selected dimension to obtain several difference features between the two irrigation areas.

4. According to the big data-based agricultural intelligent irrigation water-saving management method of claim 3, it is characterized by: The step S300 includes the following steps: Step S301: setting an arbitrarily selected irrigation area as a target irrigation area, and randomly selecting an irrigation area from other irrigation areas as a reference area, obtaining all difference features between the target irrigation area and the reference area, and obtaining a difference feature set; Step S302: arbitrarily select the ith difference feature from the difference feature set, and obtain the monitoring data of the dimension corresponding to the ith difference feature. If the data type of the monitoring data is a pure value, the monitoring data of the target irrigation area is set to D1. i The monitoring data of the reference area is D2 i , calculate the offset degree p i =(D1 i -D2 i ) / D2 i If the data type of the monitoring data is not a pure value, the similarity x between the two monitoring data is obtained through the preset similarity comparison rule. i , calculate the offset degree p i =1-x i ; Step S303: Obtain the water storage capacity of the target irrigation area as A target and the water storage capacity of the reference area A refer , the difference in water storage capacity between the two areas is ΔA=A target -A refer ; According to the formula: ； Where i is a positive integer and i∈(1,m), m is the number of difference features in the difference feature set; the influence degree y of the i-th difference feature in the target irrigation area compared with the reference area is calculated. i ; Obtain the influence degree of the ith difference feature in any two irrigation areas, calculate the average value and obtain the average influence degree of the ith difference feature (y ave ) i ; Step S304: Obtain the time interval between two irrigations in the target irrigation area as T target , according to the formula: ； Among them, S start is the water storage capacity of the target irrigation area after irrigation is completed, S th is the minimum water storage; the average water storage change per unit time ΔS of the target irrigation area is calculated t ; Randomly select a time point t0, and the theoretical water storage capacity at time point t0 is S t0 =S start -ΔS t ×t0, the water storage capacity S is obtained by monitoring the monitoring equipment at time point t0 ’ t0 , we get the deviation amplitude f=|S at time point t0 t0 -S ’ t0 | / S t0 ; Step S305: Obtain the deviation amplitude of each irrigation record in the target irrigation area at each time point, and select the deviation amplitude with the largest value as the expected deviation amplitude f of the target irrigation area. ex .

5. The method for agricultural intelligent irrigation water-saving management based on big data according to claim 4 is characterized in that: The step S400 includes the following steps: Step S401: arbitrarily select an irrigation area from the target area, obtain the irrigation with the shortest time interval from the selected irrigation area to the current time, monitor the water storage after the irrigation is completed as S0, set the time interval from the current time to the completion of the irrigation as t now , get the theoretical water storage value S of the selected irrigation area at the current moment now =S0-ΔS ’ t ×t now , where ΔS ’ t To select the water storage change value per unit time in the irrigation area; Step S402: Using monitoring equipment to monitor the real-time water storage capacity S0 at the current moment ’ , calculate the deviation amplitude f of the currently selected irrigation area now =|S now -S0 ’ | / S now ; Set the expected deviation of the selected irrigation area to f ex , if f now >f ex , an abnormal reminder will be sent for the current water storage situation in the selected irrigation area.

6. An agricultural intelligent irrigation water-saving management system, used to implement an agricultural intelligent irrigation water-saving management method based on big data as claimed in any one of claims 1 to 5, characterized in that: The management system includes a regional water storage analysis module, a regional feature analysis module, a feature impact analysis module and a real-time anomaly recognition module; The regional water storage analysis module is used to install several monitoring devices in the target field in a closed environment to monitor the water storage situation and divide the target field into regions, irrigate the corresponding region when the preset conditions are met, and collect the monitoring data of each monitoring device in the corresponding region in real time; Evaluate the water storage capacity of the corresponding area based on the collected monitoring data and generate corresponding irrigation records; The regional feature analysis module is used to re-divide the target field into a number of irrigation areas based on the difference in water storage capacity between the various areas; based on the difference between the different irrigation areas, extract the difference characteristics between the different irrigation areas; The feature impact analysis module is used to select an irrigation area at random, and compare and analyze the water storage conditions of the selected irrigation area with those of other irrigation areas to obtain the influence degree of each difference feature in the selected irrigation area; analyze the irrigation conditions presented by any irrigation record corresponding to the selected irrigation area, and analyze the expected deviation amplitude of the selected irrigation area; The real-time abnormality identification module is used to monitor the water storage situation of the target area in real time through the monitoring equipment every time the target area is irrigated, so as to obtain the real-time water storage value of each irrigation area; based on the change of the water storage value of each irrigation area, it is judged in real time whether there is an abnormality.

7. The agricultural intelligent irrigation water-saving management system according to claim 6, characterized in that: The regional water storage analysis module includes an irrigation data acquisition unit and a water storage capacity analysis unit; The irrigation data acquisition unit is used to install a number of monitoring devices in a target field in a closed environment to monitor the water storage situation and divide the target field into areas, irrigate the corresponding area when the preset conditions are met, and collect the monitoring data of each monitoring device in the corresponding area in real time; the water storage capacity analysis unit is used to evaluate the water storage capacity of the corresponding area based on the collected monitoring data, and generate corresponding irrigation records.

8. The agricultural intelligent irrigation water-saving management system according to claim 6, characterized in that: The regional feature analysis module includes an irrigation area division unit and a difference feature extraction unit; The irrigation area division unit is used to re-divide the target field into a number of irrigation areas based on the difference in water storage capacity between the areas; the difference feature extraction unit is used to extract the difference features between different irrigation areas based on the difference conditions between the different irrigation areas.

9. The agricultural intelligent irrigation water-saving management system according to claim 6, characterized in that: The characteristic impact analysis module includes an impact degree analysis unit and an expected irrigation analysis unit; The impact degree analysis unit is used to arbitrarily select an irrigation area, and compare and analyze the water storage conditions of the selected irrigation area with those of other irrigation areas to obtain the impact degree of each difference feature in the selected irrigation area; the expected irrigation analysis unit is used to analyze the irrigation conditions presented in the selected irrigation area corresponding to any irrigation record, and analyze the expected deviation amplitude of the selected irrigation area.

10. The agricultural intelligent irrigation water-saving management system according to claim 6, characterized in that: The real-time abnormality identification module includes an actual water storage monitoring unit and a water storage abnormality judgment unit; The actual water storage monitoring unit is used to monitor the water storage situation of the target area in real time through the monitoring equipment every time the target area is irrigated, so as to obtain the real-time water storage value of each irrigation area; the water storage abnormality judgment unit is used to judge whether there is an abnormality in real time based on the change of the water storage value of each irrigation area.

Images