Automatic monitoring method and device for preventing back poverty

Abstract

The invention provides an automatic monitoring method and device for preventing poverty returning, and relates to the technical field of agricultural information, and the method comprises the steps: obtaining poverty-fatting event data of a plurality of farmers; based on the poverty-fatting event data of the plurality of farmers, calculating a poverty-fatting event monitoring index of each farmer in the plurality of farmers through a pre-constructed poverty-fatting event automatic monitoring model; when the poverty-fatting event monitoring index is greater than or equal to a first preset threshold value, determining a corresponding farmer as a target poverty-fatting farmer; obtaining target poverty return risk data of the target poverty-fatting farmer, and calculating a poverty return risk index of the target poverty-fatting farmer through a pre-constructed poverty return risk automatic early warning model based on the target poverty return risk data of the target poverty-fatting farmer; and under the condition that the poverty returning risk index is greater than or equal to a second preset threshold value, determining a corresponding target poverty-causing farmer as a high-risk poverty returning farmer. Through the method provided by the invention, the assisted object can be accurately found.

Description

Technical Field

[0001] The present invention relates to the field of agricultural information technology, and in particular to an automatic monitoring method and device for preventing poverty relapse. Background Art

[0002] At present, traditional poverty prevention monitoring requires village cadres to conduct on-site visits and surveys to gain an in-depth understanding of all aspects of education, medical care, employment, etc. of all family members of each farmer's household. In order to ensure timely and comprehensive information discovery, village cadres need to visit every household at least once a month. The workload is relatively large, which can easily lead to practical business problems such as "poverty problems are difficult to discover, assistance targets are not accurately identified, and monitoring information is incomplete."

[0003] How to assess farmers’ risk of falling into poverty and accurately identify those who need assistance is a technical problem that needs to be solved at present. Summary of the invention

[0004] The present invention provides an automatic monitoring method and device for preventing poverty relapse, so as to solve the defects in the prior art.

[0005] The present invention provides an automatic monitoring method for preventing poverty relapse, comprising the following steps: Obtaining poverty-causing event data of multiple farmers; wherein the poverty-causing event data is formed based on various types of farmer information from various sources; Based on the poverty event data of the plurality of farmers, a poverty event monitoring index of each of the plurality of farmers is calculated by using a pre-constructed automatic monitoring model for poverty events; When the poverty event monitoring index is greater than or equal to the first preset threshold, the corresponding farmer is determined as a target poverty farmer; wherein the target poverty farmer refers to a farmer who is the focus of attention in the poverty event; Obtaining target re-poverty risk data of the target impoverished farmers, and calculating the re-poverty risk index of the target impoverished farmers based on the target re-poverty risk data of the target impoverished farmers through a pre-built automatic early warning model for re-poverty risk; When the poverty return risk index is greater than or equal to the second preset threshold, the corresponding target impoverished farmers are determined as high-risk poverty return farmers.

[0006] According to an automatic monitoring method for preventing poverty relapse provided by the present invention, based on the poverty event data of the plurality of farmers, a poverty event monitoring index of each of the plurality of farmers is calculated by a pre-constructed automatic monitoring model for poverty events, including: Determine multiple poverty-causing event monitoring indicators and the weight corresponding to each poverty-causing event monitoring indicator by a preset method; wherein the preset method includes but is not limited to: hierarchical analysis method, expert survey method, principal component analysis method and entropy weight method; Based on the predetermined target value of each poverty-causing event monitoring indicator, a target score for each poverty-causing event monitoring indicator is calculated; wherein the target value is used to represent the optimal value of the poverty-causing event monitoring indicator; Based on the multiple poverty-causing event monitoring indicators, the weight corresponding to each poverty-causing event monitoring indicator and the target score of each poverty-causing event monitoring indicator, the poverty-causing event monitoring index of the corresponding farmer is calculated.

[0007] According to an automatic monitoring method for preventing poverty relapse provided by the present invention, the poverty event monitoring index of the corresponding farmer is calculated based on the multiple poverty event monitoring indicators, the weight corresponding to each poverty event monitoring indicator and the target score of each poverty event monitoring indicator, which is achieved by the following formula:

[0008] in, represents the poverty event monitoring index, represents the weight corresponding to the i-th poverty event monitoring indicator, represents the target score of the i-th poverty-causing event monitoring indicator, and n represents the number of poverty-causing event monitoring indicators.

[0009] According to an automatic monitoring method for preventing poverty relapse provided by the present invention, before obtaining the target poverty relapse risk data of the target impoverished farmers, and calculating the poverty relapse risk index of the target impoverished farmers based on the target poverty relapse risk data of the target impoverished farmers through a pre-built poverty relapse risk automatic early warning model, the method further includes: Acquire the poverty return risk data of the target impoverished farmers according to a preset period, and store the poverty return risk data of the target impoverished farmers in a poverty return risk dynamic monitoring database; The automatic early warning model for the risk of returning to poverty is constructed based on the dynamic monitoring database for the risk of returning to poverty.

[0010] According to an automatic monitoring method for preventing poverty relapse provided by the present invention, after calculating the poverty relapse risk index of the target impoverished farmers based on the target poverty relapse risk data of the target impoverished farmers through a pre-constructed poverty relapse risk automatic early warning model, the method further includes: When the poverty return risk index is less than the second preset threshold and greater than or equal to the third preset threshold, the corresponding target impoverished farmer is determined as a medium-risk poverty return farmer; wherein the second preset threshold is greater than the third preset threshold; When the poverty return risk index is less than the third preset threshold, the corresponding target impoverished farmers are determined as low-risk poverty return farmers.

[0011] The present invention also provides an automatic monitoring device for preventing poverty relapse, comprising the following modules: An acquisition module, used to acquire poverty-causing event data of multiple farmers; wherein the poverty-causing event data is formed based on various types of farmer information from various sources; A first calculation module is used to calculate the poverty event monitoring index of each of the multiple farmers based on the poverty event data of the multiple farmers through a pre-built automatic poverty event monitoring model; A first determination module is used to determine the corresponding farmer as a target impoverished farmer when the poverty event monitoring index is greater than or equal to a first preset threshold; wherein the target impoverished farmer refers to a farmer who is the focus of attention in the poverty event; The second calculation module is used to obtain the target re-poverty risk data of the target impoverished farmers, and calculate the re-poverty risk index of the target impoverished farmers based on the target re-poverty risk data of the target impoverished farmers through a pre-built re-poverty risk automatic early warning model; The second determination module is used to determine the corresponding target impoverished farmers as high-risk farmers returning to poverty when the poverty returning risk index is greater than or equal to a second preset threshold.

[0012] According to an automatic monitoring device for preventing poverty relapse provided by the present invention, the first calculation module is specifically used for: Determine multiple poverty-causing event monitoring indicators and the weight corresponding to each poverty-causing event monitoring indicator by a preset method; wherein the preset method includes but is not limited to: hierarchical analysis method, expert survey method, principal component analysis method and entropy weight method; Based on the predetermined target value of each poverty-causing event monitoring indicator, a target score for each poverty-causing event monitoring indicator is calculated; wherein the target value is used to represent the optimal value of the poverty-causing event monitoring indicator; Based on the multiple poverty-causing event monitoring indicators, the weight corresponding to each poverty-causing event monitoring indicator and the target score of each poverty-causing event monitoring indicator, the poverty-causing event monitoring index of the corresponding farmer is calculated.

[0013] According to an automatic monitoring device for preventing poverty relapse provided by the present invention, the poverty event monitoring index of the corresponding farmer is calculated based on the multiple poverty event monitoring indicators, the weight corresponding to each poverty event monitoring indicator and the target score of each poverty event monitoring indicator, which is achieved by the following formula:

[0014] in, represents the poverty event monitoring index, represents the weight corresponding to the i-th poverty event monitoring indicator, represents the target score of the i-th poverty-causing event monitoring indicator, and n represents the number of poverty-causing event monitoring indicators.

[0015] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the automatic monitoring method for preventing poverty relapse as described in any one of the above is implemented.

[0016] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described automatic monitoring methods for preventing poverty relapse.

[0017] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the automatic monitoring method for preventing poverty relapse as described above is implemented.

[0018] The present invention provides an automatic monitoring method and device for preventing poverty relapse, which obtains poverty event data of multiple farmers; wherein the poverty event data is formed by various types of farmer information based on multiple sources; based on the poverty event data of the multiple farmers, a poverty event monitoring index of each of the multiple farmers is calculated through a pre-constructed automatic monitoring model for poverty events; when the poverty event monitoring index is greater than or equal to a first preset threshold, the corresponding farmer is determined as a target poverty farmer; wherein the target poverty farmer represents a farmer who is the focus of attention in the poverty event; the target poverty relapse risk data of the target poverty farmer is obtained, and based on the target poverty relapse risk data of the target poverty farmer, a poverty relapse risk index of the target poverty farmer is calculated through a pre-constructed automatic early warning model for poverty relapse risk; when the poverty relapse risk index is greater than or equal to a second preset threshold, the corresponding target poverty farmer is determined as a high-risk poverty relapse farmer. It can be seen that the present invention ensures the comprehensiveness of data by collecting various types of farmer information from various sources, calculates the poverty event monitoring index through a pre-constructed automatic monitoring model of poverty events, and determines the target impoverished farmers based on the poverty event monitoring index, with high real-time performance and high recognition accuracy. Through a pre-constructed automatic early warning model for the risk of returning to poverty, the risk of returning to poverty of the target impoverished farmers is warned, and the objects of assistance are accurately found. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 It is a flow chart of the automatic monitoring method for preventing poverty relapse provided by the present invention.

[0021] Figure 2 It is one of the complete flow charts of the automatic monitoring method for preventing poverty relapse provided by the present invention.

[0022] Figure 3 This is the second complete flow chart of the automatic monitoring method for preventing poverty relapse provided by the present invention.

[0023] Figure 4 It is a system architecture diagram of the automatic monitoring method for preventing poverty relapse provided by the present invention.

[0024] Figure 5 It is a structural schematic diagram of the automatic monitoring device for preventing poverty relapse provided by the present invention.

[0025] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0027] Combine the following Figure 1-Figure 6 An automatic monitoring method and device for preventing poverty relapse according to the present invention are described.

[0028] Figure 1 is a flow chart of the automatic monitoring method for preventing poverty relapse provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 100: Obtain poverty-causing event data of multiple farmers; wherein the poverty-causing event data is formed based on various types of farmer information from various sources.

[0029] Figure 2 This is one of the complete flow charts of the automatic monitoring method for preventing poverty relapse provided by the present invention. Figure 3 This is the second complete flow chart of the automatic monitoring method for preventing poverty relapse provided by the present invention, combined with Figure 2 and Figure 3 , the automatic monitoring method for preventing poverty relapse provided by an embodiment of the present invention is described.

[0030] It should be noted that the poverty incident data in this embodiment can have multiple sources, mainly including two channels: farmers’ voluntary reporting and survey reporting.

[0031] Specifically, farmers’ self-declaration, survey declaration, etc., that is, poverty-causing incident census data collection: data collection of poverty-causing incidents of all farmers in the jurisdiction, and summary to form a census database of farmers to prevent relapse into poverty. The update frequency of the census database can be, for example, once a quarter. Table 1 shows the indicators of the farmer census data of poverty-causing incidents.

[0032] Table 1

[0033] Specifically, a data exchange interface can also be used to connect data from medical, education, public security, civil affairs, emergency management and other departments to form a shared database of farmers' poverty events. The update frequency of the shared database can be, for example, once a quarter. Table 2 shows the indicators of shared data of poverty events departments.

[0034] Table 2

[0035] Step 200: Based on the poverty event data of the plurality of farmers, a poverty event monitoring index of each farmer in the plurality of farmers is calculated by using a pre-constructed automatic poverty event monitoring model.

[0036] Specifically, step 200 includes: Step 210: determine multiple poverty-causing event monitoring indicators and the weight corresponding to each poverty-causing event monitoring indicator through a preset method; wherein the preset method includes but is not limited to: hierarchical analysis method, expert survey method, principal component analysis method and entropy weight method.

[0037] Specifically, the weight determination should be combined with the following considerations: 1. Expert review should be organized to analyze and evaluate the importance and contribution of each indicator to determine the weight.

[0038] 2. The weights of various indicators can be determined by using methods such as hierarchical analysis method (AHP method), expert survey method (Delphi method), principal component analysis method, and entropy weight method.

[0039] 3. The weight of each primary indicator should not be less than 10%

[0040] Step 220: Calculate the target score of each poverty-causing event monitoring indicator based on the predetermined target value of each poverty-causing event monitoring indicator; wherein the target value is used to represent the optimal numerical value of the poverty-causing event monitoring indicator.

[0041] Specifically, target scores are calculated for different poverty-causing event monitoring indicators, with the score for each indicator being a number between 0 and 1.

[0042] 1. For indicators marked with yes or no, score them directly as 1 or 0.

[0043] 2. The non-indicator of the marked unit is calculated according to the following formula: Positive indicator calculation formula: Negative indicator calculation formula: in, represents the target score of the i-th poverty event monitoring indicator, represents the actual value of the monitoring indicator of the i-th poverty event, Represents the target value of the i-th poverty event monitoring indicator.

[0044] Step 230: Based on the multiple poverty-causing event monitoring indicators, the weight corresponding to each poverty-causing event monitoring indicator, and the target score of each poverty-causing event monitoring indicator, calculate the poverty-causing event monitoring index of the corresponding farmer.

[0045] Specifically, a linear weighted method is used to calculate the poverty-causing event monitoring index, with the index score being a number between 0 and 1. The higher the score, the more serious the impact of the poverty-causing event. This is achieved through the following formula:

[0046] in, represents the poverty event monitoring index, represents the weight corresponding to the i-th poverty event monitoring indicator, represents the target score of the i-th poverty-causing event monitoring indicator, and n represents the number of poverty-causing event monitoring indicators.

[0047] Step 300: When the poverty event monitoring index is greater than or equal to a first preset threshold, the corresponding farmer is determined as a target poverty-stricken farmer; wherein the target poverty-stricken farmer refers to a farmer who is the focus of attention in the poverty event.

[0048] It should be noted that the "census monitoring index" is calculated based on the indicators of the farmer census data on poverty-causing incidents, and the "shared monitoring index" is calculated based on the indicators of shared data from departments on poverty-causing incidents. The two indices are added together to obtain the "poverty-causing incident monitoring index".

[0049] The score of the “Poverty Event Monitoring Index” is a number between 0 and 2. The higher the score, the greater the impact of the poverty event.

[0050] For example, if the first preset threshold is set to 0.8, then households with a "poverty event monitoring index" score greater than or equal to 0.8 will be marked as "key focus"; households with a "poverty event monitoring index" less than 0.8 will be marked as "non-key focus".

[0051] Step 400: obtaining the target re-poverty risk data of the target impoverished farmers, and calculating the re-poverty risk index of the target impoverished farmers based on the target re-poverty risk data of the target impoverished farmers through a pre-constructed automatic early warning model for re-poverty risk.

[0052] Specifically, before obtaining the target re-poverty risk data of the target impoverished farmers in step 400, and calculating the re-poverty risk index of the target impoverished farmers based on the target re-poverty risk data of the target impoverished farmers through a pre-built re-poverty risk automatic early warning model, the method further includes: Acquire the poverty return risk data of the target impoverished farmers according to a preset period, and store the poverty return risk data of the target impoverished farmers in a poverty return risk dynamic monitoring database; The automatic early warning model for the risk of returning to poverty is constructed based on the dynamic monitoring database for the risk of returning to poverty.

[0053] Specifically, for the farmers whose "poverty event monitoring index" is marked as "key concern" in the above embodiment, regular field investigation, investigation and review are carried out to improve the dynamic monitoring database of poverty return risk; the update frequency of the dynamic monitoring database can be, for example, once a month. Table 3 shows the indicators of the dynamic monitoring data of poverty return risk.

[0054] Table 3

[0055] Step 500: When the poverty return risk index is greater than or equal to the second preset threshold, the corresponding target impoverished farmer is determined as a farmer with high risk of poverty return.

[0056] Furthermore, when the poverty return risk index is less than the second preset threshold and greater than or equal to the third preset threshold, the corresponding target impoverished farmers are determined as medium-risk poverty return farmers; wherein, the second preset threshold is greater than the third preset threshold.

[0057] When the poverty return risk index is less than the third preset threshold, the corresponding target impoverished farmers are determined as low-risk poverty return farmers.

[0058] Figure 4 This is a system architecture diagram of the automatic monitoring method for preventing poverty relapse provided by the present invention, see Figure 4 , give specific instructions.

[0059] It should be noted that the method for determining the weights of the poverty return risk warning indicators can refer to the method for determining the weights corresponding to the poverty event monitoring indicators in the above embodiment.

[0060] Furthermore, the target score of the early warning indicator for the risk of returning to poverty is determined as follows: Scores are calculated for different indicator items, and the score of each indicator is a number between 0 and 1.

[0061] 1. For indicators marked with yes or no, score them directly as 1 or 0.

[0062] 2. For indicators marked in percentage (%), the calculation is as follows: Positive indicators: if the indicator value is greater than or equal to the target value, it is worth 1 point; if the indicator value is less than the target value, it is worth 0 point.

[0063] For negative indicators, if the indicator value is less than the target value, it is worth 1 point; if it is greater than or equal to the target value, it is worth 0 point.

[0064] 3. The remaining indicators are calculated according to the following formula: Positive indicator calculation formula: Negative indicator calculation formula: in, represents the target score of the i-th poverty risk warning indicator, represents the actual value of the i-th poverty return risk warning indicator, Represents the target value of the i-th poverty return risk warning indicator.

[0065] Furthermore, a linear weighted method is used to calculate the early warning index of the risk of returning to poverty, and the index score is a number between 0 and 1. This is achieved through the following formula:

[0066] in, It represents the early warning index of the risk of returning to poverty. represents the weight corresponding to the i-th poverty return risk warning indicator, represents the target score of the i-th poverty return risk warning indicator, and n represents the number of poverty return risk warning indicators.

[0067] Specifically, the score of the "poverty return risk warning index" is a number between 0 and 1, and the higher the score, the higher the risk of returning to poverty. For example, the second preset threshold is 0.9 and the third preset threshold is 0.5.

[0068] Farmers with a "return to poverty risk warning index" score greater than or equal to 0.9 are marked as "high risk". It is recommended to provide assistance measures and continue to monitor the risk of returning to poverty.

[0069] Farmers whose "Poverty Event Monitoring Index" scores are less than 0.9 and greater than or equal to 0.5 are marked as "medium risk and continuous attention" and it is recommended to continue to monitor the risk of returning to poverty.

[0070] Farmers whose "poverty event monitoring index" is less than 0.5 are marked as "low risk", withdraw from the poverty return risk warning monitoring, and are given automatic monitoring of poverty events.

[0071] The automatic monitoring method for preventing poverty relapse provided in this embodiment adopts multi-channel collection, multi-level screening, dynamic investigation, real-time calculation and other methods to evaluate the risk of farmers falling back into poverty, realize real-time and accurate identification of farmers at high risk of falling back into poverty, avoid omissions in the work of preventing poverty relapse, improve the efficiency of the work of preventing poverty relapse, and provide a reference for later assistance to farmers.

[0072] The above is a step description of the automatic monitoring method for preventing poverty relapse provided by the present invention. It can be seen from the description of the above steps that according to the automatic monitoring method for preventing poverty relapse provided by the present invention, by obtaining poverty event data of multiple farmers; wherein the poverty event data is formed based on various types of farmer information from multiple sources; based on the poverty event data of the multiple farmers, through a pre-constructed automatic monitoring model for poverty events, the poverty event monitoring index of each farmer in the multiple farmers is calculated; when the poverty event monitoring index is greater than or equal to the first preset threshold, the corresponding farmer is determined as a target poverty farmer; wherein the target poverty farmer represents a farmer that is the focus of attention in the poverty event; the target poverty risk data of the target poverty farmer is obtained, and based on the target poverty risk data of the target poverty farmer, the poverty risk index of the target poverty farmer is calculated through a pre-constructed automatic early warning model for poverty risk; when the poverty risk index is greater than or equal to the second preset threshold, the corresponding target poverty farmer is determined as a high-risk poverty farmer. It can be seen that the present invention ensures the comprehensiveness of data by collecting various types of farmer information from various sources, calculates the poverty event monitoring index through a pre-constructed automatic monitoring model of poverty events, and determines the target impoverished farmers based on the poverty event monitoring index, with high real-time performance and high recognition accuracy. Through a pre-constructed automatic early warning model for the risk of returning to poverty, the risk of returning to poverty of the target impoverished farmers is warned, and the objects of assistance are accurately found.

[0073] The automatic monitoring device for preventing relapse into poverty provided by the present invention is described below. The automatic monitoring device for preventing relapse into poverty described below and the automatic monitoring method for preventing relapse into poverty described above can be referenced to each other.

[0074] Figure 5 Schematic diagram of the structure of the automatic monitoring device for preventing poverty relapse provided by the present invention, such as Figure 5 As shown, the automatic monitoring device for preventing poverty relapse provided by the present invention comprises: An acquisition module 501 is used to acquire poverty-causing event data of multiple farmers; wherein the poverty-causing event data is formed based on various types of farmer information from various sources; A first calculation module 502 is used to calculate the poverty event monitoring index of each of the multiple farmers based on the poverty event data of the multiple farmers through a pre-built automatic poverty event monitoring model; The first determination module 503 is used to determine the corresponding farmer as a target impoverished farmer when the poverty event monitoring index is greater than or equal to a first preset threshold; wherein the target impoverished farmer refers to a farmer who is the focus of attention in the poverty event; The second calculation module 504 is used to obtain the target re-poverty risk data of the target impoverished farmers, and calculate the re-poverty risk index of the target impoverished farmers based on the target re-poverty risk data of the target impoverished farmers through a pre-built re-poverty risk automatic early warning model; The second determination module 505 is used to determine the corresponding target impoverished farmer as a high-risk farmer returning to poverty when the poverty returning risk index is greater than or equal to a second preset threshold.

[0075] The automatic monitoring device for preventing poverty relapse provided by the present invention obtains poverty event data of multiple farmers; wherein the poverty event data is formed by various types of farmer information based on multiple sources; based on the poverty event data of the multiple farmers, a poverty event monitoring index of each farmer in the multiple farmers is calculated through a pre-constructed automatic monitoring model for poverty events; when the poverty event monitoring index is greater than or equal to a first preset threshold, the corresponding farmer is determined as a target poverty farmer; wherein the target poverty farmer represents a farmer that is the focus of attention in the poverty event; the target poverty relapse risk data of the target poverty farmer is obtained, and based on the target poverty relapse risk data of the target poverty farmer, a poverty relapse risk index of the target poverty farmer is calculated through a pre-constructed automatic early warning model for poverty relapse risk; when the poverty relapse risk index is greater than or equal to a second preset threshold, the corresponding target poverty farmer is determined as a high-risk poverty relapse farmer. It can be seen that the present invention ensures the comprehensiveness of data by collecting various types of farmer information from various sources, calculates the poverty event monitoring index through a pre-constructed automatic monitoring model of poverty events, and determines the target impoverished farmers based on the poverty event monitoring index, with high real-time performance and high recognition accuracy. Through a pre-constructed automatic early warning model for the risk of returning to poverty, the risk of returning to poverty of the target impoverished farmers is warned, and the objects of assistance are accurately found.

[0076] Based on the above embodiment, in this embodiment, the first calculation module 502 is specifically used for: Determine multiple poverty-causing event monitoring indicators and the weight corresponding to each poverty-causing event monitoring indicator by a preset method; wherein the preset method includes but is not limited to: hierarchical analysis method, expert survey method, principal component analysis method and entropy weight method; Based on the predetermined target value of each poverty-causing event monitoring indicator, a target score for each poverty-causing event monitoring indicator is calculated; wherein the target value is used to represent the optimal value of the poverty-causing event monitoring indicator; Based on the multiple poverty-causing event monitoring indicators, the weight corresponding to each poverty-causing event monitoring indicator and the target score of each poverty-causing event monitoring indicator, the poverty-causing event monitoring index of the corresponding farmer is calculated.

[0077] Based on the above embodiment, in this embodiment, the poverty event monitoring index of the corresponding farmer is calculated based on the multiple poverty event monitoring indicators, the weight corresponding to each poverty event monitoring indicator and the target score of each poverty event monitoring indicator, which is achieved by the following formula:

[0078] in, represents the poverty event monitoring index, represents the weight corresponding to the i-th poverty event monitoring indicator, represents the target score of the i-th poverty-causing event monitoring indicator, and n represents the number of poverty-causing event monitoring indicators.

[0079] Based on the above embodiment, in this embodiment, the device further includes a building module, which is specifically used for: Before obtaining the target return-to-poverty risk data of the target impoverished farmers and calculating the return-to-poverty risk index of the target impoverished farmers based on the target return-to-poverty risk data of the target impoverished farmers through a pre-constructed return-to-poverty risk automatic early warning model, the return-to-poverty risk data of the target impoverished farmers are obtained according to a preset period, and the return-to-poverty risk data of the target impoverished farmers are stored in a return-to-poverty risk dynamic monitoring database; The automatic early warning model for the risk of returning to poverty is constructed based on the dynamic monitoring database for the risk of returning to poverty.

[0080] Based on the above embodiment, in this embodiment, the second determining module 505 is specifically used to: After the target poverty return risk data of the target impoverished farmers are calculated through a pre-constructed poverty return risk automatic early warning model, the corresponding target impoverished farmers are determined as medium-risk poverty return farmers when the poverty return risk index is less than the second preset threshold and greater than or equal to the third preset threshold; wherein the second preset threshold is greater than the third preset threshold; When the poverty return risk index is less than the third preset threshold, the corresponding target impoverished farmers are determined as low-risk poverty return farmers.

[0081] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6 As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the automatic monitoring method for preventing poverty relapse, and the method includes: Obtaining poverty-causing event data of multiple farmers; wherein the poverty-causing event data is formed based on various types of farmer information from various sources; Based on the poverty event data of the plurality of farmers, a poverty event monitoring index of each of the plurality of farmers is calculated by using a pre-constructed automatic monitoring model for poverty events; When the poverty event monitoring index is greater than or equal to the first preset threshold, the corresponding farmer is determined as a target poverty farmer; wherein the target poverty farmer refers to a farmer who is the focus of attention in the poverty event; Obtaining target re-poverty risk data of the target impoverished farmers, and calculating the re-poverty risk index of the target impoverished farmers based on the target re-poverty risk data of the target impoverished farmers through a pre-built automatic early warning model for re-poverty risk; When the poverty return risk index is greater than or equal to the second preset threshold, the corresponding target impoverished farmers are determined as high-risk poverty return farmers.

[0082] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0083] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the automatic monitoring method for preventing poverty relapse provided by the above methods, the method comprising: Obtaining poverty-causing event data of multiple farmers; wherein the poverty-causing event data is formed based on various types of farmer information from various sources; Based on the poverty event data of the plurality of farmers, a poverty event monitoring index of each of the plurality of farmers is calculated by using a pre-constructed automatic monitoring model for poverty events; When the poverty event monitoring index is greater than or equal to the first preset threshold, the corresponding farmer is determined as a target poverty farmer; wherein the target poverty farmer refers to a farmer who is the focus of attention in the poverty event; Obtaining target re-poverty risk data of the target impoverished farmers, and calculating the re-poverty risk index of the target impoverished farmers based on the target re-poverty risk data of the target impoverished farmers through a pre-built automatic early warning model for re-poverty risk; When the poverty return risk index is greater than or equal to the second preset threshold, the corresponding target impoverished farmers are determined as high-risk poverty return farmers.

[0084] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the automatic monitoring method for preventing poverty relapse provided by the above methods, the method comprising: Obtaining poverty-causing event data of multiple farmers; wherein the poverty-causing event data is formed based on various types of farmer information from various sources; Based on the poverty event data of the plurality of farmers, a poverty event monitoring index of each of the plurality of farmers is calculated by using a pre-constructed automatic monitoring model for poverty events; When the poverty event monitoring index is greater than or equal to the first preset threshold, the corresponding farmer is determined as a target poverty farmer; wherein the target poverty farmer refers to a farmer who is the focus of attention in the poverty event; Obtaining target re-poverty risk data of the target impoverished farmers, and calculating the re-poverty risk index of the target impoverished farmers based on the target re-poverty risk data of the target impoverished farmers through a pre-built automatic early warning model for re-poverty risk; When the poverty return risk index is greater than or equal to the second preset threshold, the corresponding target impoverished farmers are determined as high-risk poverty return farmers.

[0085] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0086] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0087] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automatic monitoring method for preventing poverty relapse, characterized in that: include: Obtaining poverty-causing event data of multiple farmers; wherein the poverty-causing event data is formed based on various types of farmer information from various sources; Based on the poverty event data of the plurality of farmers, a poverty event monitoring index of each of the plurality of farmers is calculated by using a pre-constructed automatic monitoring model for poverty events; When the poverty event monitoring index is greater than or equal to the first preset threshold, the corresponding farmer is determined as a target poverty farmer; wherein the target poverty farmer refers to a farmer who is the focus of attention in the poverty event; Obtaining target re-poverty risk data of the target impoverished farmers, and calculating the re-poverty risk index of the target impoverished farmers based on the target re-poverty risk data of the target impoverished farmers through a pre-built automatic early warning model for re-poverty risk; When the poverty return risk index is greater than or equal to the second preset threshold, the corresponding target impoverished farmers are determined as high-risk poverty return farmers.

2. The automatic monitoring method for preventing poverty return according to claim 1, characterized in that: The poverty event data of the plurality of farmers are used to calculate the poverty event monitoring index of each of the plurality of farmers through a pre-built automatic poverty event monitoring model, including: Determine multiple poverty-causing event monitoring indicators and the weight corresponding to each poverty-causing event monitoring indicator by a preset method; wherein the preset method includes but is not limited to: hierarchical analysis method, expert survey method, principal component analysis method and entropy weight method; Based on the predetermined target value of each poverty-causing event monitoring indicator, a target score for each poverty-causing event monitoring indicator is calculated; wherein the target value is used to represent the optimal value of the poverty-causing event monitoring indicator; Based on the multiple poverty-causing event monitoring indicators, the weight corresponding to each poverty-causing event monitoring indicator and the target score of each poverty-causing event monitoring indicator, the poverty-causing event monitoring index of the corresponding farmer is calculated.

3. The automatic monitoring method for preventing poverty return according to claim 2, characterized in that: The poverty event monitoring index of the corresponding farmer is calculated based on the multiple poverty event monitoring indicators, the weight corresponding to each poverty event monitoring indicator and the target score of each poverty event monitoring indicator, and is achieved by the following formula: in, represents the poverty event monitoring index, represents the weight corresponding to the i-th poverty event monitoring indicator, represents the target score of the i-th poverty-causing event monitoring indicator, and n represents the number of poverty-causing event monitoring indicators.

4. The automatic monitoring method for preventing poverty return according to claim 1, characterized in that: Before obtaining the target re-poverty risk data of the target impoverished farmers, and calculating the re-poverty risk index of the target impoverished farmers based on the target re-poverty risk data of the target impoverished farmers through a pre-built re-poverty risk automatic early warning model, the method further includes: Acquire the poverty return risk data of the target impoverished farmers according to a preset period, and store the poverty return risk data of the target impoverished farmers in a poverty return risk dynamic monitoring database; The automatic early warning model for the risk of returning to poverty is constructed based on the dynamic monitoring database for the risk of returning to poverty.

5. The automatic monitoring method for preventing poverty return according to claim 1, characterized in that: After calculating the poverty relapse risk index of the target impoverished farmers based on the target poverty relapse risk data of the target impoverished farmers through a pre-constructed poverty relapse risk automatic early warning model, the method further includes: When the poverty return risk index is less than the second preset threshold and greater than or equal to the third preset threshold, the corresponding target impoverished farmer is determined as a medium-risk poverty return farmer; wherein the second preset threshold is greater than the third preset threshold; When the poverty return risk index is less than the third preset threshold, the corresponding target impoverished farmers are determined as low-risk poverty return farmers.

6. An automatic monitoring device for preventing poverty relapse, characterized in that: include: An acquisition module, used to acquire poverty-causing event data of multiple farmers; wherein the poverty-causing event data is formed based on various types of farmer information from various sources; A first calculation module is used to calculate the poverty event monitoring index of each of the multiple farmers based on the poverty event data of the multiple farmers through a pre-built automatic poverty event monitoring model; A first determination module is used to determine the corresponding farmer as a target impoverished farmer when the poverty event monitoring index is greater than or equal to a first preset threshold; wherein the target impoverished farmer refers to a farmer who is the focus of attention in the poverty event; The second calculation module is used to obtain the target re-poverty risk data of the target impoverished farmers, and calculate the re-poverty risk index of the target impoverished farmers based on the target re-poverty risk data of the target impoverished farmers through a pre-built re-poverty risk automatic early warning model; The second determination module is used to determine the corresponding target impoverished farmers as high-risk farmers returning to poverty when the poverty returning risk index is greater than or equal to a second preset threshold.

7. The automatic monitoring device for preventing poverty return according to claim 6, characterized in that: The first calculation module is specifically used for: Determine multiple poverty-causing event monitoring indicators and the weight corresponding to each poverty-causing event monitoring indicator by a preset method; wherein the preset method includes but is not limited to: hierarchical analysis method, expert survey method, principal component analysis method and entropy weight method; Based on the predetermined target value of each poverty-causing event monitoring indicator, a target score for each poverty-causing event monitoring indicator is calculated; wherein the target value is used to represent the optimal value of the poverty-causing event monitoring indicator; Based on the multiple poverty-causing event monitoring indicators, the weight corresponding to each poverty-causing event monitoring indicator and the target score of each poverty-causing event monitoring indicator, the poverty-causing event monitoring index of the corresponding farmer is calculated.

8. The automatic monitoring device for preventing poverty return according to claim 7, characterized in that: The poverty event monitoring index of the corresponding farmer is calculated based on the multiple poverty event monitoring indicators, the weight corresponding to each poverty event monitoring indicator and the target score of each poverty event monitoring indicator, and is achieved by the following formula: in, represents the poverty event monitoring index, represents the weight corresponding to the i-th poverty event monitoring indicator, represents the target score of the i-th poverty-causing event monitoring indicator, and n represents the number of poverty-causing event monitoring indicators.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the automatic monitoring method for preventing poverty relapse as described in any one of claims 1 to 5 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the automatic monitoring method for preventing poverty relapse as claimed in any one of claims 1 to 5 is implemented.

Images