Mobile checking, collecting and transferring cloud platform

Abstract

The invention relates to the technical field of soil environment monitoring, in particular to a mobile check acquisition circulation cloud platform, which comprises a sampling point setting module; a template selection module for performing combined form recommendation or valid form recommendation in response to the analysis condition; the information filling module is used for carrying out map index filling or filling analysis in response to the geographic form keyword or the numerical form keyword in the recommended form; the filling analysis module is used for carrying out related recommended filling or range recommended filling according to the sampling batch and the repeated information repetition degree during filling analysis; the image acquisition module is used for determining the sampling point type according to the sampling point offset degree and the sampling point feature index and responding to a judgment condition to perform feature image acquisition or associated image acquisition; and a circulation monitoring module. According to the invention, the efficiency and reliability of soil environment monitoring can be improved.

Description

A mobile verification and data collection cloud platform Technical Field

[0001] This invention relates to the field of soil environmental monitoring technology, and in particular to a mobile verification and data collection cloud platform. Background Technology

[0002] In soil environmental monitoring, the collection of sample information often relies on manual filling out of various forms, which is not only inefficient but also prone to data errors due to human negligence. Furthermore, the data flow and monitoring are lagging, making it impossible to detect anomalies in a timely manner and take corresponding measures. This seriously affects the timeliness and reliability of sample collection and monitoring. Therefore, how to improve the efficiency and reliability of soil environmental monitoring is an urgent problem to be solved by those skilled in the art.

[0003] Chinese Patent Publication No. CN104851042A discloses a land use tax information collection and verification system, including: a data browsing module, a data collection module, a data query module, a data management module, and a mobile offline database. The data browsing module browses basic geographic data and high-resolution remote sensing data, providing navigation and reference for data collection during the verification of tax-related enterprises. The data collection module collects information on the location, scope, land area, and other verification elements of tax-related enterprises on-site, and stores the collected data in the mobile offline database. The data query module queries enterprise verification data and uses multi-level display technology to present the query results in a diversified manner. The data management module accesses the offline database and uploads the collected data. However, the above solution has the following problems: it cannot flexibly set sampling points according to actual application scenarios, and it cannot automatically generate forms, affecting the accuracy of data collection and making it difficult to meet the higher requirements of soil environmental monitoring for efficient data collection and real-time monitoring of land transfer. Summary of the Invention

[0004] To address this, the present invention provides a mobile verification and data collection cloud platform to overcome the problems in existing technologies, such as the inability to flexibly set sampling points according to actual application scenarios and the inability to automatically generate forms, which affect the accuracy of data collection and make it difficult to meet the higher requirements of soil environmental monitoring for efficient data collection and real-time monitoring.

[0005] To achieve the above objectives, the present invention provides a mobile verification and data collection cloud platform, comprising: a sampling point setting module, used to uniformly set sampling points or associate sampling points for a target monitoring area in response to setting conditions; a template selection module, connected to the sampling point setting module, used to recommend combined forms or effective forms in response to analysis conditions; an information filling module, connected to the template selection module, used to fill map indexes or perform filling analysis in response to geographic form keywords or numerical form keywords in the recommended forms; a filling analysis module, connected to the information filling module, used to perform relevant or range-based filling recommendations based on sampling batches and the repetition of multiple information entries during filling analysis; an image acquisition module, connected to the template selection module, the information filling module, and the filling analysis module respectively, used to determine the sampling point type based on the sample point offset and sample point feature index, and to perform feature image acquisition or associated image acquisition in response to judgment conditions; and a circulation monitoring module, connected to the filling analysis module, used to determine the sample inspection interval based on form feature values, and to adjust the sample inspection interval or the sample inspection interval in a feature time segment based on abnormal deviation values.

[0006] Furthermore, the sampling point setting module responds to the setting condition that the regional change coefficient of the target monitoring area is less than the preset regional change coefficient or the area reference value is greater than or equal to the preset area reference value, and sets sampling points in association for the target monitoring area; the sampling point setting module responds to the setting condition that the regional change coefficient of the target monitoring area is greater than or equal to the preset regional change coefficient and the area reference value is less than the preset area reference value, and sets sampling points evenly for the target monitoring area.

[0007] Furthermore, the template selection module responds to analysis conditions where the task relevance is less than the preset task relevance or the sampling point difference is greater than or equal to the preset sampling point difference, and then recommends combined forms; the template selection module responds to analysis conditions where the task relevance is greater than or equal to the preset task relevance and the sampling point difference is less than the preset sampling point difference, and then recommends valid forms.

[0008] Furthermore, the information filling module performs map index filling for geographic form keywords; the information filling module performs filling analysis for numerical form keywords.

[0009] Furthermore, the filling analysis module performs relevant recommendation filling when the sampling batch is greater than or equal to the preset sampling batch and the repetition of multiple pieces of information is greater than or equal to the preset repetition of multiple pieces of information.

[0010] Furthermore, the filling analysis module performs range recommendation filling when the sampled batch is smaller than the preset sampled batch or the repetition of multiple pieces of information is less than the preset repetition of multiple pieces of information. In the range recommendation filling, the associated range recommendation or predicted range recommendation is performed based on the sampled batch and the batch regularity coefficient. If the sampled batch is greater than or equal to the preset sampled batch and the batch regularity coefficient is greater than or equal to the preset batch regularity coefficient, then the associated range recommendation is performed. If the sampled batch is within the first preset sampled batch range or the batch regularity coefficient is less than the preset batch regularity coefficient, then the predicted range recommendation is performed.

[0011] Furthermore, the image supplementation module determines the sampling point type based on the sampling point offset and the sampling point feature index, including: a type of sampling point with a sampling point offset greater than or equal to a preset sampling point offset or a sampling point feature index greater than or equal to a preset sampling point feature index; and a type of sampling point with a sampling point offset less than a preset sampling point offset and a sampling point feature index less than a preset sampling point feature index.

[0012] Furthermore, the image supplementation module performs feature image acquisition in response to the judgment conditions that the form change value is greater than or equal to a preset form change value or the proportion of a type of sampling point is greater than or equal to a preset proportion of a type of sampling point; the image supplementation module performs associated image acquisition in response to the judgment conditions that the form change value is less than a preset form change value and the proportion of a type of sampling point is less than a preset proportion of a type of sampling point.

[0013] Furthermore, the flow monitoring module determines the sample inspection interval based on the form feature values; wherein the sample inspection interval is positively correlated with the form feature values.

[0014] Furthermore, when the abnormal deviation value is greater than or equal to the preset abnormal deviation value, the flow monitoring module reduces the sample inspection interval; when the abnormal deviation value is less than the preset abnormal deviation value, the flow monitoring module reduces the sample inspection interval in the characteristic time segment.

[0015] Compared with the prior art, the beneficial effects of the present invention are that, in the technical solution of the present invention, the terrain complexity and monitoring range of the target monitoring area are effectively reflected by setting conditions, and then sampling points are set uniformly or in association according to the setting conditions, so that the setting of sampling points is more in line with the actual application scenario. When the sampling points are set in association, the number of duplicate sampling points is reduced, and the sampling efficiency is improved. When the sampling points are set uniformly, the distribution of sampling points is uniform, and the representativeness of the data is enhanced, thereby improving the efficiency and reliability of soil environmental monitoring.

[0016] Furthermore, this invention effectively reflects the similarity between the current task and historical tasks, as well as the degree of difference in sampling point layout between the current monitoring area and historical monitoring areas, by analyzing the conditions. Then, it adaptively recommends combined forms or effective forms based on the analysis conditions, which can take into account the personalized needs of various different soil monitoring task scenarios. For similar tasks, the effective forms are used to ensure consistency of standards; for tasks with large differences, combined form recommendations are supported to fully consider the uniqueness of the task.

[0017] Furthermore, this invention uses map indexing to fill in geographic form keywords, which can eliminate human input errors and improve data accuracy. By sampling batches and multiple information repetitions, it effectively reflects the degree of data accumulation and the degree of information repetition. Then, based on the sampling batches and multiple information repetitions, it adaptively performs relevant or range-based recommendation filling. When the sampling batches or multiple information repetitions are insufficient, it automatically performs range-based recommendation filling. This intelligent recommendation mechanism reduces the workload of manual input for users and improves the efficiency of data filling.

[0018] Furthermore, this invention effectively reflects data stability and the proportion of special sampling points by using the form change value and the proportion of a certain type of sampling point. Then, the image acquisition strategy is dynamically adjusted according to the form change value and the proportion of a certain type of sampling point, so as to prioritize the allocation of resources to the most needed sampling points, improve resource utilization efficiency, and thus enhance the targeting and effectiveness of image acquisition.

[0019] Furthermore, this invention assesses the potential risks of samples during transportation by using form feature values, and then determines the sample inspection interval based on the form feature values. This allows for dynamic adjustment of the inspection frequency to optimize monitoring efficiency and effectiveness. The method of dynamically adjusting the sample inspection interval based on abnormal deviation values ​​can effectively improve the accuracy and efficiency of monitoring, while reducing costs and risks. Attached Figure Description

[0020] Figure 1 is a module connection diagram of the mobile verification and data collection cloud platform of the present invention; Figure 2 is a flowchart of the present invention for uniformly setting sampling points or associated setting sampling points in the target monitoring area according to the setting conditions; Figure 3 is a flowchart of the present invention for recommending associated forms or valid forms according to the analysis conditions; Figure 4 is a flowchart of the present invention for collecting feature images or associated images according to the judgment conditions. Detailed Implementation

[0021] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0022] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0023] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0024] Please refer to Figures 1 to 4. This invention provides a mobile verification and data collection cloud platform, comprising: a sampling point setting module, used to uniformly set sampling points or associatedly set sampling points for a target monitoring area in response to setting conditions; a template selection module, connected to the sampling point setting module, used to recommend combined forms or effective forms in response to analysis conditions; an information filling module, connected to the template selection module, used to fill map indexes or perform filling analysis in response to geographic or numerical form keywords in the recommended forms; a filling analysis module, connected to the information filling module, used to perform related or range-based filling recommendations based on sampling batches and the repetition of multiple information entries during filling analysis; an image acquisition module, connected to the template selection module, the information filling module, and the filling analysis module respectively, used to determine the sampling point type based on sample point offset and sample point feature index, and to perform feature image acquisition or associated image acquisition in response to judgment conditions; and a circulation monitoring module, connected to the filling analysis module, used to determine the sample inspection interval based on form feature values, and to adjust the sample inspection interval or the sample inspection interval in a feature time segment based on abnormal deviation values.

[0025] The application scenario of this invention is the collection and transfer of samples during agricultural soil environmental monitoring. The target monitoring area is the region where agricultural soil environmental monitoring is required. This invention includes several historical records, each recording at least one instance of sample collection and transfer during agricultural soil environmental monitoring, including regional change coefficients, task relevance, sampling point differences, and title matching thresholds. Each historical record also has a corresponding qualification mark, indicating whether the sample collection and transfer process meets user requirements. Qualification marks can be manually recorded. It is understood that users can determine whether the sample collection and transfer process meets requirements based on self-defined indicators, which can include, but are not limited to, transfer time (the time from sample collection to transportation to the laboratory is not elaborated here). This invention also includes a data acquisition module connected to the sampling point setting module for sampling area information. Area information includes, but is not limited to, the DEM data corresponding to the target monitoring area, the area of ​​the target monitoring area, and the types of crops in the target monitoring area (details are not elaborated here). The system includes target coefficients and relevant thresholds. The correspondence between the target coefficients and relevant thresholds is expressed through a weighting formula: Target Coefficient = Weight Coefficient × Relevant Threshold. Specifically, the present invention uses the number of sub-regions, the sample inspection interval, and the reduction value of the sample inspection interval as the target coefficients, and the regional evaluation coefficient, form feature value, abnormal deviation value, and duration of feature time segment as the relevant thresholds. It can be understood that all target coefficients have corresponding relevant thresholds. For example, there is a positive correlation between the number of sub-regions and the regional evaluation coefficient. Furthermore, the positive correlation between the number of sub-regions and the regional evaluation coefficient is expressed through a weighting formula. The value of the weighting coefficient can be determined based on the user's historical experience and the degree of influence of the regional evaluation coefficient on the number of sub-regions. The value of the weighting coefficient can also be optimized based on the historical records of sample collection and transfer during multiple agricultural soil environmental monitoring sessions, combined with the multilayer perceptron. The optimization of the weighting coefficient using the multilayer perceptron is easily understood by those skilled in the art and will not be elaborated upon here. The principle for determining the weighting coefficients corresponding to other target coefficients and relevant thresholds is the same and will not be elaborated upon here.

[0026] Specifically, the sampling point setting module sets sampling points in association with the target monitoring area when the area change coefficient of the target monitoring area is less than the preset area change coefficient or the area reference value is greater than or equal to the preset area reference value; the sampling point setting module also sets sampling points uniformly in the target monitoring area when the area change coefficient of the target monitoring area is greater than or equal to the preset area change coefficient and the area reference value is less than the preset area reference value.

[0027] The regional change coefficient is the standard deviation of the elevation reference values ​​corresponding to each pixel in the DEM data of the target monitoring area. By acquiring the DEM data corresponding to the target monitoring area and loading it into GIS software, the elevation reference values ​​corresponding to each pixel in the DEM data can be obtained. The elevation reference value for a single pixel is the elevation of the center point of the square area corresponding to that pixel. It can be understood that the DEM data is measured by a satellite sensor, which can be either SRTM or ASTER, with no specific restrictions. The DEM data includes several pixels, each representing a 1m × 1m square area on the ground. The area reference value is the area of ​​the target monitoring area. The preset regional change coefficient and preset area reference value can be determined by the user according to the actual application scenario. A larger preset regional change coefficient and a smaller preset area reference value indicate better performance. The greater the demand for associated sampling points in the target monitoring area, the more appropriate the preset area change coefficient and preset area reference value are provided. The system detects the historical records of users' associated sampling point settings for the target monitoring area, and records the average of the area change coefficient and the average of the area reference value corresponding to the historical records that meet the user's needs as the preset area change coefficient and preset area reference value, respectively. The target monitoring area is divided into several sub-regions of equal area and identical shape, each sub-region being rectangular. The number of sub-regions is positively correlated with the area evaluation coefficient. Sampling points are uniformly set in the target monitoring area, including: setting a sampling point at the center of each sub-region, with the center of each sub-region being the center of its circumscribed circle; the area evaluation coefficient = area change coefficient / preset area change coefficient + area reference value / preset area reference value.

[0028] Sampling points are set up in association for the target monitoring area, including: setting one sampling point in each association combination, meaning each association combination corresponds to one sampling point; the location of the sampling point in a single association combination is not restricted and can be determined by the user; each sub-region corresponds to one association combination; a single association combination contains several sub-regions; the correlation coefficient between any two sub-regions in an association combination is greater than or equal to a preset correlation coefficient; sub-regions adjacent to an association combination are recorded as neighboring sub-regions; the correlation coefficient between any neighboring sub-region and any sub-region in the association combination is less than a preset correlation coefficient; any two sub-regions corresponding to... The correlation coefficient is calculated as (first correlation + second correlation) / 2. The crop types in the two sub-regions are detected separately. The first correlation is calculated as 1 - the larger of the number of identical crop types in the two sub-regions / the larger of the number of corresponding crop types in the two sub-regions. The second correlation is calculated as 1 - the absolute value of the difference in elevation between the corresponding sub-regions / the larger of the corresponding sub-region elevations in the two sub-regions. The elevation of a single sub-region is the average of the elevation reference values ​​corresponding to each pixel in the DEM data of that sub-region. The preset correlation coefficient value can be determined by the user based on the actual application scenario. The greater the user's demand for improved sampling accuracy, the larger the preset correlation coefficient value should be. One preset correlation coefficient value is provided: 80%. It is understood that the regional change coefficient effectively reflects the complexity of the terrain, while the area reference value effectively reflects the size of the monitoring range. When the regional change coefficient of the target monitoring area is less than the preset regional change coefficient, or the area reference value is greater than or equal to the preset area reference value, it indicates that the elevation change within the target monitoring area is small or the area is wide. Setting up sampling points through correlation allows for flexible setting of sampling points based on the actual characteristics and correlation of the area, better adapting to complex and changing monitoring scenarios. When the regional change coefficient of the target monitoring area is greater than or equal to the preset regional change coefficient, and the area reference value is less than the preset area reference value, it indicates that the elevation change within the target monitoring area is significant but the range is limited. Using a uniform setting of sampling points ensures that sampling points are evenly distributed within a smaller area, achieving more refined monitoring.

[0029] Specifically, the template selection module recommends combined forms when the task relevance is less than the preset task relevance or the sampling point difference is greater than or equal to the preset sampling point difference; and it recommends effective forms when the task relevance is greater than or equal to the preset task relevance and the sampling point difference is less than the preset sampling point difference.

[0030] The task information corresponding to the target monitoring area includes, but is not limited to, basic information, monitoring objects, and task description. Basic information includes, but is not limited to, task name, creation time, and creator. Monitoring objects include, but are not limited to, pH value, moisture content, lead, cadmium, and mercury. The task description includes, but is not limited to, task background, monitoring purpose, execution requirements, and precautions. This is the technical content of those skilled in the art, and will not be elaborated further. This invention includes several forms, each containing several titles and a photo-filling area. The photo-filling area is used to place various photos taken by the image acquisition module. Each title corresponds to several form keywords and placeholders for each keyword. Titles include, but are not limited to, work information, sample point information, and sample information. Work information includes, but is not limited to, team leader and team members. Sample point information includes, but is not limited to, city, county, and township. Sample information includes, but is not limited to, sample point coordinates, sample point altitude, and agricultural product type. Placeholders for each keyword are [...]. This is content easily understood by those skilled in the art and will not be elaborated further; the task correlation degree is the maximum value among the sub-correlation degrees of the task information corresponding to the target monitoring area and each reference task information. The task information corresponding to each target monitoring area in the historical records that can meet the user's needs is recorded as the reference task information. The sub-correlation degree between any two task information is the larger value between the number of identical keywords in the two task information and the number of keywords corresponding to the two task information. The keywords in the task information are identified using NLP technology, which is a commonly used technique by those skilled in the art and will not be elaborated further; the historical records that can meet the user's needs are recorded as reference historical records. The sampling point difference degree is the maximum value among the difference reference values ​​between the target monitoring area and each reference historical record; the difference reference value between the target monitoring area and a single reference historical record is |the sampling point distribution value corresponding to the target monitoring area - the sampling point corresponding to the reference historical record. Distribution value |; The distribution value of the sampling points corresponding to the target monitoring area is the average of the distance reference values ​​corresponding to each sampling point in the target monitoring area. For a single sampling point, the sampling point is recorded as the target sampling point, and other sampling points outside the target sampling point are recorded as reference sampling points. The distance reference value corresponding to the target sampling point is the average of the shortest distances from the target sampling point to each reference sampling point. The values ​​of preset task relevance and preset sampling point difference can be determined by the user according to the actual application scenario. The larger the value of preset task relevance and the smaller the value of preset sampling point difference, the greater the user's demand for combined form recommendations. A preset task relevance and preset sampling point difference value is provided. The user's history of effective form recommendations is detected, and the average value of the task relevance and the average value of the sampling point difference corresponding to the history that can meet the user's needs are recorded as the preset task relevance and preset sampling point difference, respectively.When performing combined form recommendations, titles with a title matching threshold greater than a preset title matching threshold or a title appearance coefficient greater than a preset title appearance coefficient are selected as the chosen titles. Based on information relevance, the corresponding selection form keywords for each chosen title are determined. The collected photo fill area, each chosen title, the corresponding selection form keywords for each chosen title, and the placeholders corresponding to each selection form keyword are used as the recommended forms. Determining the selection form keywords for each chosen title based on information relevance includes: performing selection analysis for each chosen title; when performing selection analysis for a single chosen title, the chosen title is recorded as the target chosen title, and the forms containing the target chosen title are recorded as the forms to be selected. The keywords of each form corresponding to the target selection title in the candidate forms with the highest information relevance are denoted as the selection form keywords corresponding to the target selection title; the information relevance of a single candidate form is the number of times the form keywords corresponding to the target selection title appear in the task information corresponding to the target monitoring area; for a single title, the form keywords corresponding to the title in each form that appears are denoted as reference form keywords, and the title matching threshold for the title is the number of different reference form keywords appearing in the task information corresponding to the target monitoring area, and the title appearance coefficient = the number of forms that appear with the title / the total number of forms; the preset title matching threshold and the preset title appearance coefficient... The values ​​of the preset title matching threshold and preset title visibility coefficient can be determined by the user based on the actual application scenario. The greater the user's need for improving the accuracy of the recommended forms, the smaller the values ​​of the preset title matching threshold and preset title visibility coefficient should be. A method for determining the values ​​of the preset title matching threshold and preset title visibility coefficient is provided, which detects the average value of the title matching threshold and the average value of the title visibility coefficient corresponding to each selected title in the historical records that can meet the user's needs, and records them as the preset title matching threshold and preset title visibility coefficient, respectively. When making effective form recommendations, the form with the largest matching reference value is selected as the recommended form. The matching reference value corresponding to a single form is the historical reference values ​​of each reference form selected as the recommended form. The average value of the corresponding sub-matching reference values; the sub-matching reference value corresponding to a single reference history = the sub-correlation degree between the task information corresponding to the target monitoring area and the task information corresponding to the reference history / the average value of the sub-correlation degree between the task information corresponding to the target monitoring area and the task information corresponding to each reference history + (1 - the difference reference value between the target monitoring area and the reference history / the average value of the difference reference values ​​corresponding to each reference history); it can be understood that the task correlation degree reflects the similarity between the current task and the historical task, and the sampling point difference degree is used to measure the degree of difference between the current monitoring area and the historical monitoring area in the sampling point layout, reflecting the matching of data collection needs;When the task relevance is less than the preset task relevance or the sampling point difference is greater than or equal to the preset sampling point difference, it indicates that the current task has low similarity to historical tasks or small differences in sampling point distribution. Flexible forms are needed to adapt to monitoring requirements. The system recommends combined forms; users can select applicable parts from multiple forms based on the monitoring object and execution requirements to ensure the comprehensiveness and adaptability of the form content.

[0031] When the task relevance is greater than or equal to the preset task relevance and the sampling point difference is less than the preset sampling point difference, it indicates that the current task is highly similar to a certain historical task in terms of information and sampling layout. Effective form recommendations can be made, which can improve work efficiency and ensure the standardization and comparability of data collection.

[0032] Specifically, the information filling module performs map index filling for geographic form keywords; the information filling module performs filling analysis for numerical form keywords.

[0033] Among them, geographic form keywords are form keywords whose fill information in the placeholders corresponding to form keywords can be obtained through map services. Geographic form keywords include, but are not limited to, city, county, township, sample point coordinates and sample point elevation. Numerical form keywords are other keywords whose fill information is numbers, other than geographic form keywords. Map services include: converting address information into coordinates by calling the geocoding API of Amap or Baidu Map; and converting coordinates into address information by calling the reverse geocoding API.

[0034] Other form keywords besides geographic form keywords and numerical form keywords are categorized as ordinary form keywords. For ordinary form keywords, users need to manually fill in the form information corresponding to the ordinary form keywords. The filled information corresponding to ordinary form keywords can be cached historically and automatically entered during the next sampling of the target monitoring area. Map index filling is performed, including obtaining the filling information in the placeholders corresponding to geographic form keywords through map services. It can be understood that since geographic form keywords have clear geographic meaning and spatial location attributes, their corresponding filling information can be obtained through map services.

[0035] Specifically, the filling analysis module performs relevant recommendation filling when the sampling batch is greater than or equal to the preset sampling batch and the repetition of multiple information is greater than or equal to the preset repetition of multiple information.

[0036] In this system, the sampling batch is defined as the number of reference batches plus one. The batch currently sampling the target monitoring area is designated as the target batch, and all previous samplings of the target monitoring area are designated as reference batches. For a single numerical form keyword, the ordinary keyword is designated as the target ordinary keyword. Historical records in the recommendation form that contain the target numerical form keyword and meet user needs are designated as analysis records. The average sub-information repetition rate of each analysis record is designated as the information repetition rate. The sub-information repetition rate of a single analysis record is determined by detecting the fill-in information corresponding to the target numerical form keyword in each sampling of the target monitoring area within that analysis record. The sub-information repetition rate of that analysis record is calculated as: the number of fill-in information entries that appear most frequently in each sampling of the target numerical form keyword / the number of samplings performed on the target monitoring area in that analysis record. The preset sampling batch and preset multiple information repetition rates can be determined by the user based on the actual application scenario. The smaller the preset sampling batch and preset multiple information repetition rates, the greater the user's need for relevant recommendation fill-in. A preset sampling batch is provided. The method for determining batch and preset multiple information repetition values ​​involves detecting the user's historical records of relevant recommendation filling. The average value of the sampling batch and the average value of multiple information repetition corresponding to the historical records that meet the user's needs are respectively recorded as the preset sampling batch and preset multiple information repetition. When performing relevant recommendation filling for a single numerical form keyword, the filling information that appears most frequently in each sampling of the target monitoring area corresponding to that numerical form keyword is used as the recommended filling information. It can be understood that when the sampling batch is greater than or equal to the preset sampling batch and the multiple information repetition is greater than or equal to the preset multiple information repetition, it indicates that the current sampling task has reached a high level in terms of scale and data consistency. Performing relevant recommendation filling can make the recommended filling information highly representative and credible, thereby improving the accuracy of data filling. When the sampling batch is less than the preset sampling batch or the multiple information repetition is less than the preset multiple information repetition, it indicates that the data foundation of the current sampling task is relatively weak. Performing range recommendation filling can utilize the patterns and trends in historical data to provide users with a reasonable range of filling information.

[0037] Specifically, the filling analysis module performs range recommendation filling when the sampled batch is smaller than the preset sampled batch or the repetition of multiple pieces of information is less than the preset repetition of multiple pieces of information. In the range recommendation filling, the associated range recommendation or predicted range recommendation is performed based on the sampled batch and the batch regularity coefficient. If the sampled batch is greater than or equal to the preset sampled batch and the batch regularity coefficient is greater than or equal to the preset batch regularity coefficient, the associated range recommendation is performed. If the sampled batch is within the first preset sampled batch range or the batch regularity coefficient is less than the preset batch regularity coefficient, the predicted range recommendation is performed.

[0038] In this context, all values ​​within the first preset sampling batch range are greater than 1 and less than the preset sampling batch, where the preset sampling batch is greater than 1; the batch regularity coefficient is the maximum value among the regularity reference values ​​corresponding to the target common keyword and each reference analysis record; analysis records whose sampling number is greater than the number of samplings already performed on the target monitoring area are denoted as reference analysis records; the formula for calculating the regularity reference value r corresponding to the target common keyword and a single reference analysis record is as follows: Where m represents the number of times sampling has been performed on the target monitoring area; This represents the value of the fill information corresponding to the common keyword of the target in the k-th sampling out of the number of samplings already performed on the target monitoring area. This refers to the value of the fill information corresponding to the common keyword of the target sample in the kth sampling of a single reference analysis record. This is the average value of the fill information corresponding to the target's common keywords in each sampling conducted for the target monitoring area. The value of the fill information corresponding to the target common keyword in the first m samples of a single reference analysis record for the target monitoring area is the average value, k = 1, 2, 3, ..., m. The preset batch regularity coefficient can be determined by the user based on the actual application scenario. The smaller the preset batch regularity coefficient, the greater the user's demand for related range recommendations. A preset batch regularity coefficient value is provided, and the historical records of user related range recommendations are detected. The average value of the batch regularity coefficients corresponding to the historical records that meet the user's needs is recorded as the preset batch regularity coefficient. When making related range recommendations for the target common keyword, the reference analysis records in each reference analysis record whose regularity reference value with the target common keyword is greater than the preset regularity reference value are recorded as target records. The recommendation information value corresponding to each target record is used as the recommended fill information corresponding to the target common keyword. The recommendation information value corresponding to a single target record = the value of the fill information corresponding to the target common keyword in the (m+1)th sample of that target record × The preset rule reference value can be determined by the user based on the actual application scenario. The greater the user's need to improve recommendation accuracy, the larger the preset rule reference value should be. One preset rule reference value is provided, with a preset rule reference value of 0.9. When making prediction range recommendations for target common keywords, the values ​​in the interval [the value of the target common keyword's fill information corresponding to the last sampled area for the target monitoring region - the maximum change value, and the value of the target common keyword's fill information corresponding to the last sampled area for the target monitoring region + the maximum change value] are used as the recommended fill information for the target common keyword. Historical records that meet user needs and contain the target common keyword in the recommendation form are recorded as historical records to be analyzed. Other common keywords in the recommendation form besides the target common keyword are recorded as reference common keywords. For a single historical record to be analyzed, the number of reference common keywords appearing in the recommendation form corresponding to that historical record is recorded as the relevant quantity. Historical records with a relevant quantity greater than the preset relevant quantity are recorded as relevant historical records. The change value corresponding to each relevant historical record is detected. The change value corresponding to a single relevant historical record = the maximum value among the values ​​of the target common keyword's fill information corresponding to each sample in that relevant historical record - the minimum value among the values ​​of the target common keyword's fill information corresponding to each sample in that relevant historical record. The maximum value among the change values ​​corresponding to each relevant historical record is recorded as the maximum change value. The preset value of the relevant quantity can be determined by the user based on the actual application scenario. The greater the user's need to improve the accuracy of the fill information recommendation, the higher the value of the relevant quantity. The larger the preset relevance quantity, the more important it is to provide a method for determining the preset relevance quantity. This method uses the average of the relevance quantities corresponding to each relevant historical record that meets the user's needs as the preset relevance quantity. It's important to note that if the sampling batch is 1, the user needs to manually fill in the keywords for each numerical form. It's also important to note that after the fill analysis module recommends the fill information corresponding to each numerical form keyword to the user, the user can directly select appropriate content from the recommended fill information or manually input information. The fill information corresponding to each form keyword in the recommended forms is recorded as the final information. It can be understood that when the sampling batch is greater than or equal to the preset value... When a sampled batch has a pattern coefficient greater than or equal to a preset batch pattern coefficient, it indicates that the historical data has good reference value. By analyzing the patterns in the historical sampled data, similar historical records to the current sampled batch are identified, and the filling information in these records is used to recommend an association range. This approach leverages patterns and trends in historical data to provide users with a reasonable range of filling information. Conversely, when the sampled batch falls within the first preset sampled batch range or the batch pattern coefficient is less than the preset batch pattern coefficient, it indicates that the historical data has low reference value or the current sampled batch is small. In this case, a prediction range recommendation is made, providing users with a flexible filling suggestion when sufficient historical data is lacking.

[0039] Specifically, the image supplementation module determines the sampling point type based on the sampling point offset and the sampling point feature index, including: a type of sampling point with a sampling point offset greater than or equal to a preset sampling point offset or a sampling point feature index greater than or equal to a preset sampling point feature index; and a second type of sampling point with a sampling point offset less than a preset sampling point offset and a sampling point feature index less than a preset sampling point feature index.

[0040] Wherein, the sample offset corresponding to a single sampling point is the maximum value among the sub-offsets corresponding to each common keyword for that sampling point; the sub-offset corresponding to a single common keyword = |the value of the final information corresponding to the common keyword for that sampling point in the target batch - the average value of the final information corresponding to the common keyword for each sampling point in the target batch| / the average value of the final information corresponding to the common keyword for each sampling point in the target batch; the sample feature index corresponding to a single sampling point = the number of crop types in the sub-region where the sampling point is located in the target batch / the number of crop types corresponding to each sub-region in the target batch. The average value is calculated as: (Average + Elevation of the sub-region corresponding to the sampling point) / (Average elevation of the sub-regions corresponding to each sub-region). The preset sample point offset and preset sample point feature index values ​​can be determined by the user based on the actual application scenario. The smaller the values ​​of the preset sample point offset and preset sample point feature index, the greater the demand for classifying the sampling point as a type of sampling point. A preset sample point offset and preset sample point feature index value is provided, and the average value of the sample point offset and the average value of the sample point feature index corresponding to each type of sampling point in the historical records that can meet the user's needs are detected and recorded as the preset sample point offset and preset sample point feature index, respectively.

[0041] Specifically, the image supplementation module performs feature image acquisition in response to the judgment conditions that the form change value is greater than or equal to a preset form change value or the proportion of a type of sampling point is greater than or equal to a preset proportion of a type of sampling point; the image supplementation module performs associated image acquisition in response to the judgment conditions that the form change value is less than a preset form change value and the proportion of a type of sampling point is less than a preset proportion of a type of sampling point.

[0042] Among them, the form change value is the maximum value among the sub-change values ​​corresponding to each common keyword; the sub-change value corresponding to a single common keyword is the standard deviation of the final information value corresponding to each common keyword for each sampling point in the target batch; the proportion of Class I sampling points = the total number of Class I sampling points in the target monitoring area corresponding to the target batch / the total number of sampling points in the target monitoring area corresponding to the target batch;The user can determine the preset form change value and the preset first-class sampling point percentage based on the actual application scenario. The smaller the preset form change value and the preset first-class sampling point percentage, the greater the user's need for feature image acquisition. A method for determining the preset form change value and the preset first-class sampling point percentage is provided. This method detects the user's historical feature image acquisition records and records the average form change value and the average first-class sampling point percentage corresponding to the historical records that meet the user's needs as the preset form change value and the preset first-class sampling point percentage, respectively. During feature image acquisition, images are collected at each first-class sampling point. The collected images include, but are not limited to, panoramic photos of the sampling points and soil feature photos. For capturing images of vegetation, digital cameras, mobile phones, and drones can be used; specific details are omitted. When performing correlated image acquisition, correlation analysis is performed on each sampling point. For a single sampling point, this point is designated as the target point, and other sampling points are designated as reference points. Reference points with a sampling correlation greater than a preset correlation with the target point, along with the target point, are grouped into a correlated sampling point combination. Correlation analysis continues for reference points not yet included in the correlated sampling point combination until all sampling points are included. An image is then captured for any sampling point in each correlated sampling point combination. Each correlated sampling point combination corresponds to a sampling point for which an image is captured. Point; the sampling correlation degree between any two sampling points = [(1 - the absolute value of the difference between the sample point offsets of the two sampling points / the larger value of the sample point offsets of the two sampling points) + (1 - the absolute value of the difference between the sample point feature indices of the two sampling points / the larger value of the sample point feature indices of the two sampling points)] / 2; the preset sampling correlation degree can be determined by the user according to the actual application scenario. The greater the user's need to improve the accuracy of image acquisition, the larger the preset sampling correlation degree will be. One preset sampling correlation degree is provided, with a preset sampling correlation degree of 80%; it can be understood that when the form change value is greater than or equal to the preset form change value or the proportion of a certain type of sampling point is greater than or equal to... When the percentage of a certain type of sampling point is predetermined, it indicates significant changes in soil properties or a large number of special sampling points. This suggests large data differences between different sampling points and unstable soil properties, requiring detailed image recording. Feature image acquisition can record the diversity and specificity of the soil in detail, providing rich image data for in-depth analysis. When the change value of the form is less than the predetermined change value and the percentage of a certain type of sampling point is less than the predetermined percentage of a certain type of sampling point, it indicates relatively stable soil properties and fewer special sampling points. This suggests small data differences and stable soil properties, reducing the need for feature image acquisition. By calculating the sampling correlation between sampling points, sampling points with high correlation are grouped into related sampling point combinations, and images are acquired for these combinations, improving acquisition efficiency.

[0043] Specifically, the flow monitoring module determines the sample inspection interval based on the form feature values; wherein, the sample inspection interval is positively correlated with the form feature values.

[0044] Specifically, historical records of sample package anomalies during transportation are recorded as anomaly history records, and the recommended forms corresponding to each anomaly history record are recorded as anomaly recommended forms. The form feature value is the average anomaly frequency corresponding to each numerical form keyword in the recommended forms corresponding to the target batch, and the anomaly frequency corresponding to a single numerical form keyword is the number of anomaly recommended forms that contain that numerical form keyword. After the samples collected at each sampling point are packaged, the sample packages need to be inspected during transportation. The sample inspection interval is the time interval between two adjacent inspections of the sample package, in hours.

[0045] Specifically, when the abnormal deviation value is greater than or equal to the preset abnormal deviation value, the flow monitoring module reduces the sample inspection interval; when the abnormal deviation value is less than the preset abnormal deviation value, the flow monitoring module reduces the sample inspection interval in the characteristic time segment.

[0046] The abnormal deviation value is defined as the standard deviation of the abnormal time reference value corresponding to each abnormal historical record. The abnormal time reference value for a single abnormal historical record is the time interval between the start of sample transportation and the discovery of the abnormality in the product package. The preset abnormal deviation value can be determined by the user based on the actual application scenario. A larger preset abnormal deviation value indicates a greater need for user adjustment of the characteristic time segment. A method for determining the preset abnormal deviation value is provided, which detects historical records of user adjustment of the characteristic time segment and records the abnormal deviation value corresponding to the historical records that meet the user's needs as the preset abnormal deviation value. When the abnormal deviation value is greater than or equal to the preset abnormal deviation value, and the sample inspection interval is reduced, the decrease in the sample inspection interval is compared with the abnormal deviation value. The values ​​are positively correlated; when the abnormal deviation value is less than the preset abnormal deviation value, the sample inspection interval in the characteristic time segment is reduced. The characteristic time segment is from the time when the sample started transportation in each abnormal history record to the time when the abnormality of the commodity package was discovered. The minimum value of the abnormal time reference value corresponding to each abnormal history record at the time when the sample started transportation in the target monitoring area is recorded as the first characteristic time, and the maximum value of the abnormal time reference value corresponding to each abnormal history record at the time when the sample started transportation in the target monitoring area is recorded as the second characteristic time. The time between the first characteristic time and the second characteristic time is recorded as the characteristic time segment. The sample inspection interval in the characteristic time segment is reduced. The reduction value of the sample inspection interval in the characteristic time segment is positively correlated with the duration of the characteristic time segment.

[0047] Understandably, when the abnormal deviation value is high, reducing the inspection interval can increase the inspection frequency, detect problems in time, and prevent the abnormal situation from escalating. When the abnormal deviation value is low, focusing on characteristic time periods to reduce the inspection interval can concentrate resources to monitor the high-incidence period of abnormalities.

[0048] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A mobile verification and data collection cloud platform, characterized in that, include: The sampling point setting module is used to respond to setting conditions to uniformly set sampling points or associate sampling points for the target monitoring area; The template selection module, connected to the sampling point setting module, is used to respond to analysis conditions to recommend combined forms or effective forms; the information filling module, connected to the template selection module, is used to respond to geographic form keywords or numerical form keywords in the recommended forms to fill map indexes or perform filling analysis; the filling analysis module, connected to the information filling module, is used to perform relevant recommendation filling or range recommendation filling based on the sampling batch and the repetition of multiple information during filling analysis. The image acquisition module is connected to the template selection module, the information filling module and the filling analysis module respectively, and is used to determine the sampling point type according to the sampling point offset and the sampling point feature index, and to perform feature image acquisition or associated image acquisition in response to the judgment conditions. The flow monitoring module, which is connected to the filling analysis module, is used to determine the sample inspection interval based on the form feature values, and to adjust the sample inspection interval or the sample inspection interval in the characteristic time segment based on the abnormal deviation value.

2. The mobile verification data collection and transfer cloud platform according to claim 1, characterized in that, The sampling point setting module responds to the setting conditions that the regional change coefficient of the target monitoring area is less than the preset regional change coefficient or the area reference value is greater than or equal to the preset area reference value, and sets sampling points in association for the target monitoring area. The sampling point setting module responds to the setting conditions that the regional change coefficient of the target monitoring area is greater than or equal to the preset regional change coefficient and the area reference value is less than the preset area reference value, and then uniformly sets sampling points for the target monitoring area.

3. The mobile verification data collection and transfer cloud platform according to claim 1, characterized in that, The template selection module recommends combined forms when the task relevance is less than the preset task relevance or the sampling point difference is greater than or equal to the preset sampling point difference. The template selection module also recommends valid forms when the task relevance is greater than or equal to the preset task relevance and the sampling point difference is less than the preset sampling point difference.

4. The mobile verification data collection and transfer cloud platform according to claim 1, characterized in that, The information filling module performs map index filling for geographic form keywords; the information filling module performs filling analysis for numerical form keywords.

5. The mobile verification data collection and transfer cloud platform according to claim 1, characterized in that, The filling analysis module performs relevant recommendation filling when the sampling batch is greater than or equal to the preset sampling batch and the repetition of multiple pieces of information is greater than or equal to the preset repetition of multiple pieces of information.

6. The mobile verification data collection and transfer cloud platform according to claim 1, characterized in that, The filling analysis module performs range recommendation filling when the sampling batch is smaller than the preset sampling batch or the repetition of multiple pieces of information is less than the preset repetition of multiple pieces of information. In the range recommendation filling process, the associated range recommendation or predicted range recommendation is performed based on the sampling batch and the batch regularity coefficient; If the sampled batch is greater than or equal to the preset sampled batch and the batch regularity coefficient is greater than or equal to the preset batch regularity coefficient, then an association range recommendation is made; if the sampled batch is within the range of the first preset sampled batch or the batch regularity coefficient is less than the preset batch regularity coefficient, then a prediction range recommendation is made.

7. The mobile verification data collection and transfer cloud platform according to claim 1, characterized in that, The image supplementation module determines the sampling point type based on the sampling point offset and the sampling point feature index, including: a type of sampling point with a sampling point offset greater than or equal to a preset sampling point offset or a sampling point feature index greater than or equal to a preset sampling point feature index; and a type of sampling point with a sampling point offset less than a preset sampling point offset and a sampling point feature index less than a preset sampling point feature index.

8. The mobile verification data collection and transfer cloud platform according to claim 1, characterized in that, The image supplementation module performs feature image acquisition in response to the judgment conditions that the form change value is greater than or equal to the preset form change value or the proportion of a type of sampling point is greater than or equal to the preset proportion of a type of sampling point. The image supplementation module performs associated image acquisition in response to the judgment conditions that the form change value is less than the preset form change value and the proportion of a certain type of sampling point is less than the preset proportion of a certain type of sampling point.

9. The mobile verification data collection and transfer cloud platform according to claim 1, characterized in that, The flow monitoring module determines the sample inspection interval based on the form feature values; wherein, the sample inspection interval is positively correlated with the form feature values.

10. The mobile verification data collection and transfer cloud platform according to claim 1, characterized in that, When the abnormal deviation value is greater than or equal to the preset abnormal deviation value, the flow monitoring module reduces the sample inspection interval; when the abnormal deviation value is less than the preset abnormal deviation value, the flow monitoring module reduces the sample inspection interval in the characteristic time segment.

Images