A data collection method based on portable multifunctional device
By using a portable multi-functional device for data acquisition, we analyzed the compliance, scarcity, and interoperability of experimental data. Combined with applicability and convergence, we solved the problem of insufficient control during the data acquisition process of the portable multi-functional device and improved the data acquisition efficiency.
Patent Information
- Application Number
- CN202410319418.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-20
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-03-20
AI Technical Summary
Existing portable multi-functional devices suffer from insufficient control during data acquisition, resulting in low data acquisition efficiency.
Portable experiments are conducted using a portable multifunctional device to collect experimental data, experimental types, and experimental locations. The basic value analysis unit is used to analyze the compliance, scarcity, and interoperability of the data. The application value analysis unit is combined to analyze the applicability and convergence, and the comprehensive value information of the experimental data is calculated and labeled.
This enables rational and precise control of data collection from portable multi-functional devices, improving data collection efficiency.
Smart Images

Figure CN118114053B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and in particular to a data acquisition method based on a portable multifunctional device. Background Art
[0002] With the development of science and technology, especially in the field of data collection, the portable multifunctional device for data collection can be an IoT experiment box, which only focuses on the connection between sensor equipment and IoT modules and lacks the ability to connect with the IoT cloud platform. In the teaching scene in the laboratory, data collection is separated from data viewing and analysis, which has certain teaching limitations. In addition, the existing technology has insufficient control over the data collection process of portable multifunctional devices, resulting in low data collection efficiency. Summary of the invention
[0003] The present application provides a data collection method based on a portable multi-function device, which is used to solve the technical problem in the prior art that insufficient control over the data collection process of the portable multi-function device leads to low data collection efficiency.
[0004] In view of the above problems, the present application provides a data collection method based on a portable multi-functional device.
[0005] In a first aspect, the present application provides a data collection method based on a portable multi-function device, the method comprising: using the portable multi-function device to conduct a portable test, and collect and obtain test data, test type and test location; through the basic value analysis unit, according to the test type and test location, analyzing the data compliance, data scarcity and data interoperability of the test data; based on the data compliance, data scarcity and data interoperability, calculating and obtaining the first value information of the test data; through the application value analysis unit, according to the test analyzer corresponding to the test type, performing suitability analysis and convergence analysis on the test data to obtain data suitability and data convergence; according to the data compliance, correcting the data suitability to obtain corrected data suitability, and combining the data convergence to calculate and obtain the second value information of the test data; based on the first value information and the second value information, calculating the comprehensive value information of the test data, and through the data marking unit, marking the test data according to the comprehensive value information.
[0006] In a second aspect, the present application provides a data acquisition system based on a portable multifunctional device, the system comprising: a first test module, the first test module is used to use the portable multifunctional device to conduct a portable test, and collect and obtain test data, test type and test location; a first analysis module, the first analysis module is used to analyze the data compliance, data scarcity and data interoperability of the test data according to the test type and test location through the basic value analysis unit; a first calculation module, the first calculation module is used to calculate and obtain the first value information of the test data based on the data compliance, data scarcity and data interoperability; a second analysis module Block, the second analysis module is used to perform suitability analysis and convergence analysis on the test data through the application value analysis unit according to the test analyzer corresponding to the test type, so as to obtain data suitability and data convergence; a correction module, the correction module is used to correct the data suitability according to the data compliance, obtain the corrected data suitability, and calculate and obtain the second value information of the test data in combination with the data convergence; a marking module, the marking module is used to calculate the comprehensive value information of the test data according to the first value information and the second value information, and mark the test data according to the comprehensive value information through the data marking unit.
[0007] In a third aspect, a computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the following steps when executing the computer program: using the portable multifunctional device to conduct a portable test, and collect and obtain test data, test type and test location; through the basic value analysis unit, according to the test type and test location, analyzing the data compliance, data scarcity and data interoperability of the test data; based on the data compliance, data scarcity and data interoperability, calculating and obtaining the first value information of the test data; through the application value analysis unit, according to the test analyzer corresponding to the test type, performing suitability analysis and convergence analysis on the test data to obtain data suitability and data convergence; according to the data compliance, correcting the data suitability to obtain corrected data suitability, and calculating and obtaining the second value information of the test data in combination with the data convergence; according to the first value information and the second value information, calculating the comprehensive value information of the test data, and through the data marking unit, marking the test data according to the comprehensive value information.
[0008] In a fourth aspect, a computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the following steps are implemented: using the portable multifunctional device to conduct a portable test, and collect and obtain test data, test type and test location; through the basic value analysis unit, according to the test type and test location, analyze the data compliance, data scarcity and data interoperability of the test data; based on the data compliance, data scarcity and data interoperability, calculate and obtain the first value information of the test data; through the application value analysis unit, according to the test analyzer corresponding to the test type, perform suitability analysis and convergence analysis on the test data to obtain data suitability and data convergence; according to the data compliance, correct the data suitability to obtain corrected data suitability, and calculate and obtain the second value information of the test data in combination with the data convergence; based on the first value information and the second value information, calculate the comprehensive value information of the test data, and through the data marking unit, mark the test data according to the comprehensive value information.
[0009] One or more technical solutions provided in the present application have at least the following technical effects or advantages: A data collection method based on a portable multi-function device provided in the present application relates to the field of data processing technology, and solves the technical problem in the prior art of insufficient control over the data collection process of a portable multi-function device, resulting in low data collection efficiency, and realizes reasonable and precise control over data collection by a portable multi-function device, thereby improving data collection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] Figure 1 A schematic diagram of a data collection method based on a portable multifunctional device is provided for this application;
[0011] Figure 2 A schematic diagram of the structure of a data acquisition system based on a portable multifunctional device is provided for this application;
[0012] Explanation of the accompanying drawings: first test module 1, first analysis module 2, first calculation module 3, second analysis module 4, correction module 5, marking module 6. DETAILED DESCRIPTION
[0013] The present application provides a data collection method based on a portable multi-function device, which is used to solve the technical problem of low data collection efficiency caused by insufficient control during data collection of portable multi-function devices in the prior art.
[0014] Example: Figure 1As shown, an embodiment of the present application provides a data collection method based on a portable multifunctional device, the method is applied to a portable multifunctional device, the device includes a basic value analysis unit, an application value analysis unit and a data marking unit, the method includes:
[0015] Step A100: using the portable multifunctional device to conduct a portable test, and collecting test data, test type and test location;
[0016] In the present application, a data collection method based on a portable multifunctional device provided in an embodiment of the present application is applied to a portable multifunctional device. In order to better accurately collect target data, it is necessary to use a portable multifunctional device to conduct a portable test in the target area while determining the test data, test type, and test location of the current test. The portable multifunctional device can be a device that can be moved for test teaching, and there are differences between the test results generated by the test at different locations. Since the portable multifunctional device collects a variety of common sensors and controls a variety of types of controllers, it can interact with the host computer or other experimental boxes through wired and wireless communication methods. Exemplarily, the test location of the portable multifunctional device can be a university laboratory, and the test type can be divided by sensors, microcontrollers, communication modules, and software tools, so that students, developers, and researchers can learn and practice Internet of Things related technologies, such as data collection, data transmission, remote monitoring, cloud computing, etc. Further, the portable multifunctional device is highly flexible and can adapt to different experimental needs. Various hardware devices can be added or deleted as needed to achieve various test goals. And the portable multifunctional device is highly scalable and can meet different experimental needs by adding different sensors or actuators. At the same time, it is highly customizable. Users can write their own programs according to the experimental requirements to control and manage the experiment, so as to obtain the experimental data during the experiment, which will serve as an important reference for the later data collection based on portable multi-functional devices.
[0017] Step A200: Analyzing the data compliance, data scarcity and data interoperability of the test data according to the test type and test location through the basic value analysis unit;
[0018] Furthermore, step A200 of the present application also includes:
[0019] Step A210: according to the test type and test location, collect and obtain a homogeneous sample data set and a type homogeneous sample data set, wherein the type homogeneous sample data set includes the homogeneous sample data set and includes multiple location homogeneous sample data sets of multiple sample locations;
[0020] Step A220: training a compliance analysis path according to the same family sample data set, performing compliance analysis on the test data, and obtaining the data compliance;
[0021] Step A230: Calculate the data scarcity of the test data according to the homogeneous sample data set;
[0022] Step A240: Analyze and obtain the data interoperability of the test data based on the sample data set of the same type.
[0023] Furthermore, step A240 of the present application includes:
[0024] Step A241: training and obtaining multiple location compliance analysis paths corresponding to multiple other sample locations based on the multiple location homogeneous sample data sets;
[0025] Step A242: using the compliance analysis paths of the multiple locations to perform compliance analysis on the test data to obtain compliance of multiple locations;
[0026] Step A243: Calculate and obtain the data interoperability based on the data compliance and multiple location compliances.
[0027] Furthermore, step A220 of the present application includes:
[0028] Step A221: performing compliance evaluation on a plurality of sample test data in the same family sample data set to obtain a same family sample compliance set;
[0029] Step A222: Use the same-family sample data set and the same-family sample compliance set to train and obtain the compliance analysis path.
[0030] In the present application, in order to ensure the data value of test data collected by a portable multifunctional device, it is necessary to use the above-mentioned test type and test location as basic reference data, and analyze the test data through a basic value analysis unit. The basic value analysis unit is embedded in a portable multifunctional device. The basic value analysis unit is used to perform value analysis on the test data collected by the portable multifunctional device during the data collection process.
[0031] Further, according to the test type and test location, the same family sample data set and the type same family sample data set are collected and obtained. The same family sample data refers to the test data generated by the test with the same test type and test location. The type same family sample data set refers to the test data generated by the test with the same test type but different test locations. The type same family sample data set includes the same family sample data set. On this basis, multiple test locations are extracted as multiple sample locations, and the same family sample data sets of multiple locations in the multiple sample locations are obtained according to the same family sample data set, which means that the test data generated by the same test type in the same location are summarized. Further, the same family sample data set is used as the same family sample data set. This data set is used as training data to train the compliance analysis path of the test. The compliance analysis path is used to compare the current test process, test data, test location, test type and the test standard items in the big data, so as to complete the compliance analysis of the test data. For example, the preset compliance range is (0,1). The preset compliance range is used to characterize the rationality of the test data. The greater the rationality, the more reasonable the test data. For example, in the process of monitoring the status of the equipment, there is a device that is a spare device. From the perspective of the equipment status alone, the compliance of the test data is low. On this basis, the data compliance of the test data is further analyzed in the same family sample data set. The compliance evaluation of multiple sample test data according to data compliance refers to comparing each sample test data in turn according to the preset compliance range, recording the sample test data that is not within the preset compliance range as the same family non-compliant sample data, and recording the sample test data within the preset compliance range as the same family compliant sample data, and at the same time integrating all the same family compliant sample data and recording them as the same family sample compliance set. Furthermore, the same family sample data set and the same family sample compliance set are used as basic training data, and there is a mapping relationship between the same family sample data set and the same family sample compliance set, which means that when a value is taken in the same family sample data set, the same family sample compliance set has And there is only one value corresponding, and taking a value in the compliance set of the same family samples, the same family sample data set can have multiple values corresponding, so as to obtain the compliance analysis path after serializing the compliance in the same family sample data set from large to small, and finally calculate the data scarcity of the test data according to the same family sample data set. The calculation process can be to extract the number of identical data in the same family sample data set as the numerator, and the total number of data in the same family sample data set as the denominator, calculate the proportion of identical data in the same family sample data set, and use 1 minus the calculated proportion value as the data scarcity of the test data. The greater the data scarcity, the scarcer and more valuable the test data is.
[0032] Furthermore, based on the multiple location homogeneous sample data sets in the type homogeneous sample data set as basic training data, multiple location compliance analysis paths corresponding to other multiple sample locations are trained. The multiple location homogeneous sample data sets are sample test data of the same test type at different multiple locations. On this basis, the compliance of the test data of the test type at other locations is analyzed to complete the training of multiple location compliance analysis paths corresponding to other multiple sample locations. The multiple location compliance analysis paths are the compliance of the test data at each different location. Further, the compliance analysis of the test data using the multiple location compliance analysis paths refers to judging the test Whether the data is in the compliance analysis path of multiple locations. If so, the location compliance corresponding to the test data is determined according to the compliance analysis path of multiple locations, and it is extracted and recorded to obtain the compliance of multiple locations. Furthermore, the data compliance of the current test data and the compliance of multiple locations are added together, and the average value of the two is calculated and recorded as the data interoperability of the test data. The data interoperability is used to reflect the compliance level of the test data in different test locations. The higher the data interoperability of the test data, the more the test data eliminates the impact of different locations on the test, and the more valuable the test data is, thereby ensuring the realization of data collection based on portable multi-functional devices.
[0033] Step A300: Calculate and obtain first value information of the test data based on the data compliance, data scarcity and data interoperability;
[0034] In the present application, by using the data compliance, data scarcity, and data interoperability obtained from the above analysis as the basic reference data for judging the value of the test data, it is necessary to perform weighted calculation on the data compliance, data scarcity, and data interoperability. The weighted calculation needs to be based on a large amount of data aggregation and accurate determination of the weights before performing targeted calculations. For example, the weight ratio of data compliance, data scarcity, and data interoperability can be the first influence coefficient: the second influence coefficient: the third influence coefficient is 4:2:3. The influencing parameters after the weighted calculation process are the first influence parameter*0.4, the second influence parameter*0.2, and the third influence parameter*0.3. The value information of the test data is obtained based on the weighted calculation results, and it is recorded as the first value information of the test data for output, which lays a solid foundation for the subsequent realization of data collection based on portable multi-functional devices.
[0035] Step A400: Performing applicability analysis and convergence analysis on the test data through the application value analysis unit according to the test analyzer corresponding to the test type to obtain data applicability and data convergence;
[0036] Furthermore, step A400 of the present application also includes:
[0037] Step A410: According to the test type, select and obtain a corresponding test analyzer for performing test analysis, wherein the test analyzer is used to obtain test results according to test data analysis;
[0038] Step A420: Perform test result reasoning on the test data to obtain theoretical test results;
[0039] Step A430: using the test analyzer to perform predictive analysis on the test data to obtain a predictive test result;
[0040] Step A440: Calculate and obtain the data applicability according to the deviation between the prediction test result and the theoretical test result;
[0041] Step A450: obtaining a first convergence speed of the test analyzer during supervised training, and using the test data and theoretical test results, adding the training data of the test analyzer, performing supervised training of the test analyzer, and obtaining a second convergence speed;
[0042] Step A460: Calculate and obtain the data convergence degree according to the first convergence speed and the second convergence speed.
[0043] In the present application, in order to ensure the data applicability and convergence of the experimental data during the application process, it is first necessary to analyze the applicability and convergence of the experimental data through the experimental analyzer corresponding to the experimental type in the application value analysis unit. The application value analysis unit is embedded in a portable multi-function device. The application value analysis unit is used to analyze the data applicability and data convergence of the experimental data collected by the portable multi-function device during the data collection process.
[0044] Further, according to the test type, a test analyzer corresponding to the test analysis is selected. The test analyzer is used to analyze the test data, conduct theoretical tests and generate test results corresponding to the test data. The test result inference based on the current test data refers to verifying the test theory, exploring the test laws, and confirming the scientific nature through test operations and inferring the test results, thereby obtaining theoretical test results. The test analyzer is further used to perform predictive analysis on the test data. The test means and conclusions can be used to infer the unknown from the known and the whole from the local, thereby obtaining predicted test results. In order to make the test data more applicable, the deviation between the predicted test results and the theoretical test results can be calculated first. The result of subtracting the predicted test results from the theoretical test results can be used as the deviation value, and then 1 minus the deviation value is recorded as the data applicability of the test data. The greater the data applicability, the more applicable the neural network model in the test analyzer currently used for test analysis is to the test data, and at the same time, it indicates that the test data conforms to the processing logic in the test analyzer, that is, the more valuable the test data is.
[0045] The neural network model in the test analyzer is based on the BP neural network. The BP neural network refers to a multi-layer feedforward neural network trained according to the error back propagation algorithm. The neural network model is further constructed, and the neural network model includes a data input layer, a hidden layer, and a data output layer. The neural network model is a neural network model in machine learning that can continuously perform self-iterative optimization. The neural network model is obtained through training data sets and supervision data sets. The training data set contains test analysis data, and the supervision data set is supervision data that corresponds one-to-one to the training data set.
[0046] Furthermore, the neural network model construction process is as follows: each set of training data in the training data set is input into the neural network model, and the output supervision adjustment of the neural network model is performed through the supervision data corresponding to this set of training data. When the output result of the neural network model is consistent with the supervision data, the training of the current set is completed, and when all the training data in the training data set are trained, the training of the neural network model is completed.
[0047] In order to ensure the convergence and accuracy of the neural network model, its convergence process can be that when the output data in the neural network model converges to a point and approaches a certain value, it is considered convergence. Its accuracy can be tested by testing the neural network model with a test data set. For example, the test accuracy can be set to 80%. When the test accuracy of the test data set meets 80%, the neural network model is constructed.
[0048] Furthermore, the data convergence speed of the test analyzer during supervised training is recorded as a first data convergence speed and outputted. At the same time, the test data and theoretical test results are used, and the training data of the test analyzer is added to perform supervised training of the test analyzer through the embedded neural network model. The convergence speed of the supervised training at this time is recorded as a second convergence speed. Finally, based on the first convergence speed and the second convergence speed, the data convergence degree is calculated, and the first convergence speed is subtracted from the second convergence speed and recorded as a convergence speed deviation value. The deviation value is further subtracted from 1 as the data convergence degree of the test data. The data convergence degree can be used to reflect the degree to which the convergence efficiency of the model training is reduced due to the test data, and the data convergence degree is inversely proportional to the degree of its influence, that is, the greater the data convergence degree, the smaller the degree of influence. At the same time, the more valuable the test data is, which has a limited effect on realizing data collection based on portable multi-functional devices.
[0049] Step A500: According to the data compliance, the data applicability is corrected to obtain the corrected data applicability, and combined with the data convergence, the second value information of the test data is calculated and obtained;
[0050] Furthermore, step A500 of the present application also includes:
[0051] Step A510: obtaining a suitability correction coefficient according to the data compliance, performing correction calculation on the data suitability, and obtaining the corrected data suitability;
[0052] Step A520: Perform weighted calculation on the applicability of the modified data and the data convergence to obtain the second value information.
[0053] In the present application, in order to more accurately determine the data value of the test data, it is first necessary to perform deviation correction on the data suitability based on the data compliance obtained from the above analysis, which means that the ratio of the data compliance of the test data to the mean of the historical average data compliance can be used as the suitability correction coefficient. The mean of the historical average data compliance refers to the sum of the data compliances of all test data obtained in the historical period and divided by the number of test data. The larger the suitability correction coefficient, the better the test data and the greater the suitability of the corrected data. At the same time, the data suitability may be affected by the performance of the model itself or the data trained in the historical period. Therefore, the accuracy of the suitability is improved by using compliance to correct the data usage.
[0054] Finally, weighted calculation is performed on the corrected data applicability and data convergence. For example, the weight ratio of the corrected data applicability and data convergence can be the first influence coefficient: the second influence coefficient is 4:6, and the influence parameters after the weighted calculation process are the first influence parameter*0.4, the second influence parameter*0.6. The second value information of the test data is obtained according to the weighted calculation result, so as to be used as reference data for later data collection based on the portable multi-function device.
[0055] Step A600: Calculate the comprehensive value information of the test data according to the first value information and the second value information, and mark the test data according to the comprehensive value information through a data marking unit.
[0056] Furthermore, step A600 of the present application also includes:
[0057] Step A610: Perform weighted calculation on the first value information and the second value information to obtain the comprehensive value information;
[0058] Step A620: Obtain a sample comprehensive value information set and obtain multiple sample data labeling results;
[0059] Step A630: Divide the sample comprehensive value information set to obtain multiple sample comprehensive value information intervals, and construct a mapping relationship with the multiple sample data labeling results;
[0060] Step A640: Perform mapping association according to the comprehensive value information, obtain data labeling results, and label the test data.
[0061] In the present application, in order to determine the comprehensive value of the test data collected by the portable multifunctional device, the first value information and the second value information are used as the basic data for calculation to calculate the comprehensive value information of the test data, which means that the first value information and the second value information are weighted, and the first value information is weighted based on the data compliance, data scarcity and data interoperability of the test data. The second value information is weighted based on the corrected data applicability and data convergence of the test data. The weight ratio of the first value information and the second value information can be the first influence coefficient: the second influence coefficient is 3:7. The influence parameters after the weighted calculation process are the first influence parameter*0.3 and the second influence parameter*0.7, respectively. The comprehensive value information is obtained according to the weighted calculation result, and the test data is iterated to generate a sample comprehensive value information set. Based on the sample comprehensive value information set, the data values of multiple sample data are marked in turn as multiple sample data marking results. Further, according to the data The sample comprehensive value information set is divided and classified into different data values according to the size of the value, and multiple sample comprehensive value information intervals are obtained. At the same time, a mapping relationship between multiple sample comprehensive value information intervals and multiple sample data marking results is constructed. The mapping relationship means that when a value is taken within the multiple sample data marking results, there is one and only one corresponding value in the multiple sample comprehensive value information intervals, and when a value is taken within the multiple sample comprehensive value information intervals, there can be multiple corresponding values in the multiple sample data marking results. Furthermore, through a data marking unit, data with a mapping relationship are mapped and associated with the interval according to the comprehensive value information. The data marking unit is embedded in a portable multi-function device. The data marking unit is used for the data value of the test number collected by the portable multi-function device. Exemplarily, the test data can be marked with high value or low value, thereby obtaining the data marking result, completing the operation of marking the test data, and improving the accuracy of data collection based on the portable multi-function device in the later stage.
[0062] In summary, the data collection method based on a portable multi-function device provided in the embodiment of the present application includes at least the following technical effects, which realizes the rational and precise control of data collection by the portable multi-function device, thereby improving the data collection efficiency.
[0063] Embodiment: Based on the same inventive concept as the data collection method based on a portable multifunctional device in the above embodiment, Figure 2 As shown, the present application provides a data acquisition system based on a portable multifunctional device, the system comprising:
[0064] A first test module 1, wherein the first test module 1 is used to use the portable multifunctional device to conduct a portable test and collect test data, test type and test location;
[0065] A first analysis module 2, the first analysis module 2 is used to analyze the data compliance, data scarcity and data interoperability of the test data according to the test type and test location through the basic value analysis unit;
[0066] A first calculation module 3, the first calculation module 3 is used to calculate and obtain first value information of the test data based on the data compliance, data scarcity and data interoperability;
[0067] A second analysis module 4, the second analysis module 4 is used to perform applicability analysis and convergence analysis on the test data through the application value analysis unit according to the test analyzer corresponding to the test type, so as to obtain data applicability and data convergence;
[0068] A correction module 5, wherein the correction module 5 is used to correct the data applicability according to the data compliance to obtain the corrected data applicability, and calculate and obtain the second value information of the test data in combination with the data convergence;
[0069] The marking module 6 is used to calculate the comprehensive value information of the test data according to the first value information and the second value information, and mark the test data according to the comprehensive value information through a data marking unit.
[0070] Furthermore, the system also includes:
[0071] A data collection module, the data collection module is used to collect and obtain a homogeneous sample data set and a type homogeneous sample data set according to the test type and test location, the type homogeneous sample data set includes the homogeneous sample data set and includes multiple location homogeneous sample data sets of multiple sample locations;
[0072] A third analysis module, the third analysis module is used to train a compliance analysis path according to the homogeneous sample data set, perform compliance analysis on the test data, and obtain the data compliance;
[0073] A second calculation module, the second calculation module is used to calculate the data scarcity of the test data according to the homogeneous sample data set;
[0074] A fourth analysis module is used to analyze and obtain data interoperability of the test data based on the type of sample data set of the same family.
[0075] Furthermore, the system also includes:
[0076] A first training module, the first training module is used to train and obtain multiple location compliance analysis paths corresponding to multiple other sample locations based on the multiple location homogeneous sample data sets;
[0077] a fifth analysis module, the fifth analysis module being configured to perform compliance analysis on the test data using the plurality of location compliance analysis paths to obtain compliance of a plurality of locations;
[0078] A third calculation module is used to calculate and obtain the data interoperability based on the data compliance and multiple location compliances.
[0079] Furthermore, the system also includes:
[0080] An evaluation module, the evaluation module is used to perform compliance evaluation on a plurality of sample test data in the same family sample data set to obtain a same family sample compliance set;
[0081] The second training module is used to use the same-family sample data set and the same-family sample compliance set to train and obtain the compliance analysis path.
[0082] Furthermore, the system also includes:
[0083] A selection module, the selection module is used to select and obtain a corresponding test analyzer for performing test analysis according to the test type, wherein the test analyzer is used to obtain a test result according to the test data analysis;
[0084] An inference module, the inference module is used to perform test result inference on the test data to obtain a theoretical test result;
[0085] a sixth analysis module, the sixth analysis module being used to use the test analyzer to perform predictive analysis on the test data to obtain a predictive test result;
[0086] A fourth calculation module, the fourth calculation module is used to calculate the data applicability according to the deviation between the prediction test result and the theoretical test result;
[0087] A third training module, the third training module is used to obtain a first convergence speed of the test analyzer during supervised training, and adopt the test data and theoretical test results, add the training data of the test analyzer, perform supervised training of the test analyzer, and obtain a second convergence speed;
[0088] A fifth calculation module, wherein the fifth calculation module is used to calculate and obtain the data convergence degree according to the first convergence speed and the second convergence speed.
[0089] Furthermore, the system also includes:
[0090] a sixth calculation module, the sixth calculation module being used to obtain a suitability correction coefficient according to the data compliance, and to perform correction calculation on the data suitability to obtain the corrected data suitability;
[0091] The seventh calculation module is used to perform weighted calculation on the applicability of the modified data and the data convergence to obtain the second value information.
[0092] Furthermore, the system also includes:
[0093] an eighth calculation module, the eighth calculation module being used to perform weighted calculation on the first value information and the second value information to obtain the comprehensive value information;
[0094] A result acquisition module, which is used to acquire a set of comprehensive value information of samples and acquire multiple sample data marking results;
[0095] A partitioning module, the partitioning module is used to partition the sample comprehensive value information set, obtain multiple sample comprehensive value information intervals, and construct a mapping relationship with the multiple sample data labeling results;
[0096] A mapping association module is used to perform mapping association according to the comprehensive value information, obtain data marking results, and mark the test data.
[0097] Through the above-mentioned detailed description of a data acquisition method based on a portable multi-function device in this specification, those skilled in the art can clearly know that a data acquisition system based on a portable multi-function device in this embodiment is a kind of data acquisition system based on a portable multi-function device. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.
[0098] In one embodiment, a computer-readable storage medium is provided, and the computer device may be a server. The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store news data and data such as time decay factors. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a data acquisition method based on a portable multi-function device is implemented.
[0099] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A data collection method based on a portable multifunctional device, It is characterized in that The method is applied to a portable multifunctional device, the device comprising a basic value analysis unit, an application value analysis unit and a data marking unit, and the method comprises: Using the portable multifunctional device, conducting portable tests, and collecting test data, test types and test locations; By means of the basic value analysis unit, according to the test type and test location, the data compliance, data scarcity and data interoperability of the test data are analyzed; Based on the data compliance, data scarcity and data interoperability, first value information of the test data is calculated and obtained; By means of the application value analysis unit, according to the test analyzer corresponding to the test type, the test data is subjected to applicability analysis and convergence analysis to obtain data applicability and data convergence; According to the data compliance, the data applicability is corrected to obtain the corrected data applicability, and combined with the data convergence, the second value information of the test data is calculated and obtained; Calculating comprehensive value information of the test data according to the first value information and the second value information, and marking the test data according to the comprehensive value information through a data marking unit; By means of the basic value analysis unit, the data compliance, data scarcity and data interoperability of the test data are analyzed according to the test type and test location, including: According to the test type and test location, a homogeneous sample data set and a type homogeneous sample data set are collected and acquired, wherein the type homogeneous sample data set includes the homogeneous sample data set and includes multiple location homogeneous sample data sets of multiple sample locations, wherein the homogeneous sample data refers to test data generated by tests with the same test type and test location, and the type homogeneous sample data set refers to test data generated by tests with the same test type but different test locations; According to the same family sample data set, a compliance analysis path is trained, and compliance analysis is performed on the test data to obtain the data compliance, wherein the data compliance analysis is to compare the test data with the test standard items; Calculate the data scarcity of the test data according to the homogeneous sample data set, wherein the greater the data scarcity, the more scarce the test data; According to the same type of sample data set, the data interoperability of the test data is analyzed and obtained, and the data interoperability is used to reflect the compliance level of the test data in different test locations.
2. The method according to claim 1, It is characterized in that Analyzing and obtaining the data interoperability of the test data according to the same type of sample data set includes: Based on the plurality of location homogeneous sample data sets, training and obtaining a plurality of location compliance analysis paths corresponding to a plurality of other sample locations; Using the compliance analysis paths of the multiple locations, performing compliance analysis on the test data to obtain compliance of multiple locations; The data interoperability is obtained by calculation according to the data compliance and the compliance of multiple locations.
3. The method according to claim 1, It is characterized in that According to the homogeneous sample data set, a compliance analysis path is trained to perform compliance analysis on the test data, including: Performing compliance evaluation on multiple sample test data in the same family sample data set to obtain a same family sample compliance set; The compliance analysis path is obtained by training using the same-family sample data set and the same-family sample compliance set.
4. The method according to claim 1, It is characterized in that By means of the application value analysis unit, according to the test analyzer corresponding to the test type, the test data is subjected to applicability analysis and convergence analysis to obtain data applicability and data convergence, including: According to the test type, a corresponding test analyzer for performing test analysis is selected, wherein the test analyzer is used to obtain test results according to test data analysis; Performing test result reasoning on the test data to obtain theoretical test results; Using the test analyzer, performing predictive analysis on the test data to obtain a predictive test result; Calculate and obtain the data applicability according to the deviation between the predicted test result and the theoretical test result; Obtaining a first convergence speed of the test analyzer during supervised training, and using the test data and theoretical test results, adding the training data of the test analyzer, performing supervised training of the test analyzer, and obtaining a second convergence speed; The data convergence degree is obtained by calculation according to the first convergence speed and the second convergence speed.
5. The method according to claim 1, It is characterized in that According to the data compliance, the data applicability is corrected to obtain the corrected data applicability, and combined with the data convergence, the second value information of the test data is calculated and obtained, including: According to the data compliance, a suitability correction coefficient is obtained, and a correction calculation is performed on the data suitability to obtain the corrected data suitability; The second value information is obtained by performing weighted calculation on the applicability of the modified data and the data convergence.
6. The method according to claim 1, It is characterized in that Calculating comprehensive value information of the test data according to the first value information and the second value information, and marking the test data according to the comprehensive value information by a data marking unit, including: Performing weighted calculation on the first value information and the second value information to obtain the comprehensive value information; Obtain a set of comprehensive value information of samples and obtain labeling results of multiple sample data; Dividing the sample comprehensive value information set to obtain multiple sample comprehensive value information intervals, and constructing a mapping relationship with the multiple sample data labeling results; Mapping and association are performed according to the comprehensive value information to obtain data labeling results, and the test data are labeled.
7. A data acquisition system based on a portable multifunctional device, the system include: A first test module, wherein the first test module is used to use a portable multifunctional device to conduct a portable test and collect test data, test type and test location; A first analysis module, the first analysis module is used to analyze the data compliance, data scarcity and data interoperability of the test data according to the test type and test location through a basic value analysis unit; A first calculation module, the first calculation module is used to calculate and obtain first value information of the test data based on the data compliance, data scarcity and data interoperability; A second analysis module, the second analysis module is used to perform applicability analysis and convergence analysis on the test data by applying a value analysis unit according to a test analyzer corresponding to the test type, so as to obtain data applicability and data convergence; A correction module, the correction module is used to correct the data applicability according to the data compliance to obtain the corrected data applicability, and calculate and obtain the second value information of the test data in combination with the data convergence; a marking module, the marking module being used to calculate comprehensive value information of the test data according to the first value information and the second value information, and marking the test data according to the comprehensive value information through a data marking unit; The first analysis module includes: A data collection module, the data collection module is used to collect and obtain a homogeneous sample data set and a type homogeneous sample data set according to the test type and test location, the type homogeneous sample data set includes the homogeneous sample data set and includes multiple location homogeneous sample data sets of multiple sample locations, the homogeneous sample data refers to test data generated by tests with the same test type and test location, and the type homogeneous sample data set refers to test data generated by tests with the same test type but different test locations; A third analysis module, the third analysis module is used to train a compliance analysis path according to the homogeneous sample data set, perform compliance analysis on the test data, and obtain the data compliance, wherein the data compliance analysis is to compare the test data with the test standard items; A second calculation module, the second calculation module is used to calculate the data scarcity of the test data according to the homogeneous sample data set, the greater the data scarcity, the more scarce the test data; A fourth analysis module, the fourth analysis module is used to analyze and obtain the data interoperability of the test data based on the type of homogeneous sample data set, and the data interoperability is used to reflect the compliance level of the test data in different test locations.
