A digital multifunctional platform interactive management method, system and storage medium

Abstract

The present invention discloses a digital multifunctional platform interactive management method, system and storage medium, which belongs to the field of data processing technology, including: step S1: classifying data information into multiple data sequences and transmitting them to a data management module; step S2: intercepting a first data group in the data sequence and dividing it into a first sub-data group, generating a first error correction code, recombining the first sub-data group to generate a second sub-data group and a corresponding second error correction code to transmit to a transfer unit, generating a third sub-data group and a corresponding third error correction code to transmit to a processing unit; step S3: correcting the error of the third sub-data group to generate correction data and transmit it to a control unit; step S4: the prediction result of the prediction model output data sequence is transmitted to a comprehensive platform, and the data sequence and the prediction result are output to the user type. Through the present invention, the data sequence can be detected, corrected and spatially predicted, thereby improving the transmission accuracy and applicability of the data sequence.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to a digital multifunctional platform interaction management method, system and storage medium. Background Art

[0002] In the process of merchant operation, improving merchant services is an important proposition for shopping mall operation. Shopping malls need to have a business awareness of the success of merchant customers and need to overcome difficulties with merchants. Through the digitalization of merchant services, the merchant business loop is closed, the business platform information is interactive, and the entire merchant service life cycle is recorded, which plays a great role in subsequent data analysis and optimization and improvement. The multi-functional platform interactive management can quickly and conveniently reach merchants, timely delegate information, and transform traditional offline documents into online paperless office. Digital circulation saves time, electronic information circulation for each account, rapid process approval and optimized settlement, improve merchant satisfaction, and improve the efficiency of shopping mall personnel management.

[0003] For example, the Chinese patent application "CN116796101A" discloses a method for building a digital management platform, including the following steps: obtaining relevant model data and classifying them, and publishing the classified model data; forming different functional components according to different usage requirements; building a platform interface, and adding the generated functional components into the platform interface to realize the platform multi-functional interface interaction. Based on the existing technical route, the technical solution of this invention uses the VUE framework language and takes advantage of the VUE framework to independently develop a digital platform, add the developed functional components into the platform, and coordinate the management of various models. The platform's own overall management capabilities and reusability are greatly improved for customized functional components of the project itself. For another example, the Chinese patent application "CN116628071B" discloses a data interaction method and system for a digital exhibition management platform, which involves the field of data interaction technology, constructs a digital exhibition management platform, including a data acquisition unit, a data transmission unit, a data management unit and a data interaction unit, obtains an exhibition database through the data acquisition unit, encrypts and transmits it to the data management unit through the data transmission unit, performs exhibition management parameter configuration to obtain exhibition management decision results, and performs digital exhibition data interaction based on the exhibition management decision results and the data interaction unit. The invention solves the technical problem in the prior art that the intelligent layout of exhibits in digital exhibitions is low, resulting in poor exhibition effect of the exhibited products and poor exhibition experience for exhibitors, and realizes the connected management of the user platform, thereby achieving the technical effect of improving the intelligent layout of exhibits in digital exhibitions, improving the exhibition effect of the exhibited products and the exhibition experience of exhibitors.

[0004] However, the above-mentioned prior art only sets the interaction mode of the multi-functional platform. In actual situations, the acquired data is transmitted through different communication ports, and data errors may exist. Therefore, without affecting the data transmission rate, the data is verified and corrected, and the data sequence is spatially predicted, which is beneficial to data analysis and application. Summary of the invention

[0005] To solve the above problems, the present invention provides a digital multi-functional platform interaction management method, system and storage medium to solve the problems in the prior art.

[0006] In order to achieve the above-mentioned invention object, the present invention proposes a digital multi-functional platform interaction management method, comprising:

[0007] The acquisition module collects data information, classifies the data information into multiple data sequences based on preset tag types, and transmits all data sequences to the data management module;

[0008] The data management module intercepts a first data group from all the data sequences based on a preset first time period, divides the first data group into a preset first number of first sub-data groups, sets a preset calculation process, generates a first error correction code based on the first sub-data group, recombines the first sub-data group to generate a preset second number of second sub-data groups, generates a second error correction code based on the second sub-data group, transmits the second sub-data group and the second error correction code to a transfer unit via a first transmission mode, the transfer unit recombines the second sub-data group to generate a second number of third sub-data groups, generates a third error correction code based on the third sub-data group, and transmits the third sub-data group and the third error correction code to a processing unit via a second transmission mode;

[0009] Determine whether there is an error in the third sub-data group. If yes, correct the error in the third sub-data group to generate corrected data of the first data group, and transmit the corrected data to the control unit. If no, transmit all the third sub-data groups to the control unit, and repeat until all the data sequences are transmitted to the control unit.

[0010] The prediction model obtains the spatial correlation of the data sequence based on the label type, outputs the prediction result of the data sequence based on the spatial correlation, and transmits the prediction result to the integrated platform, sets different user types based on the label type, and the integrated platform outputs the corresponding data sequence and the prediction result to the user type.

[0011] Further, determining whether the third sub-data group has an error comprises the following steps:

[0012] Calculate the verification sums of all the second sub-data groups in a preset manner, and accumulate the verification sums of all the second sub-data groups to generate a first verification sum;

[0013] Obtaining the first sub-data groups included in the third sub-data group, calculating the verification sum of the first first sub-data group and the verification sum between the adjacent first sub-data groups based on the number of the first sub-data groups and setting them as the first-round verification sum, calculating the verification sum between the first-round verification sum and the next first sub-data group and setting them as the second-round verification sum, repeating this step until all the first sub-data groups in the third sub-data group are calculated, and setting the calculation result as the verification sum of the third sub-data group, and generating a fourth error correction code based on the verification sum of the third sub-data group;

[0014] The processing unit transmits the verification sums of all the third sub-data groups and the corresponding fourth error correction codes to the transfer unit, and accumulates the verification sums of all the third sub-data groups in the transfer unit to generate a second verification sum;

[0015] The first verification sum and the second verification sum are compared. If they are equal, it is determined that there is no error in the third sub-data group. If they are not equal, it is determined that there is an error in the third sub-data group.

[0016] Furthermore, outputting the prediction result of the data sequence includes the following steps:

[0017] The data prediction module obtains the data sequence of a preset second time period, the data sequence includes position information, a time series and a target variable, the prediction model performs spatial interpolation on the data sequence based on the time series, and calculates the regression coefficient of the data sequence to generate a regression function of the target variable in the data sequence, and predicts the prediction result of the target variable in the future time based on the regression function;

[0018] The prediction result y of the target variable in the future time is calculated based on the first formula, and the first formula is: Where m is the number of time series contained in the future time, R(x; θ i ) is the value of the i-th Gaussian kernel function, x is the time series of the future time, θ i is the center point of the i-th Gaussian kernel function, β i is the i-th regression coefficient;

[0019] The i-th regression coefficient β is calculated based on the second formula i , the second formula is Where T is the number of time series contained in the second time period, βj is the jth regression coefficient, φ j is the jth weight parameter, ε i is the ith error value.

[0020] Further, the reassembling of the first sub-data group comprises the following steps:

[0021] Based on a preset time interval, the first data group is equally divided into the first number of the first sub-data groups; based on the second number, the first sub-data groups are sequentially combined to generate a plurality of combination results; two of the combination results are extracted from the combination results to generate the second sub-data group and the third sub-data group; the last first sub-data group in the third sub-data group is the same as the first first sub-data group in the second sub-data group.

[0022] Further, generating the correction data of the first data group comprises the following steps:

[0023] Based on the inverse operation of the preset calculation process, the second error correction code in the transfer unit is restored to the second sub-data group, all the second sub-data groups and the third sub-data groups are respectively summarized and compared to obtain the error position of the third sub-data group, and the correction data of the third sub-data group in the processing unit is calculated based on the error position and the second sub-data group, and all the corrected third sub-data groups are set as the correction data of the first data group.

[0024] The present invention also provides a digital multi-functional platform interaction management system, which is used to implement the digital multi-functional platform interaction management method described above, and the system mainly includes:

[0025] A collection module, used to collect data information, classify the data information into multiple data sequences based on preset tag types, and transmit all data sequences to a data management module;

[0026] A data management module, based on a preset first time period, intercepts a first data group from all the data sequences, divides the first data group into a preset first number of first sub-data groups, generates a first error correction code based on the first sub-data groups, recombines the first sub-data groups to generate a preset second number of second sub-data groups, generates a second error correction code based on the second sub-data groups, transmits the second sub-data groups and the second error correction code to a transfer unit via a first transmission mode, the transfer unit recombines the second sub-data groups to generate a second number of third sub-data groups, generates a third error correction code based on the third sub-data group, and transmits the third sub-data group and the third error correction code to a processing unit via a second transmission mode;

[0027] a data correction module, used to determine whether there is an error in the first data group, and if so, correct the error in the data sequence to generate corrected data of the first data group, and transmit the corrected data to a control unit; if not, transmit the first data group to the control unit, and repeat this step until all the data sequences are transmitted to the control unit;

[0028] A data prediction module, a prediction model obtains the spatial correlation of the data sequence based on the label type, outputs the prediction result of the data sequence based on the spatial correlation, and transmits the prediction result to the integrated platform, sets different user types based on the label type, and the integrated platform outputs the corresponding data sequence and the prediction result to the user type.

[0029] The present invention also provides a computer storage medium storing program instructions, wherein when the program instructions are executed, the device where the computer storage medium is located is controlled to execute the above-mentioned digital multi-functional platform interaction management method.

[0030] Compared with the prior art, the beneficial effects of the present invention are at least as follows:

[0031] The present invention first checks and corrects the collected data sequence through the data management module, which can effectively improve the accuracy of data transmission. The transfer unit is used to compare the first verification sum with the second verification sum to determine whether there is an error in the data sequence. Therefore, there is no need to add the verification sum of the data group during the transmission process, which can avoid the reduction of transmission efficiency. Then, the error correction code corresponding to each data group is set for transmission, and each first sub-data group in the first data group is arranged and combined to generate a second sub-data group and a third sub-data group with different combination results. Different transmission methods are used to transmit them to the processing unit of the data management module, which can avoid data channel interference between the same transmission methods. Finally, the prediction model is set to perform spatial interpolation on the data sequence and then output the prediction result, which is beneficial to the analysis and application of the data sequence. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A flowchart of the steps of a digital multi-functional platform interactive management method of the present invention;

[0033] Figure 2 It is a flow chart of the data management module in the present invention;

[0034] Figure 3 is a schematic diagram of correcting the third sub-data group in the present invention;

[0035] Figure 4 This is a structural diagram of a digital multi-functional platform interactive management system of the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0037] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0038] like Figure 1 As shown, a digital multifunctional platform interaction management method includes:

[0039] Step S1: The acquisition module collects data information, classifies the data information into multiple data sequences based on preset tag types, and transmits all data sequences to the data management module.

[0040] Specifically, in this embodiment, the digital shopping mall module is used as the field for interactive management and analysis of the multifunctional platform, and data information is collected through different data acquisition methods. The data acquisition method refers to the collection path for obtaining data information, including but not limited to web page entry, applet and system entry, etc. The data information refers to various complete data that need to be obtained, including but not limited to basic customer information, store entry frequency and consumer satisfaction in customer data, tenant location, turnover, customer unit price and sales year-on-year in merchant data, rental-sale ratio, investment attraction ratio, opening ratio and target achievement ratio in operation data, energy consumption cost, promotion cost and operation control cost in management data; by obtaining various data related to the shopping mall, the integrity of the multifunctional platform can be effectively realized. For example, by binding the customer's membership information through the applet and recording the customer's store entry according to the membership information, customer data can be obtained.

[0041] Tag types include but are not limited to customer data, merchant data, operational data, and management data. Tag types can be used to aggregate data information of the same tag type collected by different data acquisition methods to generate a data sequence, where the data sequence is a time series data containing different tag types. For example, aggregating customer membership information obtained from different merchants can reduce the frequency of customers logging in to membership when entering different merchants.

[0042] Step S2: The data management module intercepts a first data group from all data sequences based on a preset first time period, divides the first data group into a preset first number of first sub-data groups, sets a preset calculation process, generates a first error correction code based on the first sub-data group, recombine the first sub-data group to generate a preset second number of second sub-data groups, generates a second error correction code based on the second sub-data group, transmits the second sub-data group and the second error correction code to the transfer unit via the first transmission method, the transfer unit recombines the second sub-data group to generate a second number of third sub-data groups, generates a third error correction code based on the third sub-data group, and transmits the third sub-data group and the third error correction code to the processing unit via the second transmission method.

[0043] Specifically, in this embodiment, the data management module includes an input unit, a transfer unit and a processing unit. The first time period is set to 24 hours. The data sequence is divided into a plurality of first data groups by the first time period. For example, if the length of the time series included in the collected data sequence is 72 hours, it can be divided into three first data groups. The preset calculation process refers to the result of adjacent XOR operations on the first sub-data groups included in each data group. The adjacent XOR operation refers to the XOR operation of the first first sub-data group and the second first sub-data group in the data group, and then the XOR operation is performed on the result of the operation and the third first sub-data group, and so on, until all the first sub-data groups in the data group complete the XOR operation, and the final operation result is is set as the error correction code of the data group; the first number is set to 5, then the first data group is divided into 5 first sub-data groups, and by the same method, the second error correction code and the third error correction code are the results of the XOR operation of the corresponding second sub-data group and the third sub-data group; it can be simply understood that the first sub-data group is transmitted to the input unit and then recombined to generate the second sub-data group, the input unit transmits the second sub-data group to the transfer unit by the first transmission method and then recombined to generate the third sub-data group, and the transfer unit transmits the third sub-data group to the processing unit by the second transmission method, wherein the error correction code of each sub-data group is transmitted simultaneously with the sub-data group; when there is an error in the identification data sequence, the error correction code can be used to correct the corresponding data group, for example, Figure 2 The shaded part is the error correction code corresponding to each data group.

[0044] Step S3: Determine whether there is an error in the third sub-data group. If so, correct the error in the third sub-data group to generate corrected data for the first data group, and transmit the corrected data to the management and control unit. If not, transmit all third sub-data groups to the management and control unit. Repeat the process until all data sequences are transmitted to the management and control unit.

[0045] Specifically, in this embodiment, when collecting and classifying all data information, it is necessary to detect and verify the accuracy of the data information. Since different communication ports are used to collect data information, data loss or transmission errors may occur. Therefore, the data sequence will be transmitted to the management and control unit only after verification, which can improve the accuracy of data transmission; if an error in the data sequence is identified, the data sequence will be corrected to generate corresponding correction data, and transmitted to the management and control unit. The specific implementation method will be described later.

[0046] Step S4: The prediction model obtains the spatial correlation of the data sequence based on the label type, and outputs the prediction result of the data sequence based on the spatial correlation, and transmits the prediction result to the integrated platform, sets different user types based on the label type, and the integrated platform outputs the corresponding data sequence and prediction result to the user type.

[0047] Specifically, in this embodiment, the prediction model is used to analyze and predict the data sequence corresponding to each label type. The spatial correlation refers to the correlation between the time series, location information and target variable contained in the data sequence. For example, the customer P1 located in urban area A entered the shopping mall C1 10 times from 2024 / 01 / 01 / 10:00 to 11:00, and the customer P2 located in urban area B entered the shopping mall C1 2 times from 2024 / 01 / 01 / 10:00 to 11:00, where urban area A and urban area B are the location information of the customer data, the time 2024 / 01 / 01 / 11:00 is the time series, and the store entry frequency is the target variable. For another example, the turnover of the 101 merchant on the F1 floor in the shopping mall C1 at 2024 / 01 / 01 / 10:00 is 1,000 yuan, and the turnover of the 301 merchant on the F3 floor in the shopping mall C1 at 2024 / 01 / The turnover at 01 / 10:00 is 100 yuan, among which F1 layer 101 and F3 layer 301 are both the location information of merchant data, the time 2024 / 01 / 01 / 10:00 is the time series, and the turnover is the target variable; the prediction result refers to the value of the target variable in the data sequence at the future time. By analyzing and predicting the data sequence through the prediction model, the value of the target variable in the future time can be predicted and output, which is conducive to the analysis and planning of the mall. For example, in the prediction results, the number of customers and the frequency of store visits in urban area A are greater than those in urban area B, then the mall's publicity and operation can be carried out in urban area A; the comprehensive platform is a platform for realizing multi-functional data interaction management. By digitally interacting the data sequences corresponding to customer data, merchant data, operation data and management data, data browsing and data analysis can be carried out concisely and accurately, the data value of the entire link can be shared, and a digital ecosystem for the entire scene can be jointly built.

[0048] Determining whether there is an error in the third sub-data group includes the following steps:

[0049] The verification sums of all the second sub-data groups are calculated in a preset manner, and the verification sums of all the second sub-data groups are accumulated to generate a first verification sum.

[0050] Obtain the first sub-data groups included in the third sub-data group, calculate the verification sum of the first first sub-data group and the verification sum between the adjacent first sub-data groups based on the number of first sub-data groups and set them as the first-round verification sum, calculate the verification sum between the first-round verification sum and the next first sub-data group and set them as the second-round verification sum, repeat this step until all first sub-data groups in the third sub-data group are calculated, and set the calculation result as the verification sum of the third sub-data group, and generate a fourth error correction code based on the verification sum of the third sub-data group.

[0051] The processing unit transmits the verification sums of all the third sub-data groups and the corresponding fourth error correction codes to the transfer unit, and accumulates the verification sums of all the third sub-data groups in the transfer unit to generate a second verification sum.

[0052] The first verification sum is compared with the second verification sum. If they are equal, it is determined that there is no error in the third sub-data group. If they are not equal, it is determined that there is an error in the third sub-data group.

[0053] Specifically, in this embodiment, the verification sum is a result calculated by a preset method and a corresponding data group. For example, the preset method is set to the product result of a polynomial and the corresponding data group. By comparing the verification sum, it can be determined whether the corresponding data group has an error. After the transfer unit receives the second sub-data group, the verification sum of the second sub-data group is calculated respectively, and the verification sums of all the second sub-data groups are accumulated to generate a first verification sum. The first verification sum means that the second sub-data group contains the values ​​of all the first sub-data groups. After the processing unit receives the third sub-data group, it is necessary to calculate the second verification sum of all the third sub-data groups. For example, Figure 2 As shown, the third sub-data group h31 includes three first sub-data groups h1, h2 and h3, and the verification sum E1 of the first sub-data group h1 is calculated by a preset method. The verification sum E1 calculated by the preset method and the verification sum of the first sub-data group h2 are the first-round verification sum E2, and the verification sum of the first-round verification sum E2 and the first sub-data group h3 are calculated by the preset method as the second-round verification sum E3. The second-round verification sum E3 is the verification sum of the third sub-data group h31. In the same way, the verification sum E5 of the third sub-data group h32 is calculated, and the verification sum E3 and E5 are added to generate a second verification sum. The first verification sum is compared with the second verification sum to see if they are equal. If they are not equal, it means that an error occurs when the second sub-data group of the transfer unit is transmitted to the processing unit.

[0054] The prediction results of the output data sequence include the following steps:

[0055] The data prediction module obtains a data sequence of a preset second time period. The data sequence includes location information, time series and target variables. The prediction model performs spatial interpolation on the data sequence based on the time series and calculates the regression coefficient of the data sequence to generate a regression function of the target variable in the data sequence, and predicts the prediction result of the target variable in the future time based on the regression function.

[0056] The prediction result y of the target variable in the future time is calculated based on the first formula. The first formula is: Among them, m is the number of time series included in the future time, R(x; θ i ) is the value of the i-th Gaussian kernel function, x is the time series of the future time, θ i is the center point of the i-th Gaussian kernel function, β i is the ith regression coefficient.

[0057] Calculate the i-th regression coefficient β based on the second formula i , the second formula is Where T is the number of time series contained in the second time period, β j is the jth regression coefficient, φ j is the jth weight parameter, ε i is the ith error value.

[0058] Specifically, in this embodiment, in order to more comprehensively analyze the collected and transmitted data sequence, the collected data sequence can be used as historical data, and the target variable in the data sequence is predicted through the prediction model. The data sequence of the second time period corresponding to the label type is input into the prediction model. The time series refers to the time distance of the collected data sequence. For example, the data sequence contains information features of three dimensions (time series, location information, target variable). The time distance of the data sequence is 1 hour, that is, the time series of the data sequence is every 1 hour. The second time period is set to 30×24=720 hours, and the label type is set to merchant data. Then, a data sequence of 720 time series lengths is obtained. Based on the location information of the data sequence, the target variable of each time series is spatially interpolated. The spatial interpolation can be performed using the Kriging method or the cubic spline function method. Spatial regression analysis can be performed through spatial interpolation to generate a regression function, wherein the regression function refers to the function formula used by the prediction model to output the prediction result.

[0059] The first formula refers to the linear regression analysis of m Gaussian kernel functions. The Gaussian kernel function refers to the monotonic function of the Euclidean distance from any point x in space to the center point. Among them, the i-th Gaussian kernel function R(x; θ i ) is calculated as: Among them, θ iis the center point of the i-th Gaussian kernel function, α i is the width parameter of the Gaussian kernel function, |||| is the operator for calculating the spatial distance, and the function value is very small when x is far away from the center point.

[0060] The i-th regression coefficient β i The regression coefficient generated by the collected data sequence can be calculated by the second formula. The error value refers to the difference between the target variable value in the collected data sequence and the prediction result of the regression function. It can be simply understood as taking the collected data sequence as historical data, setting the regression function according to the Gaussian kernel function, and making spatial predictions on the target variable in the future.

[0061] The first sub-data set reassembly comprises the following steps:

[0062] Based on a preset time interval, the first data group is equally divided into a first number of first sub-data groups; based on a second number, the first sub-data groups are sequentially combined to generate a plurality of combination results; two combination results are extracted from the combination results to generate a second sub-data group and a third sub-data group; the last first sub-data group in the third sub-data group is the same as the first first sub-data group in the second sub-data group.

[0063] Specifically, in this embodiment, the first data group can be equally divided by setting the time interval, such as Figure 2 As shown, the first data group h11 is divided into five first sub-data groups h1, h2, h3, h4 and h5, and two combination results are extracted, namely the second sub-data groups h21 and h22 and the third sub-data groups h31 and h32, wherein the last first sub-data group h3 in the third sub-data group h31 is the same as the first first sub-data group h3 in the second sub-data group h22. Through the above combination, when an error occurs in the third sub-data group, the second sub-data group can be used to correct it.

[0064] Generating the correction data for the first data set comprises the following steps:

[0065] Based on the inverse operation of the preset calculation process, the second error correction code in the transfer unit is restored to the second sub-data group, all the second sub-data groups and the third sub-data groups are respectively summarized and compared to obtain the error position of the third sub-data group, and the correction data of the third sub-data group in the processing unit is calculated based on the error position and the second sub-data group, and all the corrected third sub-data groups are set as the correction data of the first data group.

[0066] Specifically, in this embodiment, for example, Figure 3As shown, if errors occur in the three first sub-data groups in the third sub-data group h31, the second error correction code g22 in the second sub-data group h22 and the third error correction code g31 in the third sub-data group h31 are used to perform an XOR inverse operation to generate the first sub-data group h3 of the third sub-data group h31, and then the first sub-data group h2 of the third sub-data group h31 is generated by performing an XOR inverse operation with the third error correction code g31, and finally the first sub-data group h1 of the third sub-data group h31 is generated by performing an XOR inverse operation with the third error correction code g31, that is, the third sub-data group h31 is corrected, and the corrected third sub-data group h31 and the third sub-data group h32 without errors are set as the correction data of the first data group.

[0067] The present invention first checks and corrects the collected data sequence through the data management module, which can effectively improve the accuracy of data transmission. The transfer unit is used to compare the first verification sum with the second verification sum to determine whether there is an error in the data sequence. Therefore, there is no need to add the verification sum of the data group during the transmission process, which can avoid the reduction of transmission efficiency. Then, the error correction code corresponding to each data group is set for transmission, and each first sub-data group in the first data group is arranged and combined to generate a second sub-data group and a third sub-data group with different combination results. Different transmission methods are used to transmit them to the processing unit of the data management module, which can avoid data channel interference between the same transmission methods. Finally, the prediction model is set to perform spatial interpolation on the data sequence and then output the prediction result, which is beneficial to the analysis and application of the data sequence.

[0068] It is particularly noteworthy that the present invention can verify and correct the data sequence and perform spatial prediction on the target variable in the data sequence, thereby avoiding data errors during digital interaction of the multifunctional platform.

[0069] like Figure 4 As shown, the present invention also provides a digital multi-functional platform interaction management system, which is used to implement the above-mentioned digital multi-functional platform interaction management method, and the system mainly includes:

[0070] The acquisition module is used to collect data information, classify the data information into multiple data sequences based on preset tag types, and transmit all data sequences to the data management module.

[0071] A data management module, based on a preset first time period, intercepts a first data group from all data sequences, divides the first data group into a preset first number of first sub-data groups, generates a first error correction code based on the first sub-data groups, recombines the first sub-data groups to generate a preset second number of second sub-data groups, generates a second error correction code based on the second sub-data groups, transmits the second sub-data groups and the second error correction code to a transfer unit via a first transmission method, the transfer unit recombines the second sub-data groups to generate a second number of third sub-data groups, generates a third error correction code based on the third sub-data group, and transmits the third sub-data group and the third error correction code to the processing unit via a second transmission method.

[0072] The data correction module is used to determine whether there is an error in the first data group. If so, the error in the data sequence is corrected to generate corrected data for the first data group, and the corrected data is transmitted to the control unit. If not, the first data group is transmitted to the control unit. This step is repeated until all data sequences are transmitted to the control unit.

[0073] Data prediction module, the prediction model obtains the spatial correlation of the data sequence based on the label type, and outputs the prediction results of the data sequence based on the spatial correlation, and transmits the prediction results to the comprehensive platform, sets different user types based on the label type, and the comprehensive platform outputs the corresponding data sequence and prediction results to the user type.

[0074] The present invention also provides a computer storage medium, which stores program instructions, wherein when the program instructions are executed, the device where the computer storage medium is located is controlled to execute the above-mentioned digital multi-functional platform interaction management method.

[0075] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0076] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The above-mentioned program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0077] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0078] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0079] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A digital multifunctional platform interactive management method, characterized in that: The method comprises the following steps: The acquisition module collects data information, classifies the data information into multiple data sequences based on preset tag types, and transmits all data sequences to the data management module; The data management module intercepts a first data group from all the data sequences based on a preset first time period, divides the first data group into a preset first number of first sub-data groups, sets a preset calculation process, generates a first error correction code based on the first sub-data group, recombines the first sub-data group to generate a preset second number of second sub-data groups, generates a second error correction code based on the second sub-data group, transmits the second sub-data group and the second error correction code to a transfer unit via a first transmission mode, the transfer unit recombines the second sub-data group to generate a second number of third sub-data groups, generates a third error correction code based on the third sub-data group, and transmits the third sub-data group and the third error correction code to a processing unit via a second transmission mode, wherein the preset calculation process refers to the result of adjacent XOR operations on the first sub-data groups contained in each data group, and the second error correction code and the third error correction code are both the result of XOR operations on the corresponding second sub-data group and the third sub-data group; Determine whether the third sub-data group has an error. If so, correct the error in the third sub-data group to generate corrected data of the first data group, and transmit the corrected data to the control unit. If not, transmit all the third sub-data groups to the control unit. Repeat this step until all the third sub-data groups are determined. The step of generating the correction data of the first data group comprises the following steps: Restore the second sub-data group from the second error correction code in the transfer unit based on the inverse operation of the preset calculation process, respectively summarize and compare all the second sub-data groups and the third sub-data groups to obtain the error position of the third sub-data group, calculate the correction data of the third sub-data group in the processing unit based on the error position and the second sub-data group, and set all the corrected third sub-data groups as the correction data of the first data group; The prediction model obtains the spatial correlation of the data sequence in the management and control unit based on the label type, outputs the prediction result of the data sequence in the management and control unit based on the spatial correlation, and transmits the prediction result to the integrated platform, sets different user types based on the label type, and the integrated platform outputs the corresponding data sequence in the management and control unit and the prediction result to the user type.

2. A digital multifunctional platform interactive management method according to claim 1, characterized in that: Determining whether the third sub-data set has an error comprises the following steps: Calculate the verification sums of all the second sub-data groups in a preset manner, and accumulate the verification sums of all the second sub-data groups to generate a first verification sum; Obtaining the first sub-data groups included in the third sub-data group, calculating the verification sum of the first first sub-data group and the verification sum between the adjacent first sub-data groups based on the number of the first sub-data groups and setting them as the first-round verification sum, calculating the verification sum between the first-round verification sum and the next first sub-data group and setting them as the second-round verification sum, repeating this step until all the first sub-data groups in the third sub-data group are calculated, and setting the calculation result as the verification sum of the third sub-data group, and generating a fourth error correction code based on the verification sum of the third sub-data group; The processing unit transmits the verification sums of all the third sub-data groups and the corresponding fourth error correction codes to the transfer unit, and accumulates the verification sums of all the third sub-data groups in the transfer unit to generate a second verification sum; The first verification sum and the second verification sum are compared. If they are equal, it is determined that there is no error in the third sub-data group. If they are not equal, it is determined that there is an error in the third sub-data group.

3. A digital multifunctional platform interactive management method according to claim 1, characterized in that: Outputting the prediction result of the data sequence in the control unit includes the following steps: The data prediction module obtains a data sequence in the control unit of a preset second time period, wherein the data sequence in the control unit includes position information, a time sequence and a target variable, and the prediction model performs spatial interpolation on the data sequence in the control unit based on the time sequence, and calculates a regression coefficient of the data sequence in the control unit to generate a regression function of the target variable in the data sequence in the control unit, and predicts the prediction result of the target variable in the future time based on the regression function; The prediction result y of the target variable in the future time is calculated based on the first formula, and the first formula is: Where m is the number of time series contained in the future time, R(x; θ i ) is the value of the i-th Gaussian kernel function, x is the time series of the future time, θ i is the center point of the i-th Gaussian kernel function, β i is the i-th regression coefficient; The i-th regression coefficient β is calculated based on the second formula i , the second formula is Where T is the number of time series contained in the second time period, β j is the jth regression coefficient, φ j is the jth weight parameter, ε i is the ith error value.

4. A digital multifunctional platform interactive management method according to claim 1, characterized in that: The first sub-data set reassembly comprises the following steps: The first data group is equally divided into the first number of the first sub-data groups based on a preset time interval, the first sub-data groups are sequentially combined based on the second number to generate a plurality of combination results, two of the combination results are extracted from the combination results to generate the second sub-data group and the third sub-data group, and there is a last first sub-data group in the third sub-data group that is the same as the first first sub-data group in the second sub-data group.

5. A digital multifunctional platform interaction management system, used to implement a digital multifunctional platform interaction management method as claimed in any one of claims 1 to 4, characterized in that: The system includes the following modules: A collection module, used to collect data information, classify the data information into multiple data sequences based on preset tag types, and transmit all data sequences to a data management module; A data management module, based on a preset first time period, intercepts a first data group from all the data sequences, divides the first data group into a preset first number of first sub-data groups, sets a preset calculation process, generates a first error correction code based on the first sub-data group, recombines the first sub-data group to generate a preset second number of second sub-data groups, generates a second error correction code based on the second sub-data group, transmits the second sub-data group and the second error correction code to a transfer unit via a first transmission mode, the transfer unit recombines the second sub-data group to generate a second number of third sub-data groups, generates a third error correction code based on the third sub-data group, and transmits the third sub-data group and the third error correction code to a processing unit via a second transmission mode, wherein the preset calculation process refers to the result of adjacent XOR operations on the first sub-data groups contained in each data group, and the second error correction code and the third error correction code are both the result of XOR operations on the corresponding second sub-data group and the third sub-data group; a data correction module, judging whether there is an error in the third sub-data group, and if so, correcting the error in the third sub-data group to generate corrected data of the first data group, and transmitting the corrected data to the control unit; if not, transmitting all the third sub-data groups to the control unit, and repeating this step until all the third sub-data groups are judged; restoring the second error correction code in the transfer unit to the second sub-data group based on the inverse operation of the preset calculation process, respectively summarizing and comparing all the second sub-data groups and the third sub-data group to obtain the error position of the third sub-data group, calculating the corrected data of the third sub-data group in the processing unit based on the error position and the second sub-data group, and setting all the corrected third sub-data groups as the corrected data of the first data group; A data prediction module, wherein the prediction model obtains the spatial correlation of the data sequence in the management and control unit based on the label type, and outputs the prediction result of the data sequence in the management and control unit based on the spatial correlation, and transmits the prediction result to the integrated platform, and sets different user types based on the label type, and the integrated platform outputs the corresponding data sequence in the management and control unit and the prediction result to the user type.

6. A computer storage medium, characterized in that: The computer storage medium stores program instructions, wherein when the program instructions are executed, the device where the computer storage medium is located is controlled to execute a digital multi-functional platform interaction management method as described in any one of claims 1 to 4.

Images