Intelligent ring data processing method and system based on data classification processing

Abstract

The present invention discloses a smart ring data processing method and system based on data classification processing, the method comprising: obtaining multiple ring data sent by multiple smart rings; grouping the multiple ring data based on preset classification rules to obtain multiple ring data sets; determining the prediction processing parameters of each of the ring data sets based on a neural network prediction algorithm; and sending each of the ring data sets to a corresponding processing node for data processing according to the prediction processing parameters. It can be seen that the present invention can improve the efficiency and effect of processing a large amount of ring data in a big data scenario, and reduce processing errors or unnecessary burdens on processing nodes.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a smart ring data processing method and system based on data classification processing. Background Art

[0002] A smart ring is a wearable electronic device that is generally equipped with mobile components such as sensors and NFC chips. It can be used in various applications, mainly for tracking daily activities and as a peripheral tool to support mobile devices. The existing background data processing system of smart rings is still mostly limited to one-to-one processing when processing the data of smart rings, that is, receiving and processing data after establishing communication with a single ring. This technical idea is inefficient and prone to errors when dealing with big data processing scenarios after a large number of ring products are activated. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a smart ring data processing method and system based on data classification processing, which can improve the efficiency and effect of processing a large amount of ring data in big data scenarios and reduce processing errors or unnecessary burdens on processing nodes.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a smart ring data processing method based on data classification processing, the method comprising:

[0005] Obtain multiple ring data sent by multiple smart rings;

[0006] Grouping the plurality of ring data based on a preset classification rule to obtain a plurality of ring data sets;

[0007] Determining prediction processing parameters for each of the ring data sets based on a neural network prediction algorithm;

[0008] According to the predicted processing parameters, each of the ring data sets is sent to a corresponding processing node for data processing.

[0009] As an optional implementation, in the first aspect of the present invention, the ring data includes at least one of ring sensing data, ring communication establishment data, ring notification data, ring communication termination data and ring abnormality data.

[0010] As an optional implementation, in the first aspect of the present invention, the classification rules include data volume classification rules, data type classification rules, data source classification rules, data target source classification rules and data purpose classification rules.

[0011] As an optional implementation, in the first aspect of the present invention, grouping the plurality of ring data based on a preset classification rule to obtain a plurality of ring data sets includes:

[0012] According to a plurality of preset classification rules, the plurality of ring data are grouped multiple times to obtain a plurality of grouping results;

[0013] Determine a grouping priority parameter corresponding to each of the grouping results;

[0014] According to the grouping priority parameter, a plurality of target classification rules and corresponding rule application orders are screened out from the plurality of classification rules;

[0015] Based on the rule application order, the plurality of target classification rules are applied in sequence to group the plurality of ring data to obtain a plurality of ring data sets.

[0016] As an optional implementation, in the first aspect of the present invention, determining the grouping priority parameter corresponding to each of the grouping results includes:

[0017] For each of the grouping results, the grouping result is input into a corresponding trained grouping accuracy prediction model to obtain an accuracy parameter corresponding to the grouping result; the grouping accuracy prediction model is trained by a training data set including a plurality of training grouping results corresponding to the classification rules of the grouping results and corresponding grouping accuracy annotations;

[0018] Calculating a quantity weight inversely proportional to a group quantity parameter corresponding to the grouping result; the group quantity parameter is a degree of deviation between the group quantity in the grouping result and a standard group quantity interval; the interval size of the standard group quantity interval is proportional to the total data volume corresponding to the plurality of ring data;

[0019] Calculating a time weight proportional to the grouping time corresponding to the grouping result;

[0020] The product of the accuracy parameter, the quantity weight and the time weight is calculated to obtain a grouping priority parameter corresponding to each of the grouping results.

[0021] As an optional implementation, in the first aspect of the present invention, the selecting a plurality of target classification rules and the corresponding rule application order from the plurality of classification rules according to the grouping priority parameter comprises:

[0022] According to the grouping priority parameter, all the classification rules are sorted from large to small to obtain a rule sequence;

[0023] Screening all the classification rules of the first first number in the rule sequence and whose grouping priority parameters are greater than a preset parameter threshold, to obtain a plurality of target classification rules;

[0024] The order of the multiple target classification rules in the rule sequence is determined as the corresponding rule application order.

[0025] As an optional implementation, in the first aspect of the present invention, the determining of the prediction processing parameters of each of the ring data sets based on the neural network prediction algorithm includes:

[0026] The predicted processing parameters of each of the ring data sets are input into a trained neural network model to obtain the predicted processing parameters of each of the ring data sets; the neural network model is trained by a training data set including a plurality of training ring data sets and annotated optimal processing parameters; the predicted processing parameters or the optimal processing parameters include processor performance parameters, processing rule parameters, processing node type parameters and processing costs; the processing costs include processing time, processing energy consumption and total processing input and output data volume.

[0027] As an optional implementation, in the first aspect of the present invention, sending each of the ring data sets to a corresponding processing node for data processing according to the prediction processing parameter comprises:

[0028] For each of the finger ring data sets, calculating the matching degree between the processor performance parameter and the processing node type parameter corresponding to the finger ring data set and the corresponding parameter of each candidate processing node, and obtaining the matching parameter corresponding to each of the candidate processing nodes;

[0029] Obtaining historical processing data records corresponding to each candidate processing node;

[0030] Calculate the similarity between the processing rule parameter corresponding to the ring data set and the application rule record in the historical processing data record corresponding to each candidate processing node to obtain a first similarity parameter corresponding to each candidate processing node;

[0031] Calculating the similarity between the processing cost corresponding to the ring data set and the processing cost record in the historical processing data record corresponding to each of the candidate processing nodes, and obtaining a second similarity parameter corresponding to each of the candidate processing nodes;

[0032] Calculating the product of the matching parameter, the first similarity parameter and the second similarity parameter to obtain a node parameter corresponding to each of the candidate processing nodes;

[0033] Determine the candidate processing node with the highest node parameter as the processing node corresponding to the ring data set;

[0034] Each of the ring data sets is sent to a corresponding processing node for data processing.

[0035] A second aspect of an embodiment of the present invention discloses a smart ring data processing system based on data classification processing, the system comprising:

[0036] An acquisition module, used for acquiring multiple ring data sent by multiple smart rings;

[0037] A grouping module, used for grouping the plurality of ring data based on a preset classification rule to obtain a plurality of ring data sets;

[0038] A prediction module, for determining prediction processing parameters of each of the ring data sets based on a neural network prediction algorithm;

[0039] The sending module is used to send each of the ring data sets to a corresponding processing node for data processing according to the predicted processing parameters.

[0040] As an optional implementation, in the second aspect of the present invention, the ring data includes at least one of ring sensing data, ring communication establishment data, ring notification data, ring communication termination data and ring abnormality data.

[0041] As an optional implementation, in the second aspect of the present invention, the classification rules include data volume classification rules, data type classification rules, data source classification rules, data target source classification rules and data purpose classification rules.

[0042] As an optional implementation, in the second aspect of the present invention, the specific manner in which the grouping module groups the plurality of ring data based on a preset classification rule to obtain a plurality of ring data sets includes:

[0043] According to a plurality of preset classification rules, the plurality of ring data are grouped multiple times to obtain a plurality of grouping results;

[0044] Determine a grouping priority parameter corresponding to each of the grouping results;

[0045] According to the grouping priority parameter, a plurality of target classification rules and corresponding rule application orders are screened out from the plurality of classification rules;

[0046] Based on the rule application order, the plurality of target classification rules are applied in sequence to group the plurality of ring data to obtain a plurality of ring data sets.

[0047] As an optional implementation, in the second aspect of the present invention, the specific manner in which the grouping module determines the grouping priority parameter corresponding to each of the grouping results includes:

[0048] For each of the grouping results, the grouping result is input into a corresponding trained grouping accuracy prediction model to obtain an accuracy parameter corresponding to the grouping result; the grouping accuracy prediction model is trained by a training data set including a plurality of training grouping results corresponding to the classification rules of the grouping results and corresponding grouping accuracy annotations;

[0049] Calculating a quantity weight inversely proportional to a group quantity parameter corresponding to the grouping result; the group quantity parameter is a degree of deviation between the group quantity in the grouping result and a standard group quantity interval; the interval size of the standard group quantity interval is proportional to the total data volume corresponding to the plurality of ring data;

[0050] Calculating a time weight proportional to the grouping time corresponding to the grouping result;

[0051] The product of the accuracy parameter, the quantity weight and the time weight is calculated to obtain a grouping priority parameter corresponding to each of the grouping results.

[0052] As an optional implementation, in the second aspect of the present invention, the specific manner in which the grouping module selects multiple target classification rules and the corresponding rule application order from the multiple classification rules according to the grouping priority parameter includes:

[0053] According to the grouping priority parameter, all the classification rules are sorted from large to small to obtain a rule sequence;

[0054] Screening all the classification rules of the first first number in the rule sequence and whose grouping priority parameters are greater than a preset parameter threshold, to obtain a plurality of target classification rules;

[0055] The order of the multiple target classification rules in the rule sequence is determined as the corresponding rule application order.

[0056] As an optional implementation, in the second aspect of the present invention, the prediction module determines the specific manner of the prediction processing parameters of each of the ring data sets based on the neural network prediction algorithm, including:

[0057] The predicted processing parameters of each of the ring data sets are input into a trained neural network model to obtain the predicted processing parameters of each of the ring data sets; the neural network model is trained by a training data set including a plurality of training ring data sets and annotated optimal processing parameters; the predicted processing parameters or the optimal processing parameters include processor performance parameters, processing rule parameters, processing node type parameters and processing costs; the processing costs include processing time, processing energy consumption and total processing input and output data volume.

[0058] As an optional implementation, in the second aspect of the present invention, the specific manner in which the sending module sends each of the ring data sets to a corresponding processing node for data processing according to the prediction processing parameters includes:

[0059] For each of the finger ring data sets, calculating the matching degree between the processor performance parameter and the processing node type parameter corresponding to the finger ring data set and the corresponding parameter of each candidate processing node, and obtaining the matching parameter corresponding to each of the candidate processing nodes;

[0060] Obtaining historical processing data records corresponding to each candidate processing node;

[0061] Calculate the similarity between the processing rule parameter corresponding to the ring data set and the application rule record in the historical processing data record corresponding to each candidate processing node to obtain a first similarity parameter corresponding to each candidate processing node;

[0062] Calculating the similarity between the processing cost corresponding to the ring data set and the processing cost record in the historical processing data record corresponding to each of the candidate processing nodes, and obtaining a second similarity parameter corresponding to each of the candidate processing nodes;

[0063] Calculating the product of the matching parameter, the first similarity parameter and the second similarity parameter to obtain a node parameter corresponding to each of the candidate processing nodes;

[0064] Determine the candidate processing node with the highest node parameter as the processing node corresponding to the ring data set;

[0065] Each of the ring data sets is sent to a corresponding processing node for data processing.

[0066] The third aspect of the present invention discloses another smart ring data processing system based on data classification processing, the system comprising:

[0067] A memory storing executable program code;

[0068] a processor coupled to the memory;

[0069] The processor calls the executable program code stored in the memory to execute part or all of the steps in the smart ring data processing method based on data classification processing disclosed in the first aspect of the present invention.

[0070] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the smart ring data processing method based on data classification processing disclosed in the first aspect of the present invention.

[0071] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0072] The present invention can group multiple ring data according to preset classification rules, and then determine the prediction processing parameters of the ring data set based on the neural network prediction algorithm to send them to the processing nodes with corresponding processing capabilities for data processing, thereby improving the efficiency and effect of processing a large amount of ring data in big data scenarios and reducing processing errors or unnecessary burdens on processing nodes. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0074] Figure 1 It is a flow chart of a smart ring data processing method based on data classification processing disclosed in an embodiment of the present invention.

[0075] Figure 2 It is a structural schematic diagram of a smart ring data processing system based on data classification processing disclosed in an embodiment of the present invention.

[0076] Figure 3 It is a structural schematic diagram of another smart ring data processing system based on data classification processing disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0077] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0078] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0079] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0080] The present invention discloses a smart ring data processing method and system based on data classification processing, which can group multiple ring data according to preset classification rules, and then determine the prediction processing parameters of the ring data set based on a neural network prediction algorithm to send them to a processing node with corresponding processing capabilities for data processing, thereby improving the efficiency and effect of processing a large amount of ring data in a big data scenario, and reducing processing errors or unnecessary burdens on processing nodes. The following are detailed descriptions.

[0081] Embodiment 1

[0082] See also Figure 1 , Figure 1 : is a flow chart of a smart ring data processing method based on data classification processing disclosed in an embodiment of the present invention. Figure 1 The described smart ring data processing method based on data classification processing can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the smart ring data processing method based on data classification processing may include the following operations:

[0083] 101. Acquire multiple ring data sent by multiple smart rings.

[0084] 102. Group the plurality of finger ring data based on a preset classification rule to obtain a plurality of finger ring data sets.

[0085] 103. Based on the neural network prediction algorithm, determine the prediction processing parameters of each ring data set.

[0086] 104. According to the predicted processing parameters, each ring data set is sent to a corresponding processing node for data processing.

[0087] It can be seen that the above-mentioned embodiments of the invention can group multiple ring data according to preset classification rules, and then determine the prediction processing parameters of the ring data set based on the neural network prediction algorithm to send them to the processing nodes with corresponding processing capabilities for data processing, thereby improving the efficiency and effect of processing a large amount of ring data in big data scenarios and reducing processing errors or unnecessary burdens on processing nodes.

[0088] As an optional embodiment, in the above steps, the ring data includes at least one of ring sensing data, ring communication establishment data, ring notification data, ring communication termination data and ring abnormality data.

[0089] It can be seen that through the above optional embodiments, the content of the ring data is clarified, thereby helping to improve the efficiency and effect of processing a large amount of ring data in a big data scenario, and reducing processing errors or unnecessary burdens on processing nodes.

[0090] As an optional embodiment, in the above steps, the classification rules include data volume classification rules, data type classification rules, data source classification rules, data target source classification rules and data purpose classification rules.

[0091] It can be seen that through the above optional embodiments, the types of classification rules are clarified, thereby helping to improve the efficiency and effect of processing a large amount of ring data in big data scenarios and reduce processing errors or unnecessary burdens on processing nodes.

[0092] As an optional embodiment, in the above step, the plurality of ring data are grouped based on a preset classification rule to obtain a plurality of ring data sets, including:

[0093] According to the preset multiple classification rules, the multiple ring data are grouped multiple times to obtain multiple grouping results;

[0094] Determine the grouping priority parameter corresponding to each grouping result;

[0095] According to the grouping priority parameter, multiple target classification rules and corresponding rule application orders are screened out from multiple classification rules;

[0096] Based on the rule application order, multiple target classification rules are applied in sequence to group multiple ring data to obtain multiple ring data sets.

[0097] It can be seen that through the above optional embodiments, it is possible to screen out multiple target classification rules and corresponding rule application orders based on the calculation of the grouping priority parameters corresponding to the grouping results, and then group the multiple ring data in turn to obtain multiple ring data sets, so as to achieve more reasonable data grouping, thereby assisting in improving the efficiency and effect of processing a large amount of ring data in big data scenarios, and reducing processing errors or unnecessary burdens on processing nodes.

[0098] As an optional embodiment, in the above step, determining the grouping priority parameter corresponding to each grouping result includes:

[0099] For each grouping result, the grouping result is input into a corresponding trained grouping accuracy prediction model to obtain an accuracy parameter corresponding to the grouping result; optionally, the grouping accuracy prediction model is trained by a training data set including a plurality of training grouping results corresponding to classification rules of the grouping results and corresponding grouping accuracy annotations;

[0100] Calculate a quantity weight inversely proportional to a group quantity parameter corresponding to the grouping result; optionally, the group quantity parameter is a degree of deviation between the group quantity in the grouping result and a standard group quantity interval; the interval size of the standard group quantity interval is proportional to the total data volume corresponding to the plurality of ring data;

[0101] Calculate the time weight proportional to the grouping time corresponding to the grouping result;

[0102] The product of the accuracy parameter, the quantity weight and the time weight is calculated to obtain the grouping priority parameter corresponding to each grouping result.

[0103] It can be seen that through the above optional embodiments, the grouping priority parameters corresponding to each grouping result can be obtained by predicting the grouping accuracy and calculating the corresponding weights, so as to be used for subsequent screening of multiple target classification rules and the corresponding rule application order, thereby assisting in improving the efficiency and effectiveness of processing large amounts of ring data in big data scenarios, and reducing processing errors or unnecessary burdens on processing nodes.

[0104] As an optional embodiment, in the above steps, multiple target classification rules and corresponding rule application orders are screened out from multiple classification rules according to the grouping priority parameter, including:

[0105] According to the grouping priority parameters, all classification rules are sorted from large to small to obtain a rule sequence;

[0106] Screening all the classification rules of the first number in the rule sequence and whose grouping priority parameters are greater than a preset parameter threshold, to obtain a plurality of target classification rules;

[0107] The order of multiple target classification rules in the rule sequence is determined as the corresponding rule application order.

[0108] It can be seen that through the above optional embodiments, multiple target classification rules and corresponding rule application orders can be screened out from multiple classification rules based on the sorting and screening algorithm according to the grouping priority parameters, thereby assisting in improving the efficiency and effectiveness of processing a large amount of ring data in big data scenarios and reducing processing errors or unnecessary burdens on processing nodes.

[0109] As an optional embodiment, in the above steps, determining the prediction processing parameters of each ring data set based on the neural network prediction algorithm includes:

[0110] The predicted processing parameters of each ring data set are input into the trained neural network model to obtain the predicted processing parameters of each ring data set; optionally, the neural network model is trained by a training data set including multiple training ring data sets and annotated optimal processing parameters; the predicted processing parameters or optimal processing parameters include processor performance parameters, processing rule parameters, processing node type parameters and processing costs; the processing cost includes processing time, processing energy consumption and total processing input and output data volume.

[0111] It can be seen that through the above optional embodiments, the predicted processing parameters of each ring data set can be predicted based on the neural network model trained by the training data set including multiple training ring data sets and annotated optimal processing parameters, so as to be used for subsequent processing node forwarding, thereby improving the efficiency and effect of processing a large amount of ring data in big data scenarios and reducing processing errors or unnecessary burdens on processing nodes.

[0112] As an optional embodiment, in the above steps, sending each ring data set to a corresponding processing node for data processing according to the predicted processing parameters includes:

[0113] For each ring data set, calculate the matching degree between the processor performance parameters and processing node type parameters corresponding to the ring data set and the corresponding parameters of each candidate processing node, and obtain the matching parameters corresponding to each candidate processing node;

[0114] Obtaining historical processing data records corresponding to each candidate processing node;

[0115] Calculate the similarity between the processing rule parameter corresponding to the ring data set and the application rule record in the historical processing data record corresponding to each candidate processing node to obtain a first similarity parameter corresponding to each candidate processing node;

[0116] Calculate the similarity between the processing cost corresponding to the ring data set and the processing cost record in the historical processing data record corresponding to each candidate processing node to obtain a second similarity parameter corresponding to each candidate processing node;

[0117] Calculate the product of the matching parameter, the first similarity parameter and the second similarity parameter to obtain the node parameter corresponding to each candidate processing node;

[0118] Determine the candidate processing node with the highest node parameter as the processing node corresponding to the ring data set;

[0119] Each ring data set is sent to the corresponding processing node for data processing.

[0120] It can be seen that through the above optional embodiments, the processing node corresponding to each ring data set can be determined for data processing based on the calculation of matching parameters, rule similarity and cost similarity, thereby improving the efficiency and effect of processing a large amount of ring data in big data scenarios and reducing processing errors or unnecessary burdens on processing nodes.

[0121] Embodiment 2

[0122] See also Figure 2 , Figure 2 : is a schematic diagram of the structure of a smart ring data processing system based on data classification processing disclosed in an embodiment of the present invention. Figure 2 The described smart ring data processing system based on data classification processing can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the smart ring data processing system based on data classification processing may include:

[0123] The acquisition module 201 is used to acquire multiple ring data sent by multiple smart rings.

[0124] The grouping module 202 is used to group the multiple ring data based on a preset classification rule to obtain multiple ring data sets.

[0125] The prediction module 203 is used to determine the prediction processing parameters of each ring data set based on the neural network prediction algorithm.

[0126] The sending module 204 is used to send each ring data set to a corresponding processing node for data processing according to the predicted processing parameters.

[0127] It can be seen that the above-mentioned embodiments of the invention can group multiple ring data according to preset classification rules, and then determine the prediction processing parameters of the ring data set based on the neural network prediction algorithm to send them to the processing nodes with corresponding processing capabilities for data processing, thereby improving the efficiency and effect of processing a large amount of ring data in big data scenarios and reducing processing errors or unnecessary burdens on processing nodes.

[0128] As an optional embodiment, the ring data includes at least one of ring sensing data, ring communication establishment data, ring notification data, ring communication termination data and ring abnormality data.

[0129] It can be seen that through the above optional embodiments, the content of the ring data is clarified, thereby helping to improve the efficiency and effect of processing a large amount of ring data in a big data scenario, and reducing processing errors or unnecessary burdens on processing nodes.

[0130] As an optional embodiment, the classification rules include data volume classification rules, data type classification rules, data source classification rules, data target source classification rules and data purpose classification rules.

[0131] It can be seen that through the above optional embodiments, the types of classification rules are clarified, thereby helping to improve the efficiency and effect of processing a large amount of ring data in big data scenarios and reduce processing errors or unnecessary burdens on processing nodes.

[0132] As an optional embodiment, the specific manner in which the grouping module groups the plurality of ring data based on a preset classification rule to obtain the plurality of ring data sets includes:

[0133] According to the preset multiple classification rules, the multiple ring data are grouped multiple times to obtain multiple grouping results;

[0134] Determine the grouping priority parameter corresponding to each grouping result;

[0135] According to the grouping priority parameter, multiple target classification rules and corresponding rule application orders are screened out from multiple classification rules;

[0136] Based on the rule application order, multiple target classification rules are applied in sequence to group multiple ring data to obtain multiple ring data sets.

[0137] It can be seen that through the above optional embodiments, it is possible to screen out multiple target classification rules and corresponding rule application orders based on the calculation of the grouping priority parameters corresponding to the grouping results, and then group the multiple ring data in turn to obtain multiple ring data sets, so as to achieve more reasonable data grouping, thereby assisting in improving the efficiency and effect of processing a large amount of ring data in big data scenarios, and reducing processing errors or unnecessary burdens on processing nodes.

[0138] As an optional embodiment, the specific manner in which the grouping module determines the grouping priority parameter corresponding to each grouping result includes:

[0139] For each grouping result, the grouping result is input into a corresponding trained grouping accuracy prediction model to obtain an accuracy parameter corresponding to the grouping result; optionally, the grouping accuracy prediction model is trained by a training data set including a plurality of training grouping results corresponding to classification rules of the grouping results and corresponding grouping accuracy annotations;

[0140] Calculate a quantity weight inversely proportional to a group quantity parameter corresponding to the grouping result; optionally, the group quantity parameter is a degree of deviation between the group quantity in the grouping result and a standard group quantity interval; the interval size of the standard group quantity interval is proportional to the total data volume corresponding to the plurality of ring data;

[0141] Calculate the time weight proportional to the grouping time corresponding to the grouping result;

[0142] The product of the accuracy parameter, the quantity weight and the time weight is calculated to obtain the grouping priority parameter corresponding to each grouping result.

[0143] It can be seen that through the above optional embodiments, the grouping priority parameters corresponding to each grouping result can be obtained by predicting the grouping accuracy and calculating the corresponding weights, so as to be used for subsequent screening of multiple target classification rules and the corresponding rule application order, thereby assisting in improving the efficiency and effectiveness of processing large amounts of ring data in big data scenarios, and reducing processing errors or unnecessary burdens on processing nodes.

[0144] As an optional embodiment, the specific manner in which the grouping module selects multiple target classification rules and the corresponding rule application order from multiple classification rules according to the grouping priority parameter includes:

[0145] According to the grouping priority parameters, all classification rules are sorted from large to small to obtain a rule sequence;

[0146] Screening all the classification rules of the first number in the rule sequence and whose grouping priority parameters are greater than a preset parameter threshold, to obtain a plurality of target classification rules;

[0147] The order of multiple target classification rules in the rule sequence is determined as the corresponding rule application order.

[0148] It can be seen that through the above optional embodiments, multiple target classification rules and corresponding rule application orders can be screened out from multiple classification rules based on the sorting and screening algorithm according to the grouping priority parameters, thereby assisting in improving the efficiency and effectiveness of processing a large amount of ring data in big data scenarios and reducing processing errors or unnecessary burdens on processing nodes.

[0149] As an optional embodiment, the prediction module determines the specific method of the prediction processing parameters of each ring data set based on the neural network prediction algorithm, including:

[0150] The predicted processing parameters of each ring data set are input into the trained neural network model to obtain the predicted processing parameters of each ring data set; optionally, the neural network model is trained by a training data set including multiple training ring data sets and annotated optimal processing parameters; the predicted processing parameters or optimal processing parameters include processor performance parameters, processing rule parameters, processing node type parameters and processing costs; the processing cost includes processing time, processing energy consumption and total processing input and output data volume.

[0151] It can be seen that through the above optional embodiments, the predicted processing parameters of each ring data set can be predicted based on the neural network model trained by the training data set including multiple training ring data sets and annotated optimal processing parameters, so as to be used for subsequent processing node forwarding, thereby improving the efficiency and effect of processing a large amount of ring data in big data scenarios and reducing processing errors or unnecessary burdens on processing nodes.

[0152] As an optional embodiment, the specific manner in which the sending module sends each ring data set to a corresponding processing node for data processing according to the predicted processing parameters includes:

[0153] For each ring data set, calculate the matching degree between the processor performance parameters and processing node type parameters corresponding to the ring data set and the corresponding parameters of each candidate processing node, and obtain the matching parameters corresponding to each candidate processing node;

[0154] Obtaining historical processing data records corresponding to each candidate processing node;

[0155] Calculate the similarity between the processing rule parameter corresponding to the ring data set and the application rule record in the historical processing data record corresponding to each candidate processing node to obtain a first similarity parameter corresponding to each candidate processing node;

[0156] Calculate the similarity between the processing cost corresponding to the ring data set and the processing cost record in the historical processing data record corresponding to each candidate processing node to obtain a second similarity parameter corresponding to each candidate processing node;

[0157] Calculate the product of the matching parameter, the first similarity parameter and the second similarity parameter to obtain the node parameter corresponding to each candidate processing node;

[0158] Determine the candidate processing node with the highest node parameter as the processing node corresponding to the ring data set;

[0159] Each ring data set is sent to the corresponding processing node for data processing.

[0160] It can be seen that through the above optional embodiments, the processing node corresponding to each ring data set can be determined for data processing based on the calculation of matching parameters, rule similarity and cost similarity, thereby improving the efficiency and effect of processing a large amount of ring data in big data scenarios and reducing processing errors or unnecessary burdens on processing nodes.

[0161] Embodiment 3

[0162] See also Figure 3 , Figure 3 This is another smart ring data processing system based on data classification processing disclosed in an embodiment of the present invention. Figure 3 The described smart ring data processing system based on data classification processing is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the smart ring data processing system based on data classification processing may include:

[0163] A memory 301 storing executable program codes;

[0164] a processor 302 coupled to the memory 301;

[0165] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the smart ring data processing method based on data classification processing described in the first embodiment.

[0166] Embodiment 4

[0167] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the smart ring data processing method based on data classification processing described in the first embodiment.

[0168] Embodiment 5

[0169] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the smart ring data processing method based on data classification processing described in the first embodiment.

[0170] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0171] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0172] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0173] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0174] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0175] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0176] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0177] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0178] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0179] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0180] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0181] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0182] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0183] Finally, it should be noted that the smart ring data processing method and system based on data classification processing disclosed in the embodiment of the present invention discloses only the preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A smart ring data processing method based on data classification processing, characterized in that: The method comprises: Obtain multiple ring data sent by multiple smart rings; The plurality of ring data are grouped based on a preset classification rule to obtain a plurality of ring data sets, including: According to a plurality of preset classification rules, the plurality of ring data are grouped multiple times to obtain a plurality of grouping results; For each of the grouping results, the grouping result is input into a corresponding trained grouping accuracy prediction model to obtain an accuracy parameter corresponding to the grouping result; the grouping accuracy prediction model is trained by a training data set including a plurality of training grouping results corresponding to the classification rules of the grouping results and corresponding grouping accuracy annotations; Calculating a quantity weight inversely proportional to a group quantity parameter corresponding to the grouping result; the group quantity parameter is a degree of deviation between the group quantity in the grouping result and a standard group quantity interval; the interval size of the standard group quantity interval is proportional to the total data volume corresponding to the plurality of ring data; Calculating a time weight proportional to the grouping time corresponding to the grouping result; Calculate the product of the accuracy parameter, the quantity weight and the time weight to obtain a grouping priority parameter corresponding to each of the grouping results; According to the grouping priority parameter, a plurality of target classification rules and corresponding rule application orders are screened out from the plurality of classification rules; Based on the rule application order, the plurality of target classification rules are sequentially applied to group the plurality of finger ring data to obtain a plurality of finger ring data sets; Determining prediction processing parameters of each of the ring data sets based on a neural network prediction algorithm includes: Inputting the predicted processing parameters of each of the ring data sets into a trained neural network model to obtain the predicted processing parameters of each of the ring data sets; the neural network model is trained by a training data set including a plurality of training ring data sets and annotated optimal processing parameters; the predicted processing parameters or the optimal processing parameters include processor performance parameters, processing rule parameters, processing node type parameters and processing costs; the processing costs include processing time, processing energy consumption and total processing input and output data volume; According to the prediction processing parameters, each of the ring data sets is sent to a corresponding processing node for data processing, including: For each of the finger ring data sets, calculating the matching degree between the processor performance parameter and the processing node type parameter corresponding to the finger ring data set and the corresponding parameter of each candidate processing node, and obtaining the matching parameter corresponding to each of the candidate processing nodes; Obtaining historical processing data records corresponding to each candidate processing node; Calculate the similarity between the processing rule parameter corresponding to the ring data set and the application rule record in the historical processing data record corresponding to each candidate processing node to obtain a first similarity parameter corresponding to each candidate processing node; Calculating the similarity between the processing cost corresponding to the ring data set and the processing cost record in the historical processing data record corresponding to each of the candidate processing nodes, and obtaining a second similarity parameter corresponding to each of the candidate processing nodes; Calculating the product of the matching parameter, the first similarity parameter and the second similarity parameter to obtain a node parameter corresponding to each of the candidate processing nodes; Determine the candidate processing node with the highest node parameter as the processing node corresponding to the ring data set; Each of the ring data sets is sent to a corresponding processing node for data processing.

2. The smart ring data processing method based on data classification processing according to claim 1 is characterized in that: The ring data includes at least one of ring sensing data, ring communication establishment data, ring notification data, ring communication termination data and ring abnormality data.

3. The smart ring data processing method based on data classification processing according to claim 1 is characterized in that: The classification rules include data volume classification rules, data type classification rules, data source classification rules, data target source classification rules and data purpose classification rules.

4. The smart ring data processing method based on data classification processing according to claim 1 is characterized in that: The step of selecting a plurality of target classification rules and corresponding rule application orders from the plurality of classification rules according to the grouping priority parameter includes: According to the grouping priority parameter, all the classification rules are sorted from large to small to obtain a rule sequence; Screening all the classification rules of the first first number in the rule sequence and whose grouping priority parameters are greater than a preset parameter threshold, to obtain a plurality of target classification rules; The order of the multiple target classification rules in the rule sequence is determined as the corresponding rule application order.

5. A smart ring data processing system based on data classification processing, characterized in that: The system comprises: An acquisition module, used for acquiring multiple ring data sent by multiple smart rings; A grouping module, used for grouping the plurality of ring data based on a preset classification rule to obtain a plurality of ring data sets, including: According to a plurality of preset classification rules, the plurality of ring data are grouped multiple times to obtain a plurality of grouping results; For each of the grouping results, the grouping result is input into a corresponding trained grouping accuracy prediction model to obtain an accuracy parameter corresponding to the grouping result; the grouping accuracy prediction model is trained by a training data set including a plurality of training grouping results corresponding to the classification rules of the grouping results and corresponding grouping accuracy annotations; Calculating a quantity weight inversely proportional to a group quantity parameter corresponding to the grouping result; the group quantity parameter is a degree of deviation between the group quantity in the grouping result and a standard group quantity interval; the interval size of the standard group quantity interval is proportional to the total data volume corresponding to the plurality of ring data; Calculating a time weight proportional to the grouping time corresponding to the grouping result; Calculate the product of the accuracy parameter, the quantity weight and the time weight to obtain a grouping priority parameter corresponding to each of the grouping results; According to the grouping priority parameter, a plurality of target classification rules and corresponding rule application orders are screened out from the plurality of classification rules; Based on the rule application order, the plurality of target classification rules are sequentially applied to group the plurality of finger ring data to obtain a plurality of finger ring data sets; A prediction module, for determining prediction processing parameters of each of the ring data sets based on a neural network prediction algorithm, comprising: Inputting the predicted processing parameters of each of the ring data sets into a trained neural network model to obtain the predicted processing parameters of each of the ring data sets; the neural network model is trained by a training data set including a plurality of training ring data sets and annotated optimal processing parameters; the predicted processing parameters or the optimal processing parameters include processor performance parameters, processing rule parameters, processing node type parameters and processing costs; the processing costs include processing time, processing energy consumption and total processing input and output data volume; A sending module, used for sending each of the ring data sets to a corresponding processing node for data processing according to the prediction processing parameters, comprises: For each of the finger ring data sets, calculating the matching degree between the processor performance parameter and the processing node type parameter corresponding to the finger ring data set and the corresponding parameter of each candidate processing node, and obtaining the matching parameter corresponding to each of the candidate processing nodes; Obtaining historical processing data records corresponding to each candidate processing node; Calculate the similarity between the processing rule parameter corresponding to the ring data set and the application rule record in the historical processing data record corresponding to each candidate processing node to obtain a first similarity parameter corresponding to each candidate processing node; Calculating the similarity between the processing cost corresponding to the ring data set and the processing cost record in the historical processing data record corresponding to each of the candidate processing nodes, and obtaining a second similarity parameter corresponding to each of the candidate processing nodes; Calculating the product of the matching parameter, the first similarity parameter and the second similarity parameter to obtain a node parameter corresponding to each of the candidate processing nodes; Determine the candidate processing node with the highest node parameter as the processing node corresponding to the ring data set; Each of the ring data sets is sent to a corresponding processing node for data processing.

6. A smart ring data processing system based on data classification processing, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the smart ring data processing method based on data classification processing as described in any one of claims 1-4.

Images