Intelligent ring data processing method and system based on multi-sensor data

Abstract

The present invention discloses a data processing method and system for a smart ring based on multi-sensor data, the method comprising: obtaining multiple different types of sensor data of a target user through multiple sensors of a smart ring; based on the correction rules between the sensor data, mutually correcting the multiple different types of sensor data to obtain corrected data; inputting the corrected data into a trained danger prediction model to obtain danger prediction parameters for the target user; and sending a warning message to the mobile terminal of the emergency contact of the target user for warning based on the danger prediction parameters. It can be seen that the present invention can improve the intelligence and accuracy of the smart ring in monitoring the dangerous situation of the user, improve the user experience, and provide timely warnings and help for users in danger.

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 multi-sensor data. Background Art

[0002] Smart rings are wearable electronic devices that are generally equipped with mobile components such as sensors and NFC chips. They can be used in various applications, mainly for tracking daily activities and as peripheral tools to support mobile devices. Most of the existing smart rings are still limited to using a single sensor data to make judgments when monitoring user dangers, so their danger monitoring efficiency is low and the accuracy is also relatively low. 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 multi-sensor data, which can improve the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improve the user experience, and provide timely warnings and assistance to users in danger.

[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 multi-sensor data, the method comprising:

[0005] Acquire multiple different types of sensor data of the target user through multiple sensors of the smart ring;

[0006] Based on a correction rule between the sensor data, mutually correct the multiple different types of sensor data to obtain corrected data;

[0007] Inputting the corrected data into a trained risk prediction model to obtain risk prediction parameters for the target user;

[0008] According to the danger prediction parameters, a warning message is sent to the mobile terminal of the emergency contact of the target user for warning.

[0009] As an optional implementation, in the first aspect of the present invention, the sensor data is position data, sound data, heart rate data, blood sugar data, ring posture data or ring height data.

[0010] As an optional implementation, in the first aspect of the present invention, the mutual correction of the plurality of different types of sensor data to obtain corrected data based on the correction rule between the sensor data includes:

[0011] For any two of the sensor data, determine the data types of the two sensor data;

[0012] According to the data type, determining a sensor data correction rule corresponding to the data type in a preset database;

[0013] According to the sensor data correction rule, the data values ​​of the two sensor data are corrected to obtain corrected data.

[0014] As an optional embodiment, in the first aspect of the present invention, the sensor data correction rule is any one of the normal data association rules corresponding to position and ring height, the normal data association rules corresponding to position and sound, the normal data association rules corresponding to heart rate and blood sugar, and the normal data association rules corresponding to sound and heart rate.

[0015] As an optional implementation, in the first aspect of the present invention, correcting the data values ​​of the two sensor data according to the sensor data correction rule to obtain corrected data includes:

[0016] Acquire a mathematical relationship model corresponding to the mathematical association rule corresponding to the sensor data correction rule;

[0017] Inputting the data value of one of the two sensing data into the mathematical relationship model to obtain a predicted value;

[0018] Calculating a difference between the predicted value and a data value of another one of the two sensing data;

[0019] Determine whether the difference is greater than a preset difference threshold, and if so, mark the two sensor data as abnormal;

[0020] If not, increasing or decreasing the two sensing data based on the difference so that the difference is zero;

[0021] For any of the sensor data, determining whether the number of times the sensor data is marked abnormal is greater than a preset number threshold, and if so, deleting the sensor data;

[0022] All the remaining sensing data are determined as corrected data.

[0023] As an optional implementation, in the first aspect of the present invention, the step of inputting the corrected data into a trained risk prediction model to obtain the risk prediction parameters of the target user includes:

[0024] For each data in the corrected data, according to the data type corresponding to the data, determine a risk prediction neural network model trained based on a training data set of the same data type from a plurality of candidate neural network models;

[0025] The data is input into the risk prediction neural network model to obtain the risk prediction probability corresponding to the output data;

[0026] The risk prediction parameter of the target user is calculated according to the risk prediction probability corresponding to all the data in the corrected data.

[0027] As an optional implementation, in the first aspect of the present invention, the step of calculating the risk prediction parameter of the target user according to the risk prediction probability corresponding to all data in the corrected data includes:

[0028] Calculate the weighted sum average of the risk prediction probabilities corresponding to all the data in the corrected data to obtain the risk prediction parameters of the target user; wherein the weight of the risk prediction probability of each data includes a first weight and a second weight; the first weight is proportional to the amount of the data; the second weight is proportional to the prediction accuracy of the risk prediction neural network model corresponding to the data type of the data in the verification stage.

[0029] As an optional implementation, in the first aspect of the present invention, sending a warning message to a mobile terminal of an emergency contact of the target user for warning according to the danger prediction parameter includes:

[0030] Determine whether the risk prediction parameter is greater than a preset parameter threshold value to obtain a first determination result;

[0031] When the first judgment result is no, no operation is performed;

[0032] When the first judgment result is yes, determining whether the target user has a pre-entered emergency contact, and obtaining a second judgment result;

[0033] When the second judgment result is yes, sending a warning message to the mobile terminal of the emergency contact of the target user for warning;

[0034] When the second judgment result is no, calculating the difference between the risk prediction parameter and the parameter threshold;

[0035] calculating a range value proportional to the difference;

[0036] In the contact sequence of the target user, a plurality of contacts within the number corresponding to the range value are sequentially selected to obtain a plurality of preferred contacts; the contact sequence is obtained by sorting the plurality of contacts of the target user from large to small according to the contact frequency;

[0037] Send a warning message to the mobile terminal of the preferred contact for warning.

[0038] A second aspect of an embodiment of the present invention discloses a smart ring data processing system based on multi-sensor data, the system comprising:

[0039] An acquisition module, used for acquiring multiple different types of sensing data of a target user through multiple sensors of the smart ring;

[0040] A correction module, configured to mutually correct the plurality of different types of sensor data based on a correction rule between the sensor data to obtain corrected data;

[0041] A prediction module, used for inputting the corrected data into a trained risk prediction model to obtain risk prediction parameters of the target user;

[0042] The alarm module is used to send a warning message to the mobile terminal of the emergency contact of the target user for warning according to the danger prediction parameters.

[0043] As an optional implementation, in the second aspect of the present invention, the sensor data is position data, sound data, heart rate data, blood sugar data, ring posture data or ring height data.

[0044] As an optional implementation, in the second aspect of the present invention, the correction module performs mutual correction on the multiple different types of sensor data to obtain corrected data based on the correction rule between the sensor data, including:

[0045] For any two of the sensor data, determine the data types of the two sensor data;

[0046] According to the data type, determining a sensor data correction rule corresponding to the data type in a preset database;

[0047] According to the sensor data correction rule, the data values ​​of the two sensor data are corrected to obtain corrected data.

[0048] As an optional embodiment, in the second aspect of the present invention, the sensor data correction rule is any one of the normal data association rules corresponding to position and ring height, the normal data association rules corresponding to position and sound, the normal data association rules corresponding to heart rate and blood sugar, and the normal data association rules corresponding to sound and heart rate.

[0049] As an optional implementation, in the second aspect of the present invention, the correction module corrects the data values ​​of the two sensor data according to the sensor data correction rule to obtain the corrected data in a specific manner, including:

[0050] Acquire a mathematical relationship model corresponding to the mathematical association rule corresponding to the sensor data correction rule;

[0051] Inputting the data value of one of the two sensing data into the mathematical relationship model to obtain a predicted value;

[0052] Calculating a difference between the predicted value and a data value of another one of the two sensing data;

[0053] Determine whether the difference is greater than a preset difference threshold, and if so, mark the two sensor data as abnormal;

[0054] If not, increasing or decreasing the two sensing data based on the difference so that the difference is zero;

[0055] For any of the sensor data, determining whether the number of times the sensor data is marked abnormal is greater than a preset number threshold, and if so, deleting the sensor data;

[0056] All the remaining sensing data are determined as corrected data.

[0057] As an optional implementation, in the second aspect of the present invention, the prediction module inputs the corrected data into a trained risk prediction model to obtain the specific manner of the risk prediction parameters of the target user, including:

[0058] For each data in the corrected data, according to the data type corresponding to the data, determine a risk prediction neural network model trained based on a training data set of the same data type from a plurality of candidate neural network models;

[0059] Inputting the data into the risk prediction neural network model to obtain the risk prediction probability corresponding to the output data;

[0060] The risk prediction parameter of the target user is calculated according to the risk prediction probability corresponding to all the data in the corrected data.

[0061] As an optional implementation, in the second aspect of the present invention, the prediction module calculates the specific manner of the risk prediction parameter of the target user according to the risk prediction probability corresponding to all data in the corrected data, including:

[0062] Calculate the weighted sum average of the risk prediction probabilities corresponding to all the data in the corrected data to obtain the risk prediction parameters of the target user; wherein the weight of the risk prediction probability of each data includes a first weight and a second weight; the first weight is proportional to the amount of the data; the second weight is proportional to the prediction accuracy of the risk prediction neural network model corresponding to the data type of the data in the verification stage.

[0063] As an optional implementation, in the second aspect of the present invention, the specific manner in which the alarm module sends a warning message to the mobile terminal of the emergency contact of the target user for warning according to the danger prediction parameter includes:

[0064] Determine whether the risk prediction parameter is greater than a preset parameter threshold value to obtain a first determination result;

[0065] When the first judgment result is no, no operation is performed;

[0066] When the first judgment result is yes, determining whether the target user has a pre-entered emergency contact, and obtaining a second judgment result;

[0067] When the second judgment result is yes, sending a warning message to the mobile terminal of the emergency contact of the target user for warning;

[0068] When the second judgment result is no, calculating the difference between the risk prediction parameter and the parameter threshold;

[0069] calculating a range value proportional to the difference;

[0070] In the contact sequence of the target user, a plurality of contacts within the number corresponding to the range value are sequentially selected to obtain a plurality of preferred contacts; the contact sequence is obtained by sorting the plurality of contacts of the target user from large to small according to the contact frequency;

[0071] Send a warning message to the mobile terminal of the preferred contact for warning.

[0072] The third aspect of the present invention discloses another smart ring data processing system based on multi-sensor data, the system comprising:

[0073] A memory storing executable program code;

[0074] a processor coupled to the memory;

[0075] 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 multi-sensor data disclosed in the first aspect of the present invention.

[0076] 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 multi-sensor data disclosed in the first aspect of the present invention.

[0077] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0078] The present invention can predict the user's danger prediction parameters after correction through multiple different types of sensor data obtained by the smart ring, so as to achieve accurate prediction of the user's danger through more accurate data, thereby improving the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improving the user experience, and providing timely warnings and assistance to users in danger. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] 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.

[0080] Figure 1 It is a flow chart of a smart ring data processing method based on multi-sensor data disclosed in an embodiment of the present invention.

[0081] Figure 2 It is a structural schematic diagram of a smart ring data processing system based on multi-sensor data disclosed in an embodiment of the present invention.

[0082] Figure 3 It is a structural schematic diagram of another smart ring data processing system based on multi-sensor data disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0083] 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.

[0084] 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.

[0085] 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.

[0086] The present invention discloses a smart ring data processing method and system based on multi-sensor data, which can predict the user's danger prediction parameters after correction through multiple different types of sensor data obtained by the smart ring, so as to achieve accurate prediction of the user's danger through more accurate data, thereby improving the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improving the user experience, and providing timely warnings and help for the user in danger. The following are detailed descriptions.

[0087] Embodiment 1

[0088] See also Figure 1 , Figure 1 : is a flow chart of a smart ring data processing method based on multi-sensor data disclosed in an embodiment of the present invention. Figure 1 The described smart ring data processing method based on multi-sensor data 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 multi-sensor data may include the following operations:

[0089] 101. Acquire multiple different types of sensor data of the target user through multiple sensors of the smart ring.

[0090] 102. Based on a correction rule between sensor data, multiple different types of sensor data are mutually corrected to obtain corrected data.

[0091] 103. Input the corrected data into the trained risk prediction model to obtain the risk prediction parameters of the target user.

[0092] 104. Send a warning message to the mobile terminal of the emergency contact of the target user according to the danger prediction parameter.

[0093] It can be seen that the above-mentioned embodiments of the invention can predict the user's danger prediction parameters after correction through multiple different types of sensor data obtained by the smart ring, so as to achieve accurate prediction of the user's danger through more accurate data, thereby improving the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improving the user experience, and providing timely warnings and assistance to users in danger.

[0094] As an optional embodiment, in the above steps, the sensor data is position data, sound data, heart rate data, blood sugar data, ring posture data or ring height data.

[0095] It can be seen that through the above optional embodiments, the content of the sensor data is clarified, thereby helping to improve the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improving the user experience, and providing timely warnings and assistance to users in danger.

[0096] As an optional embodiment, in the above steps, based on the correction rule between the sensor data, multiple different types of sensor data are mutually corrected to obtain corrected data, including:

[0097] For any two sensor data, determine the data types of the two sensor data;

[0098] According to the data type, a sensor data correction rule corresponding to the data type is determined in a preset database;

[0099] According to the sensor data correction rule, the data values ​​of the two sensor data are corrected to obtain corrected data.

[0100] It can be seen that through the above-mentioned optional embodiments, the data value of the sensor data can be corrected through the sensor data correction rules corresponding to the data type to obtain more accurate data, thereby helping to improve the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improve the user experience, and provide timely warnings and help for users in danger.

[0101] As an optional embodiment, in the above steps, the sensor data correction rule is any one of the normal data association rules corresponding to position and ring height, the normal data association rules corresponding to position and sound, the normal data association rules corresponding to heart rate and blood sugar, and the normal data association rules corresponding to sound and heart rate.

[0102] It can be seen that through the above optional embodiments, the types of sensor data correction rules are clarified, and the data can be corrected by pre-fitting the correlation between normal different types of data or learning the correction rules to obtain more accurate data, thereby helping to improve the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improve the user experience, and provide timely warnings and help for users in danger.

[0103] As an optional embodiment, in the above steps, according to the sensor data correction rule, correcting the data values ​​of the two sensor data to obtain corrected data includes:

[0104] Obtaining a mathematical relationship model corresponding to a mathematical association rule corresponding to a sensor data correction rule;

[0105] Inputting the data value of one of the two sensing data into the mathematical relationship model to obtain a predicted value;

[0106] calculating a difference between the predicted value and a data value of the other of the two sensor data;

[0107] Determine whether the difference is greater than a preset difference threshold, and if so, mark the two sensor data as abnormal;

[0108] If not, the two sensor data are increased or decreased based on the difference so that the difference is zero;

[0109] For any sensor data, determine whether the number of times the sensor data is marked as abnormal is greater than a preset number threshold, and if so, delete the sensor data;

[0110] All remaining sensor data are determined as corrected data.

[0111] It can be seen that through the above-mentioned optional embodiments, the sensor data can be corrected and screened through the results predicted by the mathematical relationship model to obtain more accurate data, thereby helping to improve the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improve the user experience, and provide timely warnings and help for users in danger.

[0112] As an optional embodiment, in the above step, inputting the corrected data into a trained risk prediction model to obtain the risk prediction parameters of the target user includes:

[0113] For each data in the corrected data, according to the data type corresponding to the data, determine from a plurality of candidate neural network models a risk prediction neural network model trained based on a training data set of the same data type;

[0114] The data is input into a risk prediction neural network model to obtain the risk prediction probability corresponding to the output data;

[0115] According to the risk prediction probabilities corresponding to all the data in the corrected data, the risk prediction parameters of the target user are calculated.

[0116] It can be seen that through the above optional embodiments, the neural network model obtained by training the training data sets of different data types can be used to perform danger prediction on the correction data to improve the accuracy of danger prediction, thereby improving the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improving the user experience, and providing timely warnings and assistance to users in danger.

[0117] As an optional embodiment, in the above step, calculating the risk prediction parameter of the target user according to the risk prediction probability corresponding to all data in the corrected data includes:

[0118] Calculate the weighted sum average of the risk prediction probabilities corresponding to all data in the corrected data to obtain the risk prediction parameters of the target user; optionally, the weight of the risk prediction probability of each data includes a first weight and a second weight; the first weight is proportional to the amount of data; the second weight is proportional to the prediction accuracy of the risk prediction neural network model corresponding to the data type of the data in the verification stage.

[0119] It can be seen that through the above-mentioned optional embodiments, more accurate danger prediction parameters of the target user can be calculated through preset weight calculation and weighted summation, thereby improving the accuracy of danger prediction, thereby improving the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improving the user experience, and providing timely warnings and assistance to users in danger.

[0120] As an optional embodiment, in the above step, sending a warning message to a mobile terminal of an emergency contact of the target user for warning according to the danger prediction parameter includes:

[0121] Determine whether the risk prediction parameter is greater than a preset parameter threshold value to obtain a first determination result;

[0122] When the first judgment result is no, no operation is performed;

[0123] When the first judgment result is yes, determine whether the target user has a pre-entered emergency contact to obtain a second judgment result;

[0124] When the second judgment result is yes, a warning message is sent to the mobile terminal of the emergency contact of the target user to warn;

[0125] When the second judgment result is yes or no, calculating the difference between the risk prediction parameter and the parameter threshold;

[0126] Calculate the range value proportional to the difference;

[0127] In the contact sequence of the target user, multiple contacts within the number corresponding to the range value are sequentially selected to obtain multiple preferred contacts; optionally, the contact sequence is obtained by sorting the multiple contacts of the target user from large to small according to the contact frequency;

[0128] Send a warning message to the mobile terminal of the preferred contact to warn.

[0129] It can be seen that through the above optional embodiments, when the user has no emergency contacts, multiple contacts can be selected based on the degree of urgency for warning to fully achieve the warning effect, thereby improving the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improving the user experience, and providing timely warnings and assistance to users in danger.

[0130] Embodiment 2

[0131] See also Figure 2 , Figure 2 : is a schematic diagram of a smart ring data processing system based on multi-sensor data disclosed in an embodiment of the present invention. Figure 2 The described smart ring data processing system based on multi-sensor data 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 multi-sensor data may include:

[0132] The acquisition module 201 is used to acquire multiple different types of sensing data of the target user through multiple sensors of the smart ring.

[0133] The correction module 202 is used to perform mutual correction on a plurality of different types of sensor data based on a correction rule between the sensor data to obtain corrected data.

[0134] The prediction module 203 is used to input the corrected data into the trained risk prediction model to obtain the risk prediction parameters of the target user.

[0135] The alarm module 204 is used to send a warning message to the mobile terminal of the emergency contact of the target user for warning according to the danger prediction parameters.

[0136] It can be seen that the above-mentioned embodiments of the invention can predict the user's danger prediction parameters after correction through multiple different types of sensor data obtained by the smart ring, so as to achieve accurate prediction of the user's danger through more accurate data, thereby improving the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improving the user experience, and providing timely warnings and assistance to users in danger.

[0137] As an optional embodiment, the sensor data is position data, sound data, heart rate data, blood sugar data, finger ring posture data or finger ring height data.

[0138] It can be seen that through the above optional embodiments, the content of the sensor data is clarified, thereby helping to improve the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improving the user experience, and providing timely warnings and assistance to users in danger.

[0139] As an optional embodiment, the correction module mutually corrects a plurality of different types of sensor data based on the correction rule between the sensor data to obtain the corrected data in a specific manner, including:

[0140] For any two sensor data, determine the data types of the two sensor data;

[0141] According to the data type, a sensor data correction rule corresponding to the data type is determined in a preset database;

[0142] According to the sensor data correction rule, the data values ​​of the two sensor data are corrected to obtain corrected data.

[0143] It can be seen that through the above-mentioned optional embodiments, the data value of the sensor data can be corrected through the sensor data correction rules corresponding to the data type to obtain more accurate data, thereby helping to improve the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improve the user experience, and provide timely warnings and help for users in danger.

[0144] As an optional embodiment, the sensor data correction rule is any one of the normal data association rules corresponding to position and ring height, the normal data association rules corresponding to position and sound, the normal data association rules corresponding to heart rate and blood sugar, and the normal data association rules corresponding to sound and heart rate.

[0145] It can be seen that through the above optional embodiments, the types of sensor data correction rules are clarified, and the data can be corrected by pre-fitting the correlation between normal different types of data or learning the correction rules to obtain more accurate data, thereby helping to improve the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improve the user experience, and provide timely warnings and help for users in danger.

[0146] As an optional embodiment, the correction module corrects the data values ​​of the two sensor data according to the sensor data correction rule to obtain the corrected data in a specific manner including:

[0147] Obtaining a mathematical relationship model corresponding to a mathematical association rule corresponding to a sensor data correction rule;

[0148] Inputting the data value of one of the two sensing data into the mathematical relationship model to obtain a predicted value;

[0149] calculating a difference between the predicted value and a data value of the other of the two sensor data;

[0150] Determine whether the difference is greater than a preset difference threshold, and if so, mark the two sensor data as abnormal;

[0151] If not, the two sensor data are increased or decreased based on the difference so that the difference is zero;

[0152] For any sensor data, determine whether the number of times the sensor data is marked as abnormal is greater than a preset number threshold, and if so, delete the sensor data;

[0153] All remaining sensor data are determined as corrected data.

[0154] It can be seen that through the above-mentioned optional embodiments, the sensor data can be corrected and screened through the results predicted by the mathematical relationship model to obtain more accurate data, thereby helping to improve the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improve the user experience, and provide timely warnings and help for users in danger.

[0155] As an optional embodiment, the prediction module inputs the corrected data into a trained risk prediction model to obtain the specific method of the risk prediction parameters of the target user, including:

[0156] For each data in the corrected data, according to the data type corresponding to the data, determine from a plurality of candidate neural network models a risk prediction neural network model trained based on a training data set of the same data type;

[0157] The data is input into a risk prediction neural network model to obtain the risk prediction probability corresponding to the output data;

[0158] According to the risk prediction probabilities corresponding to all the data in the corrected data, the risk prediction parameters of the target user are calculated.

[0159] It can be seen that through the above optional embodiments, the neural network model obtained by training the training data sets of different data types can be used to perform danger prediction on the correction data to improve the accuracy of danger prediction, thereby improving the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improving the user experience, and providing timely warnings and assistance to users in danger.

[0160] As an optional embodiment, the prediction module calculates the risk prediction parameters of the target user according to the risk prediction probabilities corresponding to all the data in the corrected data in a specific manner, including:

[0161] Calculate the weighted sum average of the risk prediction probabilities corresponding to all data in the corrected data to obtain the risk prediction parameters of the target user; optionally, the weight of the risk prediction probability of each data includes a first weight and a second weight; the first weight is proportional to the amount of data; the second weight is proportional to the prediction accuracy of the risk prediction neural network model corresponding to the data type of the data in the verification stage.

[0162] It can be seen that through the above-mentioned optional embodiments, more accurate danger prediction parameters of the target user can be calculated through preset weight calculation and weighted summation, thereby improving the accuracy of danger prediction, thereby improving the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improving the user experience, and providing timely warnings and assistance to users in danger.

[0163] As an optional embodiment, the specific manner in which the alarm module sends a warning message to the mobile terminal of the emergency contact of the target user according to the danger prediction parameter includes:

[0164] Determine whether the risk prediction parameter is greater than a preset parameter threshold value to obtain a first determination result;

[0165] When the first judgment result is no, no operation is performed;

[0166] When the first judgment result is yes, determining whether the target user has a pre-entered emergency contact, and obtaining a second judgment result;

[0167] When the second judgment result is yes, a warning message is sent to the mobile terminal of the emergency contact of the target user to warn;

[0168] When the second judgment result is yes or no, calculating the difference between the risk prediction parameter and the parameter threshold;

[0169] Calculate the range value proportional to the difference;

[0170] In the contact sequence of the target user, multiple contacts within the number corresponding to the range value are sequentially selected to obtain multiple preferred contacts; optionally, the contact sequence is obtained by sorting the multiple contacts of the target user from large to small according to the contact frequency;

[0171] Send a warning message to the mobile terminal of the preferred contact to warn.

[0172] It can be seen that through the above optional embodiments, when the user has no emergency contacts, multiple contacts can be selected based on the degree of urgency for warning to fully achieve the warning effect, thereby improving the intelligence and accuracy of the smart ring in monitoring the user's dangerous situation, improving the user experience, and providing timely warnings and assistance to users in danger.

[0173] Embodiment 3

[0174] See also Figure 3 , Figure 3 This is another smart ring data processing system based on multi-sensor data disclosed in an embodiment of the present invention. Figure 3 The described smart ring data processing system based on multi-sensor data 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 multi-sensor data may include:

[0175] A memory 301 storing executable program codes;

[0176] a processor 302 coupled to the memory 301;

[0177] 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 multi-sensor data described in the first embodiment.

[0178] Embodiment 4

[0179] 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 multi-sensor data described in the first embodiment.

[0180] Embodiment 5

[0181] 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 multi-sensor data described in the first embodiment.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] Finally, it should be noted that the smart ring data processing method and system based on multi-sensor data 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 multi-sensor data, characterized in that: The method comprises: Acquire multiple different types of sensor data of the target user through multiple sensors of the smart ring; Based on the correction rule between the sensor data, the plurality of different types of sensor data are mutually corrected to obtain corrected data, including: For any two of the sensor data, determine the data types of the two sensor data; According to the data type, determining a sensor data correction rule corresponding to the data type in a preset database; the sensor data correction rule is any one of a normal data association rule corresponding to heart rate and blood sugar and a normal data association rule corresponding to sound and heart rate; Acquire a mathematical relationship model corresponding to the mathematical association rule corresponding to the sensor data correction rule; Inputting the data value of one of the two sensing data into the mathematical relationship model to obtain a predicted value; Calculating a difference between the predicted value and a data value of another one of the two sensing data; Determine whether the difference is greater than a preset difference threshold, and if so, mark the two sensor data as abnormal; If not, increasing or decreasing the two sensing data based on the difference so that the difference is zero; For any of the sensor data, determining whether the number of times the sensor data is marked abnormal is greater than a preset number threshold, and if so, deleting the sensor data; Determine all remaining sensor data as corrected data; Inputting the corrected data into a trained risk prediction model to obtain risk prediction parameters for the target user includes: For each data in the corrected data, according to the data type corresponding to the data, determine a risk prediction neural network model trained based on a training data set of the same data type from a plurality of candidate neural network models; The data is input into the risk prediction neural network model to obtain the risk prediction probability corresponding to the output data; Calculate the weighted sum average of the risk prediction probabilities corresponding to all data in the corrected data to obtain the risk prediction parameter of the target user; wherein the weight of the risk prediction probability of each data includes a first weight and a second weight; the first weight is proportional to the data volume of the data; the second weight is proportional to the prediction accuracy of the risk prediction neural network model corresponding to the data type of the data in the verification phase; According to the danger prediction parameters, a warning message is sent to the mobile terminal of the emergency contact of the target user for warning.

2. The smart ring data processing method based on multi-sensor data according to claim 1 is characterized in that: The sensor data is position data, sound data, heart rate data, blood sugar data, ring posture data or ring height data.

3. The smart ring data processing method based on multi-sensor data according to claim 1 is characterized in that: The step of sending a warning message to a mobile terminal of an emergency contact of the target user for warning according to the danger prediction parameter includes: Determine whether the risk prediction parameter is greater than a preset parameter threshold value to obtain a first determination result; When the first judgment result is no, no operation is performed; When the first judgment result is yes, determining whether the target user has a pre-entered emergency contact, and obtaining a second judgment result; When the second judgment result is yes, sending a warning message to the mobile terminal of the emergency contact of the target user for warning; When the second judgment result is yes or no, calculating the difference between the risk prediction parameter and the parameter threshold; calculating a range value proportional to the difference; In the contact sequence of the target user, a plurality of contacts within the number corresponding to the range value are sequentially selected to obtain a plurality of preferred contacts; the contact sequence is obtained by sorting the plurality of contacts of the target user from large to small according to the contact frequency; Send a warning message to the mobile terminal of the preferred contact for warning.

4. A smart ring data processing system based on multi-sensor data, characterized in that: The system comprises: An acquisition module, used to acquire multiple different types of sensor data of a target user through multiple sensors of the smart ring; A correction module, used for mutually correcting the plurality of different types of sensor data to obtain corrected data based on a correction rule between the sensor data, comprises: For any two of the sensor data, determine the data types of the two sensor data; According to the data type, determining a sensor data correction rule corresponding to the data type in a preset database; the sensor data correction rule is any one of a normal data association rule corresponding to heart rate and blood sugar and a normal data association rule corresponding to sound and heart rate; Acquire a mathematical relationship model corresponding to the mathematical association rule corresponding to the sensor data correction rule; Inputting the data value of one of the two sensing data into the mathematical relationship model to obtain a predicted value; Calculating a difference between the predicted value and a data value of another one of the two sensing data; Determine whether the difference is greater than a preset difference threshold, and if so, mark the two sensor data as abnormal; If not, increasing or decreasing the two sensing data based on the difference so that the difference is zero; For any of the sensor data, determining whether the number of times the sensor data is marked abnormal is greater than a preset number threshold, and if so, deleting the sensor data; Determine all remaining sensor data as corrected data; A prediction module, used to input the corrected data into a trained risk prediction model to obtain risk prediction parameters of the target user, including: For each data in the corrected data, according to the data type corresponding to the data, determine a risk prediction neural network model trained based on a training data set of the same data type from a plurality of candidate neural network models; The data is input into the risk prediction neural network model to obtain the risk prediction probability corresponding to the output data; Calculate the weighted sum average of the risk prediction probabilities corresponding to all data in the corrected data to obtain the risk prediction parameter of the target user; wherein the weight of the risk prediction probability of each data includes a first weight and a second weight; the first weight is proportional to the data volume of the data; the second weight is proportional to the prediction accuracy of the risk prediction neural network model corresponding to the data type of the data in the verification phase; The alarm module is used to send a warning message to the mobile terminal of the emergency contact of the target user for warning according to the danger prediction parameters.

5. A smart ring data processing system based on multi-sensor data, 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 multi-sensor data as described in any one of claims 1-3.

Images