An intelligent bicycle shifting method and system based on sensor data

Abstract

The present invention relates to the technical field of bicycles, and a bicycle intelligent shifting method and system based on sensor data, comprising: obtaining an initial model set of the bicycle, obtaining a plurality of shifting ratio sets based on the initial model set, obtaining a shifting strategy group set based on the plurality of shifting ratio sets and a shifting strategy construction unit, obtaining a target model and a target riding mode, based on the target model and the target riding mode, identifying a target shifting strategy group in the shifting strategy group set, obtaining a driving feature sequence group and a user feature sequence group, using the driving feature sequence group and the user feature sequence group to retrieve a target shifting ratio in the target shifting strategy group, and using the target shifting ratio to adjust the bicycle, so as to realize intelligent shifting of the bicycle. The present invention can improve the accuracy and intelligence level of intelligent shifting of the bicycle.

Description

Technical Field

[0001] The present invention relates to the technical field of bicycles, and in particular, to a bicycle intelligent shifting method and system based on sensor data. Background Art

[0002] With the gradual improvement of environmental protection awareness and fitness awareness, cycling has become a popular short-distance travel mode, entertainment project and hobby. At the same time, with the development of bicycle technology, variable-speed bicycles have gradually changed from traditional means of transportation to multi-functional bicycles integrating functions such as sports, fitness, and tourism and leisure. Correspondingly, how to improve the intelligence level of bicycles has become an urgent problem to be solved.

[0003] Currently, most existing bicycles adopt a shifting system to achieve shifting of the bicycles.

[0004] Although the above method can achieve shifting adjustment of the bicycle, however, when performing shifting adjustment, it only depends on the speed of the bicycle during riding, and the riding intention of the user, the physiological characteristics of the user, and the characteristics of the riding road cannot be considered during adjustment. Therefore, accurately and intelligently achieving shifting adjustment of the bicycle has become an urgent problem to be solved. Summary of the Invention

[0005] The present invention provides a bicycle intelligent shifting method and a computer-readable storage medium based on sensor data, and its main purpose is to improve the accuracy and intelligence level of intelligent shifting of bicycles.

[0006] To achieve the above purpose, a bicycle intelligent shifting method based on sensor data provided by the present invention includes:

[0007] Receiving an intelligent shifting instruction, and confirming an intelligent shifting environment based on the intelligent shifting instruction, where the intelligent shifting environment includes: an intelligent shifting system and an adjustable bicycle, and the intelligent shifting system includes: a target model input unit, a driving feature acquisition unit, a physiological feature acquisition unit, and a shifting strategy construction unit;

[0008] Obtaining an initial model set of the bicycle, where the initial model set includes multiple initial models, and obtaining multiple shifting ratio sets based on the initial model set;

[0009] Obtaining a shifting strategy group set based on the multiple shifting ratio sets and the shifting strategy construction unit, where the shifting strategy group set includes multiple shifting strategy groups marked with riding modes, and each shifting strategy group includes multiple shifting ratios, and the riding modes corresponding to different shifting strategy groups are different;

[0010] The speed shift strategy group set is sent to the initiator of the intelligent speed shift instruction, a target model and a target riding mode confirmed by a user according to the speed shift strategy group set are received by a target model input unit, and a target speed shift strategy group is confirmed in the speed shift strategy group set based on the target model and the target riding mode;

[0011] A driving feature sequence group and a user feature sequence group are acquired by using a driving feature acquisition unit, a physiological feature acquisition unit and a preset detection time interval, wherein the driving feature sequence group includes: a riding speed sequence, a riding acceleration sequence and a riding slope sequence, and the user feature sequence group includes: a user heart rate sequence and a user cadence sequence;

[0012] The driving characteristic sequence group and the user characteristic sequence group are used to retrieve a target speed ratio in a target speed change strategy group, and the bicycle is adjusted using the target speed ratio to achieve intelligent speed change of the bicycle.

[0013] Optionally, acquiring a plurality of speed ratio sets based on the initial model set includes:

[0014] Extract initial models from the initial model set in sequence, and perform the following operations on the extracted initial models:

[0015] Based on the initial model, a front disc tooth number set and a rear disc tooth number set are identified, wherein the front disc tooth number set includes a plurality of front disc tooth numbers, and the rear disc tooth number set includes a plurality of rear disc tooth numbers;

[0016] The front disc tooth numbers are sequentially extracted from the front disc tooth number set, and the following operations are performed on the extracted front disc tooth numbers:

[0017] In a combined form, a plurality of tooth number combination nodes are obtained using the extracted front disc tooth number and rear disc tooth number sets, wherein the tooth number combination node includes a front disc tooth number and a rear disc tooth number;

[0018] For each of the multiple tooth number combination nodes, perform the following operations:

[0019] Calculate the ratio of the number of teeth on the front disc to the number of teeth on the rear disc in the tooth number combination node to obtain a theoretical ratio, summarize the theoretical ratios to obtain a theoretical ratio set, and perform a normalization operation on the theoretical ratios in the theoretical ratio set to obtain a normalized ratio set, wherein the normalized ratio set includes multiple normalized ratios;

[0020] Obtaining a screening ratio range based on the extracted number of front disc teeth, and using the screening ratio range to identify a screening ratio set in the normalized ratio set, wherein the screening ratio set includes a plurality of screening ratios, and all of the screening ratios are within the screening ratio range;

[0021] Summarize the set of screening ratios to obtain a set of shifting ratios, and summarize the set of shifting ratios to obtain multiple sets of shifting ratios.

[0022] Optionally, obtaining a set of shifting strategies based on the multiple sets of shifting ratios and a shifting strategy construction unit includes:

[0023] Confirm receiving a shifting strategy instruction from the shifting strategy construction unit, and parse the shifting strategy instruction to obtain multiple initial cadence ranges;

[0024] In a combined form, use the multiple initial cadence ranges and the multiple sets of shifting ratios to obtain multiple test nodes, and each test node includes an initial cadence range and a shifting ratio;

[0025] Perform the following operations on each of the multiple test nodes:

[0026] Obtain a set of test node timings based on the test node, a preset test interval time, and a preset test period. Among them, the set of test node timings includes multiple test node timings, and the test node timing includes: a test heart rate timing, a test speed timing, and a test cadence timing;

[0027] Perform the following operations on each test node timing in the set of test node timings:

[0028] Based on a pre-constructed sliding window and a sliding step, sequentially extract and analyze the heart rate timing in the test heart rate timing corresponding to the test node, and perform the following operations on the extracted analyzed heart rate timing:

[0029] Obtain an analyzed heart rate variance based on the analyzed heart rate timing, compare the analyzed heart rate variance with a preset heart rate variance threshold. After confirming that the analyzed heart rate variance is less than or equal to the heart rate variance threshold, obtain an analyzed heart rate mean using the analyzed heart rate timing. Based on the analyzed heart rate timing, confirm an analyzed speed mean in the test speed timing and an analyzed cadence mean in the test cadence timing respectively;

[0030] Summarize the analyzed heart rate mean, the analyzed speed mean, and the analyzed cadence mean respectively to obtain an analyzed heart rate mean set, an analyzed speed mean set, and an analyzed cadence mean set. Calculate a target heart rate mean based on the analyzed heart rate mean set, and obtain a target speed mean and a target cadence mean based on the analyzed speed mean set and the analyzed cadence mean set;

[0031] Associate the target heart rate mean, the target speed mean, the shifting ratio, and the target cadence mean to obtain an analyzed associated node;

[0032] Summarize the analyzed associated nodes to obtain an analyzed associated node set, and obtain a set of shifting strategies based on the analyzed associated node set.

[0033] Optionally, calculating the target heart rate average based on the analyzed heart rate average set includes:

[0034] Calculating the average of the analyzed heart rate averages in the analyzed heart rate average set to obtain the parsed heart rate average, and performing the following operations on each analyzed heart rate average in the analyzed heart rate average set:

[0035] Calculating the absolute difference between the analyzed heart rate average and the parsed heart rate average to obtain the offset heart rate, summarizing the offset heart rates to obtain the offset heart rate set, calculating the average of the offset heart rates in the offset heart rate set to obtain the offset heart rate average, and calculating the offset evaluation range based on the offset heart rate average, where the offset evaluation range is as follows:

[0036]

[0037] Where represents the offset evaluation range, are all preset coefficients, represents the offset heart rate average;

[0038] Using the offset evaluation range, identifying the target offset heart rate set in the offset heart rate set, where the target offset heart rate set includes multiple target offset heart rates, and each target offset heart rate in the multiple target offset heart rates satisfies the offset evaluation range;

[0039] Performing the following operations on each target offset heart rate in the target offset heart rate set:

[0040] Associating the target offset heart rate and the analyzed heart rate average corresponding to the target offset heart rate to obtain the parsed heart rate node, summarizing the parsed heart rate nodes to obtain the parsed heart rate node set, and calculating the target heart rate average based on the parsed heart rate node set, and the calculation formula is as follows:

[0041]

[0042] Where represents the target heart rate average, represents that there are parsed heart rate nodes in the parsed heart rate node set, represents the target offset heart rate corresponding to the th parsed heart rate node in the parsed heart rate node set, respectively represent the target offset heart rate and the analyzed heart rate average corresponding to the th parsed heart rate node in the parsed heart rate node set.

[0043] Optionally, obtaining the variable speed strategy group set based on the analyzed association node set includes:

[0044] Obtain the associated range node set of different riding modes, where the associated range node set includes multiple associated range nodes, and the associated range nodes correspond to the riding modes one by one. The associated range nodes include a target heart rate range, a target speed range, and a target cadence range;

[0045] Perform the following operations on each associated range node in the associated range node set:

[0046] Use the associated range node to retrieve in the analysis associated node set to obtain a target parsing node set, where the target parsing node set includes multiple target parsing nodes, and the target heart rate mean, target speed mean, and target cadence mean corresponding to the target parsing nodes are respectively within the target heart rate range, target speed range, and target cadence range corresponding to the associated range node;

[0047] Normalize the target parsing nodes in the target parsing node set according to the associated range node to obtain a normalized parsing node;

[0048] Summarize the normalized parsing nodes to obtain a normalized parsing node set, and use a pre-constructed clustering method to cluster the normalized parsing node set to obtain one or more clustering parsing node sets;

[0049] Perform the following operations on each clustering parsing node set in one or more clustering parsing node sets:

[0050] Use the pre-constructed variable speed ratio range set to divide the clustering parsing nodes in the clustering parsing node set to obtain multiple target clustering parsing node sets, where the variable speed ratio range set includes three variable speed ratio ranges;

[0051] Perform the following operations on each target clustering parsing node set in multiple target clustering parsing node sets:

[0052] Use the variable speed ratio range to obtain the variable speed application name, and use the variable speed application name and the riding mode to identify the target clustering parsing node set corresponding to the variable speed ratio range to obtain a variable speed strategy group, where the variable speed application names include: uphill mode, flat road mode, and downhill mode;

[0053] Summarize the variable speed strategy groups to obtain a variable speed strategy group set.

[0054] Optionally, the retrieving the target variable speed ratio in the target variable speed strategy group by using the driving feature sequence group and the user feature sequence group includes:

[0055] Based on the sliding window and the sliding step, sequentially extract an initial slope sequence in the riding slope sequence corresponding to the driving feature sequence group, where the initial slope sequence includes multiple riding slopes;

[0056] The target shift strategy node is confirmed using the initial slope sequence, where the target shift strategy node is an uphill shift strategy node, a downhill shift strategy node, or a flat road shift strategy node. Using the target shift strategy node, the first shift strategy group is identified in the target shift strategy group, where the first shift strategy group corresponds one-to-one with the shift strategy group;

[0057] Using the driving feature sequence group and the user feature sequence group, the target shift ratio is retrieved in the first shift strategy group.

[0058] Optionally, the confirming the target shift strategy node using the initial slope sequence includes:

[0059] Obtain the screening slope range. Using the screening slope range, classify slopes are screened out in the initial slope sequence, where the classify slopes are not within the screening slope range. After confirming that the classify slope is greater than 0, the classify slope is marked as the uphill slope, and the number of uphill slopes in the initial slope sequence is counted to obtain the uphill quantity;

[0060] Compare the uphill quantity with a preset slope threshold. If the uphill quantity is greater than or equal to the slope threshold, the target uphill slope is identified in the initial slope sequence. Using the target uphill slope, the interval uphill slopes are identified in the initial slope sequence. Based on the interval uphill slopes and the target uphill slope, the uphill interval time is obtained. Compare the uphill interval time with a preset interval time threshold. If the uphill interval time is greater than or equal to the interval time threshold, the interval uphill slope is used as the target uphill slope, and return to the step of identifying the interval uphill slopes in the initial slope sequence using the target uphill slope until it is confirmed that the uphill interval time is less than the interval time threshold. Then, using the target uphill slope, the target uphill time is identified in the initial slope sequence. After confirming that the target uphill time is less than the preset uphill time threshold, return to the step of sequentially extracting the initial slope sequence in the riding slope sequence corresponding to the driving feature sequence group based on the sliding window and the sliding step length until the target uphill time is greater than or equal to the preset uphill time threshold, then the uphill shift strategy node is used as the target shift strategy node;

[0061] Otherwise, based on the screening slope range, confirm that the target shift strategy node is the downhill shift strategy node;

[0062] Otherwise, confirm that the target shift strategy node is the flat road shift strategy node.

[0063] Optionally, before retrieving the target shift ratio in the first shift strategy group using the driving feature sequence group and the user feature sequence group, further includes:

[0064] After confirming that the target shifting strategy node corresponding to the first shifting strategy group is the uphill shifting strategy node, an analysis acceleration sequence is confirmed from the riding acceleration sequence by using a preset evaluation acceleration value, where the analysis acceleration sequence includes a plurality of analysis accelerations;

[0065] Analytical accelerations are sequentially extracted from the analysis acceleration sequence, and the following operations are performed on the extracted analytical accelerations:

[0066] Based on the analytical acceleration, a decomposed acceleration is confirmed from the analysis acceleration sequence, and a first decomposed acceleration is calculated based on the decomposed acceleration and the detection time interval. The calculation formula is as follows:

[0067]

[0068] Wherein, represents the first decomposed acceleration, represents the decomposed acceleration, represents the analytical acceleration, represents the detection time interval;

[0069] Based on the first decomposed acceleration, a first decomposed acceleration sequence is obtained, and the mean value of the decomposed acceleration is obtained by using the first decomposed acceleration sequence. The mean value of the decomposed acceleration is compared with a preset decomposed acceleration threshold. If the mean value of the decomposed acceleration is greater than or equal to the decomposed acceleration threshold, the target shifting ratio is retrieved from the first shifting strategy group by using the driving feature sequence group and the user feature sequence group.

[0070] Optionally, the retrieving the target shifting ratio from the first shifting strategy group by using the driving feature sequence group and the user feature sequence group includes:

[0071] The target user heart rate, the target user cadence, and the target riding speed are respectively confirmed from the driving feature sequence group and the user feature sequence group;

[0072] The evaluation differences between the target user heart rate, the target user cadence, and the target riding speed and the analysis correlation nodes in the first shifting strategy group are calculated. The calculation formula is as follows:

[0073]

[0074] Wherein, represents the evaluation difference, are all preset coefficients, respectively represent the target user heart rate and the target heart rate mean value, respectively represent the target riding speed and the target speed mean value, respectively represent the target user cadence and the target cadence mean value;

[0075] Summarize the evaluation differences to obtain an evaluation difference set, and confirm a target speed change ratio based on the evaluation difference set, where the target speed change ratio is the speed change ratio corresponding to the smallest evaluation difference in the evaluation difference set.

[0076] To achieve the above object, the present invention also provides a bicycle intelligent speed change system based on sensor data, including:

[0077] A speed change environment confirmation module, configured to receive an intelligent speed change instruction and confirm an intelligent speed change environment based on the intelligent speed change instruction, where the intelligent speed change environment includes: an intelligent speed change system and an adjustment bicycle, and the intelligent speed change system includes: a target model input unit, a driving feature acquisition unit, a physiological feature acquisition unit, and a speed change strategy construction unit;

[0078] A speed change strategy construction module, configured to obtain an initial model set of the bicycle, where the initial model set includes multiple initial models, and obtain multiple speed change ratio sets based on the initial model set;

[0079] Obtain a speed change strategy group set based on the multiple speed change ratio sets and the speed change strategy construction unit, where the speed change strategy group set includes multiple speed change strategy groups marked with riding modes, and each speed change strategy group includes multiple speed change ratios, and different speed change strategy groups correspond to different riding modes;

[0080] Send the speed change strategy group set to the initiator of the intelligent speed change instruction, use the target model input unit to receive the target model and the target riding mode confirmed by the user according to the speed change strategy group set, and confirm the target speed change strategy group in the speed change strategy group set based on the target model and the target riding mode;

[0081] A riding feature acquisition module, configured to respectively use the driving feature acquisition unit, the physiological feature acquisition unit, and a preset detection time interval to obtain a driving feature sequence group and a user feature sequence group, where the driving feature sequence group includes: a riding speed sequence, a riding acceleration sequence, and a riding slope sequence, and the user feature sequence group includes: a user heart rate sequence and a user pedal frequency sequence;

[0082] A speed change strategy confirmation module, configured to use the driving feature sequence group and the user feature sequence group to retrieve a target speed change ratio in the target speed change strategy group, and use the target speed change ratio to adjust the adjustment bicycle to achieve intelligent speed change of the bicycle.

[0083] To solve the above problems, the present invention also provides an electronic device, and the electronic device includes:

[0084] A memory, storing at least one instruction; and a processor, executing the instruction stored in the memory to implement the above-mentioned bicycle intelligent speed change method based on sensor data.

[0085] To solve the above problems, the present invention further provides a computer-readable storage medium storing at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned bicycle intelligent shifting method based on sensor data.

[0086] To solve the problems described in the background art, the present invention receives an intelligent shifting instruction and determines an intelligent shifting environment based on the intelligent shifting instruction. The intelligent shifting environment includes an intelligent shifting system and an adjustable bicycle. The intelligent shifting system includes a target model input unit, a driving feature acquisition unit, a physiological feature acquisition unit, and a shifting strategy construction unit. It can be seen that when the present invention determines the intelligent shifting environment, it determines the driving feature acquisition unit for acquiring driving features and the physiological feature acquisition unit for acquiring physiological features. Furthermore, it lays a foundation for subsequent intelligent shifting of the bicycle by combining physiological features and driving features. By adopting the form of combining physiological features and driving features, the intelligence level of the present invention is improved. The present invention obtains a set of shifting strategy groups based on the multiple sets of shifting ratios and the shifting strategy construction unit. The set of shifting strategy groups includes multiple shifting strategy groups marked with riding modes, and each shifting strategy group includes multiple shifting ratios, and the riding modes corresponding to different shifting strategy groups are different. The set of shifting strategy groups is sent to the initiating end of the intelligent shifting instruction. The target model input unit is used to receive the target model and the target riding mode confirmed by the user according to the set of shifting strategy groups. Based on the target model and the target riding mode, the target shifting strategy group is determined in the set of shifting strategy groups. It can be seen that the present invention constructs shifting strategy groups applicable to different types of bicycles before determining the target model and the target riding mode, and also considers integrating different riding modes before constructing the shifting strategy groups. Furthermore, the accuracy of the constructed shifting strategy groups is improved. Through the form of human-computer interaction, the riding mode required by the user is determined. Furthermore, the intelligence level of the present invention is improved. The present invention respectively uses the driving feature acquisition unit, the physiological feature acquisition unit, and a preset detection time interval to obtain a driving feature sequence group and a user feature sequence group. The driving feature sequence group includes a riding speed sequence, a riding acceleration sequence, and a riding slope sequence. The user feature sequence group includes a user heart rate sequence and a user cadence sequence. Using the driving feature sequence group and the user feature sequence group, the target shifting ratio is retrieved in the target shifting strategy group. The adjustable bicycle is adjusted using the target shifting ratio to achieve intelligent shifting of the bicycle. It can be seen that before performing the adjustment, the present invention also considers the physiological characteristics and riding features of the user during riding and can avoid over-adjustment. Furthermore, the accuracy and intelligence level of shifting adjustment of the bicycle are improved. Therefore, the present invention can improve the accuracy and intelligence level of intelligent shifting of the bicycle. Description of the Drawings

[0087] Figure 1 It is a schematic flowchart of a bicycle intelligent shifting method based on sensor data provided by an embodiment of the present invention;

[0088] Figure 2 It is one of the schematic flowcharts of a bicycle intelligent shifting method based on sensor data provided by an embodiment of the present invention;

[0089] Figure 3 It is another schematic flowchart of a bicycle intelligent shifting method based on sensor data provided by an embodiment of the present invention;

[0090] Figure 4 It is a functional module diagram of a bicycle intelligent shifting system based on sensor data provided by an embodiment of the present invention;

[0091] Figure 5 It is a schematic structural diagram of an electronic device for implementing the bicycle intelligent shifting method based on sensor data provided by an embodiment of the present invention.

[0092] Description of the Reference Numerals:

[0093] 1. Electronic device; 10. Processor; 11. Memory; 12. Bus.

[0094] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed Embodiments

[0095] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0096] An embodiment of the present application provides a bicycle intelligent shifting method based on sensor data. The execution subject of the bicycle intelligent shifting method based on sensor data includes, but is not limited to, at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the bicycle intelligent shifting method based on sensor data can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to: a single server, a server cluster, a cloud server, or a cloud server cluster, etc.

[0097] Referring to Figure 1 As shown, it is a schematic flowchart of a bicycle intelligent shifting method based on sensor data provided by an embodiment of the present invention. In this embodiment, the bicycle intelligent shifting method based on sensor data includes:

[0098] S1. Receive an intelligent shifting instruction, and confirm an intelligent shifting environment based on the intelligent shifting instruction. The intelligent shifting environment includes an intelligent shifting system and an adjustable bicycle. The intelligent shifting system includes a target model input unit, a driving feature acquisition unit, a physiological feature acquisition unit, and a shifting strategy construction unit.

[0099] It should be explained that the intelligent shifting instruction is an instruction issued to achieve intelligent shifting of the adjustable bicycle. The intelligent shifting environment refers to the necessary environment for achieving intelligent shifting of the adjustable bicycle. The intelligent shifting environment includes an intelligent shifting system and an adjustable bicycle. Among them, the adjustable bicycle refers to the bicycle to be intelligently shifted, and the intelligent shifting system refers to a small program or APP used to achieve intelligent shifting of the adjustable bicycle. The intelligent shifting system includes a target model input unit, a driving feature acquisition unit, a physiological feature acquisition unit, and a shifting strategy construction unit. For the specific applications of the units, please refer to the subsequent embodiments. The main purpose of the present invention is to improve the user experience of the rider.

[0100] Exemplarily, in order to improve the experience during riding, the rider of the adjustable bicycle, before riding the adjustable bicycle, connects to the intelligent shifting system through a mobile phone, selects a riding mode on the mobile phone, and then starts riding. The adjustable bicycle can intelligently adjust the gear of the adjustable bicycle in combination with the physiological characteristics of the rider and the characteristics during riding to improve the sense of experience of the rider.

[0101] S2. Obtain an initial model set of the bicycle. The initial model set includes multiple initial models, and obtain multiple shifting ratio sets based on the initial model set.

[0102] It can be understood that the initial model refers to the model of the bicycle. The initial models obtained in the embodiments of the present invention refer to the models of bicycles that can use the intelligent shifting environment to achieve intelligent shifting of the bicycle.

[0103] Further, the obtaining of multiple shifting ratio sets based on the initial model set includes:

[0104] Sequentially extract the initial models from the initial model set, and perform the following operations on the extracted initial models:

[0105] Confirm a front sprocket tooth number set and a rear sprocket tooth number set based on the initial model. The front sprocket tooth number set includes multiple front sprocket tooth numbers, and the rear sprocket tooth number set includes multiple rear sprocket tooth numbers;

[0106] Sequentially extract the front sprocket tooth numbers from the front sprocket tooth number set, and perform the following operations on all the extracted front sprocket tooth numbers:

[0107] In combination, use the extracted front sprocket tooth numbers and rear sprocket tooth number sets to obtain a plurality of tooth number combination nodes, where a tooth number combination node includes a front sprocket tooth number and a rear sprocket tooth number;

[0108] Perform the following operations on each tooth number combination node among the plurality of tooth number combination nodes:

[0109] Calculate the ratio of the front sprocket tooth number to the rear sprocket tooth number in the tooth number combination node to obtain a theoretical ratio, summarize the theoretical ratios to obtain a theoretical ratio set, and perform a normalization operation on the theoretical ratios in the theoretical ratio set to obtain a normalized ratio set, where the normalized ratio set includes a plurality of normalized ratios;

[0110] Based on the extracted front sprocket tooth numbers, obtain a screening ratio range, and use the screening ratio range to identify a screening ratio set in the normalized ratio set, where the screening ratio set includes a plurality of screening ratios, and the screening ratios are all within the screening ratio range;

[0111] Summarize the screening ratio set to obtain a speed change ratio set, and summarize the speed change ratio set to obtain a plurality of speed change ratio sets.

[0112] It should be explained that the front sprocket tooth number refers to the tooth number of the chainring of a bicycle, and the rear sprocket tooth number refers to the tooth number of the freewheel of a bicycle. Generally, by adjusting the front sprocket tooth number and the rear sprocket tooth number, the tooth ratio of the bicycle can be changed, and further, the torque that the bicycle can output can be adjusted.

[0113] It can be understood that not all the theoretical ratios in the theoretical ratio set have corresponding effects. Therefore, in the embodiments of the present invention, first, a screening ratio range is obtained according to the front sprocket tooth number, and then the screening ratio range is used to identify a screening ratio set in the normalized ratio set, so as to improve the accuracy of the obtained screening ratios. Generally, when riding a bicycle, it should be avoided to ride in a form of matching a larger front sprocket tooth number with a larger rear sprocket tooth number, that is, to avoid matching a chainring with a larger tooth number with a freewheel with a larger tooth number. Similarly, it should also be avoided to ride in a form of matching a smaller front sprocket tooth number with a smaller rear sprocket tooth number to improve the riding efficiency and reduce mechanical wear. Optionally, the analytic hierarchy process and a pre-constructed detection index set are used to evaluate different combinations of tooth number combination nodes to screen out different tooth number combination situations in the tooth number combination nodes, and further, to improve the accuracy of obtaining the screening ratio range. The detection index set can be set by experience, and the same effect can be achieved by using other methods, which will not be elaborated here.

[0114] It should be explained that the normalization operation refers to an operation of mapping a value to between 0 and 1. Optionally, the min-max normalization is used as the normalization operation, and the same effect can be achieved by using other techniques, which will not be elaborated here.

[0115] S3. Obtain a set of shifting strategy groups based on the multiple shifting ratio sets and the shifting strategy construction unit, where the set of shifting strategy groups includes multiple shifting strategy groups marked with riding modes, and each shifting strategy group includes multiple shifting ratios, and the riding modes corresponding to different shifting strategy groups are different.

[0116] It should be noted that, referring to Figure 2 as shown, the obtaining of the set of shifting strategy groups based on the multiple shifting ratio sets and the shifting strategy construction unit includes:

[0117] S31. Confirm the receipt of a shifting strategy instruction from the shifting strategy construction unit, and parse the shifting strategy instruction to obtain multiple initial cadence ranges;

[0118] S32. In a combined form, use the multiple initial cadence ranges and the multiple shifting ratio sets to obtain multiple test nodes, and each test node includes an initial cadence range and a shifting ratio;

[0119] S33. Perform the following operations on each test node among the multiple test nodes:

[0120] Obtain a set of test node timings based on the test node, a preset test interval time, and a preset test period, where the set of test node timings includes multiple test node timings, and the test node timing includes: a test heart rate timing, a test speed timing, and a test cadence timing;

[0121] S34. Perform the following operations on each test node timing in the set of test node timings:

[0122] Based on a pre-constructed sliding window and a sliding step, sequentially extract and analyze the heart rate timing in the test heart rate timing corresponding to the test node, and perform the following operations on the extracted analyzed heart rate timing:

[0123] Obtain an analyzed heart rate variance based on the analyzed heart rate timing, compare the analyzed heart rate variance with a preset heart rate variance threshold, after confirming that the analyzed heart rate variance is less than or equal to the heart rate variance threshold, obtain an analyzed heart rate mean using the analyzed heart rate timing, and based on the analyzed heart rate timing, confirm an analyzed speed mean in the test speed timing and an analyzed cadence mean in the test cadence timing respectively;

[0124] S35. Aggregate the analyzed heart rate mean, the analyzed speed mean, and the analyzed cadence mean respectively to obtain an analyzed heart rate mean set, an analyzed speed mean set, and an analyzed cadence mean set, calculate a target heart rate mean based on the analyzed heart rate mean set, and obtain a target speed mean and a target cadence mean based on the analyzed speed mean set and the analyzed cadence mean set;

[0125] S36. Associate the target heart rate mean, target speed mean, speed change ratio, and target cadence mean to obtain an analysis association node;

[0126] Summarize the analysis association nodes to obtain an analysis association node set, and obtain a set of shifting strategies based on the analysis association node set.

[0127] It can be understood that the initial cadence range refers to the pre-set cadence range. Optionally, the initial cadence range is 80 to 100 beats per minute. Generally, different initial cadence ranges can be applicable to different needs. For example, for the purpose of physical exercise, the initial cadence range should be 80 to 100 beats per minute, while for the purpose of leisure sightseeing, the initial cadence range can be 60 to 70 beats per minute. Optionally, the initial cadence range is set based on experience.

[0128] Furthermore, the test heart rate time series refers to the sequence obtained by sorting the heart rates obtained by performing heart rate tests at each test interval time within the test period in the order of time from the earliest to the latest. The methods for obtaining the test speed time series and the test cadence time series are the same as the method for obtaining the test heart rate time series, and will not be elaborated here. For example, recruit a large number of volunteers, keep the cadence within the initial cadence range during the test, and obtain a test node time series set. The test period is 5 minutes and the test time interval is 5 seconds. Then, within the test period, measure the heart rate, speed, and cadence every 5 seconds, and sort the heart rate, speed, and cadence respectively in the order of time from the earliest to the latest corresponding to the obtained heart rate, speed, and cadence to obtain the test heart rate time series, test speed time series, and test cadence time series. Among them, each volunteer corresponds to a test node time series set. Optionally, measure the cadence through a cadence sensor, measure the speed through a speed sensor, and measure the heart rate through a sports watch. Obviously, when conducting the test, the environment suitable for different gears needs to be considered. For example, when using a gear with a relatively small theoretical ratio for climbing, the test should be conducted on a road with a certain slope.

[0129] It is understandable that a sliding window refers to a window that can extract a fixed number of data in a time series. Optionally, a window with a fixed size is used as the sliding window, and the sliding step length refers to the step length of moving the sliding window each time. For example, the test heart rate time series includes 10 test heart rates, and the 10 test heart rates are respectively: 80 bpm, 83 bpm, 86 bpm, 90 bpm, 93 bpm, 95 bpm, 99 bpm, 103 bpm, 106 bpm, and 110 bpm. The size of the sliding window used is 3, and the sliding step length is 1. Then, using the sliding window and the sliding step length, multiple analyzed heart rate time series can be sequentially extracted from the test heart rate time series. Among them, the multiple analyzed heart rate time series are respectively: (80 bpm, 83 bpm, 86 bpm), (83 bpm, 86 bpm, 90 bpm), (86 bpm, 90 bpm, 93 bpm), and so on. Generally, in the initial stage of cycling, due to the warm-up stage, the heart rate of the cyclist may continuously increase. After the cyclist warms up, under the conditions of the initial cadence range and the test period, the heart rate of the cyclist should be in a relatively stable state, which means that the analyzed heart rate variance is less than or equal to the heart rate variance threshold. The analyzed heart rate variance refers to the variance of multiple test heart rates in the analyzed heart rate time series. The analyzed heart rate mean refers to the mean of multiple test heart rates in the analyzed heart rate time series.

[0130] It should be explained that in the embodiment of the present invention, the time period corresponding to the analyzed heart rate time series is the same as the time period corresponding to the analyzed speed mean and the time period corresponding to the analyzed cadence mean. Therefore, the analyzed speed time series and the analyzed cadence time series can be confirmed from the test speed time series and the test cadence time series respectively through the analyzed heart rate time series. The mean of multiple speeds in the analyzed speed time series is calculated to obtain the analyzed speed mean, and the mean of multiple cadences in the analyzed cadence time series is calculated to obtain the analyzed cadence mean. In the embodiment of the present invention, the purpose of obtaining the target heart rate mean, the target speed mean, and the target cadence mean is: to obtain the heart rate, speed, and cadence suitable for the cyclist under actual tests, and further improve the accuracy of variable speed adjustment of the bicycle in the subsequent actual cycling environment. The method for obtaining the target speed mean and the method for obtaining the target cadence mean are the same as the method for obtaining the target heart rate mean, and will not be elaborated here.

[0131] It is understandable that calculating the target heart rate mean based on the set of analyzed heart rate means includes:

[0132] Calculating the mean of the analyzed heart rate means in the set of analyzed heart rate means to obtain the parsed heart rate mean, and performing the following operations on each analyzed heart rate mean in the set of analyzed heart rate means:

[0133] Calculate the absolute difference between the calculated average heart rate and the analyzed average heart rate to obtain the offset heart rate. Aggregate the offset heart rates to obtain an offset heart rate set. Calculate the average value of the offset heart rates in the offset heart rate set to obtain the offset heart rate average value. Based on the offset heart rate average value, calculate the offset evaluation range, where the offset evaluation range is as follows:

[0134]

[0135] Among them, represents the offset evaluation range, are all preset coefficients, represents the offset heart rate average value;

[0136] Use the offset evaluation range to identify a target offset heart rate set in the offset heart rate set. Among them, the target offset heart rate set includes multiple target offset heart rates, and each target offset heart rate among the multiple target offset heart rates satisfies the offset evaluation range;

[0137] Perform the following operations on each target offset heart rate in the target offset heart rate set:

[0138] Associate the target offset heart rate and the analyzed average heart rate corresponding to the target offset heart rate to obtain an analyzed heart rate node. Aggregate the analyzed heart rate nodes to obtain an analyzed heart rate node set. Calculate the target heart rate average value based on the analyzed heart rate node set. The calculation formula is as follows:

[0139]

[0140] Among them, represents the target heart rate average value, represents that there are a total of analyzed heart rate nodes in the analyzed heart rate node set, represents the target offset heart rate corresponding to the th analyzed heart rate node in the analyzed heart rate node set, respectively represent the target offset heart rate and the analyzed average heart rate corresponding to the th analyzed heart rate node in the analyzed heart rate node set.

[0141] It should be noted that the analyzed average heart rates obtained by cyclists with different exercise habits and different physiques are different. Therefore, in the embodiments of the present invention, the offset evaluation range is determined by the offset heart rate, and the target offset heart rate set is obtained through the offset evaluation range, which can improve the universality of the obtained target offset heart rate set, that is, the target offset heart rates in the target offset heart rate set can represent the heart rates of most cyclists in a specific cycling situation.

[0142] It should be understood that in the embodiments of the present invention, weights are constructed based on the target offset heart rates in the heart rate nodes, such that the smaller the target offset heart rate, the larger the average analysis heart rate corresponding to the target offset heart rate. Furthermore, the universality of the obtained target average heart rate is improved.

[0143] Further, obtaining the variable speed strategy group set based on the analysis association node set includes:

[0144] Obtaining the associated range node sets of different riding modes, where each associated range node set includes multiple associated range nodes, and the associated range nodes correspond one-to-one with the riding modes. The associated range nodes include a target heart rate range, a target speed range, and a target cadence range;

[0145] Performing the following operations on each associated range node in the associated range node set:

[0146] Using the associated range node to retrieve in the analysis association node set to obtain a target parsing node set, where the target parsing node set includes multiple target parsing nodes, and the average target heart rate, average target speed, and average target cadence corresponding to the target parsing nodes are respectively within the target heart rate range, target speed range, and target cadence range corresponding to the associated range node;

[0147] Performing a normalization operation on the target parsing nodes in the target parsing node set according to the associated range node to obtain a normalized parsing node;

[0148] Summarizing the normalized parsing nodes to obtain a normalized parsing node set, and clustering the normalized parsing node set using a pre-constructed clustering method to obtain one or more clustered parsing node sets;

[0149] Performing the following operations on each clustered parsing node set in the one or more clustered parsing node sets:

[0150] Using a pre-constructed variable speed ratio range set to divide the clustered parsing nodes in the clustered parsing node set to obtain multiple target clustered parsing node sets, where the variable speed ratio range set includes three variable speed ratio ranges;

[0151] Performing the following operations on each target clustered parsing node set in the multiple target clustered parsing node sets:

[0152] Using the variable speed ratio range to obtain a variable speed application name, and using the variable speed application name and the riding mode to label the target clustered parsing node set corresponding to the variable speed ratio range to obtain a variable speed strategy group, where the variable speed application names include: uphill mode, flat road mode, and downhill mode;

[0153] Summarizing the variable speed strategy groups to obtain a variable speed strategy group set.

[0154] It should be explained that the riding mode refers to the mode that can be selected by the rider before riding. The riding mode can be obtained by manual setting. Obviously, different riding modes can achieve different effects. Therefore, different associated range nodes can be obtained through different riding modes. The target heart rate range, target speed range, and target cadence range in the associated range nodes can all be set in advance. For the sake of easy understanding, only the target heart rate range is taken as an example here. For example, when it is set to the fat burning stage, the required heart rate range should be maintained between 110 bpm and 140 bpm. Therefore, the riding mode is designated as the fat burning mode corresponding to the fat burning stage, and the target heart rate range corresponding to this riding mode is set to 110 bpm to 140 bpm.

[0155] It can be understood that the analysis association node set includes analysis association nodes corresponding to different test nodes. Therefore, the target analysis association node set that meets the conditions can be retrieved from the analysis association node set by using the associated range nodes. Normalizing the target analysis nodes in the target analysis node set according to the associated range nodes means: respectively normalizing the target heart rate mean value corresponding to the target analysis node by using the target heart rate range, normalizing the target speed mean value corresponding to the target analysis node by using the target speed range, and normalizing the target cadence mean value corresponding to the target analysis node by using the target cadence range, and then obtaining the target analysis nodes. The method of normalizing the target analysis nodes in the target analysis node set according to the associated range nodes is the same as the method of normalizing the theoretical ratios in the theoretical ratio set to obtain the normalized ratio set. The difference is that the maximum and minimum values in the corresponding range need to be extracted from the associated range nodes before normalizing the target analysis nodes, and the normalization operation is performed by using these maximum and minimum values.

[0156] It should be explained that the data in the normalized analysis nodes are all between 0 and 1. The purpose of normalizing the target analysis nodes is to improve the accuracy of clustering the target analysis nodes, that is, to eliminate the influence of different data in terms of numerical values, so as to improve the accuracy of the constructed variable speed strategy set. Optionally, the k-means clustering algorithm is used as the clustering method. The same effect can be achieved by using other technologies, which will not be elaborated here. For example, there are 200 normalized analysis nodes in the normalized analysis node set. Using the k-means clustering algorithm can cluster the normalized analysis nodes in the normalized analysis node set into 10 clusters, and each cluster contains normalized analysis nodes that form a clustering analysis node set.

[0157] It should be understood that the variable speed ratio range refers to the range of theoretical ratios set for different purposes according to theoretical ratios. For example, when going uphill, since a theoretical ratio with a larger torque is adopted, the range composed of the theoretical ratios with a larger torque is the variable speed ratio range. The variable speed application name is the name corresponding to the variable speed ratio range, and both the variable speed ratio range and the variable speed application name can be set artificially. For example, when adopting the theoretical ratio with a larger torque, the theoretical ratio corresponding to this case is defined as: climbing gear, and here, the climbing gear is the variable speed application name.

[0158] Furthermore, through clustering, the target clustering analysis nodes corresponding to different variable speed application names under different riding modes can be obtained. For example, when the riding mode is the fat burning mode, through clustering, the target clustering analysis nodes corresponding to climbing, downhill, and flat road riding applicable in the fat burning mode can be obtained. The purpose of identifying the target clustering analysis node set using the variable speed application name and the riding mode is to distinguish different riding modes and the road conditions applicable to different theoretical ratios under different riding modes, and thus improve the accuracy of intelligent variable speed adjustment of the bicycle. For example: there are three target clustering analysis node sets, and the riding mode corresponding to the three target clustering analysis node sets is the fat burning mode, and the variable speed application names are respectively: climbing mode, flat road mode, and downhill mode. Then, using the variable speed application name and the riding mode to identify the target clustering analysis node set respectively can identify the three target clustering analysis node sets as: fat burning mode - climbing mode - target clustering analysis node set, fat burning mode - flat road mode - target clustering analysis node set, fat burning mode - downhill mode - target clustering analysis node set.

[0159] S4. Send the variable speed strategy group set to the initiator of the intelligent variable speed instruction, receive the target model and the target riding mode confirmed by the user according to the variable speed strategy group set using the target model input unit, and based on the target model and the target riding mode, confirm the target variable speed strategy group in the variable speed strategy group set.

[0160] It should be explained that the target model refers to the model of the bicycle selected by the user in the intelligent variable speed system, and the target riding mode refers to the riding mode selected by the user according to the variable speed strategy group set. According to the target model and the target riding mode, the variable speed strategy group with the same target model and the same target riding mode can be confirmed in the variable speed strategy group set. Here, the variable speed strategy group is the target variable speed strategy group. For example: the riding mode selected by the rider is the fat burning mode, then in the variable speed strategy group set, the variable speed ratio sets corresponding to the fat burning mode - uphill mode, fat burning mode - downhill mode, and fat burning mode - downhill mode of a specific model bicycle can be confirmed.

[0161] S5. Obtain a driving feature sequence group and a user feature sequence group by using a driving feature acquisition unit, a physiological feature acquisition unit, and a preset detection time interval respectively. The driving feature sequence group includes: a cycling speed sequence, a cycling acceleration sequence, and a cycling slope sequence. The user feature sequence group includes: a user heart rate sequence and a user cadence sequence.

[0162] It can be understood that the cycling speed sequence refers to the sequence composed of cycling speeds. The cycling speed refers to the speed of the user when adjusting the bicycle during cycling. The cycling acceleration sequence refers to the sequence composed of cycling accelerations. The cycling acceleration refers to the acceleration of the user when adjusting the bicycle during cycling. The cycling slope sequence refers to the sequence composed of cycling slopes. The cycling slope refers to the slope of the user when adjusting the bicycle during cycling. The user heart rate sequence refers to the sequence composed of user heart rates. The user heart rate refers to the heart rate of the user detected when adjusting the bicycle during cycling. The user cadence sequence refers to the sequence composed of user cadences. The user cadence refers to the cadence of the user detected when adjusting the bicycle during cycling.

[0163] S6. Use the driving feature sequence group and the user feature sequence group to retrieve a target shifting ratio in the target shifting strategy group, and use the target shifting ratio to adjust the adjustable bicycle to achieve intelligent shifting of the bicycle.

[0164] It should be explained that the step of using the driving feature sequence group and the user feature sequence group to retrieve a target shifting ratio in the target shifting strategy group includes:

[0165] Based on the sliding window and the sliding step, successively extract an initial slope sequence from the cycling slope sequence corresponding to the driving feature sequence group, where the initial slope sequence includes multiple cycling slopes;

[0166] Use the initial slope sequence to confirm a target shifting strategy node. The target shifting strategy node is an uphill shifting strategy node, a downhill shifting strategy node, or a flat road shifting strategy node. Use the target shifting strategy node to identify a first shifting strategy group in the target shifting strategy group, where the first shifting strategy group corresponds one-to-one to the shifting strategy group;

[0167] Use the driving feature sequence group and the user feature sequence group to retrieve a target shifting ratio in the first shifting strategy group.

[0168] It is understandable that the method for obtaining the initial slope sequence is the same as that for analyzing the heart rate time series and can achieve the same effect, which will not be elaborated here. Here, the purpose of setting the uphill speed change strategy node, downhill speed change strategy node, and flat road speed change strategy node is to screen out different first speed change strategy groups in different theoretical ratios, so as to combine with the driving characteristic sequence group and user characteristic sequence group to realize the intelligent speed change of the bicycle.

[0169] It should be understood that there is a one-to-one correspondence between the first speed change strategy group and the speed change strategy group. That is, when the target speed change strategy node is the uphill speed change strategy node, the first speed change strategy group is the speed change strategy group corresponding to the uphill mode; when the target speed change strategy node is the downhill speed change strategy node, the first speed change strategy group is the speed change strategy group corresponding to the downhill mode; when the target speed change strategy node is the flat road speed change strategy node, the first speed change strategy group is the speed change strategy group corresponding to the flat road mode.

[0170] It is understandable that referring to Figure 3 as shown, the method for confirming the target speed change strategy node by using the initial slope sequence includes:

[0171] S61. Obtain the screening slope range, and use the screening slope range to screen out the classified slopes in the initial slope sequence. Among them, if the classified slope is not within the screening slope range and it is confirmed that the classified slope is greater than 0, then mark the classified slope as the uphill slope, and count the number of uphill slopes in the initial slope sequence to obtain the uphill quantity;

[0172] S62. Compare the uphill quantity with the preset slope threshold. If the uphill quantity is greater than or equal to the slope threshold, then identify the target uphill slope in the initial slope sequence, use the target uphill slope to identify the interval uphill slope in the initial slope sequence, obtain the uphill interval time based on the interval uphill slope and the target uphill slope, compare the uphill interval time with the preset interval time threshold. If the uphill interval time is greater than or equal to the interval time threshold, then use the interval uphill slope as the target uphill slope, and return to the step of using the target uphill slope to identify the interval uphill slope in the initial slope sequence until it is confirmed that all uphill interval times are less than the interval time threshold. Then, use the target uphill slope to identify the target uphill time in the initial slope sequence. After confirming that the target uphill time is less than the preset uphill time threshold, return to the step of sequentially extracting the initial slope sequence in the riding slope sequence corresponding to the driving characteristic sequence group based on the sliding window and the sliding step length until the target uphill time is greater than or equal to the preset uphill time threshold, then use the uphill speed change strategy node as the target speed change strategy node;

[0173] S63. Otherwise, based on the screening slope range, confirm that the target speed change strategy node is the downhill speed change strategy node;

[0174] S64. Otherwise, confirm that the target shifting strategy node is a flat road shifting strategy node.

[0175] It should be explained that the screening slope range refers to the range used to determine whether the bicycle is on a slope when the user is riding a bicycle. Optionally, the screening slope range is from -5 degrees to 5 degrees. Here, the plus and minus signs are only used to confirm uphill or downhill. When the slope of the bicycle during driving is greater than 0 degrees, it is determined that the bicycle is going uphill. On the contrary, it is determined that the bicycle is going downhill. When the number of uphill slopes is greater than or equal to the slope threshold, it is determined that when the user is riding a bicycle, the bicycle is generally in the uphill stage. Here, the uphill stage may be composed of multiple bumpy sections. Therefore, after confirming that the number of uphill slopes is greater than or equal to the slope threshold, it is also necessary to determine whether the section corresponding to the number of uphill slopes is an uphill section. Obviously, if the section is not refined and identified, and the bicycle is adjusted for shifting, it may lead to over-adjustment of the bicycle for adjustment, and further, the user experience is reduced.

[0176] It can be understood that the definition of the interval uphill slope is the same as the definition of the target uphill slope, and the interval uphill slope is adjacent to and lags behind the target uphill slope. Obviously, the present invention sets a detection time interval. Therefore, the time interval between the two can be obtained through the interval uphill slope and the target uphill slope. When the uphill interval time is greater than or equal to the interval time threshold, it is determined that the section traveled by the bicycle is a bumpy section. Therefore, it is necessary to return to the step of judging whether the section is an uphill section. Here, it is: taking the interval uphill slope as the target uphill slope, and returning to the step of identifying the interval uphill slope in the initial slope sequence by using the target uphill slope.

[0177] Furthermore, the target uphill time is the absolute difference between the time corresponding to the first target uphill slope and the time corresponding to the last target uphill slope among multiple target uphill slopes, and the uphill interval time corresponding to two adjacent target uphill slopes among multiple target uphill slopes is less than the uphill time threshold. When the target uphill time is greater than or equal to the uphill time threshold, it is determined that the section traveled by the adjusted bicycle is still an uphill section. Therefore, the adjusted bicycle can be adjusted to improve the user experience.

[0178] It should be explained that the method for confirming the downhill shifting strategy node is the same as the method for confirming the uphill shifting strategy node. The difference is that the downhill shifting strategy node refers to confirming that the section traveled by the adjusted bicycle is a downhill section. The flat road shifting strategy node is the complement of the uphill shifting strategy node and the downhill shifting strategy node. It is not difficult to understand that in the embodiments of the present invention, the user is detected by the detection time interval. Therefore, the obtained driving feature sequence group and user feature sequence group will be updated with the test data.

[0179] Further, before retrieving the target shift ratio in the first shift strategy group by using the driving feature sequence group and the user feature sequence group, the following steps are also included:

[0180] After confirming that the target shift strategy node corresponding to the first shift strategy group is an uphill shift strategy node, an analysis acceleration sequence is confirmed in the riding acceleration sequence by using a preset evaluation acceleration value, where the analysis acceleration sequence includes multiple analysis accelerations;

[0181] Successively extract the parsing accelerations in the analysis acceleration sequence, and perform the following operations on the extracted parsing accelerations:

[0182] Based on the parsing acceleration, a decomposed acceleration is confirmed in the analysis acceleration sequence, and a first decomposed acceleration is calculated based on the decomposed acceleration and the detection time interval. The calculation formula is as follows:

[0183]

[0184] Wherein, represents the first decomposed acceleration, represents the decomposed acceleration, represents the parsing acceleration, represents the detection time interval;

[0185] Based on the first decomposed acceleration, a first decomposed acceleration sequence is obtained, and a decomposed acceleration mean value is obtained by using the first decomposed acceleration sequence. Compare the decomposed acceleration mean value with a preset decomposed acceleration threshold. If the decomposed acceleration mean value is greater than or equal to the decomposed acceleration threshold, then use the driving feature sequence group and the user feature sequence group to retrieve the target shift ratio in the first shift strategy group.

[0186] It can be understood that the purpose of setting the evaluation acceleration value is to identify whether the user has the will to accelerate in the current situation. The decomposed acceleration is adjacent to the parsing acceleration and lags behind the parsing acceleration. Generally, the time corresponding to the analysis accelerations in the confirmed analysis acceleration sequence is the closest to the current time, so as to characterize the current will of the rider. The number of the multiple analysis accelerations is the evaluation acceleration value.

[0187] Further, retrieving the target shift ratio in the first shift strategy group by using the driving feature sequence group and the user feature sequence group includes:

[0188] Respectively confirm the target user heart rate, target user cadence, and target riding speed in the driving feature sequence group and the user feature sequence group;

[0189] Calculate the target user's heart rate, target user's cadence, and target riding speed and the evaluation difference between the analysis-related nodes in the first speed change strategy group. The calculation formula is as follows:

[0190]

[0191] in, represents the evaluation difference, are all preset coefficients. Respectively represent the target user heart rate and the target heart rate mean, They represent the target riding speed and the target speed mean, respectively. They represent the target user cadence and the target cadence mean respectively;

[0192] The evaluation differences are summarized to obtain an evaluation difference set, and a target speed ratio is determined based on the evaluation difference set, wherein the target speed ratio is the speed ratio corresponding to the smallest evaluation difference in the evaluation difference set.

[0193] It is understandable that the target user heart rate is obtained by using the sliding window to obtain the latest user heart rate sequence in the user heart rate sequence, wherein the user heart rate sequence includes multiple user heart rates, and the average of the multiple user heart rates in the user heart rate sequence is calculated to obtain the target user heart rate. The target user cadence and target riding speed are obtained in the same way as the target user heart rate, which will not be described here. Generally speaking, the user's physical condition needs to be considered before adjusting the gear of the bicycle, so as to provide the user with a gear that is more in line with the user's wishes and the user's physical condition, thereby improving the intelligence level of the embodiment of the present invention.

[0194] Further, the adjusting the bicycle by using the target speed ratio includes:

[0195] The target speed ratio is sent to the initiator of the intelligent speed change instruction, and after confirming the receipt of the confirmation instruction issued by the user according to the target speed ratio, the bicycle is adjusted using the target speed ratio.

[0196] It is understandable that when realizing intelligent speed shifting of the adjustable bicycle, factors such as the physical condition of the rider or user during actual riding and road conditions must also be considered. Therefore, in the embodiment of the present invention, the confirmed target speed ratio needs to be sent to the user. When the user confirms the use of the target speed ratio, the gear used by the adjustable bicycle can be adjusted to the target speed ratio.

[0197] To solve the problems described in the background art, the present invention receives an intelligent speed change instruction and determines an intelligent speed change environment based on the intelligent speed change instruction. The intelligent speed change environment includes an intelligent speed change system and an adjustable bicycle. The intelligent speed change system includes a target model input unit, a driving feature acquisition unit, a physiological feature acquisition unit, and a speed change strategy construction unit. It can be seen that when the present invention determines the intelligent speed change environment, it determines the driving feature acquisition unit for acquiring driving features and the physiological feature acquisition unit for acquiring physiological features. Furthermore, it lays a foundation for realizing intelligent speed change of the bicycle by combining physiological features and driving features in the subsequent process. By adopting the form of combining physiological features and driving features, the intelligence level of the present invention is improved. The present invention obtains a set of speed change strategy groups based on the multiple sets of speed change ratios and the speed change strategy construction unit. Among them, the set of speed change strategy groups includes multiple speed change strategy groups marked with riding modes, and each speed change strategy group includes multiple speed change ratios, and the riding modes corresponding to different speed change strategy groups are different. The set of speed change strategy groups is sent to the initiating end of the intelligent speed change instruction. The target model input unit is used to receive the target model and the target riding mode confirmed by the user according to the set of speed change strategy groups. Based on the target model and the target riding mode, the target speed change strategy group is determined in the set of speed change strategy groups. It can be seen that the present invention constructs speed change strategy groups applicable to different types of bicycles before determining the target model and the target riding mode, and also considers integrating different riding modes before constructing the speed change strategy groups. Furthermore, the accuracy of the constructed speed change strategy groups is improved. Through the form of human-computer interaction, the riding mode required by the user is confirmed, and thus the intelligence level of the present invention is improved. The present invention respectively uses the driving feature acquisition unit, the physiological feature acquisition unit, and a preset detection time interval to obtain a driving feature sequence group and a user feature sequence group. The driving feature sequence group includes a riding speed sequence, a riding acceleration sequence, and a riding slope sequence. The user feature sequence group includes a user heart rate sequence and a user pedal frequency sequence. Using the driving feature sequence group and the user feature sequence group, the target speed change ratio is retrieved in the target speed change strategy group. The adjustable bicycle is adjusted using the target speed change ratio to realize intelligent speed change of the bicycle. It can be seen that before performing the adjustment, the present invention also considers the physiological characteristics and riding features of the user during riding and can avoid over-adjustment. Furthermore, the accuracy and intelligence level of speed change adjustment of the bicycle are improved. Therefore, the present invention can improve the accuracy and intelligence level of intelligent speed change of the bicycle.

[0198] As Figure 4 shown, it is a functional module diagram of a bicycle intelligent speed change system based on sensor data provided by an embodiment of the present invention.

[0199] The bicycle intelligent variable speed system 100 based on sensor data according to the present invention can be installed in an electronic device. According to the functions achieved, the bicycle intelligent variable speed system 100 based on sensor data can include a variable speed environment confirmation module 101, a variable speed strategy construction module 102, a riding feature acquisition module 103, and a variable speed strategy confirmation module 104. The modules in the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, and are stored in the memory of the electronic device.

[0200] The variable speed environment confirmation module 101 is configured to receive an intelligent variable speed instruction and confirm an intelligent variable speed environment based on the intelligent variable speed instruction. The intelligent variable speed environment includes an intelligent variable speed system and an adjustable bicycle, and the intelligent variable speed system includes a target model input unit, a driving feature acquisition unit, a physiological feature acquisition unit, and a variable speed strategy construction unit.

[0201] The variable speed strategy construction module 102 is configured to obtain an initial model set of the bicycle. The initial model set includes multiple initial models, and multiple variable speed ratio sets are obtained based on the initial model set.

[0202] A variable speed strategy group set is obtained based on the multiple variable speed ratio sets and the variable speed strategy construction unit. The variable speed strategy group set includes multiple variable speed strategy groups marked with riding modes, and each variable speed strategy group includes multiple variable speed ratios, and the riding modes corresponding to different variable speed strategy groups are different.

[0203] The variable speed strategy group set is sent to the initiating end of the intelligent variable speed instruction, and the target model and the target riding mode confirmed by the user according to the variable speed strategy group set are received by using the target model input unit. Based on the target model and the target riding mode, the target variable speed strategy group is confirmed in the variable speed strategy group set.

[0204] The riding feature acquisition module 103 is configured to respectively obtain a driving feature sequence group and a user feature sequence group by using the driving feature acquisition unit, the physiological feature acquisition unit, and a preset detection time interval. The driving feature sequence group includes a riding speed sequence, a riding acceleration sequence, and a riding slope sequence, and the user feature sequence group includes a user heart rate sequence and a user cadence sequence.

[0205] The variable speed strategy confirmation module 104 is configured to retrieve a target variable speed ratio in the target variable speed strategy group by using the driving feature sequence group and the user feature sequence group, and use the target variable speed ratio to adjust the adjustable bicycle to realize intelligent variable speed of the bicycle.

[0206] Specifically, when the modules in the bicycle intelligent shifting system 100 based on sensor data in the embodiments of the present invention are used, they adopt the same technical means as those in the Figure 1 bicycle intelligent shifting method based on sensor data described above, and can achieve the same technical effects, which will not be elaborated here.

[0207] As Figure 5 shown, it is a schematic structural diagram of an electronic device for implementing the bicycle intelligent shifting method based on sensor data provided by an embodiment of the present invention.

[0208] The electronic device 1 may include a processor 10, a memory 11, and a bus 12, and may further include a computer program stored in the memory 11 and executable on the processor 10, such as a program for the bicycle intelligent shifting method based on sensor data.

[0209] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disc, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as the mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 1. Further, the memory 11 also includes the internal storage unit of the electronic device 1 and the external storage device. The memory 11 can not only be used to store application software installed on the electronic device 1 and various types of data, such as the code of the program for the bicycle intelligent shifting method based on sensor data, but also be used to temporarily store data that has been output or will be output.

[0210] In some embodiments, the processor 10 may be composed of an integrated circuit. For example, it may be composed of a single packaged integrated circuit, or may be composed of multiple packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, connecting various components of the entire electronic device through various interfaces and lines, and by running or executing programs or modules stored in the memory 11 (such as a program for a bicycle intelligent shifting method based on sensor data, etc.), and calling data stored in the memory 11, to perform various functions of the electronic device 1 and process data.

[0211] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is set to enable connection communication between the memory 11 and at least one processor 10, etc.

[0212] Figure 5 Only the electronic device with components is shown. Those skilled in the art can understand that, Figure 5 the shown structure does not constitute a limitation on the electronic device 1, and it may include fewer or more components than shown, or combine certain components, or have a different component arrangement.

[0213] For example, although not shown, the electronic device 1 may further include a power supply (such as a battery) for powering each component. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management system, so as to implement functions such as charge management, discharge management, and power consumption management through the power management system. The power supply may also include any components such as one or more DC or AC power supplies, a recharge system, a power failure detection circuit, a power converter or inverter, a power status indicator, etc. The electronic device 1 may also include various sensors, a Bluetooth module, a Wi-Fi module, etc., which will not be elaborated here.

[0214] Furthermore, the electronic device 1 may further include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used to establish a communication connection between the electronic device 1 and other electronic devices.

[0215] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display the information processed in the electronic device 1 and to display a visual user interface.

[0216] The program of the bicycle intelligent shifting method based on sensor data stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can implement:

[0217] Receiving an intelligent shifting instruction, and confirming an intelligent shifting environment based on the intelligent shifting instruction, where the intelligent shifting environment includes: an intelligent shifting system and an adjustable bicycle, and the intelligent shifting system includes: a target model input unit, a driving feature acquisition unit, a physiological feature acquisition unit, and a shifting strategy construction unit;

[0218] Obtaining an initial model set of the bicycle, where the initial model set includes multiple initial models, and obtaining multiple shifting ratio sets based on the initial model set;

[0219] Obtaining a shifting strategy group set based on the multiple shifting ratio sets and the shifting strategy construction unit, where the shifting strategy group set includes multiple shifting strategy groups marked with riding modes, and each shifting strategy group includes multiple shifting ratios, and the riding modes corresponding to different shifting strategy groups are different;

[0220] Sending the shifting strategy group set to the initiating end of the intelligent shifting instruction, using the target model input unit to receive the target model and the target riding mode confirmed by the user according to the shifting strategy group set, and confirming a target shifting strategy group in the shifting strategy group set based on the target model and the target riding mode;

[0221] Respectively using the driving feature acquisition unit, the physiological feature acquisition unit, and a preset detection time interval to obtain a driving feature sequence group and a user feature sequence group, where the driving feature sequence group includes: a riding speed sequence, a riding acceleration sequence, and a riding slope sequence, and the user feature sequence group includes: a user heart rate sequence and a user pedal frequency sequence;

[0222] Using the driving feature sequence group and the user feature sequence group, retrieve a target shifting ratio in the target shifting strategy group, and use the target shifting ratio to adjust the adjustable bicycle, so as to realize intelligent shifting of the bicycle.

[0223] Specifically, for the specific implementation method of the above instructions by the processor 10, reference may be made to Figures 1 to 5 the description of the relevant steps in the corresponding embodiment, which will not be elaborated here.

[0224] Furthermore, if the modules / units integrated in the electronic device 1 are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or system capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory).

[0225] The present invention also provides a computer-readable storage medium, where the readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, it can implement:

[0226] Receiving an intelligent shifting instruction, and confirming an intelligent shifting environment based on the intelligent shifting instruction, where the intelligent shifting environment includes: an intelligent shifting system and an adjustable bicycle, and the intelligent shifting system includes: a target model input unit, a driving feature acquisition unit, a physiological feature acquisition unit, and a shifting strategy construction unit;

[0227] Obtaining an initial model set of the bicycle, where the initial model set includes multiple initial models, and obtaining multiple shifting ratio sets based on the initial model set;

[0228] Obtaining a shifting strategy group set based on the multiple shifting ratio sets and the shifting strategy construction unit, where the shifting strategy group set includes multiple shifting strategy groups marked with riding modes, and each shifting strategy group includes multiple shifting ratios, and the riding modes corresponding to different shifting strategy groups are different;

[0229] Sending the shifting strategy group set to the initiating end of the intelligent shifting instruction, receiving, by using the target model input unit, a target model and a target riding mode confirmed by the user according to the shifting strategy group set, and confirming a target shifting strategy group in the shifting strategy group set based on the target model and the target riding mode;

[0230] The driving feature acquisition unit, physiological feature acquisition unit and a preset detection time interval are respectively used to obtain a driving feature sequence group and a user feature sequence group. The driving feature sequence group includes: a cycling speed sequence, a cycling acceleration sequence and a cycling slope sequence. The user feature sequence group includes: a user heart rate sequence and a user cadence sequence;

[0231] The driving feature sequence group and the user feature sequence group are used to retrieve a target shifting ratio in a target shifting strategy group, and the target shifting ratio is used to adjust the bicycle, so as to realize intelligent shifting of the bicycle.

[0232] In several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and there may be other partitioning methods in actual implementation.

[0233] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0234] In addition, in each embodiment of the present invention, the functional modules can be integrated in a processing unit, or each unit exists physically alone, or two or more units are integrated in one unit. The above integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional modules.

[0235] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0236] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A bicycle intelligent speed change method based on sensor data, characterized in that, The method includes: Receiving an intelligent shifting instruction, and confirming an intelligent shifting environment based on the intelligent shifting instruction, where the intelligent shifting environment includes: an intelligent shifting system and an adjustable bicycle, and the intelligent shifting system includes: a target model input unit, a driving feature acquisition unit, a physiological feature acquisition unit, and a shifting strategy construction unit; Obtaining an initial model set of the bicycle, where the initial model set includes multiple initial models, and obtaining multiple shifting ratio sets based on the initial model set; The obtaining multiple shifting ratio sets based on the initial model set includes: Sequentially extracting initial models from the initial model set, and performing the following operations on the extracted initial models: Confirming a front sprocket tooth number set and a rear sprocket tooth number set based on the initial model, where the front sprocket tooth number set includes multiple front sprocket tooth numbers, and the rear sprocket tooth number set includes multiple rear sprocket tooth numbers; Sequentially extracting front sprocket tooth numbers from the front sprocket tooth number set, and performing the following operations on each of the extracted front sprocket tooth numbers: Obtaining multiple tooth number combination nodes in a combined form by using the extracted front sprocket tooth number and the rear sprocket tooth number set, where each tooth number combination node includes a front sprocket tooth number and a rear sprocket tooth number; Performing the following operations on each tooth number combination node in the multiple tooth number combination nodes: Calculating the ratio of the front sprocket tooth number to the rear sprocket tooth number in the tooth number combination node to obtain a theoretical ratio, summarizing the theoretical ratios to obtain a theoretical ratio set, and performing a normalization operation on the theoretical ratios in the theoretical ratio set to obtain a normalized ratio set, where the normalized ratio set includes multiple normalized ratios; Obtaining a screening ratio range based on the extracted front sprocket tooth number, and using the screening ratio range to confirm a screening ratio set in the normalized ratio set, where the screening ratio set includes multiple screening ratios, and the screening ratios are all within the screening ratio range; Summarizing the screening ratio set to obtain a shifting ratio set, and summarizing the shifting ratio sets to obtain multiple shifting ratio sets; Obtaining a shifting strategy group set based on the multiple shifting ratio sets and the shifting strategy construction unit, where the shifting strategy group set includes multiple shifting strategy groups marked with riding modes, and each shifting strategy group includes multiple shifting ratios, and the riding modes corresponding to different shifting strategy groups are different; Sending the shifting strategy group set to the initiating end of the intelligent shifting instruction, receiving, by using the target model input unit, a target model and a target riding mode confirmed by the user according to the shifting strategy group set, and confirming a target shifting strategy group in the shifting strategy group set based on the target model and the target riding mode; Respectively using the driving feature acquisition unit, the physiological feature acquisition unit, and a preset detection time interval to obtain a driving feature sequence group and a user feature sequence group, where the driving feature sequence group includes: a riding speed sequence, a riding acceleration sequence, and a riding slope sequence, and the user feature sequence group includes: a user heart rate sequence and a user cadence sequence; Using the driving feature sequence group and the user feature sequence group to retrieve a target shifting ratio in the target shifting strategy group, and using the target shifting ratio to adjust the adjustable bicycle to achieve intelligent shifting of the bicycle.

2. The bicycle intelligent shifting method based on sensor data according to claim 1, wherein, The obtaining of the set of shifting strategy groups based on the multiple shifting ratio sets and the shifting strategy construction unit includes: Confirm the receipt of the shifting strategy instruction from the shifting strategy construction unit, and parse the shifting strategy instruction to obtain multiple initial cadence ranges; In a combined form, use the multiple initial cadence ranges and the multiple shifting ratio sets to obtain multiple test nodes, and each test node includes an initial cadence range and a shifting ratio; Perform the following operations on each of the multiple test nodes: Obtain a test node time series set based on the test node, the preset test interval time, and the preset test period. Among them, the test node time series set includes multiple test node time series, and the test node time series includes: test heart rate time series, test speed time series, and test cadence time series; Perform the following operations on each test node time series in the test node time series set: Based on the pre-constructed sliding window and sliding step, sequentially extract and analyze the heart rate time series in the test heart rate time series corresponding to the test node, and perform the following operations on the extracted analyzed heart rate time series: Obtain the analyzed heart rate variance based on the analyzed heart rate time series, compare the analyzed heart rate variance with the preset heart rate variance threshold. After confirming that the analyzed heart rate variance is less than or equal to the heart rate variance threshold, use the analyzed heart rate time series to obtain the analyzed heart rate mean. Based on the analyzed heart rate time series, confirm the analyzed speed mean in the test speed time series and the analyzed cadence mean in the test cadence time series respectively; Summarize the analyzed heart rate mean, the analyzed speed mean, and the analyzed cadence mean respectively to obtain the analyzed heart rate mean set, the analyzed speed mean set, and the analyzed cadence mean set. Calculate the target heart rate mean based on the analyzed heart rate mean set, and obtain the target speed mean and the target cadence mean based on the analyzed speed mean set and the analyzed cadence mean set; Associate the target heart rate mean, the target speed mean, the shifting ratio, and the target cadence mean to obtain an analyzed associated node; Summarize the analyzed associated nodes to obtain an analyzed associated node set, and obtain the set of shifting strategy groups based on the analyzed associated node set.

3. The bicycle intelligent shifting method based on sensor data according to claim 2, characterized in that, The calculating of the target heart rate mean based on the analyzed heart rate mean set includes: Calculate the mean of the analyzed heart rate means in the analyzed heart rate mean set to obtain the parsed heart rate mean, and perform the following operations on each analyzed heart rate mean in the analyzed heart rate mean set: Calculate the absolute difference between the analyzed heart rate mean and the parsed heart rate mean to obtain the offset heart rate, summarize the offset heart rates to obtain the offset heart rate set, calculate the mean of the offset heart rates in the offset heart rate set to obtain the offset heart rate mean, and calculate the offset evaluation range based on the offset heart rate mean. Among them, the offset evaluation range is as follows: Among them, represents the offset evaluation range, are all preset coefficients, represents the mean offset heart rate; Use the offset evaluation range to confirm the target offset heart rate set in the offset heart rate set. Among them, the target offset heart rate set includes multiple target offset heart rates, and each target offset heart rate in the multiple target offset heart rates satisfies the offset evaluation range; Perform the following operations on each target offset heart rate in the target offset heart rate set: Associate the target offset heart rate with the average analysis heart rate corresponding to the target offset heart rate to obtain an analysis heart rate node. Aggregate the analysis heart rate nodes to obtain an analysis heart rate node set. Calculate the average target heart rate based on the analysis heart rate node set. The calculation formula is as follows: Among them, represents the average target heart rate, represents that there are analyzed heart rate nodes in the analyzed heart rate node set, represents the target offset heart rate corresponding to the th analyzed heart rate node in the analyzed heart rate node set, respectively represent the target offset heart rate and the analyzed heart rate average corresponding to the th analyzed heart rate node in the analyzed heart rate node set.

4. The bicycle intelligent shifting method based on sensor data according to claim 3, characterized in that, The obtaining of the variable speed strategy group set based on the analysis association node set includes: Obtain an association range node set for different riding modes. Among them, the association range node set includes multiple association range nodes, and the association range nodes correspond to the riding modes one by one. The association range nodes include a target heart rate range, a target speed range, and a target cadence range; Perform the following operations on each association range node in the association range node set: Use the association range node to retrieve in the analysis association node set to obtain a target analysis node set. Among them, the target analysis node set includes multiple target analysis nodes, and the average target heart rate, average target speed, and average target cadence corresponding to the target analysis nodes are respectively within the target heart rate range, target speed range, and target cadence range corresponding to the association range node; According to the association range node, perform a normalization operation on the target analysis nodes in the target analysis node set to obtain a normalized analysis node; Aggregate the normalized analysis nodes to obtain a normalized analysis node set. Use a pre-constructed clustering method to cluster the normalized analysis node set to obtain one or more clustered analysis node sets; Perform the following operations on each clustered analysis node set in the one or more clustered analysis node sets: Use a pre-constructed variable speed ratio range set to divide the clustered analysis nodes in the clustered analysis node set to obtain multiple target clustered analysis node sets. Among them, the variable speed ratio range set includes three variable speed ratio ranges; Perform the following operations on each target clustered analysis node set in the multiple target clustered analysis node sets: Use the variable speed ratio range to obtain a variable speed application name. Use the variable speed application name and the riding mode to identify the target clustered analysis node set corresponding to the variable speed ratio range to obtain a variable speed strategy group. Among them, the variable speed application names include: uphill mode, flat road mode, and downhill mode; Aggregate the variable speed strategy groups to obtain a variable speed strategy group set.

5. The bicycle intelligent shifting method based on sensor data according to claim 4, wherein The retrieving of the target variable speed ratio in the target variable speed strategy group by using the driving feature sequence group and the user feature sequence group includes: Based on the sliding window and the sliding step, sequentially extract an initial slope sequence from the riding slope sequence corresponding to the driving feature sequence group. Among them, the initial slope sequence includes multiple riding slopes; Use the initial slope sequence to confirm a target variable speed strategy node. The target variable speed strategy node is an uphill variable speed strategy node, a downhill variable speed strategy node, or a flat road variable speed strategy node. Use the target variable speed strategy node to identify a first variable speed strategy group in the target variable speed strategy group. Among them, the first variable speed strategy group corresponds to the variable speed strategy group one by one; Use the driving feature sequence group and the user feature sequence group to retrieve the target variable speed ratio in the first variable speed strategy group.

6. The bicycle intelligent shifting method based on sensor data according to claim 5, wherein, The confirming of the target variable speed strategy node by using the initial slope sequence includes: Obtain the screening slope range, and use the screening slope range to screen out the classified slopes in the initial slope sequence. Among them, the classified slopes are not within the screening slope range. After confirming that the classified slopes are greater than 0, mark the classified slopes as uphill slopes, and count the number of uphill slopes in the initial slope sequence to obtain the uphill quantity; Compare the uphill quantity with the preset slope threshold. If the uphill quantity is greater than or equal to the slope threshold, identify the target uphill slope in the initial slope sequence. Use the target uphill slope to identify the interval uphill slope in the initial slope sequence. Obtain the uphill interval time based on the interval uphill slope and the target uphill slope. Compare the uphill interval time with the preset interval time threshold. If the uphill interval time is greater than or equal to the interval time threshold, use the interval uphill slope as the target uphill slope, and return to the step of using the target uphill slope to identify the interval uphill slope in the initial slope sequence until it is confirmed that all uphill interval times are less than the interval time threshold. Then, use the target uphill slope to identify the target uphill time in the initial slope sequence. After confirming that the target uphill time is less than the preset uphill time threshold, return to the step of sequentially extracting the initial slope sequence in the riding slope sequence corresponding to the driving feature sequence group based on the sliding window and the sliding step length until the target uphill time is greater than or equal to the preset uphill time threshold, then use the uphill shift strategy node as the target shift strategy node; Otherwise, based on the screening slope range, confirm that the target shift strategy node is the downhill shift strategy node; Otherwise, confirm that the target shift strategy node is the flat road shift strategy node.

7. The bicycle intelligent shifting method based on sensor data according to claim 6, wherein Before retrieving the target shift ratio in the first shift strategy group by using the driving feature sequence group and the user feature sequence group, it further includes: After confirming that the target shift strategy node corresponding to the first shift strategy group is the uphill shift strategy node, use the preset evaluation acceleration value to confirm the analysis acceleration sequence in the riding acceleration sequence, where the analysis acceleration sequence includes multiple analysis accelerations; Sequentially extract the parsed accelerations in the analysis acceleration sequence, and perform the following operations on the extracted parsed accelerations: Based on the parsed acceleration, confirm the decomposed acceleration in the analysis acceleration sequence, and calculate the first decomposed acceleration based on the decomposed acceleration and the detection time interval. The calculation formula is as follows: Among them, represents the first decomposed acceleration, represents the decomposed acceleration, represents the analyzed acceleration, represents the said detection time interval; Obtain the first decomposed acceleration sequence based on the first decomposed acceleration, use the first decomposed acceleration sequence to obtain the mean value of the decomposed acceleration, compare the mean value of the decomposed acceleration with the preset decomposed acceleration threshold. If the mean value of the decomposed acceleration is greater than or equal to the decomposed acceleration threshold, retrieve the target shift ratio in the first shift strategy group by using the driving feature sequence group and the user feature sequence group.

8. The bicycle intelligent shifting method based on sensor data according to claim 7, characterized in that, The retrieving the target shift ratio in the first shift strategy group by using the driving feature sequence group and the user feature sequence group includes: Respectively confirm the target user heart rate, the target user cadence, and the target riding speed in the driving feature sequence group and the user feature sequence group; Calculate the evaluation differences between the target user's heart rate, the target user's cadence, and the target cycling speed and the analysis association nodes in the first variable speed strategy group. The calculation formula is as follows: Among them, represents the evaluation difference, are all preset coefficients, respectively represent the heart rate of the target user and the average heart rate, respectively represent the target cycling speed and the average target speed, respectively represent the cadence of the target user and the average cadence; Summarize the evaluation differences to obtain an evaluation difference set, and confirm the target variable speed ratio based on the evaluation difference set. Among them, the target variable speed ratio is the variable speed ratio corresponding to the smallest evaluation difference in the evaluation difference set.

9. An intelligent bicycle variable speed system based on sensor data, characterized in that, The system includes: A variable speed environment confirmation module, configured to receive an intelligent variable speed instruction and confirm an intelligent variable speed environment based on the intelligent variable speed instruction. The intelligent variable speed environment includes: an intelligent variable speed system and an adjustable bicycle. The intelligent variable speed system includes: a target model input unit, a driving feature acquisition unit, a physiological feature acquisition unit, and a variable speed strategy construction unit; A variable speed strategy construction module, configured to obtain an initial model set of the bicycle. The initial model set includes multiple initial models, and obtain multiple variable speed ratio sets based on the initial model set; The obtaining multiple variable speed ratio sets based on the initial model set includes: Sequentially extract the initial models from the initial model set, and perform the following operations on the extracted initial models: Confirm a front chainring tooth number set and a rear sprocket tooth number set based on the initial model. The front chainring tooth number set includes multiple front chainring tooth numbers, and the rear sprocket tooth number set includes multiple rear sprocket tooth numbers; Sequentially extract the front chainring tooth numbers from the front chainring tooth number set, and perform the following operations on each of the extracted front chainring tooth numbers: Obtain multiple tooth number combination nodes in a combined form by using the extracted front chainring tooth number and the rear sprocket tooth number set. Each tooth number combination node includes a front chainring tooth number and a rear sprocket tooth number; Perform the following operations on each tooth number combination node among the multiple tooth number combination nodes: Calculate the ratio of the front chainring tooth number to the rear sprocket tooth number in the tooth number combination node to obtain a theoretical ratio. Summarize the theoretical ratios to obtain a theoretical ratio set, and perform a normalization operation on the theoretical ratios in the theoretical ratio set to obtain a normalized ratio set. The normalized ratio set includes multiple normalized ratios; Obtain a screening ratio range based on the extracted front chainring tooth number, and use the screening ratio range to confirm a screening ratio set in the normalized ratio set. The screening ratio set includes multiple screening ratios, and all the screening ratios are within the screening ratio range; Summarize the screening ratio set to obtain a variable speed ratio set, and summarize the variable speed ratio set to obtain multiple variable speed ratio sets; Obtain a variable speed strategy group set based on the multiple variable speed ratio sets and the variable speed strategy construction unit. The variable speed strategy group set includes multiple variable speed strategy groups marked with riding modes. Each variable speed strategy group includes multiple variable speed ratios, and the riding modes corresponding to different variable speed strategy groups are different; Send the variable speed strategy group set to the initiator of the intelligent variable speed instruction, use the target model input unit to receive the target model and the target riding mode confirmed by the user according to the variable speed strategy group set, and confirm the target variable speed strategy group in the variable speed strategy group set based on the target model and the target riding mode; A riding feature acquisition module, which is used to respectively obtain a driving feature sequence group and a user feature sequence group by using a driving feature acquisition unit, a physiological feature acquisition unit and a preset detection time interval. The driving feature sequence group includes: a riding speed sequence, a riding acceleration sequence and a riding slope sequence. The user feature sequence group includes: a user heart rate sequence and a user cadence sequence; A shifting strategy confirmation module, which is used to use the driving feature sequence group and the user feature sequence group to retrieve a target shifting ratio in a target shifting strategy group, and use the target shifting ratio to adjust the bicycle, so as to realize intelligent shifting of the bicycle.

Images