Algorithm library control method and system and wearable intelligent device
By allocating sensor data to the algorithm queue according to frequency and classifying and managing it, the problem of inefficient multi-frequency algorithm processing in wearable devices is solved, and efficient sensor data processing is achieved.
Patent Information
- Application Number
- CN202510407032.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-02
- Publication Date
- 2025-07-18
AI Technical Summary
Existing wearable smart devices are inefficient when processing multi-frequency algorithms and cannot effectively manage and schedule sensor data at different frequencies.
By allocating sensor data to the corresponding multiple algorithm queues according to frequency, and controlling the respective corresponding algorithm queues for processing, including the acceleration sensor data driving the algorithm library operation, cache the remaining data, and scheduling other queue data processing based on preset time intervals.
The classification management and scheduling of sensor data of different frequencies is realized, the operating logic of the algorithm library is optimized, and the processing efficiency of different frequencies is improved.
Smart Images
Figure CN120335961A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of algorithm control, and further relates to an algorithm library control method, system, and wearable intelligent device. Background Art
[0002] With the continuous progress of technology, wearable intelligent devices are increasingly widely used in people's lives, such as smart watches, smart bracelets, health monitoring devices, etc. These wearable intelligent devices usually need to process a variety of sensor data, and the processing of these sensor data usually involves multiple algorithms with different execution frequencies. However, existing wearable intelligent devices usually adopt a single algorithm control architecture when processing multi-frequency algorithms, and this architecture has the problem of low efficiency when processing algorithms with different frequencies. Summary of the Invention
[0003] To solve the above technical problems, this application provides an algorithm library control method, system, and wearable intelligent device, which improve the processing efficiency of algorithms with different frequencies.
[0004] In a first aspect, this application provides an algorithm library control method, including: obtaining a variety of sensor data; when the variety of sensor data includes acceleration sensor data, allocating the variety of sensor data to corresponding multiple algorithm queues according to frequency, where each type of sensor data corresponds to one algorithm queue; controlling the algorithm queues allocated with the sensor data to process their respective corresponding sensor data and output processing results.
[0005] The above algorithm library control method, when the variety of sensor data includes acceleration sensor data, allocates the variety of sensor data to corresponding algorithm queues for processing according to frequency, and controls the algorithm queues allocated with the sensor data to process their respective corresponding sensor data, and then outputs processing results, thereby improving the processing efficiency of algorithms with different frequencies.
[0006] In one implementation, multiple said algorithm queues include a first frequency algorithm queue, a second frequency algorithm queue, a third frequency algorithm queue, and a fourth frequency algorithm queue; when the multiple said sensor data includes acceleration sensor data, distributing the multiple said sensor data to corresponding algorithm queues according to frequency specifically includes: when the multiple said sensor data includes the acceleration sensor data and there is first sensor data in the multiple said sensor data whose frequency is the same as that of the acceleration sensor data, distributing the first sensor data and the acceleration sensor data to the first frequency algorithm queue; caching the remaining said sensor data in the multiple said sensor data except the first sensor data and the acceleration sensor data; controlling the second frequency algorithm queue, the third frequency algorithm queue, and the fourth frequency algorithm queue to sequentially obtain the sensor data with corresponding frequencies from the remaining said sensor data based on a preset execution time interval of the algorithm queue.
[0007] The above algorithm library control method distributes the first sensor data whose frequency is the same as that of the acceleration sensor data and the acceleration sensor data to the first frequency algorithm queue. At the same time, by caching the remaining sensor data except the first sensor data and the acceleration sensor data, and controlling the second frequency algorithm queue, the third frequency algorithm queue, and the fourth frequency algorithm queue to sequentially obtain the sensor data with corresponding frequencies from the cache based on a preset execution time interval of the algorithm queue, it realizes the classified management and scheduling of sensor data with different frequencies, optimizes the operation logic of the algorithm library, improves the processing efficiency of algorithms with different frequencies, and at the same time solves the problems of the operation and control of algorithms with different frequencies.
[0008] In one implementation, it further includes: when the multiple said sensor data includes the acceleration sensor data and there is no first sensor data in the multiple said sensor data whose frequency is the same as that of the acceleration sensor data, distributing the acceleration sensor data to the first frequency algorithm queue.
[0009] In one implementation, it further includes: when the multiple said sensor data does not include acceleration sensor data, setting driving acceleration data; based on the driving acceleration data, distributing the multiple said sensor data to corresponding multiple algorithm queues according to frequency.
[0010] In one implementation, the obtaining of multiple sensor data specifically includes: obtaining multiple pieces of original sensor data, where the multiple pieces of original sensor data include first original sensor data, second original sensor data, third original sensor data, and fourth original sensor data; respectively performing interpolation processing on the second original sensor data, the third original sensor data, and the fourth original sensor data; filtering the interpolated second original sensor data according to the frequency of the algorithm queue corresponding to the second original sensor data; filtering the interpolated third original sensor data according to the frequency of the algorithm queue corresponding to the third original sensor data; filtering the interpolated fourth original sensor data according to the frequency of the algorithm queue corresponding to the fourth original sensor data; and using the first original sensor data, the filtered second original sensor data, the filtered third original sensor data, and the filtered fourth original sensor data as the multiple pieces of sensor data.
[0011] In one implementation, the obtaining of multiple sensor data specifically includes: obtaining multiple pieces of original sensor data through multiple sensors with the same frequency, where the multiple pieces of original sensor data include first original sensor data, second original sensor data, third original sensor data, and fourth original sensor data; filtering the second original sensor data according to the frequency of the algorithm queue corresponding to the second original sensor data; filtering the third original sensor data according to the frequency of the algorithm queue corresponding to the third original sensor data; filtering the fourth original sensor data according to the frequency of the algorithm queue corresponding to the fourth original sensor data; and using the first original sensor data, the filtered second original sensor data, the filtered third original sensor data, and the filtered fourth original sensor data as the multiple pieces of sensor data.
[0012] In a second aspect, the present application provides an algorithm library control system, including: an input module configured to obtain multiple sensor data; a distribution module configured to, when the multiple sensor data includes acceleration sensor data, distribute the multiple sensor data to corresponding multiple algorithm queues according to frequency, where each piece of sensor data corresponds to one algorithm queue; and a control module configured to control the algorithm queues to which the sensor data is distributed to process their respective corresponding sensor data and output a processing result.
[0013] In one implementation, the multiple algorithm queues include a first frequency algorithm queue, a second frequency algorithm queue, a third frequency algorithm queue, and a fourth frequency algorithm queue. The allocation module includes: an allocation sub-module configured to, when the multiple sensor data includes the acceleration sensor data and there is first sensor data in the multiple sensor data that has the same frequency as the acceleration sensor data, allocate the first sensor data and the acceleration sensor data to the first frequency algorithm queue; a caching sub-module configured to cache the remaining sensor data in the multiple sensor data except the first sensor data and the acceleration sensor data; and the allocation sub-module configured to, based on a preset execution time interval of the algorithm queue, control the second frequency algorithm queue, the third frequency algorithm queue, and the fourth frequency algorithm queue to sequentially obtain the sensor data of corresponding frequencies from the remaining sensor data.
[0014] In one implementation, the allocation sub-module is configured to, when the multiple sensor data includes the acceleration sensor data and there is no first sensor data in the multiple sensor data that has the same frequency as the acceleration sensor data, allocate the acceleration sensor data to the first frequency algorithm queue.
[0015] In one implementation, it further includes: a setting module configured to, when the acceleration sensor data is not included in the multiple sensor data, set driving acceleration data; and the allocation module configured to, based on the driving acceleration data, allocate the multiple sensor data to corresponding multiple algorithm queues according to the frequency.
[0016] In a third aspect, the present application further provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the algorithm library control method in any of the above implementations are implemented.
[0017] In a fourth aspect, the present application further provides a wearable intelligent device including a memory and a processor. A computer program is stored on the memory. When the computer program is executed by the processor, the steps of the algorithm library control method in any of the above implementations are implemented.
[0018] Compared with the prior art, the present invention has at least one of the following beneficial effects:
[0019] 1. When the acceleration sensor data is included in the multiple sensor data, the multiple sensor data is allocated to corresponding algorithm queues according to the frequency for processing, and the algorithm queues of the allocated sensor data are controlled to process their respective corresponding sensor data, and then the processing results are output, improving the processing efficiency of different frequency algorithms.
[0020] 2. The first sensor data with the same frequency as the acceleration sensor data and the acceleration sensor data are assigned to the first frequency algorithm queue. At the same time, the remaining sensor data excluding the first sensor data and the acceleration sensor data are cached, and based on the preset algorithm queue execution time interval, the second frequency algorithm queue, the third frequency algorithm queue, and the fourth frequency algorithm queue are controlled to sequentially obtain the sensor data of the corresponding frequency from the cache, realizing the classified management and scheduling of sensor data with different frequencies, optimizing the operation logic of the algorithm library, improving the processing efficiency of algorithms with different frequencies, and at the same time solving the problems of the operation and control of algorithms with different frequencies. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] The above characteristics, technical features, advantages and their implementation manners of the present invention will be further described below in a clear and understandable manner in combination with the drawings in the preferred embodiments.
[0022] Figure 1 The flowchart of an algorithm library control method provided by an embodiment of the present application is shown;
[0023] Figure 2 The flowchart of a sensor data allocation provided by an embodiment of the present application is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the specific embodiments of the present invention will be described below with reference to the drawings. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts, and other embodiments can also be obtained.
[0025] For the sake of simplicity of the drawings, only the parts related to the invention are schematically shown in each drawing, and they do not represent the actual structure of the product. In addition, for the sake of simplicity and easy understanding of the drawings, in some drawings, only one of the components with the same structure or function is schematically shown, or only one of them is marked. In this document, "one" not only means "only one", but also means "more than one" situation.
[0026] It should also be further understood that the term "and / or" used in the specification and claims of the present application refers to any combination and all possible combinations of one or more of the related listed items, and includes these combinations.
[0027] In this text, it should be noted that unless otherwise clearly stipulated and defined, the terms "installation", "connection", and "linkage" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0028] In addition, in the description of this application, the terms "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.
[0029] It should be noted that the above embodiments can be freely combined according to needs. The above are only the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art of this technology, without departing from the principle of the present invention, several improvements and retouches can still be made, and these improvements and retouches should also be regarded as the protection scope of the present invention.
[0030] Wearable intelligent devices usually need to process various sensor data, such as acceleration sensors, gyroscopes, geomagnetic sensors, barometers, heart rate sensors, positioning sensors, etc., to achieve various functions, such as motion monitoring, health analysis, navigation, etc. However, the processing of these sensor data usually involves multiple algorithms with different execution frequencies. For example, the acceleration sensor data may need to be processed at a frequency of 50 Hz, while the heart rate data may only need to be processed at a frequency of 1 Hz. Therefore, in the embodiments of this application, by setting multiple algorithm queues, each algorithm queue processes the sensor data corresponding to its frequency, and then outputs the corresponding processing results, improving the processing efficiency of algorithms with different frequencies.
[0031] The following will be elaborated with reference to the drawings:
[0032] Refer to the attached Figure 1 , which shows a flowchart of an algorithm library control method provided by the embodiments of this application. As Figure 1 shown, it includes:
[0033] S100, obtain various sensor data.
[0034] S110, when the various sensor data includes acceleration sensor data, allocate the various sensor data to the corresponding multiple algorithm queues according to the frequency, where each type of sensor data corresponds to one algorithm queue.
[0035] S120, control the algorithm queues to which the sensor data is allocated to process their respective corresponding sensor data and output the processing results.
[0036] The multiple sensor data includes acceleration sensor data, gyroscope data, geomagnetic data, photoplethysmography sensor data, barometer data, heart rate data, positioning data, HRV (heart rate variability) data, etc. Each type of sensor data has a corresponding frequency. For example, the frequencies of acceleration sensor data, gyroscope data, and geomagnetic data are all 50 Hz, the frequency of photoplethysmography sensor data is 25 Hz, the frequency of barometer data is 10 Hz, and the frequencies of heart rate data, positioning data, and HRV data are all 1 Hz. Similarly, the algorithm queues can be divided into 4 categories according to the frequency (or execution frequency), for example, the 50 Hz algorithm queue, the 25 Hz algorithm queue, the 10 Hz algorithm queue, and the 1 Hz algorithm queue.
[0037] The entire algorithm library is driven by the acceleration sensor data, and the algorithm switches are set outside the algorithm library. After the algorithm switches are set, the algorithm result callback function is registered. Then, multiple sensor data is received through the interface of the algorithm library. When the multiple sensor data passed into the algorithm library includes acceleration sensor data, at this time, the algorithm library is driven by the acceleration sensor data, and the multiple sensor data is divided into the corresponding algorithm queues according to the frequency. For example, the acceleration sensor data, gyroscope data, and geomagnetic data can be assigned to the 50 Hz algorithm queue, the photoplethysmography sensor data can be assigned to the 25 Hz algorithm queue, the barometer data can be assigned to the 10 Hz algorithm queue, and the heart rate data, positioning data, and HRV data can be assigned to the 1 Hz algorithm queue.
[0038] Control the algorithm queues of the respective assigned sensor data, process the corresponding sensor data, and assign the processing results to the algorithm result callback function for output. The output of the results between each algorithm queue is independent of each other. For example, the 50 Hz algorithm queue can directly output the processing result after completion without waiting for the other algorithm queues to complete. The processing results of these 4 algorithm queues for their respective sensor data usually include steps, step frequency, step length, distance, longitude and latitude, ascent height, descent height, average heart rate, maximum / minimum heart rate, calories, exercise status, cycling, walking, running, going upstairs / downstairs, wearing status, cycling speed, longitude and latitude, distance, ascent height, descent height, heart rate, wrist - raising status, sedentary status, stress value, sleep quality, number of swimming laps, swimming distance, swimming posture, number of strokes, etc.
[0039] When the multiple sensor data in the embodiments of the present application includes acceleration sensor data, the multiple sensor data is divided into the corresponding algorithm queues according to the frequency for processing, and the algorithm queues of the assigned sensor data are controlled to process the corresponding sensor data, and then the processing results are output, which improves the processing efficiency of algorithms with different frequencies.
[0040] Reference appendix Figure 2 , which shows a flowchart of sensor data allocation provided by an embodiment of the present application. As Figure 2 shown, when acceleration sensor data is included in multiple sensor data, the multiple sensor data is allocated to corresponding algorithm queues according to frequency, specifically including:
[0041] S200, when acceleration sensor data is included in multiple sensor data and there is first sensor data with the same frequency as the acceleration sensor data in the multiple sensor data, allocate the first sensor data and the acceleration sensor data to the first frequency algorithm queue;
[0042] S210, cache the remaining sensor data in the multiple sensor data except the first sensor data and the acceleration sensor data;
[0043] S220, based on a preset execution time interval of the algorithm queue, control the second frequency algorithm queue, the third frequency algorithm queue, and the fourth frequency algorithm queue to sequentially obtain sensor data corresponding to their respective frequencies from the remaining sensor data.
[0044] The multiple algorithm queues include a first frequency algorithm queue (or 50Hz algorithm queue), a second frequency algorithm queue (or 25Hz algorithm queue), a third frequency algorithm queue (or 10Hz algorithm queue), and a fourth frequency algorithm queue (or 1Hz algorithm queue). When the multiple sensor data passed into the algorithm library includes acceleration sensor data and first sensor data with the same frequency as the acceleration sensor data. At this time, directly allocate the acceleration sensor data and the first sensor data to the first frequency algorithm queue for processing, and cache the remaining sensor data in the buffer area of the algorithm library. Further, according to the preset execution time interval of the algorithm queue, control the second frequency algorithm queue, the third frequency algorithm queue, and the fourth frequency algorithm queue to sequentially obtain the sensor data corresponding to their respective frequencies from the buffer area and process them. Finally, each algorithm queue assigns its respective processing result to the algorithm result callback function for output.
[0045] In the embodiment of the present application, by allocating the first sensor data with the same frequency as the acceleration sensor data and the acceleration sensor data to the first frequency algorithm queue. At the same time, by caching the remaining sensor data except the first sensor data and the acceleration sensor data, and based on the preset execution time interval of the algorithm queue, controlling the second frequency algorithm queue, the third frequency algorithm queue, and the fourth frequency algorithm queue to sequentially obtain the sensor data corresponding to their respective frequencies from the cache, the classification management and scheduling of sensor data with different frequencies are realized, the operation logic of the algorithm library is optimized, the processing efficiency of algorithms with different frequencies is improved, and at the same time, the problems of operation and control of algorithms with different frequencies are solved.
[0046] In an embodiment of the present application, it further includes: when the acceleration sensor data is included in the multiple sensor data and there is no first sensor data with the same frequency as the acceleration sensor data among the multiple sensor data, the acceleration sensor data is assigned to the first frequency algorithm queue.
[0047] When the first sensor data is not included in the multiple sensor data passed into the algorithm library, the acceleration sensor data is assigned to the first frequency algorithm queue for processing, and the remaining sensor data is cached in the buffer area in the algorithm library, waiting to be acquired and processed by the second frequency algorithm queue, the third frequency algorithm queue, and the fourth frequency algorithm queue.
[0048] Similarly, if the sensor data corresponding to the second frequency algorithm queue is not included in the multiple sensor data passed into the algorithm library, then the second frequency algorithm queue is directly skipped, and according to the preset algorithm queue execution time interval, the third frequency algorithm queue and the fourth frequency algorithm queue are controlled to sequentially acquire the sensor data corresponding to their respective frequencies from the buffer area and perform processing. Similarly, the same applies if the third frequency algorithm queue or the fourth frequency algorithm queue is not included in the multiple sensor data passed into the algorithm library.
[0049] In an embodiment of the present application, it further includes: when the acceleration sensor data is not included in the multiple sensor data, drive acceleration data is set; based on the drive acceleration data, the multiple sensor data is assigned to the corresponding multiple algorithm queues according to the frequency.
[0050] When the acceleration sensor data is not included in the multiple sensor data passed into the algorithm library, the algorithm library cannot be driven to run at this time. Therefore, it is necessary to set the drive acceleration data to drive the algorithm library to run, and then the multiple sensor data can be assigned to the corresponding algorithm queues according to the frequency according to the allocation method in the foregoing embodiment.
[0051] In one embodiment of the present application, multiple sensor data are acquired, specifically including: acquiring multiple pieces of original sensor data, where the multiple pieces of original sensor data include first original sensor data, second original sensor data, third original sensor data, and fourth original sensor data; performing interpolation processing on the second original sensor data, third original sensor data, and fourth original sensor data respectively; filtering the interpolated second original sensor data according to the frequency of the algorithm queue corresponding to the second original sensor data; filtering the interpolated third original sensor data according to the frequency of the algorithm queue corresponding to the third original sensor data; filtering the interpolated fourth original sensor data according to the frequency of the algorithm queue corresponding to the fourth original sensor data; and using the first original sensor data, the filtered second original sensor data, the filtered third original sensor data, and the filtered fourth original sensor data as the multiple sensor data.
[0052] The frequencies of the first original sensor data, second original sensor data, third original sensor data, and fourth original sensor data are 50 Hz, 25 Hz, 10 Hz, and 1 Hz respectively. At the same time, the frequencies of the algorithm queues corresponding to the first original sensor data, second original sensor data, third original sensor data, and fourth original sensor data are also 50 Hz, 25 Hz, 10 Hz, and 1 Hz respectively. Interpolation processing is performed on the second original sensor data, third original sensor data, and fourth original sensor data respectively, and the frequencies of the interpolated second original sensor data, third original sensor data, and fourth original sensor data are all 50 Hz. Further, the interpolated second original sensor data, third original sensor data, and fourth original sensor data are filtered according to the frequencies of their respective corresponding algorithm queues, and the frequencies of the filtered second original sensor data, third original sensor data, and fourth original sensor data are 25 Hz, 10 Hz, and 1 Hz respectively. Finally, the first original sensor data, the filtered second original sensor data, the filtered third original sensor data, and the filtered fourth original sensor data are used as the multiple sensor data.
[0053] That is to say, the first original sensor data can include the acceleration sensor data, gyroscope data, geomagnetic data, etc. of the foregoing embodiments; the filtered second original sensor data can include the photoplethysmogram sensor data of the foregoing embodiments; the filtered third original sensor data can include the barometer data of the foregoing embodiments; and the filtered fourth original sensor data can include the heart rate data, positioning data, and HRV data of the foregoing embodiments.
[0054] In one embodiment of the present application, multiple sensor data are obtained, specifically including: obtaining multiple pieces of original sensor data through multiple sensors with the same frequency. The multiple pieces of original sensor data include the first original sensor data, the second original sensor data, the third original sensor data, and the fourth original sensor data; filtering the second original sensor data according to the frequency of the algorithm queue corresponding to the second original sensor data; filtering the third original sensor data according to the frequency of the algorithm queue corresponding to the third original sensor data; filtering the fourth original sensor data according to the frequency of the algorithm queue corresponding to the fourth original sensor data; and using the first original sensor data, the filtered second original sensor data, the filtered third original sensor data, and the filtered fourth original sensor data as the multiple sensor data.
[0055] The original sensor data corresponding to the sensor with a frequency of 50 Hz is the first original sensor data, the original sensor data corresponding to the sensor with a frequency of 25 Hz is the second original sensor data, the original sensor data corresponding to the sensor with a frequency of 10 Hz is the third original sensor data, and the original sensor data corresponding to the sensor with a frequency of 1 Hz is the fourth original sensor data. Among them, when the sensors with frequencies of 25 Hz, 10 Hz, and 1 Hz sample data, the frequencies need to be all adjusted to 50 Hz for sampling. That is, the frequencies of the sampled first original sensor data, second original sensor data, third original sensor data, and fourth original sensor data are all 50 Hz.
[0056] The frequencies of the algorithm queues corresponding to the first original sensor data, the second original sensor data, the third original sensor data, and the fourth original sensor data are 50 Hz, 25 Hz, 10 Hz, and 1 Hz respectively. Then, the second original sensor data, the third original sensor data, and the fourth original sensor data are filtered according to the frequencies of their respective corresponding algorithm queues. The frequencies of the filtered second original sensor data, third original sensor data, and fourth original sensor data are 25 Hz, 10 Hz, and 1 Hz respectively. Finally, the first original sensor data, the filtered second original sensor data, the filtered third original sensor data, and the filtered fourth original sensor data are used as the multiple sensor data.
[0057] An embodiment of the present application also provides an algorithm library control system, including: an input module configured to obtain a variety of sensor data; an allocation module configured to, when the variety of sensor data includes acceleration sensor data, allocate the variety of sensor data to corresponding multiple algorithm queues according to frequencies, where each type of sensor data corresponds to an algorithm queue; and a control module configured to control the algorithm queues to which the sensor data is allocated to process their respective corresponding sensor data and output a processing result.
[0058] The relevant content of the embodiment of the present application has been described in the foregoing embodiment, and will not be elaborated herein.
[0059] In an embodiment of the present application, the multiple algorithm queues include a first frequency algorithm queue, a second frequency algorithm queue, a third frequency algorithm queue, and a fourth frequency algorithm queue. The allocation module includes: an allocation sub-module configured to, when the variety of sensor data includes acceleration sensor data and there is first sensor data in the variety of sensor data whose frequency is the same as that of the acceleration sensor data, allocate the first sensor data and the acceleration sensor data to the first frequency algorithm queue; a cache sub-module configured to cache the remaining sensor data in the variety of sensor data except the first sensor data and the acceleration sensor data; and an allocation sub-module configured to, based on a preset execution time interval of the algorithm queue, control the second frequency algorithm queue, the third frequency algorithm queue, and the fourth frequency algorithm queue to sequentially obtain the sensor data corresponding to their frequencies from the remaining sensor data.
[0060] In an embodiment of the present application, the allocation sub-module is configured to, when the variety of sensor data includes acceleration sensor data and there is no first sensor data in the variety of sensor data whose frequency is the same as that of the acceleration sensor data, allocate the acceleration sensor data to the first frequency algorithm queue.
[0061] In an embodiment of the present application, it further includes: a setting module configured to set driving acceleration data when the variety of sensor data does not include acceleration sensor data; and an allocation module configured to, based on the driving acceleration data, allocate the variety of sensor data to corresponding multiple algorithm queues according to frequencies.
[0062] An embodiment of the present application also provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the algorithm library control method in any of the foregoing embodiments are implemented.
[0063] An embodiment of the present application also provides a wearable intelligent device, including a memory and a processor. A computer program is stored on the memory. When the computer program is executed by the processor, the steps of the algorithm library control method in any of the foregoing embodiments are implemented.
[0064] It should be noted that the above-mentioned embodiments can be freely combined as needed. The above are only the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.
Claims
1. An algorithm library control method, characterized in that, Including: Obtain a variety of sensor data; When the acceleration sensor data is included in the variety of sensor data, allocate the variety of sensor data to corresponding multiple algorithm queues according to frequency, where each type of sensor data corresponds to one algorithm queue; Control the algorithm queues assigned with the sensor data to process their respective corresponding sensor data and output the processing results.
2. The algorithm library control method according to claim 1, wherein The multiple algorithm queues include a first frequency algorithm queue, a second frequency algorithm queue, a third frequency algorithm queue, and a fourth frequency algorithm queue; when the acceleration sensor data is included in the variety of sensor data, allocating the variety of sensor data to corresponding algorithm queues according to frequency specifically includes: When the acceleration sensor data is included in the variety of sensor data and there is first sensor data with the same frequency as the acceleration sensor data in the variety of sensor data, allocate the first sensor data and the acceleration sensor data to the first frequency algorithm queue; Cache the remaining sensor data in the variety of sensor data excluding the first sensor data and the acceleration sensor data; Based on a preset algorithm queue execution time interval, control the second frequency algorithm queue, the third frequency algorithm queue, and the fourth frequency algorithm queue to sequentially obtain the sensor data with corresponding frequencies from the remaining sensor data.
3. The algorithm library control method according to claim 2, wherein It further includes: When the acceleration sensor data is included in the variety of sensor data and there is no first sensor data with the same frequency as the acceleration sensor data in the variety of sensor data, allocate the acceleration sensor data to the first frequency algorithm queue.
4. The algorithm library control method according to claim 1, characterized in that It further includes: When the acceleration sensor data is not included in the variety of sensor data, set the driving acceleration data; Based on the driving acceleration data, allocate the variety of sensor data to corresponding multiple algorithm queues according to frequency.
5. The algorithm library control method according to claim 1, wherein The obtaining of a variety of sensor data specifically includes: Obtain a variety of original sensor data, where the variety of original sensor data includes first original sensor data, second original sensor data, third original sensor data, and fourth original sensor data; Perform interpolation processing on the second original sensor data, the third original sensor data, and the fourth original sensor data respectively; Filter the interpolated second original sensor data according to the frequency of the algorithm queue corresponding to the second original sensor data; Filter the interpolated third original sensor data according to the frequency of the algorithm queue corresponding to the third original sensor data; Filter the interpolated fourth original sensor data according to the frequency of the algorithm queue corresponding to the fourth original sensor data; Use the first original sensor data, the filtered second original sensor data, the filtered third original sensor data, and the filtered fourth original sensor data as the variety of sensor data.
6. The algorithm library control method according to claim 1, wherein The obtaining of a variety of sensor data specifically includes: Obtain multiple pieces of original sensor data through multiple sensors with the same frequency. The multiple pieces of original sensor data include first original sensor data, second original sensor data, third original sensor data, and fourth original sensor data; Filter the second original sensor data according to the frequency of the algorithm queue corresponding to the second original sensor data; Filter the third original sensor data according to the frequency of the algorithm queue corresponding to the third original sensor data; Filter the fourth original sensor data according to the frequency of the algorithm queue corresponding to the fourth original sensor data; Use the first original sensor data, the filtered second original sensor data, the filtered third original sensor data, and the filtered fourth original sensor data as the multiple pieces of sensor data.
7. An algorithm library control system, characterized in that, Comprising: An input module configured to obtain multiple pieces of sensor data; An allocation module configured to, when the multiple pieces of sensor data include acceleration sensor data, allocate the multiple pieces of sensor data to corresponding multiple algorithm queues according to frequency, where each piece of sensor data corresponds to one algorithm queue; A control module configured to control the algorithm queues to which the sensor data is allocated to process their respective corresponding sensor data and output the processing results.
8. The algorithm library control system according to claim 7, wherein The multiple algorithm queues include a first-frequency algorithm queue, a second-frequency algorithm queue, a third-frequency algorithm queue, and a fourth-frequency algorithm queue. The allocation module includes: An allocation sub-module configured to, when the multiple pieces of sensor data include the acceleration sensor data and there is first sensor data in the multiple pieces of sensor data with the same frequency as the acceleration sensor data, allocate the first sensor data and the acceleration sensor data to the first-frequency algorithm queue; A cache sub-module configured to cache the remaining sensor data in the multiple pieces of sensor data except the first sensor data and the acceleration sensor data; The allocation sub-module is configured to, based on a preset time interval for algorithm queue execution, control the second-frequency algorithm queue, the third-frequency algorithm queue, and the fourth-frequency algorithm queue to sequentially obtain the sensor data with corresponding frequencies from the remaining sensor data.
9. The algorithm library control system according to claim 8, characterized in that The allocation sub-module is configured to, when the multiple pieces of sensor data include the acceleration sensor data and there is no first sensor data in the multiple pieces of sensor data with the same frequency as the acceleration sensor data, allocate the acceleration sensor data to the first-frequency algorithm queue.
10. A wearable intelligent device, characterized in that, Comprising a memory and a processor, and a computer program is stored on the memory. When the computer program is executed by the processor, the steps of the algorithm library control method according to any one of claims 1-6 are implemented.