CN113642805A - Algorithm optimization method of Internet of things equipment, electronic equipment and readable storage medium - Google Patents
Algorithm optimization method of Internet of things equipment, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN113642805A CN113642805A CN202110998002.4A CN202110998002A CN113642805A CN 113642805 A CN113642805 A CN 113642805A CN 202110998002 A CN202110998002 A CN 202110998002A CN 113642805 A CN113642805 A CN 113642805A
- Authority
- CN
- China
- Prior art keywords
- data
- algorithm
- training
- internet
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000005457 optimization Methods 0.000 title claims abstract description 37
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 157
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 14
- 230000036541 health Effects 0.000 description 12
- 238000013459 approach Methods 0.000 description 6
- 238000007726 management method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 239000000047 product Substances 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000001133 acceleration Effects 0.000 description 4
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 4
- 230000005484 gravity Effects 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 2
- 238000013523 data management Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 230000011664 signaling Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/20—Analytics; Diagnosis
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Computing Systems (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Telephone Function (AREA)
Abstract
The application discloses an algorithm optimization method of Internet of things equipment, electronic equipment and a readable storage medium, wherein the algorithm optimization method is applied to a server and comprises the following steps: acquiring summarized data and an algorithm result; the summarized data at least comprises sensor data acquired by the Internet of things equipment by using a sensor, and an algorithm result is obtained by processing the sensor data by the Internet of things equipment by using a preset algorithm; if the algorithm result does not meet the preset standard data, training at least part of the summarized data to obtain a training result; and comparing the training result with preset standard data to repeatedly train the summarized data until the accuracy of the preset algorithm meets the preset accuracy. Through the mode, the preset algorithm optimization of the Internet of things equipment can be realized.
Description
Technical Field
The present application relates to the field of internet of things, and in particular, to an algorithm optimization method for internet of things devices, an electronic device, and a readable storage medium.
Background
Generally, with the improvement of various requirements of people for using product equipment, when the product equipment is used for collecting information, a user often wants to keep the timeliness of collecting information of the product equipment and the accuracy of a collection result in the product equipment.
Generally, to obtain an acquisition result by product equipment, an algorithm code is often packaged in the product equipment, and the acquired acquisition information is calculated and processed, so that an acquisition result corresponding to the acquired information is obtained. However, such encapsulated algorithmic code is often solidified on the hardware circuitry of the production device.
Disclosure of Invention
The embodiment of the application provides an algorithm optimization method for internet of things equipment in a first aspect, the algorithm optimization method is applied to a server, and the method comprises the following steps: acquiring summarized data and an algorithm result; the summarized data at least comprises sensor data acquired by the Internet of things equipment by using a sensor, and an algorithm result is obtained by processing the sensor data by the Internet of things equipment by using a preset algorithm; if the algorithm result is not equal to the preset standard data, training at least part of the summarized data to obtain a training result; and comparing the training result with preset standard data to repeatedly train the summarized data until the accuracy of the preset algorithm meets the preset accuracy.
A second aspect of the embodiments of the present application provides an algorithm optimization method for internet of things devices, where the algorithm optimization method is applied to a mobile terminal, and includes:
acquiring summarized data and an algorithm result; the summarized data at least comprises sensor data acquired by the Internet of things equipment by using a sensor, and an algorithm result is obtained by processing the sensor data by the Internet of things equipment by using a preset algorithm;
and sending the summarized data and the algorithm result to a server so that the server trains at least part of the summarized data to obtain a training result when the algorithm result does not meet the preset standard data, and comparing the training result with the preset standard data to determine an optimization scheme aiming at the preset algorithm.
A third aspect of the embodiments of the present application provides a server, where the server includes an obtaining module, configured to obtain summarized data and an algorithm result; the summarized data at least comprises sensor data acquired by the Internet of things equipment by using a sensor, and an algorithm result is obtained by processing the sensor data by the Internet of things equipment by using a preset algorithm;
the training module is used for training at least part of the summarized data to obtain a training result if the algorithm result does not meet the preset standard data;
and the comparison module is used for comparing the training result with the preset standard data until the accuracy rate aiming at the preset algorithm meets the preset accuracy rate.
A fourth aspect of embodiments of the present application provides an electronic device, where the electronic device includes a processor and a memory, where the memory stores a computer program, and the processor is configured to execute the computer program to implement the method of the first aspect or the second aspect of embodiments of the present application.
A fifth aspect of embodiments of the present application provides a computer-readable storage medium, which stores a computer program, and the computer program is capable of implementing the method of the first aspect or the second aspect of embodiments of the present application when executed by a processor.
The beneficial effect of this application is: when the algorithm result is judged not to meet the preset standard data, the summarized data are trained, the training results obtained through training are compared, the training algorithm which does not meet the preset standard data is adjusted and optimized, the preset algorithm is optimized, and the accuracy of the algorithm result of the Internet of things equipment is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of the overall hardware framework of the algorithm optimization method of the present application;
FIG. 2 is a schematic flow chart of a first embodiment of the algorithm optimization method of the present application;
FIG. 3 is a schematic flow chart of one embodiment of step 12 of FIG. 1;
FIG. 4 is a schematic flow chart of one embodiment of step 13 of FIG. 1;
FIG. 5 is a schematic flow chart of a second embodiment of the algorithm optimization method of the present application;
FIG. 6 is a schematic flow chart diagram illustrating one embodiment of step 11 of FIG. 4;
FIG. 7 is a schematic view of a system business design scenario of the algorithm optimization method of the present application;
FIG. 8 is a system signaling flow diagram of the algorithm optimization method of the present application;
FIG. 9 is a schematic diagram of a server according to a third aspect of the present application;
FIG. 10 is a schematic diagram of an electronic device according to a fourth aspect of the present application;
FIG. 11 is a schematic diagram of a fifth aspect of the present application providing a computer-readable storage medium;
FIG. 12 is a schematic block diagram of the hardware architecture of the electronic device of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when", "upon" or "in response to a determination" or "in response to a detection". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted contextually to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".
In order to explain the technical solution of the present application, firstly, a hardware system of an algorithm optimization method is provided, please refer to fig. 1, where fig. 1 is a schematic diagram of an overall hardware framework of the algorithm optimization method of the present application; the hardware system includes an internet of things device 100, a mobile device 200, and a server 300, wherein, as shown in fig. 1, the mobile device 200 may be a smartphone.
Data exchange can be performed between the internet of things device 100 and the mobile device 200, and the mobile device 200 can send an instruction to the internet of things device 100. The internet of things device 100 performs an execution operation corresponding to the instruction after acquiring the specific instruction, for example, the internet of things device 100 executes the acquisition instruction to acquire the acquired data, so that the acquired data is sent to the mobile device 200, and the mobile device 200 forwards the acquired data and sends the acquired data to the server 300. The server 300 is configured to process the collected data to obtain a processing result, and forward the processing result through the mobile device 200 to feedback control the internet of things device 100, such as updating the algorithm version.
The following description is made by using specific embodiments, referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the algorithm optimization method of the present application, where the algorithm optimization distribution is applied to the server 300, and specifically includes the following steps:
s11: acquiring summarized data and an algorithm result;
typically, sensors may be provided in the Internet of things (IoT) device 100 for collecting the required data. For example, the internet of things device 100 may be a bracelet or a watch, wherein the bracelet or the watch may be provided with a gravity acceleration sensor for detecting the number of steps taken by the user; a heart rate sensor may also be provided for monitoring the heart rate of the user.
Specifically, a preset algorithm corresponding to the gravity acceleration sensor is packaged in the bracelet or the watch and used for processing the acquired data to obtain an algorithm result of the step number; similarly, a preset algorithm corresponding to the heart rate sensor is packaged in the bracelet or the watch and used for processing the collected data to obtain an algorithm result of the heart rate.
The summarized data at least comprises sensor data acquired by the internet of things equipment 100 through a sensor, and the algorithm result is obtained by processing the sensor data through the internet of things equipment 100 through a preset algorithm. Of course, the internet of things device 100 may also be other devices, and the sensor in the internet of things device 100 may also be other sensors, which is not limited herein.
S12: if the algorithm result does not meet the preset standard data, training at least part of the summarized data to obtain a training result;
generally, preset standard data, such as gold standard data, can be acquired on the mobile terminal 200, and accurate data acquired by wearing a professional medical device (watch or bracelet) can be used as an algorithm optimization target value. And sends the preset standard data to the server 300 for a comparison condition for judging whether the algorithm result is accurate.
And when the algorithm result is judged not to meet the preset standard data, training the summarized data, specifically, training at least part of the summarized data to obtain a training result, wherein the training result is used for verifying whether the algorithm corresponding to the training has accuracy or not, and further improving the realizability of the optimization algorithm.
S13: and comparing the training result with preset standard data to repeatedly train the summarized data until the accuracy of the preset algorithm meets the preset accuracy.
Training at least part of the summarized data through a training algorithm to obtain a training result for comparison with preset standard data. Specifically, when the training result does not satisfy the preset standard data, for example, the training result is not equal to the preset standard data, an optimization scheme for the preset algorithm may be determined.
Specifically, the system is provided with a preset accuracy rate, for example, 5%, for judging whether at least part of the training summary data of the training algorithm approaches the preset standard data. Generally, the summarized data can be repeatedly trained by adjusting codes of the training algorithm or calling a more proper training algorithm module until the obtained training result is compared with the preset standard data, and the training is stopped when the accuracy of the preset algorithm meets the preset accuracy.
Further, the codes of the preset algorithm are packaged in the internet of things device 100, the preset algorithm is to be optimized, the algorithm for training the summarized data is optimized, which is also called a training algorithm, and then the optimized training algorithm is used for further training at least part of the summarized data until the training result approaches the preset standard data, the training is stopped, and the training algorithm corresponding to the training result approaching the preset standard data is used for optimizing the preset algorithm.
Therefore, when the algorithm result is not equal to the preset standard data, the summarized data are trained, the training results obtained through training are compared, the training algorithm which does not meet the preset standard data is adjusted and optimized, the preset algorithm is optimized, and the accuracy of the algorithm result of the internet of things device 100 is improved.
Further, obtaining summary data and algorithm results includes: acquiring summarized data and an algorithm result sent by the mobile terminal 200; the summarized data comprises mobile terminal information, internet of things equipment information and sensor data, and the internet of things equipment information, the sensor data and an algorithm result are acquired from the internet of things equipment 100 by the mobile terminal.
The mobile terminal information at least comprises user information, scene information and environment information, the internet of things equipment information comprises at least one of an equipment model and an algorithm version, and further the mobile terminal information further comprises at least one of camera data and microphone data.
Further, at least a portion of the summarized data is trained to obtain a training result, referring to fig. 3, fig. 3 is a schematic flowchart of an embodiment of step 12 in fig. 1, and the method specifically includes the following steps:
s21: determining a training task;
generally, the training platform of the server 300 is preset with training tasks, including algorithms and summaries of summarized data, where the summarized data has address identifiers of device models, so as to facilitate identification and acquisition of the training platform. And if the data do not meet the preset standard data, more summarized data can be obtained for model training.
Specifically, a training task corresponding to the training algorithm may be obtained according to the algorithm result, where a code source in the training task is a code database, and the training task corresponding to the code database has a display interface for manually adjusting parameters therein or manually modifying codes therein, such as gitlab.
The gitlab is an open source project for the warehouse management system, the git is used as a code management tool, the webpage service is built on the basis of the git, and public or private projects can be accessed through a webpage interface. It has functionality similar to github, enabling browsing of source code, managing defects and annotations.
S22: screening the summarized data to obtain data to be trained;
generally, the acquired summarized data is doped with noise information, so that the summarized data can be screened, for example, the noise information is denoised, and obvious unreasonable parameters, such as false oscillation step number sensor data, are removed to obtain data to be trained, in order to facilitate the effective implementation of a training algorithm.
Specifically, the server 300 is provided with a health data center, which is a system for providing user management, device management, and data storage, and may be further used to screen summarized data to obtain data to be trained, which is used as the data to be trained.
S23: and training the data to be trained by utilizing the training task to obtain a training result.
Under the condition of training tasks, the data to be trained can be synchronized to the training tasks of the training platform for training, and therefore the training result of the time is obtained and is used as actual data compared with preset standard data.
Specifically, a training model is arranged on the training platform, a training algorithm is packaged in the training model, and specifically, the training model can train data to be trained by referring to data to obtain a training result, wherein the reference result can be reference algorithm result data obtained by wearing wearable equipment, such as reference step number, heart rate and the like.
Further, the training result is compared with the preset standard data to determine the optimization scheme for the preset algorithm, please refer to fig. 4, fig. 4 is a flowchart illustrating an embodiment of step 13 in fig. 1, and the method specifically includes the following steps:
s31: judging whether the algorithm result meets preset standard data or not;
if the algorithm result does not meet the preset standard data, the method proceeds to step S32, i.e., the training task is adjusted, and the step of screening the summarized data to obtain the data to be trained is executed;
if the algorithm result meets the preset standard data, the process proceeds to step S33, that is, the preset algorithm is replaced with the algorithm corresponding to the training task.
Furthermore, the preset algorithm is replaced by an algorithm corresponding to the training task, and the method comprises the following steps:
the algorithm corresponding to the training task is sent to the mobile terminal 200, so that the mobile terminal 200 sends the algorithm corresponding to the training task to the internet of things device 100 to replace the preset algorithm.
In addition, a second aspect of the present application further provides an algorithm optimization method for an internet of things device, where the algorithm optimization method is applied to a mobile terminal 200, please refer to fig. 5, and fig. 5 is a flowchart of a second embodiment of the algorithm optimization method, where the method specifically includes the following steps:
s41: acquiring summarized data and an algorithm result;
typically, sensors may be provided in the Internet of things (IoT) device 100 for collecting the required data. For example, the internet of things device 100 may be a bracelet or a watch, wherein the bracelet or the watch may be provided with a gravity acceleration sensor for detecting the number of steps taken by the user; a heart rate sensor may also be provided for monitoring the heart rate of the user.
Specifically, a preset algorithm corresponding to the gravity acceleration sensor is packaged in the bracelet or the watch and used for processing the acquired data to obtain an algorithm result of the step number; similarly, a preset algorithm corresponding to the heart rate sensor is packaged in the bracelet or the watch and used for processing the collected data to obtain an algorithm result of the heart rate.
The summarized data at least comprises sensor data acquired by the internet of things equipment 100 by using a sensor, and an algorithm result is obtained by processing the sensor data by the internet of things equipment 100 by using a preset algorithm;
s42: and sending the summarized data and the algorithm result to a server so that the server trains at least part of the summarized data to obtain a training result when the algorithm result does not meet the preset standard data, and comparing the training result with the preset standard data so as to train the summarized data repeatedly until the accuracy of the preset algorithm meets the preset standard.
In general, the mobile terminal 200 may acquire preset standard data, such as gold standard data, from a third-party medical institution as accurate data, which may be used as an algorithm optimization target value. And sends the preset standard data to the server 300 for judging whether the algorithm result is accurate.
The summarized data and the algorithm result are sent to the server 300, and when the server 300 determines that the algorithm result does not meet the preset standard data, the summarized data are trained, specifically, at least part of the summarized data can be trained to obtain a training result, so as to verify whether the algorithm corresponding to the training has accuracy, and further improve the realizability of the optimization algorithm.
Specifically, the system is provided with a preset accuracy rate, for example, 5%, for judging whether at least part of the training summary data of the training algorithm approaches the preset standard data. Generally, the summarized data can be repeatedly trained by adjusting codes of the training algorithm or calling a more proper training algorithm module until the obtained training result is compared with the preset standard data, and the training is stopped when the accuracy of the preset algorithm meets the preset accuracy.
Further, at least part of the summarized data is trained through a training algorithm, and a training result can be obtained for comparison with the preset standard data. Specifically, when the training result does not satisfy the preset standard data, for example, the training result is not equal to the preset standard data, an optimization scheme for the preset algorithm may be determined.
Generally, codes of a preset algorithm are packaged in the internet of things device 100, the preset algorithm is to be optimized, the algorithm for training the summarized data is optimized, the training algorithm is also called a training algorithm, the optimized training algorithm is used for further training at least part of the summarized data, when a training result approaches to preset standard data, the training is stopped, and the training algorithm corresponding to the training result approaching to the preset standard data is used for optimizing the preset algorithm.
Therefore, when the algorithm result is judged not to be equal to the preset standard data, the summarized data are trained, the training results obtained through training are compared, the training algorithm which does not meet the preset standard data is adjusted and optimized, the preset algorithm is optimized, and the accuracy of the algorithm result of the Internet of things equipment is improved.
Further, referring to fig. 6, fig. 6 is a schematic flowchart of an embodiment of step 11 in fig. 4, and the method specifically includes the following steps:
s51: sending an acquisition instruction to the Internet of things equipment so as to enable the Internet of things equipment to acquire data;
generally, the mobile terminal serves as an upper layer of an issuing instruction of collected data, the collected instruction can be sent to the internet of things equipment, a sensor is arranged on the internet of things equipment, and the sensor can be enabled through the collected instruction, so that the sensor of the internet of things equipment can collect data according to the collected instruction.
Specifically, the internet of things device 100 is provided with bluetooth as a communication connection. The mobile terminal 200 may be a mobile phone, a display screen and a bluetooth are provided at a mobile phone end, the display screen displays an installed collection application (app), and the mobile phone and the internet of things device 100 can perform data communication by matching the bluetooth on the mobile phone with the bluetooth on the internet of things device. For example, information such as an APP selection algorithm and a scene is collected at a mobile phone terminal, information such as the height and the weight of a volunteer is filled in, and collection is started by clicking.
S52: acquiring Internet of things equipment information, sensor data and algorithm results sent by Internet of things equipment to obtain collected data;
the mobile terminal 200 is used as an intermediate carrier for data transmission, because the mobile terminal 200 and the internet of things device 100 can perform data communication, the internet of things device information, the sensor data and the algorithm result sent by the internet of things device can be obtained through a communication channel created by the data communication, and the collected data is obtained.
Specifically, the acquisition app of the mobile terminal may be set to a preset time period, and in the preset time period, acquisition data corresponding to the preset time period may be acquired.
S53: fusing the collected data with the mobile terminal information to obtain summarized data;
the mobile short message, the acquired reference data and the acquired data are collected by the mobile phone terminal acquisition App in a unified mode to obtain summarized data, which can also be called as file data, a file server is arranged on the server 300 and used for acquiring the file data, and the summarized data are uploaded to a health data center of the server 300 through the access server 300.
The mobile terminal information at least comprises user information, scene information and environment information, the internet of things equipment information comprises at least one of an equipment model and an algorithm version, and further the mobile terminal information further comprises at least one of camera data and microphone data.
Further, the algorithm optimization method further comprises the following steps: and sending an acquisition ending instruction to the internet of things device 100 so that the internet of things device 100 ends data acquisition. Specifically, after the internet of things device 100 collects a preset time period, the mobile phone terminal collects App clicks to finish collection, so that a collection finishing instruction is sent to the internet of things device 100.
In addition, in order to further understand the optimization algorithm method, the present application provides a specific system service scenario for detailed description, please refer to fig. 7, and fig. 7 is a schematic diagram of a system service design scenario of the algorithm optimization method of the present application; the system comprises the internet of things device 100, the mobile terminal 200 and the server 300, wherein data interaction can be performed between the internet of things device 100 and the mobile terminal 200, and data interaction can also be performed between the mobile terminal 200 and the server 300.
The internet of things device 100 may include a sensor 110 and a first processor 120, wherein the sensor 110 is configured to collect internet of things device information, and the first processor 120 is configured to process a portion of the internet of things device information.
The mobile terminal 200 includes a second processor 210 and a touch screen, and is configured to respond to a touch operation of a user to obtain a user instruction, and the second processor 210 is configured to process the user instruction and obtain mobile terminal information.
The server 300 includes a data processing center 310 and a file server 320, wherein the data processing center 310 is provided with at least one training platform 311, the file server 320 can store data acquired from the mobile terminal 200, and the training platform 311 is used for training by calling the data stored in the file server 320.
Further, the internet of things device (IoT device) 100 may be a bracelet or a watch, the mobile terminal 200 may be a mobile phone, and the server 300 may also be a cloud or a data processing center, which is not limited.
Specifically, the collection APP on the mobile terminal 200 connects the IoT device 100 such as a watch/a bracelet through bluetooth, and here, a mobile phone and a bracelet are specifically used for example. Please refer to fig. 8, fig. 8 is a schematic diagram of a system signaling flow of the algorithm optimization method of the present application, which specifically includes the following steps:
s601: sending an acquisition instruction;
information such as APP selection algorithm, scene are collected at the mobile phone end, information such as height and weight of a volunteer is filled, collection is started by clicking, and a collection instruction is sent to the bracelet. The bracelet starts to collect data after receiving a start instruction issued by the mobile phone.
Specifically, bracelet device information, sensor data, and algorithm results obtained by processing sensor data by the bracelet may be collected.
S602: sending the acquired data and the algorithm result;
specifically, IoT equipment information such as imei and algorithm versions, sensor data and algorithm result data are transmitted to the acquisition App through Bluetooth, wherein the algorithm result is obtained by processing the sensor data through a preset algorithm by the bracelet.
The mobile phone is provided with a data acquisition unit, and can temporarily store acquired data and algorithm results.
S603: sending an acquisition stopping instruction;
after the collection is carried out for a period of time, the mobile phone collects App clicks to finish the collection, namely the mobile phone sends a collection finishing instruction to the bracelet. And the bracelet finishes the collection after receiving the collection finishing instruction. This step may be before step S602, or after step S602, as long as the bracelet is not affected to send the collected data and the algorithm result to the mobile phone, and is not limited specifically.
S604: fusing the collected data with the mobile terminal information to obtain summarized data;
the mobile phone acquisition App fuses scene information, environment information, user information, reference data and acquired IoT data worn by the IoT device 100, that is, collects the acquired data and the mobile phone information in a unified manner to obtain summarized data, also called file data.
Specifically, at least user information, scene information, and environment information are generally fused, and microphone data, camera data, contest data, and gold bidding data may be selectively collected singly or in multiple ways.
S605: sending the summarized data and the algorithm result;
specifically, the mobile phone sends the summarized data and the algorithm result to the server 300, that is, uploads the file data to the file server 320, where the file server 320 can be called from the server 300. The summarized data may be uploaded to the data processing center 310, also referred to as a health data center, by way of an access service.
S606: if the algorithm result does not meet the preset standard data, training the summarized data to obtain a training result;
based on the server 300, the health data center of the server 300 is provided with a health laboratory, which may be used for laboratory data storage, test user management, data management, and data security. The summary data and the algorithm result are sent to the data management.
The server 300 further has a training platform 311, and the service user creates a training task on the training (Falcon) platform 311, where a code source of the training task may be gitlab. The business user screens the data needing to be trained at this time in the health data center, screens the Falcon task needing to be used, and synchronizes the data to the Falcon platform 311 after the screening is completed.
And when the algorithm result does not meet the preset standard data, the server 300 starts a task, performs model training on the summarized data by adopting a training algorithm, and stores the result data to the health data center in a callback mode after the training is finished.
S607: comparing the preset standard data with the training result, and repeatedly training the summarized data until the accuracy of the preset algorithm meets the preset accuracy;
and comparing the training result with preset standard data (also called golden standard data) in a health data center. Generally, the health data center is provided with a preset accuracy rate for judging the accuracy of the training result, so as to determine whether the preset algorithm needs to be optimized, and if the training result data is not equal to the gold standard data, the training algorithm is optimized.
Specifically, the training process steps can be repeated by modifying the training algorithm until the accuracy of the training algorithm is satisfactorily improved, and the training is stopped when the obtained training result approaches the golden standard data infinitely.
S608: sending a new algorithm code;
when a satisfactory training result is obtained, the new algorithm code corresponding to the training result can be found to meet the requirements, and the new algorithm code can be established and sent to the mobile phone.
S609: forwarding the new algorithm code;
the mobile phone is used as an intermediate carrier for reprinting, and the new algorithm code is continuously forwarded to the bracelet.
S610: and calling new algorithm codes to upgrade the algorithm version.
After receiving the new algorithm code, the wristband may call a new version of the training algorithm to upgrade the preset algorithm of the IoT device 100, that is, upgrade the algorithm version of the IoT device 100.
In addition, the system can complete all stages from the completion of the acquisition to the preparation training within ten minutes as soon as the time from the data acquisition to the preparation training is shortened. And (3) creating an efficient model training platform, thereby realizing the purpose of fast algorithm iteration and improving the product competitiveness.
Therefore, the method builds a full-link health algorithm tool system from collection, storage, training, safety and the like through internal collection, management and application of data, continuously improves a health algorithm tool chain, provides end-to-end one-stop service, lays a foundation for data analysis and application, builds big data analysis and user insight based on exercise health through user data statistics and mining, and is convenient for three-party data docking and application.
In addition, a server is further provided in a third aspect of the present application, please refer to fig. 9, where fig. 9 is a schematic structural diagram of a server provided in the third aspect of the present application, and the server 6 includes an obtaining module 61, a training module 62, and a comparing module 63, where the obtaining module is configured to obtain summarized data and an algorithm result; the summarized data at least comprises sensor data acquired by the Internet of things equipment by using a sensor, and an algorithm result is obtained by processing the sensor data by the Internet of things equipment by using a preset algorithm; the training module is used for training at least part of the summarized data to obtain a training result if the algorithm result does not meet the preset standard data; and the comparison module is used for comparing the training result with the preset standard data until the accuracy rate aiming at the preset algorithm meets the preset accuracy rate.
In addition, a fourth aspect of the present application further provides an electronic device, please refer to fig. 10, where fig. 10 is a schematic structural diagram of an electronic device according to the fourth aspect of the present application, and the electronic device 7 includes: a processor 71 and a memory 72, the memory 72 having stored therein a computer program 721, the processor 71 being configured to execute the computer program 721 to implement the method according to the first or second aspect of the embodiments of the present application.
In addition, a fifth aspect of the present application further provides a computer-readable storage medium, please refer to fig. 11, fig. 11 is a schematic structural diagram of a computer-readable storage medium according to the fifth aspect of the present application, the computer-readable storage medium 80 stores a computer program 81, and the computer program 81 can be executed by a processor to implement the method according to the first aspect or the second aspect of the embodiments of the present application.
Referring to fig. 12, fig. 12 is a schematic block diagram of a hardware architecture of an electronic device according to the present application, where the electronic device 900 may be an industrial computer, a tablet computer, a mobile phone, a notebook computer, and the like, and the mobile phone is taken as an example in the embodiment. The electronic device 900 may include a Radio Frequency (RF) circuit 910, a memory 920, an input unit 930, a display unit 940, a sensor 950, an audio circuit 960, a wifi (wireless fidelity) module 970, a processor 980, a power supply 990, and the like. Wherein the RF circuit 910, the memory 920, the input unit 930, the display unit 940, the sensor 950, the audio circuit 960, and the WiFi module 970 are respectively connected to the processor 980; the power supply 990 is used to supply power to the entire electronic device 900.
Specifically, the RF circuit 910 is used for transmitting and receiving signals; the memory 920 is used for storing data instruction information; the input unit 930 is used for inputting information, and may specifically include a touch panel 931 and other input devices 932 such as operation keys; the display unit 940 may include a display panel or the like; the sensor 950 includes an infrared sensor, a laser sensor, etc. for detecting a user approach signal, a distance signal, etc.; a speaker 961 and a microphone 962 are connected to the processor 980 through the audio circuit 960 for emitting and receiving sound signals; the WiFi module 970 is configured to receive and transmit WiFi signals, and the processor 980 is configured to process data information of the mobile phone.
The above description is only a part of the embodiments of the present application, and not intended to limit the scope of the present application, and all equivalent devices or equivalent processes performed by the content of the present application and the attached drawings, or directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (10)
1. An algorithm optimization method for Internet of things equipment is applied to a server, and comprises the following steps:
acquiring summarized data and an algorithm result; the summarized data at least comprises sensor data acquired by the Internet of things equipment by using a sensor, and the algorithm result is obtained by processing the sensor data by the Internet of things equipment by using a preset algorithm;
if the algorithm result does not meet preset standard data, training at least part of the summarized data to obtain a training result;
and comparing the training result with preset standard data to repeatedly train the summarized data until the accuracy of the preset algorithm meets the preset accuracy.
2. The method of claim 1,
the acquiring summarized data and algorithm results comprises:
acquiring summarized data and an algorithm result sent by a mobile terminal; the summarized data comprises mobile terminal information, Internet of things equipment information and the sensor data, and the Internet of things equipment information, the sensor data and the algorithm result are acquired from the Internet of things equipment by the mobile terminal;
the mobile terminal information at least comprises user information, scene information and environment information, and the Internet of things equipment information comprises at least one of equipment model and algorithm version.
3. The method of claim 1,
the training at least part of the summarized data to obtain a training result comprises:
screening the summarized data to obtain data to be trained;
and training the data to be trained by utilizing the training task to obtain a training result.
4. The method of claim 3,
the comparing the training result with preset standard data to train the summarized data repeatedly until the accuracy of the preset algorithm meets a preset accuracy includes:
if the algorithm result does not meet the preset standard data, adjusting the training task, and performing the step of screening the summarized data to obtain data to be trained;
and if the algorithm result meets preset standard data, replacing the preset algorithm with the algorithm corresponding to the training task.
5. The method of claim 4,
replacing the preset algorithm with the algorithm corresponding to the training task comprises:
and sending the algorithm corresponding to the training task to the mobile terminal so that the mobile terminal sends the algorithm corresponding to the training task to the internet of things equipment to replace the preset algorithm.
6. An algorithm optimization method for Internet of things equipment is applied to a mobile terminal, and comprises the following steps:
acquiring summarized data and an algorithm result; the summarized data at least comprises sensor data acquired by the Internet of things equipment by using a sensor, and the algorithm result is obtained by processing the sensor data by the Internet of things equipment by using a preset algorithm;
and sending the summarized data and the algorithm result to a server so that the server trains at least part of the summarized data to obtain a training result when the algorithm result does not meet preset standard data, and comparing the training result with the preset standard data to determine an optimization scheme aiming at the preset algorithm.
7. The method of claim 6,
the acquiring summarized data and algorithm results comprises:
sending an acquisition instruction to the Internet of things equipment so as to enable the Internet of things equipment to acquire data;
acquiring the Internet of things equipment information, the sensor data and the algorithm result sent by the Internet of things equipment to obtain collected data;
fusing the collected data with the mobile terminal information to obtain the summarized data;
the mobile terminal information comprises at least one of user information, scene information, environment information, camera data and microphone data, and the Internet of things equipment information comprises at least one of equipment model and algorithm version.
8. A server, comprising:
the acquisition module is used for acquiring summarized data and an algorithm result; the summarized data at least comprises sensor data acquired by the Internet of things equipment by using a sensor, and the algorithm result is obtained by processing the sensor data by the Internet of things equipment by using a preset algorithm;
the training module is used for training at least part of the summarized data to obtain a training result if the algorithm result does not meet preset standard data;
and the comparison module is used for comparing the training result with preset standard data until the accuracy rate aiming at the preset algorithm meets the preset accuracy rate.
9. An electronic device, comprising: a processor and a memory, the memory having stored therein a computer program for execution by the processor to implement the method of any one of claims 1-7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when being executed by a processor, is adapted to carry out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110998002.4A CN113642805A (en) | 2021-08-27 | 2021-08-27 | Algorithm optimization method of Internet of things equipment, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110998002.4A CN113642805A (en) | 2021-08-27 | 2021-08-27 | Algorithm optimization method of Internet of things equipment, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113642805A true CN113642805A (en) | 2021-11-12 |
Family
ID=78424200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110998002.4A Pending CN113642805A (en) | 2021-08-27 | 2021-08-27 | Algorithm optimization method of Internet of things equipment, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113642805A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106951925A (en) * | 2017-03-27 | 2017-07-14 | 成都小多科技有限公司 | Data processing method, device, server and system |
| CN107862468A (en) * | 2017-11-23 | 2018-03-30 | 深圳市智物联网络有限公司 | The method and device that equipment Risk identification model is established |
| CN109948803A (en) * | 2019-03-12 | 2019-06-28 | 深圳灵图慧视科技有限公司 | Algorithm model optimization method, device and equipment |
| CN112070000A (en) * | 2020-09-07 | 2020-12-11 | 上海闻泰信息技术有限公司 | Intelligent recognition algorithm training method and device, terminal server and storage medium |
| CN112257733A (en) * | 2019-10-25 | 2021-01-22 | 北京沃东天骏信息技术有限公司 | Model iteration method, second electronic device and storage medium |
| CN112560612A (en) * | 2020-12-03 | 2021-03-26 | 杭州海康威视数字技术股份有限公司 | System, method, computer device and storage medium for determining business algorithm |
| CN112711621A (en) * | 2021-01-18 | 2021-04-27 | 湛江市前程网络有限公司 | Universal object interconnection training platform and control method and device |
-
2021
- 2021-08-27 CN CN202110998002.4A patent/CN113642805A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106951925A (en) * | 2017-03-27 | 2017-07-14 | 成都小多科技有限公司 | Data processing method, device, server and system |
| CN107862468A (en) * | 2017-11-23 | 2018-03-30 | 深圳市智物联网络有限公司 | The method and device that equipment Risk identification model is established |
| CN109948803A (en) * | 2019-03-12 | 2019-06-28 | 深圳灵图慧视科技有限公司 | Algorithm model optimization method, device and equipment |
| CN112257733A (en) * | 2019-10-25 | 2021-01-22 | 北京沃东天骏信息技术有限公司 | Model iteration method, second electronic device and storage medium |
| CN112070000A (en) * | 2020-09-07 | 2020-12-11 | 上海闻泰信息技术有限公司 | Intelligent recognition algorithm training method and device, terminal server and storage medium |
| CN112560612A (en) * | 2020-12-03 | 2021-03-26 | 杭州海康威视数字技术股份有限公司 | System, method, computer device and storage medium for determining business algorithm |
| CN112711621A (en) * | 2021-01-18 | 2021-04-27 | 湛江市前程网络有限公司 | Universal object interconnection training platform and control method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108345543B (en) | Data processing method, device, equipment and storage medium | |
| CN108182626B (en) | Service pushing method, information acquisition terminal and computer readable storage medium | |
| CN107204964B (en) | Authority management method, device and system | |
| JP2017504121A (en) | Measuring device of user behavior and participation using user interface in terminal device | |
| CN112540996B (en) | Service data verification method and device, electronic equipment and storage medium | |
| CN106021112A (en) | Program testing system, method and device | |
| CN114595124B (en) | Time sequence abnormity detection model evaluation method, related device and storage medium | |
| CN111338910A (en) | Log data processing method, log data display method, log data processing device, log data display device, log data processing equipment and log data storage medium | |
| CN110287466A (en) | A kind of physical template generation method and device | |
| CN111475399B (en) | Virtual test method and device | |
| CN112131093A (en) | Chaos test-based test case automatic generation method and device | |
| CN113868132A (en) | Application program testing method and device, electronic equipment and storage medium | |
| CN106294087B (en) | Statistical method and device for operation frequency of business execution operation | |
| CN107103086B (en) | Data acquisition auditing method and system, and computer readable storage medium | |
| CN113642805A (en) | Algorithm optimization method of Internet of things equipment, electronic equipment and readable storage medium | |
| US20230083205A1 (en) | Method and apparatus for reporting movement path, storage medium, and electronic device | |
| CN106909481A (en) | Interface test method, interface test device and electronic equipment | |
| CN114896165A (en) | Testing method and device of conversation robot system, electronic equipment and storage medium | |
| CN114648336A (en) | Face payment method and device, electronic equipment and storage medium | |
| CN113468260A (en) | Data analysis method and device, electronic equipment and storage medium | |
| CN112053216A (en) | Risk management method of financial product and related device | |
| CN111723003A (en) | Gray scale testing method and device, electronic equipment and storage medium | |
| CN114490307A (en) | Unit testing method, device and storage medium | |
| CN112418806A (en) | Clinical research project management system | |
| CN111913942A (en) | Data quality detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |