CN117480492A - Equipment performance monitoring system - Google Patents
Equipment performance monitoring system Download PDFInfo
- Publication number
- CN117480492A CN117480492A CN202280023725.5A CN202280023725A CN117480492A CN 117480492 A CN117480492 A CN 117480492A CN 202280023725 A CN202280023725 A CN 202280023725A CN 117480492 A CN117480492 A CN 117480492A
- Authority
- CN
- China
- Prior art keywords
- model
- error
- state
- transition
- generator
- 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
- 238000012544 monitoring process Methods 0.000 title description 3
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000006243 chemical reaction Methods 0.000 claims abstract description 21
- 230000004044 response Effects 0.000 claims abstract description 8
- 230000007704 transition Effects 0.000 claims description 41
- 238000005259 measurement Methods 0.000 claims description 22
- 238000001514 detection method Methods 0.000 claims description 17
- 238000004891 communication Methods 0.000 claims description 6
- 230000003287 optical effect Effects 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 description 19
- 238000011156 evaluation Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 239000012634 fragment Substances 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000002604 ultrasonography Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Jib Cranes (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The present invention relates to a system and corresponding method and computer implemented software for improving the performance of at least one electronic device, said device comprising at least one sensor and defining a model of the device's reaction in response to data generated by at least one of said sensors. The system comprises a model generator configured to analyze data generated from the sensor and a reaction to the data and to register an error in the reaction compared to an expected reaction, wherein the model generator is configured to adjust a device model by minimizing an error between an actual output of the model and an expected output of the model based on a set of samples recorded on the at least one electronic device, wherein the recorded samples comprise information related to: and which of a plurality of predefined states the device is in when the error occurred, the time when the error occurred, and the number of errors at a specified time and/or state.
Description
Technical Field
The present invention relates to a system and method for analyzing device performance.
Background
Advanced electronic devices are often manufactured for specific applications in which the device is tuned to handle real world situations. This may include devices such as mobile phones or speech recognition devices in which certain assumptions have been made to enhance the relevant signals and suppress other signals such as background noise etc. or they may include automatic functions that can handle transitions between different modes of use. Although these parameters are chosen to be as realistic as possible, in some cases the background noise or voice command may be different from the assumed actual situation. Although many electronic devices have systems for software updates, it is difficult to obtain sufficiently good information about the device's performance, and thus the update may be insufficient.
Because of differences in the acoustic configuration of the devices, each device must be manually adjusted and calibrated to ensure consistency in performance. This, of course, is a time consuming and costly process. It is therefore an object of the invention to simplify the process.
Disclosure of Invention
It is an object of the invention to provide a system for improving the performance of an electronic device. This is achieved as described in the appended claims.
According to the invention, the device is able to submit device specific information to a preferred cloud-based platform, and the platform is provided with certain product specifications. Based on this information, the system can generate a machine learning model using machine learning techniques. The platform receives performance sample information from the device, compares it to specifications provided by the manufacturer, adjusts the model, and feeds it back into the device as an update. By such means, the platform may adjust the performance of the device by using a machine learning procedure.
For example, device specific software may report measured ultrasound activity in the device environment. The specifications provided by the device manufacturer are based on assumed activities, which means that the device may not be sufficiently adapted to the real environment. For example, the device may be adapted to handle a small number of devices nearby using the same ultrasound measurements, but in some cases, such as in a concert, the background sound profile may be so different that the disturbance reduces the performance of the device.
Another example may relate to a device for playback in an intelligent speaker system, wherein the system should automatically switch to a different speaker when the system is moved into another area. The reported errors may be used to adjust the characteristics of the software device to improve the transition.
Another example relates to changes in screen, microphone and/or speaker performance and functionality when the handset is lifted to the user's ear.
The device may then report measurements representing these conditions, and the analysis concludes that changes must be made to the device design and report the changes back to the manufacturer.
The analysis is preferably performed in a cloud-based system that is capable of communicating with the device and that is capable of both receiving information from and reporting information to the manufacturer.
Another use of the invention may be to control a mobile phone or the like by means of gestures made by a user. By reporting the measured deviation between the pre-determined Cheng Shoushi to be interpreted by the device and the actual actions of one or more specific users, the system can adjust for this.
Drawings
The invention will now be described in more detail with reference to the accompanying drawings, which illustrate the invention by way of example.
Fig. 1 illustrates a simplified version of the invention.
Fig. 2 illustrates a preferred embodiment of the present invention in more detail.
Fig. 3 illustrates the process steps in a machine learning sequence according to the present invention.
Fig. 4 illustrates the definition of recorded errors used by the system.
Detailed Description
As shown in fig. 1, device manufacturers and application developers are allowed to take advantage of their presence and gesture sensing capabilities without having expertise in acoustic or signal processing. This may be accomplished through a cloud-based machine learning platform and use advanced machine learning techniques to detect the presence of a user and predict room occupancy, as well as provide gesture recognition.
The illustration shows the technical architecture of a device manufacturer 1 and a device 3, both in communication with a machine learning service platform 2, preferably cloud-based. The device manufacturer 1 need only define the operating environment of its products (e.g. its memory, storage and computing power, and its power consumption, mechanical settings and component characteristics) and choose their required performance according to software range and sensitivity. Subsequently, in addition to the system-provided set of machine-learning classifiers, the present invention also provides a software integration package specific to its device. Each classifier is a set of parameters that are used to map the reflected ultrasound signals to a set of categories (e.g., one nearby user, two nearby users, or no user). These classifiers require only a small amount of processing power and can therefore be run on any intelligent device.
Of course, machine learning classifiers require a large amount of device-specific data to achieve maximum accuracy. The training is performed in a service platform 2 that hosts data for training the classifier and provides updates based on any new information uploaded to the machine learning training center. The cloud also includes advanced signal processing libraries (for preprocessing acoustic data and reducing the amount of memory and processing power required for classification) and empirical data about hardware performance (i.e., ultrasound recording databases in which any particular impact of the performance characteristics of the various acoustic components and their mechanical design is shown). These libraries work in concert with each other to optimize overall system performance.
After a system according to the present invention is installed on a smart device or configured to communicate with the system, its range, field of view, and performance may be further adjusted (by the manufacturer or end user) through an Application Programming Interface (API). The device may also determine the accuracy of the presence determination by correlating the results with other inputs (such as tactical interactions), thereby optimizing itself, essentially customizing the user experience and improving its future response according to the user's environment.
The invention provides a cloud-based platform which comprises a machine learning algorithm, a recording database and a signal processing tool, and the cloud-based platform works together to reduce deployment time required by standard audio and acoustic configuration and enable the standard audio and acoustic configuration to be more 'plug and play'.
A detailed overview of the system is illustrated in fig. 2.
Manufacturer 1 initially provides instructions to the system as to how the device should react to certain sensor outputs from the sensors included in device 3. The manufacturer also provides the machine learning system with the necessary computer code, sensor characteristics and constraints for model adjustment, as well as the communication protocol by which the machine learning system communicates with the device. The manufacturer may provide predetermined limits for model tuning and communicate directly with the device to receive data from the device, e.g., the same data communicated to the machine learning system for evaluation or development purposes.
Manufacturer 1 also provides machine learning platform 2 with the necessary information including models and adjustment possibilities within these models, as well as the expected response to sensor outputs in the device. This also includes the necessary code for communicating with each device.
Manufacturer 1 is also able to receive updated models from machine learning service model generator 2b in order to evaluate the models from data received from device 3.
The device 3 may comprise two different units 3a, 3b, including a software application 3a adapted to collect data from the device and a processor/engine 3b. The recorded data may come from sensors or from other performance measurements, for example by comparing different data types recorded under the same conditions, and user feedback related to the measurements or conditions received through an appropriate user interface. These data are reported to the cloud-based storage facility 2a for further processing and evaluation. In addition to the data received from the device 3, the storage facility 2a may also contain data collected from other similar devices under relevant conditions.
In addition to the data measured during use of the device, the engine or processor 3b in the device may also report performance to the cloud-based machine learning platform 2.
The engine 3b includes code that allows integration of new models and parameters provided by the system with the aim of improving device performance in specific operations through the learning process of the system.
The cloud-based system 2 is adapted to use the information stored in the storage facility 2a and information related to the model in the device to build an updated model in the model generator 2b based on the properties and capabilities of the device or the reaction from the device and possibly information retrieved from similar devices received from the manufacturer. The generated model may then be fed into the device engine 3b, for example as a software update, to adjust the performance of the device 3.
The model may also be simulated and the simulation results reported back to manufacturer 1 through a visual user interface for further evaluation.
The system according to the invention may also provide the manufacturer 1 with test means to send test cases to the device to check the performance of the device, for example for detecting errors of the software 3a or the hardware 3b.
As described above, the cloud-based system may be adapted to provide support services for different types of devices based on engine code and control parameters from a device manufacturer database and a data store comprising data collected from the device 3 and measurement data and capabilities provided by the device, both the manufacturer and the device being provided with interfaces for suitable communication interfaces for communication with the system.
Monitoring these data provides a basis for machine learning, as the system is able to model and update the performance of the device from new data received from the device and manufacturer. This may include adjusting control parameters in the model based on initial parameters provided by the manufacturer to change the performance of the device by implementing new models and parameters in the device engine or processor controlling the operation. As mentioned above, this will provide a simplified and cost effective method to improve the apparatus.
Examples of this procedure are cited below, in which
An exemplary process according to the present invention performed in a cloud-based system 2 is illustrated in fig. 3, the process comprising the steps of:
10. data from any number of sensors in the device 3, which may be selected from cameras, acoustic sensors, inertial sensors, radar or optical measurements, is collected in cloud memory in the device software 3 a.
11. Specific contents of the marked data, such as data type, time, etc., are marked in the cloud data storage 2 a.
12. The stored data is erased using a manufacturer defined erase routine.
13. The sampled data is preprocessed to model.
14. A model representing the data is constructed based on the preprocessed data.
15. Through an iterative process, the best model is selected based on device performance.
16. The generated new model is deployed in the device.
The step of selecting a model in step 15 may be performed by analyzing user statistics, registering user feedback or software rules such as a comparison between expected performance and measured response in known cases. This step may also include measuring or selecting additional data, such as additional data from other sensors.
An example of how data may be used is illustrated in fig. 4.
Fig. 4 illustrates a transition between the two states 21a and 21B. In these different situations, the device should react in different ways, e.g. the user of the mobile phone picks up the mobile phone from the table and puts the mobile phone to the ear. In this case, the handset may react by enabling the speaker and microphone or disabling the touch sensitivity of the screen. This can be achieved using motion and orientation sensors in the handset.
In state 21a, the sensor should be able to sense the condition of steady state period 22a, i.e. the handset is on a desk, with a high certainty and a low error probability reporting the handset state. Similarly, active use of the handset in state 21b, such as placing the handset at the ear, will be in steady state for period 22e, where the number of error reports is less. However, during the process of lifting the handset to the ear, there will be a transition period 22c where the sensor has difficulty reporting the correct state and accurately adjusting the correct moment or position defining the transition. The transition period may have a known or predetermined length.
According to the present invention, the transition from the first state 21a to the second state 21b further includes a pre-transition state period 22b and a post-transition state period 22d. The pre-transition state and the post-transition state may be defined according to a distance from the assumed transition period 22c or a time before and after occurrence of the transition state period 22 c. Of course, the specific time and distance depends on the type of transition. Further, the pre-transition time and distance and the post-transition time and distance before and after the transition period 22c may be different. Hereinafter, the time periods 22a-22e will also be referred to as "segments".
Referring to the example above in which the handset is lifted from the table towards the ear, the transition may be defined at the moment when the handset is in a substantially upright position. Then, the pre-transition time is the time the handset measures the movement until the assumed halfway time, and the post-transition time represents the latter half time. The number of errors in the pre-transition period and the post-transition period should be small, but the greater the distance from the assumed transition time and/or position, the greater the likelihood of being a true error.
When the steady state, pre-transition state, post-transition state and transition state have been established, the operational error may be detected by the user manually or by analyzing the signal and determining a predetermined error value. The error values may be subdivided into three different types based on their size and/or duration, such as:
error count (Boolean value)
The o error boolean value (error detected, whatever the size/duration of the error)
The o error boolean value (error is less than a predetermined magnitude or less than a predetermined duration).
The o error boolean value (error greater than a predetermined magnitude or exceeding a predetermined duration).
Error count (summary)
Error count (error detected, whatever the size/duration of the error
The o error count (error is less than a predetermined magnitude or less than a predetermined duration).
The o error count (error greater than a predetermined magnitude or exceeding a predetermined duration).
Furthermore, the type of error may also be determined based on the state at which the error occurred. These detected errors can then be used for machine learning.
In addition to the type of error, the presence or location of errors in the segments 22a-22e may be used to obtain information about the errors experienced. For example, it may be:
at any point within the segment
Entire segment
At the beginning of the fragment
At the end of the segment
At the middle of the segment, independent of any errors at the beginning and end.
Other combinations may also be defined, such as errors at the beginning of the segment, but not in the middle or at the end.
Based on these detected errors, different situations can be defined, such as the following examples:
example 1:
technical definition:
fragment: a post-transition 22d from state 0 (not detected) to state 1 (detected).
Error value: boolean value.
Error type: errors in the entire segment.
Analysis:
the system does not detect a transition from state 0 to state 1 for a sufficient period of time.
The possible representation is:
the "approach" cannot be detected when the handset is placed at the ear.
When the area comprises a plurality of defined and detected areas, the user's entry into the new area cannot be detected when he walks into the new area, for example when playing from a device using a smart speaker system.
Example 2:
technical definition:
fragment: pre-transition 22b from state 0 (not detected) to state 1 (detected)
Error value: duration of time
Error type: errors occur at the end of the segment.
Analysis:
the system detects the transition from state 0 to state 1 earlier. How early can be seen from the duration.
The representation is:
the duration of early detection when the handset is placed at the ear.
Example 3:
technical definition:
fragment: steady state 22a
Error value: counting.
Error type: at the middle of the segment, there is no relation to any error at the beginning and end.
Analysis:
the system loses state 1 at least once, does not include late detection (counting starts only after state 1 is reached), and excludes early transitions (counting ignores if a transition of another state occurs at the end of the segment). The error count provides the number.
The representation is:
the handset loses functionality multiple times, such as flashing while talking.
When playing using the smart speaker device, the playback will jump to other areas while staying in an area.
Based on the amount of error information and registration data about the occurrence of errors stored in the cloud-based storage system 2a and the model 2b with relevant parameters in the cloud-based system provided by the manufacturer database, machine-based learning is adapted to propose and compare the models in the simulation and evaluation process in order to find the model and the relevant parameters most likely to reduce the amount of errors. In this way, for example, if the registration of a large number of errors is due to the late switching of modes when lifting the handset to the ear, the model can be adjusted to switch in advance when registering a corresponding movement.
The selected model is then transmitted to the manufacturer for evaluation. In this way, the manufacturer can obtain a new model that is tuned to the actual use of the device, thereby improving performance under changing conditions.
Based on the model, the manufacturer may use hardware or software tests transmitted to the device software application 3a and/or hardware 3b, or reprogram the device with hardware or firmware according to the new model.
Accordingly, one aspect of the present invention may be summarized as providing a computer system and corresponding method for optimizing the performance of a device, the system comprising a data storage adapted to receive predetermined information about the performance of a processor of the device and data collected from sensors in the device, such as acoustic detectors, motion sensors, etc., which are indicative of the use and performance of the device under actual conditions.
More particularly, the present invention relates to a computer system for improving the performance of at least one electronic device. The apparatus includes: a sensor and software for sampling predetermined information related to selected operations performed by the device, and a predetermined model specifying the reaction of the device under predetermined conditions. The sensor may comprise a camera, an acoustic sensor, an inertial sensor, a radar or a measurement such as an optical measurement. The model is initially provided by the manufacturer, specifying the planned performance of the device under certain conditions.
The computer system is further configured to receive and store the sampled information from the device and device information from a manufacturer related to the device, the information including the model.
The information sampled by the device also includes reported errors and/or deviations in the model performance associated with the sampled information. These errors may be detected by the device software or reported by the user through a suitable interface.
The computer system is adapted to generate an adjusted model based on the reported error and the measurements by the sensor and a previous model, and to generate an updated model based on a deviation between the initial model and the measured performance. The updated model is transmitted to the device and can be reported to the manufacturer, who can further reprogram and/or test the performance of the model before updating and testing at the device by updating the firmware or software, such as an application.
The sampling information is preferably marked with a data type, time and/or location marker to ensure a relationship between the sampling information and the reporting information.
To analyze the error detection and related measurements in the sampled information, the system may use a set of predetermined rules configured to iteratively reconfigure the model to reduce the number of error detections.
The set of predetermined rules may include classifying errors according to predetermined steady state and transition states and pre-transition and post-transition states, the iterations configured to reduce errors in the steady state, pre-transition and post-transition states.
Preferably, the computer system is a cloud-based computer system comprising: a data store for receiving measurement data and information relating to device performance characteristics from a device; a model generator for generating an adjusted model based on an initial model provided by the manufacturer and data stored in the data store; and a model evaluation unit for evaluating the generated model and transmitting the model to the manufacturer.
The evaluation unit and the model generator iteratively regenerate and evaluate the model to generate an improved model.
The method and computer implemented software according to the invention comprises the steps of:
in at least one device, sampling information related to error detection and measurements related to said error detection, the detection comprising reports from a user or errors detected by device software,
in said computer network, receiving said information sampled by said device, the network further comprising storage means comprising information relating to device software and capabilities and a model specifying device capabilities,
in the network, the model is adjusted based on the reported errors and the associated measurements,
transmitting the adjusted model to the device, which updates the software according to the adjusted model.
According to another aspect, the present invention relates to a system for improving the performance of at least one electronic device, wherein the device comprises at least one sensor and a model of the device's reaction is defined in response to data generated by the at least one sensor.
The system includes a model generator configured to analyze data generated by the sensor and a reaction to the data, wherein the reaction may be based on an analysis of device performance under measurement conditions or may be provided through an interface used. Errors in the registered response compared to the expected response according to the model.
The model generator is configured to adjust the device model by minimizing an error between an actual output of the model and a desired output of the model based on the set of samples recorded on the at least one electronic device.
The recorded samples include information related to:
which of a plurality of predefined states the device is in when an error occurs,
time of error occurrence
Specifying the amount of error at a time and/or state.
The predefined states are preferably related to transition conditions and include a steady state, a pre-transition state, a transition state, and a post-transition state.
The specific time preferably comprises the beginning of a state, the middle of a state, the end of a state, all of a state or a combination thereof, for example to define the duration of the pre-transition state and/or the time during the state to which the reaction refers.
Thus, the error count may include a boolean count, a summary count, or a duration ratio.
The model generator is preferably a network system in communication with a plurality of devices, wherein the generator is further adapted to communicate with a manufacturer, provided with an initial model and expected performance of the devices, and the devices may be provided with a user interface configured to receive error reports from device users.
The error may be registered at a measured deviation between the expected reaction of the device and the measured reaction, or may be reported via a user interface configured to receive the reaction from the user, e.g. reporting the deviation from an expected operational model.
The system may be configured to analyze error detection and related measurements in the sampled data based on a set of predetermined rules, and the system may be configured to iteratively reconfigure the model based on compiled set reactions or consecutively based on a set of the number of last received reactions in order to reduce the number of error detections.
The sensors in the device may include at least one of cameras, acoustic sensors, inertial sensors, radar or optical measurements, and the analysis of the device performance may be based on one or more of the sensors during a state change.
Yet another aspect of the invention relates to a method for improving the performance of a particular type of device, the method comprising the steps of:
in at least one device, information relating to error detection and measurements relating to said error detection are sampled, the detection comprising a report from a user or an error detected by device software,
in a model generator, receiving said information sampled by said device, the generator further comprising storage means comprising information relating to device software and capabilities and a model specifying device capabilities,
in the generator, the model is adjusted based on the reported errors and the associated measurements,
transmitting the adjusted model to the device, the device updating software according to the adjusted model, and
wherein the model generator adjusts the device model by minimizing an error between an actual output of the model and a desired output of the model based on a set of samples recorded on the at least one electronic device, wherein the recorded samples include information related to:
which of a plurality of predefined states the device is in when an error occurs,
time of error occurrence
Specifying the amount of error at a time and/or state.
The predefined states are preferably related to transitions and include a steady state, a pre-transition state, a transition state, and a post-transition state.
The specific time preferably includes a start of a state, an intermediate of a state, an end of a state, all of a state, or a combination thereof, and the error count includes a boolean count, a summary count, or a duration ratio.
Claims (15)
1. A system for improving the performance of at least one electronic device, the device comprising at least one sensor and defining a model of the device's reaction in response to data generated by at least one of the sensors,
the system includes a model generator configured to analyze data generated from the sensor and a reaction to the data and register an error of the reaction compared to an expected reaction, wherein
The model generator is configured to adjust a device model by minimizing an error between an actual output of the model and a desired output of the model based on a set of samples recorded on the at least one electronic device, wherein the recorded samples include information related to:
which of a plurality of predefined states the device is in when an error occurs,
time of error occurrence
Specifying the amount of error at a time and/or state.
2. The system of claim 1, wherein the predefined state relates to a transition, and the predefined state comprises a steady state, a pre-transition state, a transition state, and a post-transition state.
3. The system of claim 1, wherein the particular time comprises a start of a state, an intermediate of a state, an end of a state, all of a state, or a combination thereof.
4. The system of claim 1, wherein the error count comprises a boolean count, a summary count, or a duration ratio.
5. The system of claim 1, wherein the model generator is a network system in communication with a plurality of devices.
6. The system of claim 5, wherein the generator is further adapted to communicate with a manufacturer, the generator being provided with an initial model and expected performance of the device.
7. The system of claim 1, wherein the device is provided with a user interface configured to receive error reports from a device user.
8. The system of claim 1, wherein the error is registered as a measured deviation between an expected reaction and a measured reaction of the device.
9. The system of claim 1, configured to analyze error detection and correlation measurements in the sampled data based on a set of predetermined rules, the system configured to iteratively reconfigure the model so as to reduce the number of error detections.
10. The system of claim 1, wherein the sensor comprises at least one of: camera devices, acoustic sensors, inertial sensors, radar or optical measurements.
11. A method for improving the performance of a particular type of device, the method comprising the steps of:
● in at least one device, information related to error detection and measurements related to said error detection are sampled, said detection comprising reports from a user or errors detected by device software,
● in a model generator, receiving said information sampled by said device, said generator further comprising storage means, said storage means comprising information relating to device software and capabilities and comprising a model specifying device capabilities,
● in the generator, based on the reported error sumThe relevant measurement results are used to adjust the model,
● transmitting the adjusted model to the device, the device updating software to correspond to the adjusted model, and wherein the model generator adjusts a device model by minimizing an error between an actual output of the model and a desired output of the model based on a set of samples recorded on the at least one electronic device, wherein the recorded samples include information related to:
which of a plurality of predefined states the device is in when an error occurs,
time of error occurrence
Specifying the amount of error at a time and/or state.
12. The method of claim 11, wherein the predefined state relates to a transition, and the predefined state comprises a steady state, a pre-transition state, a transition state, and a post-transition state.
13. The method of claim 11, wherein the particular time comprises a start of a state, an intermediate of a state, an end of a state, all of a state, or a combination thereof.
14. The system of claim 11, wherein the error count comprises a boolean count, a summary count, or a duration ratio.
15. Computer implemented software product configured to perform the steps of at least one of claims 11 to 14.
Applications Claiming Priority (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US202163165369P | 2021-03-24 | 2021-03-24 | |
| US63/165,369 | 2021-03-24 | ||
| NO20210589 | 2021-05-11 | ||
| PCT/EP2022/057423 WO2022200309A1 (en) | 2021-03-24 | 2022-03-22 | Device performance monitoring system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117480492A true CN117480492A (en) | 2024-01-30 |
Family
ID=83744646
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202280023725.5A Pending CN117480492A (en) | 2021-03-24 | 2022-03-22 | Equipment performance monitoring system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN117480492A (en) |
| NO (1) | NO20210589A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| NO20220004A1 (en) | 2022-01-03 | 2023-07-04 | Elliptic Laboratories Asa | Robust virtual sensor |
-
2021
- 2021-05-11 NO NO20210589A patent/NO20210589A1/en unknown
-
2022
- 2022-03-22 CN CN202280023725.5A patent/CN117480492A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| NO20210589A1 (en) | 2022-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10530499B2 (en) | Methodology of using the various capabilities of the smart box to perform testing of other functionality of the smart device | |
| CN109412900B (en) | Network state recognition method, model training method and model training device | |
| CN112364439B (en) | Simulation test method and device for automatic driving system and storage medium | |
| CN102231131B (en) | Testing software in electronic device | |
| CN104516812A (en) | Method and device for testing software | |
| CN109359056A (en) | A kind of applied program testing method and device | |
| EP3525524B1 (en) | Determination of device body location | |
| KR20190029463A (en) | Tracking of maintenance trajectory in elevator system | |
| CN117480492A (en) | Equipment performance monitoring system | |
| CN108227007A (en) | It is adjustable to enter safety sensor | |
| CN114760339A (en) | Fault prediction method, apparatus, device, medium, and product | |
| CN106253996A (en) | Sensitivity decay testing method and device | |
| CN106445806A (en) | Software testing method and device | |
| CN115668786A (en) | Adaptive radio configuration in a wireless network | |
| US20240176725A1 (en) | Device performance monitoring system | |
| JP2024512022A (en) | Equipment performance monitoring system | |
| US20100120416A1 (en) | Method for generating a signal train which can be played back on a tester for testing a mobile radio | |
| KR20130029635A (en) | Evaluation module for speech recognition performance and method thereof | |
| CN111650454A (en) | Method, device and system for evaluating state of electronic equipment and storage medium | |
| US20240144098A1 (en) | Artificial intelligence (ai)-channel state information (csi) automated labeling method | |
| US11546035B2 (en) | Event detection method and system thereof | |
| KR20220071771A (en) | System, apparatus and method for recognizing license plate of vehicle and appratus for managing the same | |
| KR20240030037A (en) | Apparatus for sound recognition and method for controlling thereof | |
| CN117969973A (en) | Electromagnetic monitoring real-time analysis system, method, device and medium | |
| CN113593564A (en) | Processing method for device test, test system, electronic device and storage medium |
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 |