Power anomaly detection method, image forming apparatus, model training method, and model training apparatus

Abstract

The embodiment of the invention provides a power anomaly detection method, image forming equipment, and a model training method and equipment. In the technical scheme provided by the embodiment of the invention, the power anomaly detection method comprises the following steps: acquiring current detection data of the image forming equipment, the detection data comprising the complete machine power, the environment temperature and the working state of the image forming equipment; and inputting the current detection data into a power anomaly detection model to obtain an anomaly detection result. Power anomaly detection can be carried out without adding a monitoring circuit to each power consumption module, so that the detection cost is reduced.

Description

[Technical field]

[0001] The present invention relates to the field of printer power detection, and in particular to a power anomaly detection method, an image forming device, and a model training method and device. [Background technology]

[0002] The power of a laser printer is relatively high. There are multiple power supplies and power consumption modules inside the printer. For example, the fixing heating module, image scanning engine, laser emission unit, imaging control module, etc. all have their own power supply voltages and consume power. If the power is abnormal, it may cause the printer's energy consumption to increase and may even cause safety problems.

[0003] One solution is to add monitoring circuits to these power consumption modules, for example, by monitoring the electrical signals of the branches by means of series-parallel sensors to determine the power consumption. However, this method will increase the hardware circuit cost. [Summary of the invention]

[0004] In view of this, the embodiments of the present invention provide a power anomaly detection method, an image forming device, a model training method and a device, which can perform power anomaly detection without adding a monitoring circuit to each power consumption module, thereby reducing the detection cost.

[0005] In a first aspect, an embodiment of the present invention provides a power anomaly detection method, the method comprising:

[0006] Acquire current detection data of the image forming device, wherein the detection data includes the whole machine power, ambient temperature and working status of the image forming device;

[0007] The current detection data is input into a power anomaly detection model to obtain an anomaly detection result.

[0008] Optionally, after inputting the current detection data into the power anomaly detection model to obtain an anomaly detection result, the method further includes:

[0009] It is determined that the anomaly detection result includes an anomaly handling strategy, and an operation corresponding to the anomaly handling strategy is performed.

[0010] Optionally, before executing the operation corresponding to the exception handling strategy, the method further includes:

[0011] If the exception handling policy is applicable to the image forming device, an operation corresponding to the exception handling policy is performed.

[0012] Optionally, the working state includes a main state and working parameters corresponding to the main state.

[0013] Optionally, the working state further includes sub-states and working parameters corresponding to the sub-states.

[0014] Optionally, the detection data further includes: a fault code, wherein the fault code is used to indicate an abnormality type corresponding to a main state or an abnormality type corresponding to a sub-state.

[0015] On the other hand, an embodiment of the present invention provides a model training method, the method comprising:

[0016] Preliminary training of the AI ​​model is performed by inputting a large amount of historical detection data of normal operation of the image forming device into the AI ​​model;

[0017] The AI ​​model is corrected and trained using historical detection data of abnormal working of the image forming device to obtain a power abnormality detection model; the power abnormality detection model is used to output an abnormality detection result based on the current detection data of the image forming device, and the detection data includes: the whole machine power, ambient temperature and working status of the image forming device.

[0018] Optionally, before the method uses the historical detection data of the abnormal operation of the image forming device to perform correction training on the AI ​​model to obtain the power abnormality detection model, it also includes:

[0019] In response to a scoring operation on an output result of the AI ​​model, correction training is performed on the AI ​​model.

[0020] On the other hand, an embodiment of the present invention provides an image forming device, including a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, and is characterized in that the program instructions implement the steps of the above-mentioned power anomaly detection method when loaded and executed by the processor.

[0021] On the other hand, an embodiment of the present invention provides a model training device, comprising a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, and is characterized in that the program instructions implement the steps of the above-mentioned model training method when loaded and executed by the processor.

[0022] On the other hand, an embodiment of the present invention provides a storage medium, which includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the above-mentioned power anomaly detection method or model training method.

[0023] In the technical scheme of the power anomaly detection method, image forming device, model training method and device provided by the embodiment of the present invention, the power anomaly detection method comprises: obtaining the current detection data of the image forming device, the detection data comprises the whole machine power, ambient temperature and working state of the image forming device; inputting the current detection data into the power anomaly detection model to obtain the anomaly detection result. It is not necessary to add a monitoring circuit to each power consumption module to perform power anomaly detection, thereby reducing the detection cost.

Brief Description of the Drawings

[0024] Figure 1 A flow chart of a power anomaly detection method provided by an embodiment of the present invention;

[0025] Figure 2 A flowchart of another power anomaly detection method provided by an embodiment of the present invention;

[0026] Figure 3 Schematic diagram of anomaly detection results in an embodiment of the present invention;

[0027] Figure 4 is a schematic diagram of the power supply level of the image forming device in an embodiment of the present invention;

[0028] Figure 5 A schematic diagram of three types of power detection protection implemented by the power anomaly detection method provided in an embodiment of the present invention;

[0029] Figure 6 Schematic diagram of the input and output of the power anomaly detection model in an embodiment of the present invention;

[0030] Figure 7 A schematic diagram of a self-check process of a whole machine component in an embodiment of the present invention;

[0031] Figure 8 A flowchart of a model training method provided by an embodiment of the present invention;

[0032] Fig. 9 A flowchart of another model training method provided by an embodiment of the present invention;

[0033] Fig.10 This is a schematic diagram of input data when training an AI model in an embodiment of the present invention;

[0034] Fig.11 A schematic diagram of the structure of a power anomaly detection device provided by an embodiment of the present invention;

[0035] Fig.12 A schematic diagram of the structure of a model training device provided by an embodiment of the present invention;

[0036] Fig.13A schematic diagram of an electronic device provided by an embodiment of the present invention. [Specific implementation method]

[0037] In order to better understand the technical solution of the present invention, the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0038] It should be clear that the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0040] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0041] For laser printers, the whole machine working power is relatively large (generally more than 500W), of which the fixing component accounts for the largest proportion of the whole machine power. If the heating circuit or detection circuit corresponding to the fixing component is abnormal, it may cause abnormal heating of the fixing, causing machine failure, or even fire safety accidents.

[0042] The current mainstream solution is to install a sensor to detect the temperature of the fixing component and take corresponding protective measures. The biggest disadvantage of this solution is that it can only detect and protect the fixing component, but cannot protect the entire machine. Improper assembly of the temperature sensor will also cause deviations in temperature detection, making the protection ineffective.

[0043] Printers are electrical devices, and their working conditions can be reflected in their power consumption to a certain extent. For a printer that is not turned on, the power consumption should be zero or close to zero; when the printer is in standby mode, all motors stop running, and the fuser is in a low-power output state or no output; when the printer is printing, several motors start running, and the fuser is heated (full power output for a certain period of time), and the power consumption of the whole machine will increase significantly.

[0044] One solution is to add a monitoring circuit to each power consumption module inside the printer, for example, by monitoring the electrical signal of the branch circuit by means of series-parallel sensors to determine the power consumption. However, this method will increase the hardware circuit cost.

[0045] In view of the above technical problems, an embodiment of the present invention provides a power anomaly detection method, which can perform power anomaly detection without adding a monitoring circuit to each power consumption module, thereby reducing the detection cost.

[0046] Figure 1 Flow chart of a power anomaly detection method provided by an embodiment of the present invention. The power anomaly detection method provided by an embodiment of the present invention is applied to an image forming device including a power anomaly detection model, such as Figure 1 As shown, the method includes: step 101-step 102.

[0047] Step 101 : obtaining current detection data of an image forming device, where the detection data includes the whole machine power, ambient temperature and working status of the image forming device.

[0048] Step 102: Input the current detection data into the power anomaly detection model to obtain an anomaly detection result.

[0049] In a technical solution of a power anomaly detection method provided by an embodiment of the present invention, the method comprises: obtaining current detection data of an image forming device, the detection data including the whole machine power, ambient temperature and working state of the image forming device; inputting the current detection data into a power anomaly detection model to obtain an anomaly detection result. Power anomaly detection can be performed without adding a monitoring circuit to each power consumption module, thereby reducing the detection cost.

[0050] Figure 2 A flowchart of another power anomaly detection method provided by an embodiment of the present invention is as follows: Figure 2 As shown, the method includes: step 201-step 203.

[0051] Step 201: Acquire current detection data of the image forming device.

[0052] In the embodiment of the present invention, each step is performed by an image forming device, for example, the image forming device is a printer.

[0053] Exemplarily, the detection data includes the whole machine power, ambient temperature, and working status of the image forming device.

[0054] The embodiment of the present invention adds a voltage detection element (such as a voltage sensor) and a current detection element (such as a current sensor) in the electrical circuit of the image forming device, and collects the device input voltage and device input current of the image forming device through the voltage detection element and the current detection element.

[0055] Among them, the device input voltage and device input current of the image forming device are the voltage and current of the whole machine, which refer to the AC voltage and current input from the mains to the image forming device. A sensor can be added to the AC input part of the image forming device for detection.

[0056] Exemplarily, a current sensor may be provided at one end of the AC power source, and a voltage sensor may be provided at two ends of the AC power source.

[0057] Among them, the commonly used methods for voltage sampling include voltage dividers, optocouplers, and voltage transformers; the commonly used methods for current sampling include shunt resistors, Hall effect sensors, and current transformers.

[0058] Among them, the ambient temperature has a significant impact on the performance of the internal components of the laser printer and the heating process. For example, too low a temperature will make it take longer for the fixing component to heat to the target temperature. Therefore, the abnormal detection of power needs to take into account the impact of ambient temperature.

[0059] There are a large number of integrated modules that can be used for ambient temperature detection. The embodiment of the present invention can use an ambient temperature sensor preset inside the image forming device.

[0060] Exemplarily, the whole machine power of the image forming device is calculated according to the collected device input voltage and device input current. The power calculation formula is: P=U*I*cosθ, where θ is the vector angle between voltage U and current I.

[0061] Exemplarily, the working state includes a main state and working parameters corresponding to the main state.

[0062] Exemplarily, the working state also includes sub-states and working parameters corresponding to the sub-states.

[0063] The working parameters carried by the working state, such as the voltage and current of the motor and other components involved in the module (rather than the voltage and current of the whole machine), for example, when the main state is printing and the sub-state is developing, the developing power supply voltage and the voltage and current of the developing roller can be used as working parameters. When the main state is scanning and the sub-state is scanning by the automatic document feeder (ADF), the power supply, motor voltage and motor current of the ADF motor can be used as working parameters. When the main state is printing and the sub-state is heating, the fixing target temperature or paper type can be used as working parameters. It should be noted that the aforementioned voltage, current and other parameters can be determined based on the signal sent by the controller instead of the actual measured data. For example, when the controller determines the target developing voltage, the target developing voltage can be used as a working parameter. This is because the target developing voltage will also affect the power of the printer. Using the target developing voltage as a working parameter does not require measuring circuit parameters through additional voltage or current detection elements, which helps to further save costs.

[0064] For printers, the main working states are: initialization, standby, sleep, printing, scanning, and failure. Different main states are subdivided into different sub-states. For example, the main printing state will have sub-states such as paper feeding, correction, development, and fixing. Different working states have different numbers of working electrical components, resulting in different power consumption.

[0065] Exemplarily, the detection data also includes: a fault code. The fault code is used to indicate the abnormality type corresponding to the main state or the abnormality type corresponding to the sub-state.

[0066] Among them, the image forming device can read the working status and fault code from the device firmware program.

[0067] Step 202: Input the current detection data into the power anomaly detection model to obtain an anomaly detection result.

[0068] Exemplarily, the power anomaly detection model is a model obtained by training an artificial intelligence (AI) model, and is used to output anomaly detection results based on input detection data.

[0069] Step 203: Determine that the anomaly detection result includes an anomaly handling strategy, and perform an operation corresponding to the anomaly handling strategy.

[0070] In the embodiment of the present invention, the image forming device may also issue an alarm according to the abnormality type to prompt the user that the abnormality exists.

[0071] In some possible embodiments, step 203 specifically includes: determining that the abnormality detection result includes an abnormality handling strategy, and if the abnormality handling strategy is applicable to the image forming device, executing an operation corresponding to the abnormality handling strategy.

[0072] Before executing the operation corresponding to the exception handling policy, it is necessary to determine whether the exception handling policy is applicable to the image forming device. If so, the operation corresponding to the exception handling policy is executed; if not, the operation corresponding to the exception handling policy is not executed.

[0073] In the embodiment of the present invention, among the operations corresponding to the exception handling strategy, the last operation that can start the protection effect is to disconnect the power supply. Figure 4 FIG. 1 is a schematic diagram of the power supply level of the image forming device in an embodiment of the present invention. Figure 4 As shown, the power supply in the whole machine is in a tree-like and hierarchical structure. The first-level power supply is the whole machine power supply; the second-level power supply includes: main power supply and other power supplies. Among them, the third-level power supply under the main power supply branch includes: print engine power supply and scanning engine power supply; the third-level power supply under the other power supply branch includes: data board power supply, panel power supply and others. Among them, the fourth-level power supply under the print engine power supply branch includes: fixing power supply, main motor power supply, laser scanning unit (Laser Scanning Unit, LSU) component power supply, and other component power supplies; the fourth-level power supply under the scanning engine power supply branch includes: ADF motor power supply and other component power supplies.

[0074] In the scenario where the power classification is sufficiently detailed, the embodiment of the present invention can specifically turn off the corresponding power supply so that the failure of some components does not affect the use of other components. For example, when a print engine failure is detected, only turning off the print engine power supply can allow the printer to continue to use the scanning function, thereby improving the overall availability of the machine.

[0075] In summary, the embodiment of the present invention detects the voltage, current and ambient temperature of the whole machine through sensors, and reads the working status and fault code of the device from the device firmware program; the image forming device is placed in different states of the above parameters, and the printer is manually marked to determine what type of abnormality it is in, or what type of abnormality handling strategy should be adopted; the above information is used as input to train the AI ​​model to obtain a power abnormality detection model. In actual use, the image forming device monitors the voltage, current, ambient temperature, working status, and fault code of the whole machine in real time, and inputs them into the power abnormality detection model, and then the model outputs the abnormality detection result. Among them, when the abnormality detection result is abnormal, the abnormality detection result includes the abnormality type and the abnormality handling strategy.

[0076] Optionally, the embodiment of the present invention can also add a humidity detection element and an atmospheric pressure detection component in the electrical circuit of the image forming device. The detection data also includes: environmental humidity and atmospheric pressure values.

[0077] For example, Figure 5 A schematic diagram of three types of power detection protection implemented by the power anomaly detection method provided in an embodiment of the present invention, such as Figure 5 As shown, the embodiment of the present invention realizes fixed threshold protection of power, AI model protection and self-check of whole machine components through whole machine power, ambient temperature and humidity, atmospheric pressure value, etc.

[0078] Among them, the fixed threshold protection is a conventional threshold type protection, which determines in real time whether the current power is within the allowable power range of the current machine working state. If it exceeds the range, an alarm is issued and the main power supply is disconnected.

[0079] After the fixed threshold protection is activated, the main power supply will be disconnected. If the abnormality cannot be resolved after disconnecting the main power supply, the power supply of the entire machine will be disconnected.

[0080] As shown in Table 1, different working states correspond to different allowable power ranges. The range value of the fixed threshold protection is a combination of the theory and actual measurement of the R&D personnel. In principle, the larger the range value, the more likely it is to avoid false alarms.

[0081] Table 1 Allowable power range of image forming equipment in different working states

[0082] Serial number Working status Minimum allowed power Maximum allowable power 1 Power on A1 A2 2 Preheat B1 B2 3 Standby C1 C2 4 Hibernation D1 D2 5 Fault E1 E2 6 Print F1 F2 7 scanning G1 G2 8 Print + Scan H1 H2

[0083] Due to differences in the materials used by the printer and the environment, the operating power of the printer will vary from person to person. Strategies such as fixed threshold protection have their application limitations. Figure 6 Schematic diagram of the input and output of the power anomaly detection model in the embodiment of the present invention. Since the AI ​​model based on the neural network has the ability to learn data, the power anomaly detection model is obtained by training the AI ​​model, such as Figure 6 As shown, the embodiment of the present invention transmits the real-time whole machine power, working status, ambient temperature and humidity values, and atmospheric pressure value (altitude) into the power anomaly detection model. The power anomaly detection will analyze the abnormal situation of the current printer, that is, whether there is an abnormality, and if so, give the type of abnormality; when there is an abnormality, infer the abnormal component, that is, which component has the abnormality, and give an abnormality handling strategy.

[0084] For example, the self-test of the whole machine components can be initiated and confirmed by the user. The printer turns on each component separately, lets it work independently, and then performs power detection to determine whether the component is working normally. The normal power value range of each component is determined by the R&D personnel based on actual measurements and is a program-fixed value. After the test of each component is completed, turn on the whole machine test and try to copy or print a page of document to check whether the operating power is normal.

[0085] For example, Figure 7 FIG. 1 is a schematic diagram of a self-check process of a whole machine component in an embodiment of the present invention. Figure 7As shown, after confirming to start the self-check, the main motor self-check is performed first. If the main motor is detected to be abnormal, prompts and suggestions are given through error reporting; if the main motor is detected to be normal, the LSU motor self-check is continued. If the LSU motor is detected to be abnormal, prompts and suggestions are given through error reporting; if the LSU motor is detected to be normal, other components are continued to be self-checked. If other components are abnormal, prompts and suggestions are given through error reporting; if others are detected to be normal, the whole machine self-check is performed. If the whole machine self-check is abnormal, prompts and suggestions are given through error reporting; if the whole machine self-check is normal, the self-check is completed and the process ends.

[0086] Therefore, the embodiments of the present invention can perform fixed threshold protection, AI model protection and whole-machine component self-check on power, which can better protect the safety of image forming equipment and improve the availability of the printer to a certain extent.

[0087] In summary, the power anomaly detection method provided by the embodiment of the present invention has at least the following beneficial effects:

[0088] 1) The embodiment of the present invention does not need to add a monitoring circuit to each power consumption module, and can also perform power anomaly detection, thereby reducing the detection cost.

[0089] 2) The embodiment of the present invention takes into account the current working state of the image forming device when determining the exception handling strategy. For example, if the model output result indicates that there is a serious abnormality, the power supply of the image forming device can be turned off regardless of the current working state of the image forming device. If a subunit has a non-serious fault and a job is currently being executed, the power supply of the subunit can be turned off after the job is processed. If the abnormality detection result does not belong to the normal value but cannot be classified into a specific abnormality, the current detection data is recorded in the memory for reporting to the server, etc. Since the training parameters include the current working state, different processing strategies can be made when the image forming device is in different states. In contrast, in conventional image forming device technology, the entire machine is generally stopped if any module has an abnormality, even if the problem is not a serious problem. Therefore, the embodiment of the present invention can improve the user's usage efficiency.

[0090] 3) The embodiment of the present invention takes the ambient temperature into consideration when determining the abnormality handling strategy. This is because there are a large number of motors inside the image forming device, and when the motor has abnormally high power, it is likely to accumulate heat due to rapid heating. Therefore, the embodiment of the present invention also takes the ambient temperature as a factor of power abnormality, and uses the ambient temperature sensor inside the image forming device instead of setting a contact temperature sensor for each motor, which can enhance the accuracy of the machine learning model while saving hardware costs.

[0091] 4) The embodiment of the present invention uses fault codes as the input of the model. On the one hand, it takes into account that the firmware program of the image forming device itself has preset fault detection logic, and the fault code can be used instead of obtaining other complex parameters to save the cost of the training stage. On the other hand, it takes into account that different image forming devices may have different fault codes. For example, for the failure of the fixing component to be inserted incorrectly, the fault codes of some models generally classify it as a fixing failure. Once a fixing failure occurs, the whole machine will shut down; while the fault codes of some models classify it as a separate failure called "fixing missing insertion". This failure can be solved by restarting or reassembly by the user without the need for after-sales maintenance access. This shows that the relationship between the fault code and the exception handling strategy is relatively close. The fault code can ensure that the solution strategy provided by the model is adapted to this type of model.

[0092] With respect to the above power anomaly detection model, an embodiment of the present invention provides a model training method.

[0093] Figure 8 A flow chart of a model training method provided by an embodiment of the present invention, such as Figure 8 As shown, the method includes: step 301-step 302.

[0094] Step 301: Perform preliminary training on the AI ​​model by inputting a large amount of historical detection data showing that the image forming device is working normally into the AI ​​model.

[0095] Step 302: Use the historical detection data of the image forming device's working abnormalities to correct and train the AI ​​model to obtain a power abnormality detection model; the power abnormality detection model is used to output an abnormality detection result based on the current detection data of the image forming device, and the detection data includes: the whole machine power, ambient temperature and working status of the image forming device.

[0096] In a technical solution of a model training method provided by an embodiment of the present invention, the method includes: preliminary training of the AI ​​model by inputting a large amount of historical detection data of normal operation of the image forming device into the AI ​​model; correcting and training the AI ​​model using historical detection data of abnormal operation of the image forming device to obtain a power anomaly detection model; the power anomaly detection model is used to output an anomaly detection result according to the current detection data of the image forming device, and the detection data includes: the whole machine power, ambient temperature and working status of the image forming device. Power anomaly detection can be performed without adding a monitoring circuit to each power consumption module, thereby reducing the detection cost.

[0097] Fig. 9 A flowchart of another model training method provided by an embodiment of the present invention is as follows: Fig. 9 As shown, the method includes: step 401-step 403.

[0098] Step 301: Perform preliminary training on the AI ​​model by inputting a large amount of historical detection data showing that the image forming device is working normally into the AI ​​model.

[0099] This step is at the factory stage, where R&D and testing personnel build various usage environments and scenarios to input a large amount of historical detection data of the normal operation of image forming equipment into the AI ​​model.

[0100] Exemplarily, the historical detection data is historical detection data.

[0101] For example, Fig.10 Schematic diagram of input data when training an AI model in an embodiment of the present invention, such as Fig.10 As shown in the figure, when the AI ​​model is trained, the input data includes the whole machine power, ambient temperature, working status, fault code, strategy / abnormal type. Among them, the historical detection data includes the whole machine power, ambient temperature, working status, and fault code.

[0102] The different working states of the image forming equipment have different numbers of working electrical components, resulting in different power consumption. Therefore, to better train the AI ​​model, it is necessary to subdivide the working state as much as possible. Each specific working state can carry working parameters as needed and provide them to the AI ​​model so that anomalies can be identified more accurately.

[0103] Fig.10 In the training phase, the "strategy / exception type" is manually determined in advance. For example, an engineer can observe and determine what state the current state of the printer belongs to and what strategy should be executed during the training phase. In the actual use phase, the "strategy / exception type" is an output value.

[0104] Optionally, the historical detection data also includes: ambient humidity and atmospheric pressure values.

[0105] Step 402: In response to the scoring operation on the output results of the AI ​​model, the AI ​​model is subjected to the first correction training.

[0106] This step is at the factory stage, where R&D and testing personnel simulate fault scenarios to score the output results of the AI ​​model to correct and train the AI ​​model.

[0107] When training an AI model, a mechanism is needed to "score" the output results. The printer itself has a fault detection mechanism. When the trigger conditions are met, the printer will report fault information and enter a fault (error) state. Different faults are distinguished by different fault code values ​​in the printer. If the value is 0, it means there is no fault. Whether the printer eventually fails is an important basis for the AI ​​model scoring mechanism.

[0108] For example, Fig.10As shown in the figure, the input data for AI model training also includes "scoring". "Scoring" is optional. The purpose is to avoid inaccurate problems caused by only using "strategy / anomaly type" training. After the trained model is initially obtained, the output results of the AI ​​model can be scored by developers and testers to help the AI ​​model adjust the output results.

[0109] Step 403: Use the historical detection data of the abnormal operation of the image forming device to perform a second correction training on the AI ​​model to obtain a power anomaly detection model.

[0110] This step is to collect the usage data of the user's machine at the user stage, screen out the historical detection data of working abnormalities in the machines that eventually fail, use the historical detection data of working abnormalities of the image forming equipment to correct and train the AI ​​model, and obtain the power anomaly detection model.

[0111] Fig.11 A schematic diagram of a power anomaly detection device provided by an embodiment of the present invention is shown in FIG. Fig.11 As shown, the device includes: a first processing module.

[0112] The first processing module is used to obtain current detection data of the image forming device, wherein the detection data includes the entire power, ambient temperature and working status of the image forming device; and input the current detection data into the power anomaly detection model to obtain an anomaly detection result.

[0113] Optionally, the processing module is further configured to determine that the anomaly detection result includes an anomaly handling strategy, and execute an operation corresponding to the anomaly handling strategy.

[0114] Optionally, the processing module is further configured to execute an operation corresponding to the exception handling strategy if the exception handling strategy is applicable to the image forming device.

[0115] Optionally, the working state includes a main state and working parameters corresponding to the main state.

[0116] Optionally, the working state further includes sub-states and working parameters corresponding to the sub-states.

[0117] Optionally, the detection data further includes: a fault code, wherein the fault code is used to indicate an abnormality type corresponding to a main state or an abnormality type corresponding to a sub-state.

[0118] The power anomaly detection device provided by the embodiment of the present invention can be used to achieve the above Figures 1 to 7 For a detailed description of the power anomaly detection method, please refer to the above-mentioned embodiment of the power anomaly detection method, which will not be repeated here.

[0119] In a technical solution of a power anomaly detection device provided by an embodiment of the present invention, the current detection data of an image forming device is obtained, and the detection data includes the whole machine power, ambient temperature and working status of the image forming device; the current detection data is input into a power anomaly detection model to obtain an anomaly detection result. Power anomaly detection can be performed without adding a monitoring circuit to each power consumption module, thereby reducing the detection cost.

[0120] Fig.12 A schematic diagram of the structure of a model training device provided by an embodiment of the present invention is shown in FIG. Fig.12 As shown, the device includes: a second processing module.

[0121] The second processing module is used to perform preliminary training on the AI ​​model by inputting a large amount of historical detection data of normal operation of the image forming device into the AI ​​model; use the historical detection data of abnormal operation of the image forming device to perform correction training on the AI ​​model to obtain a power abnormality detection model; the power abnormality detection model is used to output an abnormality detection result according to the current detection data of the image forming device, and the detection data includes: the whole machine power, ambient temperature and working status of the image forming device.

[0122] Optionally, the second processing module uses historical detection data of abnormal operation of the image forming device to perform correction training on the AI ​​model to obtain a power abnormality detection model, and is also used to: perform correction training on the AI ​​model in response to a scoring operation on the output result of the AI ​​model.

[0123] Fig.13 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Fig.13 As shown, the electronic device may include at least one processor; and at least one memory connected to the processor in communication, wherein: the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the instructions of this specification. Figure 1 to Figure 7 The power anomaly detection method provided by the embodiment shown or Figure 8-10 The model training method provided by the illustrated embodiment. The electronic device may be the above-mentioned image forming device or model training device.

[0124] Fig.13 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present invention is shown. Fig.13 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0125] like Fig.13As shown, the electronic device is in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: one or more processors 21, a memory 23, and a communication bus 24 connecting different system components (including the memory 23 and the processor 21).

[0126] The communication bus 24 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnection (PCI) bus.

[0127] Electronic devices typically include a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, removable and non-removable media.

[0128] The memory 23 may include a computer system readable medium in the form of a volatile memory, such as a random access memory (RAM) and / or a cache memory. The electronic device may further include other removable / non-removable, volatile / non-volatile computer system storage media. The memory 23 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present invention.

[0129] A program / utility having a set (at least one) of program modules may be stored in the memory 23, such program modules including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules generally perform the functions and / or methods of the embodiments described in this specification.

[0130] The processor 21 executes various functional applications and data processing by running the programs stored in the memory 23, such as implementing the Figure 1 to Figure 7The power anomaly detection method provided by the embodiment shown or Figure 8-10 The model training method provided by the illustrated embodiment.

[0131] An embodiment of the present invention provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, wherein the computer instructions enable the computer to execute the instructions of the present invention. Figure 1 to Figure 7 Power abnormality detection method provided by the illustrated embodiment Figure 8-10 The model training method provided by the illustrated embodiment.

[0132] The above-mentioned non-transitory computer-readable storage medium can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (Read Only Memory; hereinafter referred to as: ROM), an erasable programmable read-only memory (Erasable Programmable Read Only Memory; hereinafter referred to as: EPROM) or flash memory, optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0133] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0134] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0135] Computer program code for performing the operations of this specification may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0136] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0137] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of this specification. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0138] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this specification, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0139] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of this specification includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of this specification belong.

[0140] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0141] It should be noted that the terminals involved in the embodiments of this specification may include but are not limited to personal computers (Personal Computer; hereinafter referred to as: PC), personal digital assistants (Personal Digital Assistant; hereinafter referred to as: PDA), wireless handheld devices, tablet computers (Tablet Computer), mobile phones, MP3 players, MP4 players, etc.

[0142] In the several embodiments provided in this specification, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0143] In addition, each functional unit in each embodiment of this specification may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0144] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (Processor) to perform some steps of the method described in each embodiment of this specification. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk and other media that can store program codes.

[0145] The above description is only a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this specification should be included in the scope of protection of this specification.

Claims

1. A power anomaly detection method, characterized in that: The method comprises: Acquire current detection data of the image forming device, wherein the detection data includes the whole machine power, ambient temperature and working status of the image forming device; The current detection data is input into a power anomaly detection model to obtain an anomaly detection result.

2. The method according to claim 1, characterized in that After inputting the current detection data into the power anomaly detection model to obtain an anomaly detection result, the method further includes: It is determined that the anomaly detection result includes an anomaly handling strategy, and an operation corresponding to the anomaly handling strategy is performed.

3. The method according to claim 2, characterized in that Before executing the operation corresponding to the exception handling strategy, the method further includes: If the exception handling policy is applicable to the image forming device, an operation corresponding to the exception handling policy is performed.

4. The method according to any one of claims 1 to 3, characterized in that: The working state includes a main state and working parameters corresponding to the main state.

5. The method according to claim 4, characterized in that The working state also includes sub-states and working parameters corresponding to the sub-states.

6. The method according to claim 1, characterized in that The detection data also includes: a fault code, and the fault code is used to indicate the abnormal type corresponding to the main state or the abnormal type corresponding to the sub-state.

7. A model training method, characterized in that: The method comprises: Preliminary training of the AI ​​model is performed by inputting a large amount of historical detection data of normal operation of the image forming device into the AI ​​model; The AI ​​model is corrected and trained using historical detection data of abnormal working of the image forming device to obtain a power abnormality detection model; the power abnormality detection model is used to output an abnormality detection result based on the current detection data of the image forming device, and the detection data includes: the whole machine power, ambient temperature and working status of the image forming device.

8. The method according to claim 7, characterized in that Before the AI ​​model is corrected and trained using the historical detection data of the abnormal operation of the image forming device to obtain the power abnormality detection model, the method further includes: In response to a scoring operation on an output result of the AI ​​model, correction training is performed on the AI ​​model.

9. An image forming device, comprising a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, characterized in that: When the program instructions are loaded and executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A model training device, comprising a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, characterized in that: When the program instructions are loaded and executed by a processor, the method according to claim 7 or 8 is implemented.

11. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 8.

Images