Equipment investigation data processing method

Abstract

The invention relates to the technical field of data processing, and discloses an equipment investigation data processing method, which comprises the following steps: acquiring historical data information of to-be-analyzed equipment in response to the situation that the to-be-analyzed equipment meets an investigation triggering condition of a set fault type; based on the historical data information, determining a device datum line of the to-be-analyzed device for pushing the questionnaire; detecting an equipment reference value of the to-be-analyzed equipment, wherein the equipment reference value is used for representing the actual operation state of the to-be-analyzed equipment; and sending a customized questionnaire used for equipment investigation to an application program logging in the target account, the target account being bound with equipment whose deviation degree of the equipment reference value relative to the equipment reference line is greater than a set threshold. According to the technical scheme, fixed pushing of the survey file is effectively avoided, the application program of the target account is pertinently logged in to send the customized questionnaire, the pertinence of the survey file is remarkably improved, the effectiveness of the questionnaire and the reasonability of a pushing mechanism are effectively improved, and therefore the user experience is effectively improved.

Description

A method for processing equipment survey data Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically to a method for processing equipment survey data. Background Technology

[0002] Questionnaire surveys on product usage are a crucial way to obtain genuine feedback on product usage and improve product and after-sales service quality. How these surveys are distributed and how they are analyzed effectively significantly impacts the results. Current technologies often use scheduled push notifications or simple event triggers. For example, timer-based periodic push notifications for satisfaction surveys often contain static questions that are easily out of touch with device status. Other solutions push surveys only after detecting device malfunctions or app functionalities. In short, these technologies typically use fixed templates and random push notifications, lacking targeted questionnaires based on specific device conditions and appropriate timing for push notifications. Furthermore, the analysis methods for these surveys are relatively simplistic, resulting in relatively low reference value for the survey results. Summary of the Invention

[0003] In view of this, the present invention provides a method for processing equipment survey data to push survey questionnaires to users in a targeted manner, thereby improving the rationality of pushing equipment survey questionnaires.

[0004] In a first aspect, the present invention provides a method for processing equipment survey data, the method comprising: in response to a survey triggering condition for a set fault type being met by the equipment to be analyzed, acquiring historical data information of the equipment to be analyzed; determining a baseline for the equipment to be analyzed to push a survey questionnaire based on the historical data information; detecting a baseline value of the equipment to be analyzed, the baseline value being used to characterize the actual operating status of the equipment to be analyzed; and sending a customized survey questionnaire for equipment survey to an application logged into a target account, wherein the target account is bound to a device whose baseline value deviates from the baseline by a degree greater than a set threshold.

[0005] The device survey data processing method of this invention, when the device to be analyzed meets the survey trigger conditions of a set fault type, first determines the device baseline for pushing the survey questionnaire based on the device's historical data information, and detects the device baseline value of the device to be analyzed. If the target account has a device whose baseline value deviates from the device baseline by more than a set threshold, then a customized survey questionnaire for device survey is sent to the application logged into the target account. In this way, the fixed push of survey documents is effectively avoided, and instead, customized survey questionnaires are sent to the application logged into the target account, significantly improving the relevance of the survey documents, effectively improving the validity of the questionnaire and the rationality of the push mechanism, thereby effectively improving the user experience.

[0006] In some optional implementations, the baseline for the device to which the survey questionnaire is pushed is determined based on historical data information, including: determining the historical fault weighted baseline, the current state compensation baseline, and the reliability weighted baseline based on historical data information; and determining the product of the historical fault weighted baseline, the current state compensation baseline, and the reliability weighted baseline as the device baseline.

[0007] In some optional implementations, the historical fault weighted baseline is determined using the following formula: Historical Fault Weighted Baseline = Fault Frequency Weight * Historical Baseline of Fault A in the Past 3 Months + (X / Total Number of Equipment Faults) * Fault Count Weight; where Fault A represents a fault of the set fault type, the historical baseline of Fault A in the past 3 months is the average of the set baselines determined when Fault A occurred in the equipment under analysis in the past 3 months; X represents the total number of times Fault A occurred in the equipment under analysis; and the total number of equipment faults represents the total number of all faults that occurred in the equipment under analysis.

[0008] In some alternative implementations, the current state compensation baseline of the equipment is determined by the following operation: obtaining the influence coefficients of multiple set factors on the equipment to be analyzed, including at least two of the seasonal compensation coefficient, the equipment usage nature compensation coefficient, and the regional compensation coefficient; and determining the current state compensation baseline by multiplying the multiple influence coefficients.

[0009] In some alternative implementations, the equipment reliability weighted baseline is determined using the following formula: Equipment reliability weighted baseline = lower limit + amplitude * Math.exp(-mean time between failures / time constant); where mean time between failures is the total equipment uptime / the total number of equipment failures.

[0010] In some optional implementations, detecting the device baseline value of the device to be analyzed includes: acquiring multiple dimension baseline values ​​of the device, the multiple dimension baseline values ​​being used to characterize the failure impact value of multiple dimension influencing factors on the device failure; and using the product of the multiple dimension baseline values ​​as the device baseline value of the device to be analyzed.

[0011] In some optional implementations, multiple dimensional benchmarks include time-based benchmarks, severity-based benchmarks, environmental-based benchmarks, and user habit-based benchmarks.

[0012] In some alternative implementations, a customized questionnaire for device surveys is sent to an application logged into the target account, including: generating a customized questionnaire that matches the device to be analyzed based on the actual operating status of the device when the device's baseline deviation from the device baseline is greater than a set threshold; and sending the customized questionnaire to the application logged into the target account.

[0013] In some optional implementations, a customized questionnaire matching the device under analysis is generated based on the actual operating status of the device under analysis. This includes: obtaining basic weight coefficients for multiple preset question types, user characteristic coefficients for the device under analysis, and real-time status coefficients for the device under analysis, wherein the real-time status coefficients of the device under analysis are used to indicate the operating environment and the degree of correlation between the fault type and the preset question type; determining the weight of the preset question type based on the product of the basic weight coefficients, user characteristic coefficients, and device status coefficients of the preset question type; and randomly generating a customized questionnaire based on the weights of multiple preset question types. The customized questionnaire contains a set number of survey questions, and the number of questions of each type in the survey questions conforms to the weights of multiple preset question types.

[0014] In some optional implementations, the equipment state coefficient is determined using the following formula: Equipment state coefficient = Fault correlation coefficient * Environmental coefficient; wherein, the fault correlation coefficient is used to indicate the degree of matching between the preset problem type and the fault type of the equipment to be analyzed. If the preset problem type matches the fault of the equipment to be analyzed, the fault correlation coefficient is the first preset correlation coefficient; the environmental coefficient is used to characterize the degree of matching between the environment in which the equipment to be analyzed is currently located and the environment associated with the preset problem type. If the humidity at the location of the equipment to be analyzed is greater than or equal to a set humidity threshold, the weight of the preset problem type condensation problem is configured as the first environmental coefficient. If the hardness of the current water quality of the equipment to be analyzed is greater than or equal to a set hardness threshold, the weight of the preset problem type scaling problem is configured as the second environmental coefficient. The environmental coefficient is the product of multiple environmental coefficients.

[0015] In some optional implementations, the investigation triggering conditions include at least one of the following: the device to be analyzed sends maintenance information to indicate that the device needs maintenance; the number of times abnormal power consumption of the device to be analyzed is detected within a set time is greater than or equal to a first set number; the number of times the device to be analyzed sends fault information to indicate that the device is faulty is greater than or equal to a second set number within a set time. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 is a flowchart illustrating a method for processing equipment survey data according to an embodiment of the present invention; Figure 2 is a flowchart illustrating another method for processing equipment survey data according to an embodiment of the present invention; Figure 3 is a flowchart illustrating a specific application example of the method for processing equipment survey data according to an embodiment of the present invention; Figure 4 is a schematic diagram illustrating a questionnaire delivery method in a specific application example of the method for processing equipment survey data according to an embodiment of the present invention; Figure 5 is a structural block diagram of an apparatus for processing equipment survey data according to an embodiment of the present invention; Figure 6 is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, 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 those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] This invention provides a method for processing equipment survey data. For users who need to receive survey reports, it performs multi-data source analysis and dynamically calculates a questionnaire that better meets the actual needs of users. This improves the rationality of pushing equipment survey questionnaires, allows for targeted delivery of questionnaires to users, and obtains users' real problems or needs through the survey questionnaire. This provides more accurate user feedback information for product upgrades or service improvements, thereby effectively improving product quality, reducing customer complaints, and enhancing user experience.

[0020] According to an embodiment of the present invention, a method for processing equipment survey data is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0021] This embodiment provides a device survey data processing method, which can be used in the above-mentioned smart home server, etc. Figure 1 is a flowchart of the device survey data processing method according to an embodiment of the present invention. As shown in Figure 1, the process includes the following steps: Step S101, in response to the device to be analyzed meeting the survey trigger condition of the set fault type, the historical data information of the device to be analyzed is obtained.

[0022] In some optional implementations, the survey trigger conditions for the device under analysis to meet the set fault type may include the device needing maintenance, the device issuing abnormal energy consumption or other abnormal alerts, and a significant increase in the frequency of device faults. Specific quantitative standards can be set for this information. For example, for the case of the device needing maintenance, the mere fact that the device needs maintenance can be used as a survey trigger condition. For cases such as abnormal energy consumption, the survey trigger condition can be set when the frequency of abnormal energy consumption within a set time period is greater than or equal to a preset frequency.

[0023] In some optional implementations, the historical data information of the device mainly includes historical fault information, specifically including the fault type and the time when a certain type of fault occurred. For example, the number of times fault A has occurred in the device under analysis from the time the device was turned on to the current time is X. Here, each piece of historical data can also be timestamped to store historical data within a preset time period in a stack or similar manner, such as historical data from the past 3 years or historical data from the past year. Fault types can be recorded based on fault codes reported by the device, or other suitable recording methods can be used.

[0024] For example, the following situations can be used to determine whether to send a survey questionnaire and generate a customized survey questionnaire for the device to be analyzed when a survey questionnaire needs to be sent: the survey is triggered within 24 hours after the device is reported for repair; the survey is triggered when abnormal energy consumption is detected for 3 consecutive days; the survey is triggered when the user's network has been in operation for more than 30 days; the survey is triggered when the device reports multiple faults in a short period of time. The terms "short period of time" and "multiple times" can be quantified according to the actual situation, such as more than 2 times within a week.

[0025] Step S102: Based on historical data, determine the baseline for pushing survey questionnaires to the devices to be analyzed.

[0026] In some optional implementations, the equipment baseline can include multi-dimensional baselines to generate more reasonable survey questionnaires based on historical data. Examples include: historical fault-weighted baselines, current equipment state compensation baselines, and equipment reliability-weighted baselines. This approach fully considers both the historical operating status of the equipment and effectively analyzes its current actual operating status, resulting in more reasonable survey questionnaire delivery.

[0027] Step S103: Detect the equipment reference value of the device to be analyzed. The equipment reference value is used to characterize the actual operating status of the device to be analyzed.

[0028] In some optional implementations, multiple dimensional benchmarks include time-based benchmarks, severity-based benchmarks, environmental-based benchmarks, and user habit-based benchmarks.

[0029] The time dimension baseline primarily characterizes information such as the current month, as the operating environment of the equipment varies depending on the month, including temperature and humidity. The severity baseline characterizes the severity of different fault types. The environmental dimension primarily assesses the water quality of equipment such as water heaters. User usage habits primarily assess personalized data such as equipment usage frequency and the duration of each usage session. Therefore, the actual operating status of the equipment under analysis can be analyzed based on multiple dimensions.

[0030] Step S104: Send a customized questionnaire for device research to the application logged into the target account, wherein the target account is bound to a device whose baseline value deviates from the device baseline by a set threshold.

[0031] In some optional implementations, device baseline values ​​for multiple devices can be detected separately based on steps S102-S103. Here, a preset threshold can be configured. When the deviation of a device's baseline value from the device baseline exceeds the preset threshold, it is determined that a questionnaire needs to be pushed to the corresponding device to be analyzed. At this time, a customized questionnaire matching the device can be generated based on historical data information of the device to be analyzed.

[0032] It's important to note that the device being analyzed can be a water heater, etc., and can typically be accessed via a mobile phone or other terminal to log into a target account and bind the device to that account. In practical applications, the server can interact with the user's client to obtain and maintain information about the user's logged-in and bound devices. Furthermore, the server's processes for obtaining, storing, and processing user information comply with relevant laws and regulations. The server can periodically analyze the devices and, when the deviation from the device's baseline exceeds a set threshold, push customized survey documents to the application logged into the target account that has bound the device.

[0033] The device survey data processing method of this invention, when the device to be analyzed meets the survey trigger conditions of a set fault type, first determines the device baseline for pushing the survey questionnaire based on the device's historical data information, and detects the device baseline value of the device to be analyzed. If the target account has a device whose baseline value deviates from the device baseline by more than a set threshold, then a customized survey questionnaire for device survey is sent to the application logged into the target account. In this way, the fixed push of survey documents is effectively avoided, and instead, customized survey questionnaires are sent to the application logged into the target account, significantly improving the relevance of the survey documents, effectively improving the validity of the questionnaire and the rationality of the push mechanism, thereby effectively improving the user experience.

[0034] This embodiment provides a device survey data processing method, which can be used in the above-mentioned smart home server, etc. Figure 2 is a flowchart of the device survey data processing method according to an embodiment of the present invention. As shown in Figure 2, the process includes the following steps: Step S201, in response to the device to be analyzed meeting the survey trigger condition of the set fault type, the historical data information of the device to be analyzed is obtained.

[0035] In some optional implementations, the investigation triggering conditions include at least one of the following: the device to be analyzed sends maintenance information to indicate that the device needs maintenance; the number of times abnormal power consumption of the device to be analyzed is detected within a set time is greater than or equal to a first set number; the number of times the device to be analyzed sends fault information to indicate that the device is faulty is greater than or equal to a second set number within a set time.

[0036] Here, you can set a timeframe to trigger the investigation operation within 24 or 36 hours after receiving a device repair report. The timeframe, the first set number of times, and the second set number of times can be set according to the actual situation, such as the characteristics of the device.

[0037] For other detailed information, please refer to step S101 above, which will not be repeated here.

[0038] Step S202: Based on historical data, determine the baseline for pushing survey questionnaires to the devices to be analyzed.

[0039] Specifically, step S202 may include: step S2021, determining the historical fault weighted baseline, the current equipment status compensation baseline, and the equipment reliability weighted baseline based on historical data information.

[0040] In some optional implementations, the historical fault weighted baseline is determined using the following formula: Historical Fault Weighted Baseline = Fault Frequency Weight * Historical Baseline for Fault A in the Past 3 Months + (X / Total Number of Equipment Faults) * Fault Count Weight; where Fault A represents a fault of the defined fault type, and the historical baseline for Fault A in the past 3 months is the average of the defined baselines determined when Fault A occurred on the equipment under analysis in the past 3 months, which can be 0.6 or other suitable values. Alternatively, the historical baseline for Fault A in the past 3 months can be changed to the historical baseline for Fault A within a suitable time period such as 2 months, 5 months, or 6 months, depending on the actual situation.

[0041] X represents the total number of times fault A occurred in the equipment being analyzed, and the total number of equipment faults represents the total number of all faults that occurred in the equipment being analyzed. The weight of the number of faults can be 0.4 or other suitable values.

[0042] In some alternative implementations, the current state compensation baseline of the equipment is determined by the following steps: Step a1, obtain the influence coefficients of multiple set factors on the equipment to be analyzed, including at least two of the seasonal compensation coefficient, the equipment usage nature compensation coefficient, and the regional compensation coefficient.

[0043] The seasonal compensation coefficient primarily reflects the impact of seasonal changes on equipment use. For example, if it is currently summer, there may be minor issues such as large fluctuations in gas pressure, allowing for a higher fault baseline threshold to avoid excessive alarms, resulting in a compensation coefficient > 1. In practical applications, compensation coefficients for other seasonal factors affecting the equipment can also be set according to actual needs.

[0044] The equipment usage nature compensation coefficient is mainly used to reflect the impact of different usage natures on equipment lifespan and failure frequency. For example, equipment usage nature can include household and commercial use. Commercial equipment has a significantly higher usage frequency. If the equipment to be analyzed is commercial equipment, it is generally in a long-term operating state and has a higher usage frequency. Therefore, the failure judgment criteria are relaxed, and the compensation coefficient is >1.

[0045] The regional compensation coefficient is mainly used to reflect the impact of different regional environments on equipment use. For example, the impact of region on equipment use varies in plateau regions, high-temperature areas, the Central Plains region, and cold regions. Different regional compensation coefficients can be pre-configured according to the actual situation.

[0046] Here, we take the seasonal compensation coefficient, equipment usage compensation coefficient, and regional compensation coefficient as examples to explain the multi-dimensional influence coefficients. In practical applications, other influence coefficients can be configured according to needs.

[0047] Step a2: The product of multiple influence coefficients is determined as the current state compensation baseline.

[0048] In some optional implementations, the product of multiple influence coefficients can be used to determine the current state compensation baseline. Here, the multiple influence coefficients can be configured according to actual needs, and the present invention does not specifically limit the number of influence coefficients, etc.

[0049] In some alternative implementations, the calculation process of the equipment reliability weighted baseline can incorporate the equipment mean time between failures (MTBF) into the baseline calculation. The longer the MTBF, the higher the sensitivity and the earlier the warning. Conversely, the shorter the MTBF, the more relaxed the standard is to avoid frequent false alarms.

[0050] Specifically, the weighted baseline for equipment reliability is determined using the following formula: Weighted baseline for equipment reliability = Lower limit + Amplitude * Math.exp(-Mean Time Between Failures / Time Constant); where the Mean Time Between Failures is the total uptime of the equipment divided by the total number of equipment failures. The lower limit is a pre-configured fixed value.

[0051] Step S2022: The product of the historical fault weighted baseline, the current equipment status compensation baseline, and the equipment reliability weighted baseline is determined as the equipment baseline.

[0052] In some optional implementations, the equipment baseline can be obtained by multiplying the historical fault weighted baseline, the current equipment state compensation baseline, and the equipment reliability weighted baseline obtained in step S2021 above.

[0053] Step S203: Detect the equipment reference value of the device to be analyzed. The equipment reference value is used to characterize the actual operating status of the device to be analyzed.

[0054] Specifically, step S203 may include: step S2031, obtaining multiple dimension benchmark values ​​of the device, which are used to characterize the fault impact values ​​of multiple dimension influencing factors on the device failure.

[0055] In some optional implementations, multiple dimensional benchmarks include time-based benchmarks, severity-based benchmarks, environmental-based benchmarks, and user habit-based benchmarks.

[0056] Specifically, the time dimension baseline value is mainly used to indicate the time since the last failure of the equipment. The longer the time since the last failure, the more stable the equipment is after repair. Therefore, when calculating the time decay coefficient based on the current time and the time of the last failure, the difference in months between the current time and the time of the last failure is used. The shorter the time difference, the greater the weight. It can be set to decay by 30% every 3 months, calculated using the following formula: Time dimension baseline value = (∑Math.pow(0.7, difference in months between the time of the last failure and the current time / 3)) / total number of failures; where the total number of failures can be determined based on historical data.

[0057] The severity baseline calculation process can be performed by pre-configuring a fault level weight table and using the following formula to calculate the average weight of all faults in the equipment to be analyzed: Severity baseline value = ∑ Configured fault baseline value / Total number of faults. Fault levels can categorize different types of faults into different fault weights, and can also incorporate actual maintenance handling methods, such as whether equipment parts were replaced, and feedback on maintenance difficulty.

[0058] During the calculation of environmental baseline values, higher ambient humidity can lead to incomplete combustion and equipment condensation, increasing the failure rate. Poor water quality increases the rate of scaling and also raises the failure rate. In practical applications, the influence of other environmental dimensions can also be considered. Here, the following formula is used to calculate the environmental baseline values.

[0059] Environmental baseline value = Humidity at equipment location > 70% ? 1.15:1 * Current water quality at equipment < 90% ? 1.25:1.

[0060] Specifically, if the ambient humidity at the location of the device being analyzed is greater than 70%, a value of 1.15 is used; otherwise, a value of 1 is used. If the current water quality of the water used by the device is poor, below 90%, a value of 1.25 is used; otherwise, a value of 1 is used. The baseline value for the environmental dimension is obtained by multiplying the humidity determined based on the device location and the current water quality.

[0061] The calculation of the user usage habit dimension baseline value mainly characterizes the impact of user usage habits on the analyzed device. It can compensate for situations such as high-frequency user use and extreme user temperature settings. For example, the user usage habit dimension baseline value can be calculated using the following formula: User usage habit dimension baseline value = Daily usage frequency > 10 × 1.3:1 * Extreme device temperature × 1.3:1; where, if the user uses the device more than 10 times per day, the value is 1.3; otherwise, the value is 1. Similarly, if the user sets an extreme temperature on the device, the value is 1.3; otherwise, the value is 1. Extreme temperature can be determined by configuring and judging extreme temperature thresholds. For example, a user setting a temperature greater than or equal to 50℃ can be considered an extreme temperature setting.

[0062] Step S2032: The product of multiple dimension benchmark values ​​is used as the equipment benchmark value of the device to be analyzed.

[0063] Multiple dimensional benchmark values ​​can be selected and calculated according to the actual situation. The product of the selected and calculated multiple dimensional benchmark values ​​can be used as the equipment benchmark value of the equipment to be analyzed.

[0064] Step S204: Send a customized questionnaire for device research to the application logged into the target account, wherein the target account is bound to a device whose baseline value deviates from the device baseline by a set threshold.

[0065] Here, whether the deviation of the equipment reference value from the equipment baseline exceeds a set threshold can be calculated using non-linear amplification of the deviation. Specifically, it can be calculated using the following formula.

[0066] The baseline deviation is calculated as follows: `Baseline deviation = Baseline > Baseline? Math.pow(Baseline - Baseline, 1.2): 0;` where the threshold value can be set according to actual needs; here it is configured as 1.2. The baseline deviation characterizes the degree of deviation of the device's baseline value from the device's baseline. If the device's baseline value is greater than the device's baseline, the difference between the two is calculated. If the difference is greater than or equal to 1.2, the deviation of the device's baseline value from the device's baseline is determined to be greater than the set threshold; otherwise, the deviation is determined to be less than the set threshold. For devices whose baseline deviation from the device's baseline is greater than the set threshold, the target account to which the device is pre-bound can be determined, and a customized questionnaire for device research can be sent to the application logged into that target account.

[0067] Specifically, step S204 may include: step S2041, when the deviation of the device's reference value from the device baseline is greater than a set threshold, generating a customized questionnaire that matches the device to be analyzed based on the actual operating status of the device to be analyzed.

[0068] In some optional implementations, step S2041 may include: step b1, obtaining the basic weight coefficients of multiple preset problem types, the user characteristic coefficients of the device to be analyzed, and the real-time status coefficients of the device to be analyzed, wherein the real-time status coefficients of the device to be analyzed are used to indicate the operating environment of the device to be analyzed and the degree of correlation between the fault type and the preset problem type.

[0069] The base weight coefficients for multiple preset question types can be derived statistically from experience or historical data, primarily used to characterize the global importance of a question. The base weight coefficient for each preset question type can be loaded from a pre-configured base question weight table or a database. Different preset question types can be configured with different base weight coefficients; if different preset question types are of equal importance, the same base weight coefficient can also be configured for different preset question types.

[0070] The user characteristic coefficients of the device to be analyzed can be configured to amplify or reduce the weight of issues based on user characteristics, focusing on personalized user needs. Here, the user characteristic coefficients of the device to be analyzed can be calculated using the following formula: User characteristic coefficient of the device to be analyzed = Feature matching coefficient + Behavior reinforcement coefficient; where, Feature matching coefficient = (User profile: Age > Elderly? Safety-related issue coefficient * 1.3:1) * (User profile: User location > Coastal? Humidity-related issue coefficient * 1.3:1) ...; Behavior reinforcement coefficient = (User's daily temperature adjustment frequency > 5? Temperature-related issue coefficient * 1.3:1) * (User's daily power on / off frequency > 5? Start / stop-related issue coefficient * 1.3:1) ...; The ellipsis "..." in the formulas for calculating the feature matching coefficient and behavior reinforcement coefficient indicates that other user characteristics and behaviors can be configured according to actual conditions. The phrase "(X-feature or X-behavior load setting conditions? X-feature or X-behavior related issues * preset coefficient: 1)" indicates that "if a user has X-feature, the feature matching coefficient of the X-feature related issues will be determined as the preset coefficient, or if the user's behavior matches X-behavior, the behavior reinforcement coefficient of the X-behavior related issues will be adjusted to the preset coefficient." Here, the preset coefficient is set to 1.3. In practical applications, the preset coefficient can be configured according to actual needs.

[0071] The real-time status coefficient of the device under analysis is used to characterize the dynamic adjustment of question weights based on the device's real-time status, ensuring a strong correlation between the survey questionnaire and the actual problems of the current device. The real-time status coefficient of the device under analysis can be calculated using the following formula: Real-time status coefficient of the device under analysis = Fault correlation coefficient * Environmental coefficient; where the fault correlation coefficient indicates the degree of matching between the preset question type and the fault type of the device under analysis. If the preset question type matches the fault of the device under analysis, the fault correlation coefficient is the first set correlation coefficient. For example, the first set correlation coefficient is 2. The fault correlation coefficient can be determined using the following formula: The environmental coefficient characterizes the degree of matching between the current environment of the device under analysis and the environment associated with the preset question type. If the humidity at the location of the device under analysis is greater than or equal to a set humidity threshold, the weight of the preset question type "condensation problem" is configured as the first environmental coefficient. If the hardness of the current water quality of the device under analysis is greater than or equal to a set hardness threshold, the weight of the preset question type "scaling problem" is configured as the second environmental coefficient. The environmental coefficient is the product of multiple environmental coefficients.

[0072] The fault correlation coefficient and environmental coefficient can be determined using the following formula.

[0073] Fault correlation coefficient = Problem type matches current equipment fault ? 2 : 1; Specifically, if the problem type matches the current equipment fault type of the equipment to be analyzed, the fault correlation coefficient of the equipment to be analyzed is set to 2; otherwise, the fault correlation coefficient of the equipment to be analyzed is set to 1.

[0074] The environmental coefficient is calculated as follows: (High humidity in the equipment's location? Condensation problem weight * 1.3 : 1) * Poor current water quality? Scaling problem weight * 0.3 : 1). Specifically, if the humidity in the area where the equipment is being analyzed is high, the weight for condensation problems is set to 1.3; otherwise, the weight for condensation-related problems is set to 1. Whether the humidity in the area where the equipment is being analyzed is high can be determined by pre-configuring a humidity table, for example, by pre-configuring a table quantifying high, medium, and low humidity in the area where the equipment is designed to operate. If the current water quality is poor, the weight for scaling-related problems is set to 1.3; otherwise, the weight for scaling-related problems is set to 1. Problem types can include condensation problems, scaling problems, etc., and a question bank can be pre-configured with labeling of problem types.

[0075] Step b2: Determine the weight of the preset problem type based on the product of the basic weight coefficient of the preset problem type, the user characteristic coefficient of the device to be analyzed, and the device status coefficient of the device to be analyzed.

[0076] By multiplying the basic weight coefficients, user characteristic coefficients, and equipment status coefficients of the device to be analyzed as determined in step b1, the weights of the preset problem types can be determined. Thus, the weights of various preset problem types can be determined.

[0077] Step b3: Based on the weights of multiple preset question types, a customized questionnaire is randomly generated. The customized questionnaire contains a set number of survey questions, and the number of each type of question in the survey questions conforms to the weights of multiple preset question types.

[0078] In some optional implementations, a question bank containing multiple types of preset questions can be pre-configured. For each preset question type, multiple questions are pre-configured, and the number of questions for that preset question type can be determined based on the weights of the multiple preset question types. Then, a corresponding number of questions of that preset question type are randomly selected from the question bank. This allows for the random generation of a customized questionnaire. This questionnaire closely reflects the actual operating status of the device being analyzed and the usage habits of users of that device. It can accurately obtain real user experience data based on user feedback from the questionnaire, and the questions users see when processing or answering the questionnaire are highly relevant to their own situation and the device they are using, effectively reducing the appearance of irrelevant questions and improving the user experience.

[0079] Step S2042: Send the customized questionnaire to the application where the target account is logged in.

[0080] Please refer to step S104 above for details, which will not be repeated here.

[0081] This embodiment provides a device survey data processing method, which can be used in the above-mentioned smart home server, etc. Figure 3 is a flowchart of a specific application example of the device survey data processing method according to the embodiment of the present invention. As shown in Figure 3, the process includes the following steps: Step S301, determine whether the device to be analyzed has a repair record within 24 hours. If so, proceed to step S304; otherwise, proceed to step S302.

[0082] Step S302: Determine if the device to be analyzed has experienced abnormal energy consumption for 3 consecutive days. If so, proceed to step S304; otherwise, proceed to step S303.

[0083] Step S303: Determine if the device under analysis reports multiple faults in a short period of time. If so, proceed to step S304; otherwise, proceed to step S305.

[0084] For details, please refer to step S101 of the embodiment shown in Figure 1 and step S201 of the embodiment shown in Figure 2. For example, if the number of times the device to be analyzed sends fault information to characterize the device fault within a set time is greater than or equal to a second set number, it is determined that the device to be analyzed reports faults multiple times in a short period of time.

[0085] Step S304: Trigger the judgment to push the survey questionnaire.

[0086] Step S305: Determine that the survey questionnaire does not need to be sent, and end the determination.

[0087] Step S306: Determine whether the device to be analyzed is experiencing fault A. If yes, proceed to step S307; otherwise, proceed to step S308.

[0088] Step S307: Query the total number of times fault A occurred X in the historical data information.

[0089] Step S308: Query fault A, which has occurred X times in history, and analyze the baseline of historical fault data.

[0090] The detailed process of historical fault data baseline analysis can be found in the analysis of equipment baselines in the embodiments shown in Figures 1 and 2 above, and will not be repeated here. Steps S309-S312 are all processes for analyzing historical fault data baselines.

[0091] Step S309, historical fault weighted baseline = 0.6 * historical baseline of fault A in the past 3 months + (X / total number of equipment faults) * 0.4.

[0092] Step S310, Equipment current status compensation baseline = seasonal compensation coefficient * commercial compensation coefficient * regional compensation coefficient.

[0093] Step S311, Equipment reliability weighted baseline = lower limit + amplitude * Math.exp(-mean time between failures / time constant).

[0094] Step S312, Equipment baseline = historical fault weighted baseline * current equipment condition compensation baseline * equipment reliability weighted baseline.

[0095] Step S313: Analyze the historical fault data baseline values ​​of the equipment to be analyzed.

[0096] For details, please refer to the analysis of the equipment baseline values ​​of the device to be analyzed in the embodiments shown in Figures 1 and 2 above, which will not be repeated here. Steps S314-S318 are all analysis processes of historical fault data baseline values.

[0097] Step S314, time dimension baseline value = (∑Math.pow(0.7, difference between the time of fault i and the current time in months / 3)) / total number of faults.

[0098] Step S315, Severity baseline value = ∑ Configured fault baseline value / Total number of faults.

[0099] Step S316, Environmental dimension baseline value = Humidity at the device location > 70%? 1.15:1 * Current water quality of the device.

[0100] Step S317, User usage habit dimension baseline value = Daily usage frequency > 10? 1.3:1 * Device extreme temperature? 1.3:1.

[0101] Step S318, the device's baseline value = time dimension baseline value * severity baseline value * environment dimension baseline value * user usage habit dimension baseline value.

[0102] Here, multiple dimensional benchmark values ​​can be selected according to the actual situation. For details, please refer to the process of determining the equipment benchmark values ​​of the device to be analyzed in the embodiments shown in Figures 1 and 2 above; it will not be repeated here.

[0103] Step S319: Determine whether the deviation between the device reference value and the device baseline of the device to be analyzed is greater than a set threshold. If yes, proceed to step S320; otherwise, proceed to step S304. Since these two steps are far apart in the figure, step S304 is repeated in the attached figure near step S319.

[0104] For details, please refer to step S104 in the embodiment shown in Figure 1 and step S204 in the embodiment shown in Figure 2, which will not be repeated here.

[0105] Step S320: Dynamically generate a customized survey questionnaire.

[0106] For details, please refer to the generation process of the customized survey questionnaire in the embodiments shown in Figures 1 and 2 above, which will not be repeated here. Steps S321-S329 are all about the generation process of the customized survey questionnaire.

[0107] Step S321, Basic weight = Load basic weights from the configuration table or database. Different problem types have different basic weights.

[0108] Step S322, Feature matching coefficient = (User profile's age is advanced? Security-related issues coefficient * 1.3:1) * (User profile's region is coastal? Humidity-related issues coefficient * 1.3:1) ...

[0109] Step S323, Behavior reinforcement coefficient = (User's daily temperature adjustment frequency > 5? Temperature-related problem coefficient * 1.3:1) * (User's daily power on / off frequency > 5? Start / stop related problem coefficient * 1.3:1)...

[0110] Step S324, User profile coefficient = Feature matching coefficient + Behavior reinforcement coefficient.

[0111] Step S325, Fault correlation coefficient = Problem type matches current equipment fault? 2:1.

[0112] Step S326, Environmental coefficient = (High humidity in the area where the equipment is located? Condensation problem weight * 1.3:1) * Poor current water quality for the equipment? Scaling problem weight * 0.3:1).

[0113] Step S327, Equipment state coefficient = Fault correlation coefficient * Environmental coefficient.

[0114] Step S328, Problem weight = Basic weight * User profile coefficient * Device status coefficient.

[0115] Step S329: Sort all types of questions by weight and select the top 10 questions for user survey.

[0116] Step S330: Send out the survey questionnaire.

[0117] For details, please refer to step S104 in the embodiment shown in Figure 1 and step S204 in the embodiment shown in Figure 2, which will not be repeated here.

[0118] It should be noted that because Figure 3 involves many operational steps, some descriptions of the operational steps in Figure 3 have been simplified to keep the figures clear. The text descriptions here shall prevail.

[0119] Figure 4 is a schematic diagram of the questionnaire push method in a specific application example of the equipment survey data processing method according to an embodiment of the present invention. Referring to Figure 4, the technical solution logic of the embodiments shown in Figures 1-3 above is summarized and explained. As shown in Figure 4, a fault baseline is analyzed based on historical fault data of the equipment, a status baseline is analyzed based on the real-time status of the equipment, and a behavior baseline is analyzed based on user behavior characteristics. Equipment baselines are obtained based on data from multiple devices, and equipment baseline values ​​are obtained based on data from the device to be analyzed. After determining the equipment baseline value and the equipment baseline, a baseline comparison engine is triggered to determine whether the deviation between the equipment baseline value and the equipment baseline of the device to be analyzed is greater than a set threshold. If the deviation between the equipment baseline value and the equipment baseline of the device to be analyzed is greater than the set threshold, a customized survey questionnaire is pushed.

[0120] Customized questionnaires can be generated by referring to the process shown in Figures 1-3 above. For example, a fault diagnosis questionnaire can be pushed to the device being analyzed that deviates most from the fault baseline; a performance optimization questionnaire can be pushed to the device that deviates most from the state baseline; and a usage habit questionnaire can be pushed to the device that deviates most from the behavioral baseline. Here, multiple types of questionnaires are used as pre-configured customized questionnaires. In practical applications, the embodiments shown in Figures 1-3 above can also be referred to to dynamically generate customized questionnaires that match the actual operating status of the device being analyzed and the user behavior habits of those using the device.

[0121] This embodiment also provides a device for processing survey data, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0122] This embodiment provides a device for processing survey data, as shown in Figure 5, including: an acquisition module 501, used to acquire historical data information of the device to be analyzed in response to a survey trigger condition that the device to be analyzed meets a set fault type; a baseline module 502, used to determine the device baseline for pushing survey questionnaires to the device to be analyzed based on the historical data information; a detection module 503, used to detect the device baseline value of the device to be analyzed, the device baseline value being used to characterize the actual operating status of the device to be analyzed; and a sending module 504, used to send a customized survey questionnaire for device survey to an application logged into a target account, wherein the target account is bound to a device whose device baseline value deviates from the device baseline by a set threshold.

[0123] In some optional implementations, the baseline module 502 includes: a multi-dimensional unit for determining a historical fault-weighted baseline, a current equipment state compensation baseline, and a equipment reliability-weighted baseline based on historical data information; and a baseline determination unit for determining the equipment baseline by multiplying the historical fault-weighted baseline, the current equipment state compensation baseline, and the equipment reliability-weighted baseline.

[0124] In some optional implementations, the multi-dimensional unit uses the following formula to determine the historical fault weighted baseline: Historical fault weighted baseline = Fault frequency weight * Historical baseline of fault A over the past 3 months + (X / Total number of equipment faults) * Fault frequency weight; where fault A represents a fault of the set fault type, the historical baseline of fault A over the past 3 months is the average value of the set baselines determined when fault A occurred in the equipment under analysis over the past 3 months; X represents the total number of times fault A occurred in the equipment under analysis; and the total number of equipment faults represents the total number of all faults that occurred in the equipment under analysis.

[0125] In some optional implementations, the multi-dimensional unit determines the current state compensation baseline of the equipment by: obtaining the influence coefficients of multiple set factors on the equipment to be analyzed, the influence coefficients including at least two of the seasonal compensation coefficient, the equipment usage nature compensation coefficient, and the regional compensation coefficient; and determining the product of the multiple influence coefficients as the current state compensation baseline.

[0126] In some optional implementations, the multi-dimensional unit uses the following formula to determine the equipment reliability weighted baseline: Equipment reliability weighted baseline = lower limit + amplitude * Math.exp(-mean time between failures / time constant); where mean time between failures is the total equipment uptime / the total number of equipment failures.

[0127] In some optional implementations, the detection module 503 includes: a baseline value acquisition unit, used to acquire multiple dimension baseline values ​​of the device, the multiple dimension baseline values ​​being used to characterize the fault impact values ​​of multiple dimension influencing factors on the device failure; and a baseline value calculation unit, used to use the product of the multiple dimension baseline values ​​as the device baseline value of the device to be analyzed.

[0128] In some optional implementations, multiple dimensional benchmarks include time-based benchmarks, severity-based benchmarks, environmental-based benchmarks, and user habit-based benchmarks.

[0129] In some optional implementations, the sending module includes: a questionnaire generation unit, used to generate a customized questionnaire matching the device to be analyzed based on the actual operating status of the device to be analyzed when the deviation of the device baseline value from the device baseline is greater than a set threshold; and a questionnaire sending unit, used to send the customized questionnaire to the application logged into the target account.

[0130] In some optional implementations, the questionnaire generation unit includes: a factor weighting subunit, used to obtain the basic weight coefficients of multiple preset question types, the user characteristic coefficients of the device to be analyzed, and the real-time status coefficients of the device to be analyzed, wherein the real-time status coefficients of the device to be analyzed are used to indicate the degree of correlation between the operating environment and fault type of the device to be analyzed and the preset question types; a question weighting subunit, used to determine the weight of the preset question types based on the product of the basic weight coefficients of the preset question types, the user characteristic coefficients of the device to be analyzed, and the device status coefficients of the device to be analyzed; and a generation subunit, used to randomly generate a customized questionnaire based on the weights of multiple preset question types, wherein the customized questionnaire contains a set number of survey questions, and the number of each type of question in the survey questions conforms to the weights of multiple preset question types.

[0131] In some optional implementations, the equipment state coefficient is determined using the following formula: Equipment state coefficient = Fault correlation coefficient * Environmental coefficient; wherein, the fault correlation coefficient is used to indicate the degree of matching between the preset problem type and the fault type of the equipment to be analyzed. If the preset problem type matches the fault of the equipment to be analyzed, the fault correlation coefficient is the first preset correlation coefficient; the environmental coefficient is used to characterize the degree of matching between the environment in which the equipment to be analyzed is currently located and the environment associated with the preset problem type. If the humidity at the location of the equipment to be analyzed is greater than or equal to a set humidity threshold, the weight of the preset problem type condensation problem is configured as the first environmental coefficient. If the hardness of the current water quality of the equipment to be analyzed is greater than or equal to a set hardness threshold, the weight of the preset problem type scaling problem is configured as the second environmental coefficient. The environmental coefficient is the product of multiple environmental coefficients.

[0132] In some optional implementations, the investigation triggering conditions include at least one of the following: the device to be analyzed sends maintenance information to indicate that the device needs maintenance; the number of times abnormal power consumption of the device to be analyzed is detected within a set time is greater than or equal to a first set number; the number of times the device to be analyzed sends fault information to indicate that the device is faulty is greater than or equal to a second set number within a set time.

[0133] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0134] In this embodiment, the device survey data processing apparatus is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0135] This invention also provides a computer device having the device survey data processing apparatus shown in FIG5 above.

[0136] Please refer to Figure 6, which is a schematic diagram of a computer device according to an optional embodiment of the present invention. As shown in Figure 6, the computer device includes one or more processors 10, a memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components communicate with each other using different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 6 uses one processor 10 as an example.

[0137] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0138] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0139] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0140] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0141] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0142] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0143] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0144] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended technical solutions.

Claims

1. A method for processing equipment survey data, characterized in that, The method includes: in response to a survey trigger condition that the device to be analyzed meets a set fault type, acquiring historical data information of the device to be analyzed; based on the historical data information, determining a device baseline for pushing survey questionnaires to the device to be analyzed; detecting a device baseline value of the device to be analyzed, the device baseline value being used to characterize the actual operating status of the device to be analyzed; and sending a customized survey questionnaire for device survey to an application logged into a target account, wherein the target account is bound to a device whose deviation from the device baseline value is greater than a set threshold.

2. The method according to claim 1, characterized in that, The step of determining the equipment baseline for the survey questionnaire pushed to the device to be analyzed based on the historical data information includes: determining the historical fault weighted baseline, the current equipment status compensation baseline, and the equipment reliability weighted baseline based on the historical data information; and determining the equipment baseline by multiplying the historical fault weighted baseline, the current equipment status compensation baseline, and the equipment reliability weighted baseline.

3. The method according to claim 2, characterized in that, The historical fault weighted baseline is determined using the following formula: Historical fault weighted baseline = Fault frequency weight * Historical baseline of fault A over the past 3 months + (X / Total number of equipment faults) * Fault frequency weight; where fault A represents the fault of the set fault type, the historical baseline of fault A over the past 3 months is the average value of the set baselines determined when fault A occurred in the equipment under analysis over the past 3 months; X represents the total number of times fault A occurred in the equipment under analysis; and the total number of equipment faults represents the total number of all faults that occurred in the equipment under analysis.

4. The method according to claim 2, characterized in that, The current state compensation baseline of the equipment is determined by the following operation: obtaining the influence coefficients of multiple set factors on the equipment to be analyzed, wherein the influence coefficients include at least two of the seasonal compensation coefficient, the equipment usage nature compensation coefficient, and the regional compensation coefficient; and determining the current state compensation baseline by multiplying the multiple influence coefficients.

5. The method according to claim 2, characterized in that, The weighted baseline for equipment reliability is determined using the following formula: Weighted baseline for equipment reliability = lower limit + amplitude * Math.exp(-mean time between failures / time constant); where the mean time between failures is the total operating time of the equipment / the total number of equipment failures.

6. The method according to claim 1, characterized in that, The detection of the device baseline value of the device to be analyzed includes: obtaining multiple dimension baseline values ​​of the device, wherein the multiple dimension baseline values ​​are used to characterize the failure impact value of multiple dimension influencing factors on the failure of the device; and using the product of the multiple dimension baseline values ​​as the device baseline value of the device to be analyzed.

7. The method according to claim 6, characterized in that, The multiple dimensional benchmarks include time-based benchmarks, severity-based benchmarks, environmental-based benchmarks, and user habit-based benchmarks.

8. The method according to claim 1, characterized in that, The step of sending a customized questionnaire for device research to the application logged into the target account includes: when the deviation of the device's baseline value from the device baseline is greater than a set threshold, generating a customized questionnaire that matches the device to be analyzed based on the actual operating status of the device; and sending the customized questionnaire to the application logged into the target account.

9. The method according to claim 8, characterized in that, The process of generating a customized questionnaire matching the device under analysis based on its actual operating status includes: obtaining basic weight coefficients for multiple preset question types, user characteristic coefficients for the device under analysis, and real-time status coefficients for the device under analysis, wherein the real-time status coefficients of the device under analysis are used to indicate the degree of correlation between the operating environment and fault types of the device under analysis and the preset question types; determining the weight of the preset question type based on the product of the basic weight coefficients, user characteristic coefficients, and device status coefficients of the preset question type; and randomly generating the customized questionnaire based on the weights of the multiple preset question types, wherein the customized questionnaire contains a set number of survey questions, and the number of each type of question in the survey questions conforms to the weights of the multiple preset question types.

10. The method according to claim 9, characterized in that, The equipment status coefficient is determined using the following formula: Equipment status coefficient = Fault correlation coefficient * Environmental coefficient; wherein, the fault correlation coefficient is used to indicate the degree of matching between the preset problem type and the fault type of the equipment to be analyzed. If the preset problem type matches the fault of the equipment to be analyzed, the fault correlation coefficient is taken as the first preset correlation coefficient; the environmental coefficient is used to characterize the degree of matching between the environment where the equipment to be analyzed is currently located and the environment associated with the preset problem type. If the humidity at the location of the equipment to be analyzed is greater than or equal to a set humidity threshold, the weight of the preset problem type condensation problem is configured as the first environmental coefficient. If the hardness of the current water quality of the equipment to be analyzed is greater than or equal to a set hardness threshold, the weight of the preset problem type scaling problem is configured as the second environmental coefficient. The environmental coefficient is the product of multiple environmental coefficients.

11. The method according to claim 1, characterized in that, The survey triggering conditions include at least one of the following: the device to be analyzed sends maintenance information to indicate that the device needs maintenance; the number of times the device to be analyzed is detected to have abnormal power consumption within a set time is greater than or equal to a first set number; the number of times the device to be analyzed sends fault information to indicate that the device is faulty within a set time is greater than or equal to a second set number.

Images