Equipment screening method and device based on equipment operating rate, equipment and medium

Abstract

The embodiment of the invention provides an equipment screening method and device based on an equipment operating rate, equipment and a medium, which can be applied to financial science and technology scenes and medical science and technology scenes, and the method comprises the following steps: obtaining historical state data of candidate equipment; calculating the probability that the candidate equipment is in an equipment state in a preset time period to obtain state probability distribution; according to the state probability distribution, calculating the information entropy of the device state of the candidate device to obtain a target information entropy; based on the target information entropy, performing clustering processing on the candidate equipment to obtain a target class; based on the target class, calculating the operating rate of the candidate equipment to obtain the operating rate of the equipment; and screening the candidate equipment according to the equipment operating rate. According to the embodiment of the invention, the equipment screening precision can be improved.

Description

Technical Field

[0001] The present application relates to the field of equipment operation and maintenance technology, and is applicable to financial technology scenarios and medical technology scenarios, and in particular to an equipment screening method and device based on equipment operating rate, equipment and medium. Background Art

[0002] Equipment leasing services refer to transactions in which the lessee purchases leased equipment from the seller based on the lessee's selection of the seller and the leased equipment, provides the equipment to the lessee for use, and pays rent. Today, many businesses and factories rely on equipment leasing services to conduct business and conduct production. In this scenario, the equipment utilization rate measures the intensity of equipment usage and is a key indicator for assessing the status of leased equipment. The equipment utilization rate can be used by the lessee to determine whether the leased equipment is necessary; the lessor can use the equipment utilization rate to determine the degree of wear and tear on the leased equipment and reassess the equipment's value. For example, hospital managers can determine the need for leasing new equipment based on the utilization rates of equipment in different departments; and financial leasing companies can adjust the density of shared equipment deployment based on the utilization rates of shared equipment.

[0003] Related technologies typically use the ratio of a device's actual operating time to its planned available time as the operating rate to screen equipment. However, the actual operating time doesn't fully reflect the intensity of equipment usage, and the equipment screening accuracy is insufficient. Therefore, improving equipment screening accuracy has become a pressing technical challenge. Summary of the Invention

[0004] The main purpose of the embodiments of the present application is to propose an equipment screening method and device, equipment and medium based on equipment operating rate, aiming to improve the accuracy of equipment screening.

[0005] To achieve the above objectives, a first aspect of an embodiment of the present application proposes an equipment screening method based on equipment operating rate, the method comprising:

[0006] Obtaining historical status data of the candidate device; wherein the historical status data includes the device status of the candidate device at a historical time;

[0007] Calculating the probability that the candidate device is in the device state during a preset period of time to obtain a state probability distribution; wherein the preset period of time is determined by historical time;

[0008] According to the state probability distribution, the information entropy of the device state of the candidate device is calculated to obtain the target information entropy;

[0009] Based on the target information entropy, the candidate devices are clustered to obtain the target class;

[0010] Based on the target class, the operating rate of the candidate equipment is calculated to obtain the equipment operating rate;

[0011] Screen candidate equipment based on equipment operating rate.

[0012] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes an equipment screening device based on equipment operating rate, the device comprising:

[0013] A data acquisition module is used to acquire historical status data of the candidate device; wherein the historical status data includes the device status of the candidate device at a historical time;

[0014] A probability calculation module is used to calculate the probability that the candidate device is in the device state during a preset period of time to obtain a state probability distribution; wherein the preset period of time is determined by historical time;

[0015] An information entropy calculation module is used to calculate the information entropy of the device state of the candidate device according to the state probability distribution to obtain the target information entropy;

[0016] The device clustering module is used to cluster candidate devices based on target information entropy to obtain target classes;

[0017] The operating rate calculation module is used to calculate the operating rate of candidate equipment based on the target class to obtain the equipment operating rate;

[0018] The equipment screening module is used to screen candidate equipment based on the equipment operating rate.

[0019] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, the memory stores a computer program, and the processor implements the method of the above-mentioned first aspect when executing the computer program.

[0020] To achieve the above-mentioned purpose, the fourth aspect of the embodiments of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method of the above-mentioned first aspect.

[0021] The equipment screening method and device, equipment and medium based on equipment operating rate proposed in this application are based on the historical status data of candidate equipment, and calculate the probability of candidate equipment being in different equipment states in a time range specified by a preset time period to obtain a state probability distribution; according to the state probability distribution, the equipment state of the candidate equipment is calculated by information entropy to obtain the target information entropy; the uncertainty of the equipment state of different candidate equipment in the same time range is quantified by information entropy, reflecting whether the candidate equipment has a certain operating regularity; clustering processing is performed according to the target information entropy, and the target equipment can be divided into target categories according to the degree of equipment operating regularity, so that the candidate equipment can be classified and calculated according to the equipment category, thereby improving the accuracy of the operating rate calculation, and the obtained operating rate is more in line with the actual usage intensity of the equipment; equipment is screened according to the operating rate to improve the equipment screening accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flow chart of the method provided in an embodiment of the present application;

[0023] Figure 2 yes Figure 1 Flowchart of step S103 in FIG.

[0024] Figure 3 yes Figure 1 Flowchart of step S104 in FIG.

[0025] Figure 4 yes Figure 3 Flowchart of step S302 in FIG.

[0026] Figure 5 yes Figure 4 Flowchart of step S405 in FIG.

[0027] Figure 6 yes Figure 1 Flowchart of step S105 in FIG.

[0028] Figure 7 is another flow chart of the method provided in an embodiment of the present application;

[0029] Figure 8 is a schematic structural diagram of the device provided in an embodiment of the present application;

[0030] Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0032] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and so on, in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0034] First, let’s analyze some of the terms used in this application:

[0035] Artificial intelligence (AI) is a new technical discipline that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence. A branch of computer science, AI seeks to understand the essence of intelligence and create new intelligent machines that can respond in a manner similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. AI can simulate the information processes of human consciousness and thinking. It also encompasses theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, to perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0036] Equipment Condition Monitoring (ECM) refers to the real-time collection, processing, and analysis of various parameters and signals of equipment during operation using various sensors and technologies to determine whether the equipment is working normally. Equipment Condition Monitoring integrates multidisciplinary knowledge such as mechanical engineering, electronic engineering, signal processing, and data analysis. Its main goal is to promptly detect abnormal conditions and potential failures of equipment, prevent production interruptions, economic losses, and safety accidents caused by sudden equipment failures, and ensure that the equipment can operate continuously and stably. It also helps to optimize equipment maintenance plans, reduce maintenance costs, and improve equipment life and reliability. It is an important link in modern industrial production and equipment management, and is widely used in many fields such as manufacturing, energy, and transportation.

[0037] Based on this, the embodiments of the present application provide an equipment screening method and device, equipment and medium based on equipment operating rate, aiming to improve the accuracy of equipment screening.

[0038] The equipment screening method and device based on equipment operating rate provided in the embodiments of the present application, as well as the equipment and medium, are specifically illustrated through the following embodiments. First, the equipment screening method based on equipment operating rate in the embodiments of the present application is described.

[0039] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0040] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0041] An embodiment of the present application provides an equipment screening method based on equipment operating rate, which relates to the field of equipment operation and maintenance technology. An embodiment of the present application provides an equipment screening method based on equipment operating rate, which can be applied to a terminal, or to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers, or as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements an equipment screening method based on equipment operating rate, etc., but is not limited to the above forms.

[0042] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0043] It should be noted that in each specific embodiment of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained. The non-Company's software tools or components that appear in the embodiments of the present application are merely examples and do not represent actual use.

[0044] Figure 1 This is an optional flowchart of the method provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S106.

[0045] Step S101, obtaining historical status data of a candidate device; wherein the historical status data includes the device status of the candidate device at a historical time;

[0046] Step S102, calculating the probability that the candidate device is in the device state during a preset period, and obtaining a state probability distribution; wherein the preset period is determined by historical time;

[0047] Step S103, calculating the information entropy of the device state of the candidate device according to the state probability distribution to obtain the target information entropy;

[0048] Step S104: clustering the candidate devices based on the target information entropy to obtain a target class;

[0049] Step S105, based on the target class, calculate the operating rate of the candidate equipment to obtain the equipment operating rate;

[0050] Step S106: Screen candidate equipment based on equipment operating rate.

[0051] As can be understood, a probability distribution is a mathematical model that describes the likelihood of a system being in various states, typically represented by a probability vector or probability distribution function. In the embodiments of the present application, the state probability distribution is obtained by calculating the probability of a candidate device being in a device state during a preset time period. The state probability distribution is used to describe the likelihood of a candidate device being in various device states during a preset time period.

[0052] It can be understood that information entropy is a quantitative indicator to measure the degree of information uncertainty or the amount of information. In the embodiment of the present application, the target information entropy is calculated for the device state of the candidate device through the state probability distribution. The target information entropy quantifies the uncertainty of the device state of the candidate device in a preset time period, reflecting whether the candidate device has a certain operating law. The larger the target information entropy, the higher the uncertainty of the device state, that is, the more likely the candidate device is to switch the device state frequently; the smaller the target information entropy, the lower the uncertainty of the device state, that is, the more likely the candidate device is to remain in a certain device state. For example, shared bicycles will circulate between multiple users, frequently switching between the running state and the shutdown state, and the uncertainty of the device state is high; for example, industrial conveyor belts usually remain in the running state for a fixed period of time, and the uncertainty of the device state is low.

[0053] Clustering is the process of rationally dividing a dataset into several subsets based on the similarity between data objects, each of which is called a cluster. The goal of cluster analysis is to make the data points similar within a cluster and different between clusters. In the embodiments of the present application, clustering candidate devices based on target information entropy essentially groups similar candidate devices into clusters based on the uncertainty of their states. The utilization rates of the candidate devices are then classified and calculated based on their state characteristics, more objectively reflecting the intensity of device usage. For example, shared bicycles are often used for short trips and high frequency. Using the utilization rate as the ratio of actual operating time to planned available time, as used in related methods, would fail to capture the actual usage intensity of the bicycles under these usage patterns. Specifically, suppose a shared bicycle in area A is used 10 times, each for 5 minutes, within an hour; while a shared bicycle in area B is used once for 50 minutes. If the utilization rates of the two devices are calculated to be the same using related methods, the shared bicycle in area A cannot be selected for adjustment. But in fact, given the usage rate and intensity of shared bicycles in Area A, financial leasing companies need to increase the density of shared bicycles in Area A.

[0054] In summary, considering that there are many types of rental equipment and they are used in different industries, each has its own operating rules. Only using the operating time as an indicator for calculating the operating rate cannot accurately reflect the usage intensity of multiple types of rental equipment. Steps S101 to S106 shown in the embodiment of the present application, based on the historical status data of the candidate equipment, calculate the probability of the candidate equipment being in different equipment states by specifying a time range through a preset period, and obtain a state probability distribution; according to the state probability distribution, the device state of the candidate equipment is calculated by information entropy to obtain the target information entropy; the uncertainty of the device state of different candidate equipment in the same time range is quantified by information entropy to reflect whether the candidate equipment has a certain operating rule; clustering processing is performed according to the target information entropy, and the target equipment can be divided into target classes according to the degree of the equipment operating rule, so that the candidate equipment can be classified and calculated according to the equipment category, thereby improving the accuracy of the operating rate calculation, and the obtained operating rate is more in line with the actual usage intensity of the equipment; the equipment is screened according to the operating rate to improve the accuracy of equipment screening.

[0055] In step S101 of some embodiments, the candidate device may be a shared device such as a shared power bank, a shared bicycle, a shared car, a server, or other shared devices; it may also be a medical device such as a surgical robot, an ultrasound diagnostic device, a blood pressure meter, or other financial devices such as a money counter and an ATM, but is not limited thereto.

[0056] In step S101 of some embodiments, the device status of the candidate device may be, but is not limited to, a running state, a shutdown state, a maintenance state, a busy state, an idle state, or the like.

[0057] In step S102 of some embodiments, the preset time period can be in units of minutes, hours, days, etc., but is not limited thereto. For example, the device status of the blood pressure monitor from 8:00 to 9:00 every day in the past is obtained to obtain historical status data; the preset time period is determined to be 8:00 to 9:00, and the probability of the blood pressure monitor being in different device states from 8:00 to 9:00 is calculated to obtain a state probability distribution.

[0058] In step S102 of some embodiments, historical status data can be sampled, the number of occurrences of each device state in the sampled data points can be counted, and its proportion to the total number of sampling points can be calculated to obtain a state probability distribution; the length of time that the candidate device is in each device state during a preset time period can also be calculated, and its ratio to the length of the preset time period can be calculated to obtain a state probability distribution; this is not limited to this.

[0059] See also Figure 2 In some embodiments, step S103 may include but is not limited to steps S201 to S203:

[0060] Step S201, calculating the self-information of the running state according to the running probability to obtain the first self-information;

[0061] Step S202, calculating the self-information of the shutdown state according to the shutdown probability to obtain a second self-information;

[0062] Step S203 : calculating the information entropy of the device state according to the first self-information amount and the second self-information amount to obtain the target information entropy.

[0063] As is easy to understand, self-information refers to the amount of information contained in a single event and is used to measure the uncertainty of that event. In the embodiments of the present application, the self-information of the running state and the shutdown state is calculated separately to measure the uncertainty of the running state and the shutdown state. Based on the self-information of the running state and the shutdown state, the target information entropy of the device state is calculated to quantify the uncertainty of the device state of the candidate device during a preset time period, that is, to quantify the frequency with which the candidate device switches between the running state and the shutdown state.

[0064] In steps S201 to S203 shown in the embodiment of the present application, the self-information of the running state and the shutdown state is calculated respectively to measure the uncertainty of the running state and the shutdown state; based on the self-information of the running state and the shutdown state, the target information entropy of the device state is calculated, and the target information entropy quantifies the frequency of switching between the running state and the shutdown state of the candidate device. Based on this, the equipment is clustered to calculate the operating rate, which can improve the accuracy of the operating rate calculation.

[0065] In some embodiments, step S203 may include but is not limited to: calculating the self-information of the maintenance status based on the maintenance probability to obtain the third self-information; calculating the information entropy of the equipment status based on the first self-information, the second self-information and the third self-information to obtain the target information entropy.

[0066] In some embodiments, step S203 may include but is not limited to: taking the operation probability as the weight of the first self-information amount and the shutdown probability as the weight of the second self-information amount, performing weighted calculation on the first self-information amount and the second self-information amount to obtain the information entropy of the device state.

[0067] In some embodiments, there are multiple preset time periods; step S102 may include but is not limited to: calculating the probability that the candidate device is in the device state in each preset time period, and obtaining several state probability distributions; step S103 may include but is not limited to: calculating the information entropy of the device state of the candidate device according to the several state probability distributions, and obtaining several information entropy values; and taking the average value or cumulative value of the several information entropy values as the target information entropy.

[0068] Taking the FinTech scenario as an example, the candidate device is an ATM, and the device status includes operating status and downtime status. The device status of the ATM is obtained for each day of the past month to obtain historical status data. To simplify the explanation, in this embodiment, if a user uses the ATM on a certain day, the ATM is considered to be in operating status on that day; otherwise, the ATM is considered to be in downtime on that day. Based on the historical status data, the number of days the ATM is in operating status and downtime status is counted respectively to obtain the operating days and downtime days. The ratio of the operating days and downtime days to the total number of days is calculated respectively to obtain the operating probability P1 and the downtime probability P2; based on this calculation, the first self-information amount I1 = -log2(P1) and the second self-information amount I2 = -log2(P2) are obtained; and the target information entropy H = P1I1 + P2I2 is calculated.

[0069] Taking the medical technology scenario as an example, the candidate device is a blood pressure monitor, and the device status includes the running status and the shutdown status. The device status of the blood pressure monitor is obtained every hour from 8:00 to 18:00 every day for the past month to obtain historical status data. To simplify the explanation, in this embodiment, if a user uses the blood pressure monitor in a certain hour, the blood pressure monitor is considered to be in the running state for that hour; otherwise, the blood pressure monitor is considered to be in the shutdown state for that hour. Statistics show that the blood pressure monitor is in the running state for 20 days from 8:00 to 9:00 and in the shutdown state for 10 days; in the running state for 15 days from 9:00 to 10:00 and in the shutdown state for 15 days; in the running state for 12 days from 10:00 to 11:00 and in the shutdown state for 18 days; no more examples are listed here. The calculated probability of the blood pressure monitor operating between 8:00 and 9:00 is 0.5, and the probability of it being down is 0.5, resulting in an information entropy of 0.918 bits for that hour. Similarly, we calculate 10 information entropies for 10 time periods between 8:00 and 18:00, and the cumulative value of these 10 information entropies is calculated as the target information entropy.

[0070] See also Figure 3 In some embodiments, step S104 may include but is not limited to steps S301 to S302:

[0071] Step S301, obtaining the leasing mode of the candidate device;

[0072] Step S302 : clustering the candidate devices based on the target information entropy and the leasing mode to obtain a target class.

[0073] In steps S301 to S302 shown in the embodiment of the present application, taking into account that the leasing mode will directly affect the way the device is used, such as the device status of a shared device usually has a high degree of uncertainty, the embodiment of the present application uses the leasing mode as a categorical feature and participates in clustering together with the target information entropy, further improving the clustering accuracy and accurately classifying candidate devices with similar operating rules into one category.

[0074] In step S301 of some embodiments, the leasing model can be converted into a data format suitable for clustering model processing by natural number encoding, unique hot encoding, target encoding, etc. The leasing model may include, but is not limited to, a sharing model, a payment model, an equipment type, a lease term, and a deployment area. Among them, the sharing model can be shared use or exclusive use, the payment model can be pay-by-time, pay-by-usage (such as network traffic), pay-by-equipment output, or pay-by-number of times, the equipment type can be production equipment, medical equipment, financial equipment, transportation equipment, or other equipment, the lease term can be daily, monthly, or annual, and the deployment area can be an industrial area or a residential area, but is not limited to this.

[0075] For simplicity, assume a company has two types of assets for lease: financial equipment and transportation equipment. The leasing model is represented by a binary vector, where the components represent, in order, the sharing model, payment model, equipment type, lease term, and deployment area. When each component is 1, it indicates shared use, pay-per-use, transportation equipment, short-term lease, and residential deployment area. When each component is 0, it indicates exclusive use, pay-per-use, financial equipment, long-term lease, and industrial deployment area. For example, if a candidate device is a shared bicycle, its leasing models include shared use, pay-per-use, transportation equipment, short-term lease, and residential deployment area. Its leasing model is represented by the binary vector [1, 1, 1, 1]; if a candidate device is a shared car, its leasing models include shared use, pay-per-use, transportation equipment, long-term lease, and residential deployment area. Its leasing model is represented by the binary vector [1, 0, 1, 0, 1]. It is easy to understand that the leasing mode vector can be in binary form or in natural number form. For example, when the vector component representing the payment mode is 0, it means paying by time; when it is 1, it means paying by usage; when it is 2, it means paying by equipment output; and when it is 3, it means paying by number of times.

[0076] In some embodiments, step S302 may include, but is not limited to, obtaining the operating time and operating frequency of candidate devices; and clustering the candidate devices based on the target information entropy, rental mode, operating time, and operating frequency to obtain a target class. In this embodiment of the present application, the target information entropy, operating time, and operating frequency are used as numerical features, and the rental mode is used as a categorical feature. Clustering the candidate devices using these numerical and categorical features improves clustering accuracy.

[0077] See also Figure 4 In some embodiments, step S302 may include but is not limited to steps S401 to S405:

[0078] Step S401, calculating the Euclidean distance between any two candidate devices based on the target information entropy to obtain a first distance;

[0079] Step S402: extracting frequent itemsets from the rental model to obtain target frequent itemsets; wherein the target frequent itemsets include frequent attributes;

[0080] Step S403, calculating the difference between the candidate devices based on the frequent attributes to obtain a first difference;

[0081] Step S404, calculating the difference between the candidate devices based on the infrequent attribute to obtain a second difference; the infrequent attribute does not belong to the target frequent item set;

[0082] Step S405 : Classifying the candidate devices into a target class based on the first distance, the weighted values of the first difference, and the second difference; wherein the weight of the first difference is greater than the weight of the second difference.

[0083] It is easy to understand that frequent itemsets refer to attribute combinations that appear in a data set with a frequency greater than a preset threshold. Mining frequent itemsets is the basis of association rule learning and is often used in market basket analysis, recommendation systems, network intrusion detection and other fields.

[0084] In related technologies, clustering based on categorical features usually increases inter-cluster differences by assigning high weights to scarce categorical features.

[0085] Considering that the rental model is different from numerical features, numerical features (such as target information entropy) can automatically capture the joint relationship between features through the geometric relationship in the vector space when calculating their Euclidean distance, while the rental model is a categorical feature. By comparing two classification values by matching the dissimilarity measure (the same classification value is 1, and the different classification values are 0), it is difficult to capture the joint relationship between features, and the clustering accuracy is insufficient. Steps S401 to S405 shown in the embodiment of the present application extract frequent itemsets from the rental model to obtain frequent attributes with strong correlation, assign high weights to them so that the frequent attributes dominate the clustering process. Candidate devices in the same cluster are highly consistent in frequent attributes, which improves the similarity within the cluster and more accurately classifies candidate devices with similar operating rules into one category.

[0086] In some embodiments, step S401 may include but is not limited to: obtaining the operating time and operating frequency of the candidate devices; using the target information entropy, operating time and operating frequency as numerical features, and calculating the Euclidean distance between any two candidate devices based on the numerical features to obtain a first distance.

[0087] In step S401 of some embodiments, the Euclidean distance can be calculated using the standard Euclidean distance formula, which is applicable to situations where each numerical feature has the same importance; the Euclidean distance can also be calculated using the weighted Euclidean distance formula, which is applicable to situations where each numerical feature has different importance; but this is not limited to this.

[0088] In some embodiments, step S402 may include but is not limited to: obtaining the rental patterns of candidate devices as a data set; combining the rental patterns, counting the frequency of occurrence of each pattern group in the data set, and calculating the support of each pattern group based on the frequency of occurrence; and filtering out the target frequent item set from the pattern group based on the support.

[0089] In step S403 of some embodiments, the first difference may be calculated by Hamming distance, Manhattan distance, etc., without limitation. Similarly, in step S404 of some embodiments, the second difference may be calculated by Hamming distance, Manhattan distance, etc., without limitation.

[0090] For example, the leasing mode values of candidate devices are obtained to construct a data set, which includes: the leasing mode value of the first candidate device is {shared use, pay-per-use, transportation equipment, short-term lease, residential area}, the leasing mode value of the second candidate device is {exclusive use, pay-per-time, financial equipment, long-term lease, industrial area}, the leasing mode value of the third candidate device is {shared use, pay-per-use, other equipment, short-term lease, residential area}, etc. The frequency of occurrence of each pattern in the dataset is counted to calculate the support of each pattern. A support threshold is set and patterns with support greater than the support threshold are selected, such as {shared use}, {pay per use}, and {residential area}. These patterns are then combined into binary sets, such as {shared use, pay per use}, {shared use, residential area}, and {pay per use, residential area}. Similarly, the support of each binary set is calculated and, based on the support, frequent binary sets {shared use, pay per use} and {shared use, residential area} with support greater than the support threshold are selected. A three-item set is constructed based on the frequent binary sets, such as {shared use, pay per use, residential area}. The support of this three-item set is calculated. If the support is greater than the support threshold, the three-item set is used as the target frequent itemset. Otherwise, the frequent binary set with the highest support is selected as the target frequent itemset. It is easy to understand that the support thresholds described above can be set to the same value or different values. Assume that {shared use, pay-per-use, residential area} is the frequent attribute in the target frequent item set. According to the above embodiment, the rental mode of shared bicycles is obtained as [1, 1, 1, 1, 1], and the rental mode of shared cars is obtained as [1, 0, 1, 0, 1]. Accordingly, the weights of the first two vector components and the last vector in the rental mode are set to be greater than the weights of other components. Based on the frequent attributes, the first difference value between the shared power bank and the shared car is calculated to be 1, and the weight of the frequent attribute is 0.4. Based on the infrequent attributes, the second difference value between the shared power bank and the shared car is calculated to be 1, and the weight of the infrequent attribute is 0.1. The weight of the first distance is set to 0.5.

[0091] See also Figure 5 In some embodiments, step S405 may include but is not limited to steps S501 to S502:

[0092] Step S501, performing weighted calculation on the first difference and the second difference to obtain a second distance;

[0093] Step S502: performing weighted calculation on the first distance and the second distance to obtain a target distance; wherein the weight of the second distance is determined based on the number of rental modes;

[0094] Step S503: Classify the candidate devices into target classes based on the target distance.

[0095] In related technologies, domain experts often manually set the weights of the distances corresponding to categorical features, which is not objective. In this embodiment, steps S501 to S503 automatically set the weight of the second distance based on the number of rental models, ensuring that the first and second distances contribute equally to the clustering results.

[0096] In step S502 of some embodiments, the total number of cluster features can be calculated, and the ratio of the number of rental modes to the total number can be calculated as the weight of the second distance. Specifically, the number of numerical features is calculated as the first number; the number of rental modes is calculated as the second number; the ratio of the first number to the total number is calculated as the weight of the first distance (e.g., the numerical features include target information entropy, operating time, and operating frequency, the first number is calculated to be 3, and the weight of the first distance is 0.375); the ratio of the second number to the total number is calculated as the weight of the second distance (e.g., the rental mode includes sharing mode, payment mode, device type, rental period, and delivery area, the second number is calculated to be 5, and the weight of the second distance is 0.625).

[0097] In some embodiments, in step S502, the first distance and the second distance may be normalized separately, and then the normalized values of the first and second distances may be weighted to obtain the target distance. Specifically, the numerical feature is considered as a feature dimension, the first quantity is set to 1, the number of rental modes is calculated as the second quantity, the reciprocal of the total quantity is calculated as the weight of the first distance, and the ratio of the second quantity to the total quantity is calculated as the weight of the first distance.

[0098] In some embodiments, step S503 may include but is not limited to: dividing the candidate devices into sample points and center points; dividing the sample points into the target class corresponding to the nearest center point based on the target distance between the sample points and the center points; updating the center point of the target class to re-divide the sample points into the target class until the clustering stop condition is met.

[0099] See also Figure 6 In some embodiments, step S105 may include but is not limited to steps S601 to S603:

[0100] Step S601: Filtering a first device class from the target class based on target information entropy;

[0101] Step S602: Obtain a first calculation indicator based on the first device type; the first calculation indicator includes an operating time indicator and an operating load indicator; the operating time indicator is calculated based on the device operating time, and the operating load indicator is calculated based on the device operating load;

[0102] Step S603: Calculate the operating rate of the candidate equipment according to the operating time index and the operating load index to obtain the equipment operating rate.

[0103] It can be understood that based on the target information entropy, the first device class with weak uncertainty in device status is screened out from the target class. The candidate devices belonging to the first device class are more likely to remain in a certain device state, that is, the time continuity of the device state is stronger, and the actual usage intensity of the candidate devices can be reflected by the operating time index and the operating load index.

[0104] In steps S601 to S603 shown in the embodiment of the present application, based on the target information entropy, the first equipment class with weak uncertainty in equipment status is screened out from the target class; based on the operating time index and the operating load index, the operating rate of the candidate equipment belonging to the first equipment class is calculated, which can more comprehensively and accurately reflect the actual usage intensity of the candidate equipment.

[0105] In step S601 of some embodiments, the target class obtained by clustering processing includes at least two device classes, and the one with the smallest mean value of target information entropy or the smallest mean value of clustering features is taken as the first device class, but this is not limited thereto.

[0106] In step S602 of some embodiments, the operating time indicator may include, but is not limited to, the ratio of the maximum single operating time to the average single operating time, the ratio of the current monthly operating time to the average monthly operating time of similar equipment, etc. The operating load indicator may include, but is not limited to, the ratio of the maximum instantaneous load to the average load, the overload operating time, etc.

[0107] In step S603 of some embodiments, an average value or a weighted value may be calculated for the operating time index and the operating load index to serve as the operating rate of the candidate equipment.

[0108] See also Figure 7 In some embodiments, after step S603, the equipment screening method based on equipment operating rate may further include but is not limited to steps S701 to S703:

[0109] Step S701: Based on the target information entropy, a second device class is screened from the target class; wherein the candidate devices in the first device class have a first information entropy mean value, and the candidate devices in the second device class have a second information entropy mean value, and the second information entropy mean value is greater than the first information entropy mean value;

[0110] Step S702: Obtain a second calculation indicator based on the second device type; the second calculation indicator includes an operation number indicator and an operation interval indicator; the operation number indicator is calculated based on the number of device operations, and the operation interval indicator is calculated based on the device operation interval time;

[0111] Step S703: Calculate the operating rate of the candidate equipment according to the operating number index and the operating interval index to obtain the equipment operating rate.

[0112] It can be understood that based on the target information entropy, the first device class with strong uncertainty in device status is screened out from the target class. The candidate devices belonging to the first device class are more likely to switch device status frequently, that is, the time continuity of the device status is weak. The operation number index and the operation interval index can reflect the actual usage intensity of the candidate devices.

[0113] In steps S701 to S703 shown in the embodiment of the present application, based on the target information entropy, the second equipment class with strong uncertainty in equipment status is screened out from the target class; based on the operation number index and the operation interval index, the operating rate of the candidate equipment belonging to the second equipment class is calculated, which can more comprehensively and accurately reflect the actual usage intensity of the candidate equipment.

[0114] In step S701 of some embodiments, the target class obtained by clustering processing includes at least two device classes, and the one with the largest mean value of target information entropy or the largest mean value of clustering features is used as the second device class, but is not limited thereto.

[0115] In step S702 of some embodiments, the operation number indicator may include, but is not limited to, the ratio of the maximum daily operation number to the average daily operation number, the number of overload operations, etc. The operation interval indicator may include, but is not limited to, the ratio of the shortest daily operation time interval to the average daily operation time interval, the ratio of the maximum operation time interval to the average daily operation time interval, etc.

[0116] In step S703 of some embodiments, an average value or a weighted value may be calculated for the operation number index and the operation interval index to serve as the operating rate of the candidate equipment.

[0117] In some embodiments, after step S703, the equipment screening method based on equipment operating rate may further include, but is not limited to, the following: based on the target information entropy, screening a third equipment class from the target class, wherein the candidate equipment in the third equipment class has a third information entropy mean; the third information entropy mean is less than the second information entropy mean, and the third information entropy mean is greater than the first information entropy mean; obtaining a third calculation indicator based on the third equipment class; the third calculation indicator may include an operating time indicator, an operating load indicator, an operating number indicator, and an operating interval indicator. For example, the first equipment class may include assembly line manipulators, inspection robots, etc., whose equipment states generally have a periodic pattern; the second equipment class may include warehouse trucks, agricultural machinery, clothing production equipment, etc., whose equipment states have some regularity and are affected by external factors (such as order fluctuations and environmental changes); the third equipment class may include emergency generators, shared bicycles, etc., whose equipment states have no obvious regularity, with equipment starting and stopping randomly and driven by sudden tasks.

[0118] In step S106 of some embodiments, candidate equipment with an operating rate greater than a preset threshold can be screened out, and an equipment purchase plan can be pushed to the equipment user; candidate equipment with an operating rate less than a preset threshold can also be screened out, and an equipment recycling plan can be pushed to the equipment user; this is not limited to this.

[0119] The equipment screening method based on equipment operating rate provided in the embodiment of the present application is based on the historical status data of the candidate equipment, and calculates the probability of the candidate equipment being in different equipment states by specifying a time range through a preset time period to obtain a state probability distribution; according to the state probability distribution, the equipment state of the candidate equipment is calculated by information entropy to obtain a target information entropy; the uncertainty of the equipment state of different candidate equipment in the same time range is quantified by information entropy, reflecting whether the candidate equipment has a certain operating regularity; the usage information is introduced through the leasing model, and clustered together with the target information entropy as a clustering feature, and at the same time, the frequent attributes in the leasing model are given a high weight so that the frequent attributes dominate the clustering process, and the candidate equipment with similar operating regularities are accurately classified into one category according to the degree of equipment operating regularity; the target equipment is divided into target classes, so that the candidate equipment is classified and calculated according to the equipment category, the accuracy of the operating rate calculation is improved, and the obtained operating rate is more in line with the actual usage intensity of the equipment; the equipment is screened according to the operating rate to improve the equipment screening accuracy.

[0120] See also Figure 8 The present application also provides an equipment screening device based on equipment operating rate, which can implement the above method. The device includes:

[0121] A data acquisition module is used to acquire historical status data of the candidate device; wherein the historical status data includes the device status of the candidate device at a historical time;

[0122] A probability calculation module is used to calculate the probability that the candidate device is in the device state during a preset period of time to obtain a state probability distribution; wherein the preset period of time is determined by historical time;

[0123] An information entropy calculation module is used to calculate the information entropy of the device state of the candidate device according to the state probability distribution to obtain the target information entropy;

[0124] The device clustering module is used to cluster candidate devices based on target information entropy to obtain target classes;

[0125] The operating rate calculation module is used to calculate the operating rate of candidate equipment based on the target class to obtain the equipment operating rate;

[0126] The equipment screening module is used to screen candidate equipment based on the equipment operating rate.

[0127] The specific implementation of the device is basically the same as the specific embodiment of the above method, and will not be repeated here.

[0128] The present application also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the above method when executing the computer program. The electronic device can be any smart terminal including a tablet computer, an in-vehicle computer, or the like.

[0129] See also Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0130] The processor 901 can be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0131] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called by the processor 901 to execute the methods of the embodiments of this application.

[0132] Input / output interface 903, used to implement information input and output;

[0133] Communication interface 904, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0134] Bus 905 , which transmits information between various components of the device (e.g., processor 901 , memory 902 , input / output interface 903 , and communication interface 904 );

[0135] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0136] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and the computer program implements the above method when executed by a processor.

[0137] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0138] The equipment screening method, apparatus, equipment and medium based on equipment operating rate provided in the embodiments of the present application calculate the probability of candidate equipment being in different equipment states in a time range specified by a preset time period to obtain a state probability distribution; based on the state probability distribution, information entropy is calculated for the equipment state of the candidate equipment to obtain a target information entropy; the uncertainty of the equipment state of different candidate equipment in the same time range is quantified by information entropy to reflect whether the candidate equipment has a certain operating regularity; clustering processing is performed based on the target information entropy, and the target equipment can be divided into target categories according to the degree of equipment operating regularity, so that the candidate equipment can be classified and calculated according to the equipment category, thereby improving the accuracy of the operating rate calculation, and the obtained operating rate is more in line with the actual usage intensity of the equipment; the equipment is screened according to the operating rate to improve the equipment screening accuracy.

[0139] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0140] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0141] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0142] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0143] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0144] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0145] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as 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.

[0146] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0147] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0148] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes multiple instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: various media that can store programs, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0149] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. The equipment screening method based on equipment operating rate is characterized by: The method comprises: Acquire historical status data of the candidate device; wherein the historical status data includes the device status of the candidate device at a historical time; Calculating the probability that the candidate device is in the device state during a preset period of time to obtain a state probability distribution; wherein the preset period of time is determined by the historical time; Calculating information entropy of the device state of the candidate device according to the state probability distribution to obtain target information entropy; Based on the target information entropy, clustering the candidate devices to obtain a target class; Based on the target class, calculating the operating rate of the candidate equipment to obtain the equipment operating rate; The candidate equipment is screened according to the equipment operating rate.

2. The method according to claim 1, characterized in that The clustering of the candidate devices based on the target information entropy to obtain a target class includes: Obtaining a lease mode of the candidate device; Based on the target information entropy and the leasing mode, clustering processing is performed on the candidate devices to obtain a target class.

3. The method according to claim 2, characterized in that The clustering of the candidate devices based on the target information entropy and the leasing mode to obtain a target class includes: Based on the target information entropy, calculating the Euclidean distance between any two candidate devices to obtain a first distance; Extracting frequent itemsets from the rental model to obtain a target frequent itemset; wherein the target frequent itemset includes frequent attributes; Calculating the difference between the candidate devices based on the frequent attributes to obtain a first difference; Calculating the difference between the candidate devices based on the infrequent attribute to obtain a second difference; the infrequent attribute does not belong to the target frequent item set; The candidate device is classified into a target class based on weighted values of the first distance, the first difference, and the second difference, wherein the weight of the first difference is greater than the weight of the second difference.

4. The method according to claim 3, characterized in that Classifying the candidate devices into a target class based on the weighted values of the first distance, the first difference, and the second difference includes: performing weighted calculation on the first difference and the second difference to obtain a second distance; Performing a weighted calculation on the first distance and the second distance to obtain a target distance; wherein the weight of the second distance is determined based on the number of the rental modes; Based on the target distance, the candidate devices are classified into the target class.

5. The method according to any one of claims 1 to 4, characterized in that: The device state includes an operating state and a shutdown state; the state probability distribution includes an operating probability and a shutdown probability; and calculating the information entropy of the device state of the candidate device according to the state probability distribution to obtain the target information entropy includes: Calculating the self-information of the operating state according to the operating probability to obtain a first self-information; Calculating the self-information of the shutdown state according to the shutdown probability to obtain a second self-information; The information entropy of the device state is calculated according to the first self-information amount and the second self-information amount to obtain the target information entropy.

6. The method according to any one of claims 1 to 4, characterized in that: The step of calculating the operating rate of the candidate equipment based on the target class to obtain the equipment operating rate includes: Based on the target information entropy, screening out a first device class from the target class; Obtaining a first calculation indicator based on the first device category; the first calculation indicator includes an operating time indicator and an operating load indicator; the operating time indicator is calculated based on the device operating time, and the operating load indicator is calculated based on the device operating load; The operating rate of the candidate equipment is calculated according to the operating time index and the operating load index to obtain the equipment operating rate.

7. The method according to claim 6, characterized in that Also includes: Based on the target information entropy, a second device class is screened out from the target class; wherein the candidate devices in the first device class have a first information entropy mean value, and the candidate devices in the second device class have a second information entropy mean value, and the second information entropy mean value is greater than the first information entropy mean value; Obtain a second calculation indicator based on the second device type; the second calculation indicator includes an operation number indicator and an operation interval indicator; the operation number indicator is calculated based on the number of device operations, and the operation interval indicator is calculated based on the device operation interval time; The operating rate of the candidate equipment is calculated according to the operation number index and the operation interval index to obtain the equipment operating rate.

8. The equipment screening device based on equipment operating rate is characterized by: The device comprises: A data acquisition module is used to acquire historical status data of the candidate device; wherein the historical status data includes the device status of the candidate device at a historical time; A probability calculation module, configured to calculate the probability that the candidate device is in the device state during a preset period of time, and obtain a state probability distribution; wherein the preset period of time is determined by the historical time; An information entropy calculation module, configured to calculate the information entropy of the device state of the candidate device according to the state probability distribution to obtain a target information entropy; A device clustering module, configured to cluster the candidate devices based on the target information entropy to obtain a target class; An operating rate calculation module, configured to calculate the operating rate of the candidate equipment based on the target class to obtain the equipment operating rate; The equipment screening module is used to screen the candidate equipment according to the equipment operating rate.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images