Method, device, storage medium and processor for describing working condition data

Abstract

Embodiments of the present application provide a description method and device for working condition data, a storage medium and a processor. The method comprises: determining a plurality of label levels for describing the working condition data; determining target working condition data to be described, and determining a first label value of each target working condition data; determining a second label value of each target working condition data based on an anomaly detection model; determining a third label value of each target working condition data through a preset classification algorithm; determining a fourth label value of each target working condition data based on a membership function; and describing each target working condition data according to the first label value, the second label value, the third label value and the fourth label value of each target working condition data. The technical solution can more objectively, comprehensively and accurately describe the working condition data, and can describe the working condition data according to the four-level label values, so that the description of each working condition data is more detailed and can meet different needs of users.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a description method and device for working condition data, an engineering vehicle, a storage medium and a processor. BACKGROUND

[0002] Data label technology, as the basis of profiling technology, has been widely used. However, the current data label structure is single in function and can only be applied to a single scene, and cannot be applied in multiple scenes, multiple needs and multiple roles. Moreover, the existing data label technology either directly uses the original data as the corresponding label value or simply performs statistical calculation on the original data to obtain the corresponding label value. The label value obtained through the above technical solution has low accuracy, and the data description based on these label values will result in inaccurate and detailed data description results, and the type description of the data is single and not comprehensive, which cannot meet the different needs of users. SUMMARY

[0003] The purpose of the embodiments of the present application is to provide a description method and device for working condition data, an engineering vehicle, a storage medium and a processor.

[0004] In order to achieve the above purpose, the first aspect of the present application provides a description method for working condition data, comprising:

[0005] determining a plurality of label levels for describing the working condition data of the engineering vehicle, the plurality of label levels comprising an initial label, a first level label, a second level label and a third level label;

[0006] determining a plurality of target working condition data to be described based on business needs, and determining the initial data value of each target working condition data as the first label value of the initial label of each target working condition data, wherein the initial data value includes the fuel consumption and driving speed of the engineering vehicle;

[0007] determining the second label value of the first level label of each target working condition data based on an anomaly detection model;

[0008] dividing all target working condition data into a plurality of working condition data sets through a preset classification algorithm, and determining the class label and membership function of each working condition data set;

[0009] determining the third label value of the second level label of each target working condition data according to the class label of each working condition data set;

[0010] determining the function value of each target working condition data based on the membership function of each working condition data set, and determining the fourth label value of the third level label of each target working condition data according to the function value;

[0011] The first label value, the second label value, the third label value and the fourth label value of each target working condition data are used to describe each target working condition data.

[0012] In the embodiment of the present application, the second label value of the first level label of each target working condition data is determined based on the anomaly detection model, which includes: inputting each target working condition data into the anomaly detection model in sequence to output the probability of each target working condition data through the anomaly detection model; for any one target working condition data, if the probability of the target working condition data is greater than the probability threshold corresponding to the target working condition data, the second label value is determined as the first preset value; for any one target working condition data, if the probability of the target working condition data is less than the probability threshold corresponding to the target working condition data, the second label value is determined as the second preset value.

[0013] In the embodiment of the present application, the preset classification algorithm is a clustering algorithm, and the step of dividing all target working condition data into a plurality of working condition data sets through the preset classification algorithm includes: determining a plurality of clustering centers of the clustering algorithm for all target working condition data; for any one clustering center, determining the distance between each target working condition data and the clustering center, selecting the target working condition data within the preset range of the distance of the clustering center, and determining all selected target working condition data as one working condition data set.

[0014] In the embodiment of the present application, the class label and the membership function of each working condition data set are determined, which includes: for any one working condition data set, determining the center point feature of the clustering center corresponding to the working condition data set, and determining the feature value of the center point feature as the class label; for any one working condition data set, generating the membership function of the working condition data set according to the distribution rule of all target working condition data of the working condition data set and the constraint condition for the working condition data set.

[0015] In the embodiment of the present application, the description method further includes: after each target working condition data is described according to the first label value, the second label value, the third label value and the fourth label value of each target working condition data, obtaining the login information of the user; determining the data authority of the user according to the login information, and determining the target label level corresponding to the data authority; in the case that the viewing instruction triggered by the user is received, returning the label value of the target label level of the target working condition data to the user according to the viewing instruction.

[0016] In the embodiments of the present application, the data permission of the user is determined according to the login information, and the target label level corresponding to the data permission is determined, including: in the case that the login information is the first identity information, determining that the data permission is to view the target label level corresponding to the first identity information, and determining that the target label level includes at least one of the initial label, the second level label and the third level label; in the case that the login information is the second identity information, determining that the data permission is to view the target label level corresponding to the second identity information, and determining that the target label level includes at least one of the first level label and the third level label; in the case that the login information is the third identity information, determining that the data permission is to view the target label level corresponding to the third identity information, and determining that the target label level is the second level label.

[0017] In the embodiments of the present application, the description method further includes: after returning the label value of the target label level of the target working condition data to the user according to the viewing instruction, visualizing the label value through the display device; and / or in the case that the label value includes the second preset value, receiving an abnormal analysis instruction returned by the user, wherein the abnormal analysis instruction is obtained by the user analyzing the second preset value; and determining, according to the abnormal analysis instruction, that the target working condition data with the label value including the second preset value is the target working condition data to be optimized.

[0018] The second aspect of the present application provides a processor configured to execute the above-described description method for working condition data.

[0019] The third aspect of the present application provides a description device for working condition data, including the above-described processor.

[0020] The fourth aspect of the present application provides an engineering vehicle, including the above-described description device for working condition data.

[0021] The fifth aspect of the present application provides a machine-readable storage medium, which stores instructions thereon, the instructions, when executed by a processor, cause the processor to be configured to execute the above-described description method for working condition data.

[0022] The technical scheme is characterized in that: a plurality of label levels describing the working condition data of the engineering vehicle are determined, including an initial label, a first level label, a second level label and a third level label; a plurality of target working condition data to be described are determined based on a business requirement, and an initial data value of each target working condition data is determined as a first label value of the initial label of each target working condition data, wherein the initial data value includes fuel consumption and driving speed of the engineering vehicle; a second label value of the first level label of each target working condition data is determined based on an anomaly detection model; all target working condition data are divided into a plurality of working condition data sets through a preset classification algorithm, and a class label and a membership function of each working condition data set are determined; a third label value of the second level label of each target working condition data is determined according to the class label of each working condition data set; a function value of each target working condition data is determined based on the membership function of each working condition data set, and a fourth label value of the third level label of each target working condition data is determined according to the function value; and each target working condition data is described according to the first label value, the second label value, the third label value and the fourth label value of each target working condition data. The above technical scheme can more objectively, more comprehensively and more accurately describe the working condition data, and can describe the working condition data according to the four level label values, so that the description of each working condition data is more detailed, and different requirements of users can be met.

[0023] Other features and advantages of the embodiments of the present application will be described in detail in the following specific implementation part. BRIEF DESCRIPTION OF DRAWINGS

[0024] The accompanying drawings are included to provide a further understanding of the embodiments of the present application, and constitute a part of the specification, and are used to explain the embodiments of the present application together with the following specific implementation, but do not constitute a limitation to the embodiments of the present application. In the drawings:

[0025] Figure 1 A first flowchart of a description method for working condition data according to an embodiment of the present application is schematically shown;

[0026] Figure 2 A second flowchart of a description method for working condition data according to an embodiment of the present application is schematically shown;

[0027] Figure 3 A third flowchart of a description method for working condition data according to an embodiment of the present application is schematically shown;

[0028] Figure 4 An internal structure diagram of a computer device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0029] To make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. It should be understood that the specific implementation described herein is only used to explain and illustrate the embodiments of the present application and should not be used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0030] Figure 1 A first flowchart for a description method of working condition data according to an embodiment of the present application is schematically shown. As shown in the figure, Figure 1 In an embodiment of the present application, a description method of working condition data is provided, comprising the following steps:

[0031] Step 101, determining a plurality of label levels for describing the working condition data of the engineering vehicle, the plurality of label levels comprising an initial label, a first level label, a second level label and a third level label.

[0032] Step 102, determining a plurality of target working condition data to be described based on business requirements, and determining an initial data value of each target working condition data as a first label value of the initial label of each target working condition data, wherein the initial data value comprises fuel consumption and driving speed of the engineering vehicle.

[0033] Step 103, determining a second label value of the first level label of each target working condition data based on an anomaly detection model.

[0034] Step 104, dividing all target working condition data into a plurality of working condition data sets by a preset classification algorithm, and determining a class label and a membership function of each working condition data set.

[0035] Step 105, determining a third label value of the second level label of each target working condition data according to the class label of each working condition data set.

[0036] Step 106, determining a function value of each target working condition data based on the membership function of each working condition data set, and determining a fourth label value of the third level label of each target working condition data according to the function value.

[0037] Step 107, describing each target working condition data according to the first label value, the second label value, the third label value and the fourth label value of each target working condition data.

[0038] The working condition data refers to basic physical information, dynamic behavior information, and static behavior information of the engineering vehicle, such as a meter section of the pump truck, a factory month, a chassis type, an age, a cumulative pumping volume, a pumping volume, and fuel consumption. The processor can determine multiple label levels describing the working condition data of the engineering vehicle. The multiple label levels include an initial label, a first-level label, a second-level label, and a third-level label. After determining the multiple label levels, the processor can determine multiple target working condition data to be described based on a business requirement, and determine an initial data value of each target working condition data as a first label value of the initial label of each target working condition data. The initial data value includes fuel consumption and a driving speed of the engineering vehicle. After determining the first label value, the processor can determine a second label value of the first-level label of each target working condition data based on an anomaly detection model. After determining the second label value, the processor can divide all the target working condition data into multiple working condition data sets by a preset classification algorithm, and determine a class label and a membership function of each working condition data set. After determining the class label of each working condition data set, the processor can determine a third label value of the second-level label of each target working condition data according to the class label of each working condition data set. After determining the membership function of each working condition data set, the processor can determine a function value of each target working condition data based on the membership function of each working condition data set, and determine a fourth label value of the third-level label of each target working condition data according to the function value. The processor can describe each target working condition data according to the first label value, the second label value, the third label value, and the fourth label value of each target working condition data.

[0039] The above technical solution can more objectively, more comprehensively, and more accurately describe each working condition data, and can describe the working condition data according to four label values of the working condition data, so that the description of each data is more precise, and different requirements of users can be met.

[0040] In one embodiment, determining the second label value of the first-level label of each target working condition data based on the anomaly detection model includes: sequentially inputting each target working condition data into the anomaly detection model to output a probability of each target working condition data through the anomaly detection model; for any one target working condition data, in a case where the probability of the target working condition data is greater than a probability threshold corresponding to the target working condition data, determining the second label value as a first preset value; for any one target working condition data, in a case where the probability of the target working condition data is less than the probability threshold corresponding to the target working condition data, determining the second label value as a second preset value.

[0041] The processor can determine the second label value of the first level label of each target working condition data based on the anomaly detection model. Specifically, the processor can input each target working condition data to the anomaly detection model in sequence to output the probability of each target working condition data through the anomaly detection model. After obtaining the probability of each target working condition data, the processor can compare the probability of each target working condition data with the probability threshold corresponding to the target working condition data. For any one target working condition data, in the case that the probability of the target working condition data is greater than the probability threshold corresponding to the target working condition data, the processor can determine that the second label value of the target working condition data is the first preset value. In the case that the probability of the target working condition data is less than the probability threshold corresponding to the target working condition data, the processor can determine that the second label value of the target working condition data is the second preset value.

[0042] For example, the processor can construct the anomaly detection model by a Gaussian distribution algorithm, a deep method, a distance method, etc. Taking a Gaussian distribution anomaly detection model constructed by the Gaussian distribution algorithm as an example, the first preset value represents normal, and the second preset value represents abnormal. The processor can input the target working condition data A and the target working condition data B to the Gaussian distribution anomaly detection model in sequence to output the probability P(A) of the target working condition data A and the probability P(B) of the target working condition data B through the Gaussian distribution anomaly detection model. The processor can compare the probability P(A) of the target working condition data A with the probability threshold ε A of the target working condition data A. P(A) > ε A , the processor can determine that the second label value of the target working condition data A is normal. The processor can compare the probability P(B) of the target working condition data B with the probability threshold ε B of the target working condition data B. P(B) < ε B , the processor can determine that the second label value of the target working condition data B is abnormal. Through the second label value, it can be determined whether each working condition data is normal, which is beneficial to judge the state of the engineering vehicle.

[0043] In one embodiment, the preset classification algorithm is a clustering algorithm, and dividing all target working condition data into multiple working condition data sets by the preset classification algorithm comprises: determining multiple clustering centers of the clustering algorithm for all target working condition data; for any one clustering center, determining the distance between each target working condition data and the clustering center, selecting target working condition data within a preset range of the distance of the clustering center, and determining all selected target working condition data as one working condition data set.

[0044] The processor can divide all the target working condition data into a plurality of working condition data sets by a preset classification algorithm. Specifically, the preset classification algorithm can be a clustering algorithm, a decision tree, a support vector machine, etc. Taking the clustering algorithm as an example, the processor can determine a plurality of cluster centers of the clustering algorithm for all the target working condition data. For any one cluster center, the processor can determine the distance between each target working condition data and the cluster center, and select the target working condition data within a preset range of the cluster center. And all the selected target working condition data are determined as a working condition data set.

[0045] For example, the processor can divide all the target working condition data into a plurality of working condition data sets by using a K-means clustering algorithm. Specifically, the processor can perform K clustering on the target working condition data A1, A2, A3, A4, A5 to obtain m cluster centers for all the target working condition data. Wherein, i = 1, 2. For the cluster center m1, the processor can determine the distance between the target working condition data A1, A2, A3, A4, A5 and the cluster center m1. The processor can select the target working condition data A1, A2, A3 within a preset range of the cluster center m1, and determine the selected target working condition data A1, A2, A3 as a working condition data set. For the cluster center m2, the processor can determine the distance between the target working condition data A1, A2, A3, A4, A5 and the cluster center m2. The processor can select the target working condition data A4, A5 within a preset range of the cluster center m2, and determine the selected target working condition data A4, A5 as a working condition data set. i For example, the processor can divide all the target working condition data into a plurality of working condition data sets by using a K-means clustering algorithm. Specifically, the processor can perform K clustering on the target working condition data A1, A2, A3, A4, A5 to obtain m cluster centers for all the target working condition data. Wherein, i = 1, 2. For the cluster center m1, the processor can determine the distance between the target working condition data A1, A2, A3, A4, A5 and the cluster center m1. The processor can select the target working condition data A1, A2, A3 within a preset range of the cluster center m1, and determine the selected target working condition data A1, A2, A3 as a working condition data set. For the cluster center m2, the processor can determine the distance between the target working condition data A1, A2, A3, A4, A5 and the cluster center m2. The processor can select the target working condition data A4, A5 within a preset range of the cluster center m2, and determine the selected target working condition data A4, A5 as a working condition data set.

[0046] In one embodiment, determining the class label and the membership function of each working condition data set comprises: for any one working condition data set, determining the center point feature of the cluster center corresponding to the working condition data set, and determining the feature value of the center point feature as the class label; for any one working condition data set, generating the membership function of the working condition data set according to the distribution rule of all the target working condition data of the working condition data set and the constraint condition for the working condition data set.

[0047] The processor can determine the class label and the membership function of each working condition data set. Specifically, for any one working condition data set, the processor can determine the center point feature of the cluster center corresponding to the working condition data set. And the feature value of the center point feature is determined as the class label of the working condition data set. For any one working condition data set, the processor can generate the membership function of the working condition data set according to the distribution rule of all the target working condition data of the working condition data set and the constraint condition for the working condition data set.

[0048] For example, the processor can divide all the target working condition data into multiple working condition data sets by using a K-means clustering algorithm. Specifically, the processor can perform K clustering on the target working condition data A1, A2, A3, A4, and A5 to obtain m cluster centers for all the target working condition data. Wherein, i = 1, 2. For the cluster center m1, the processor can determine the distances between the target working condition data A1, A2, A3, A4, and A5 and the cluster center m1. The processor can select the target working condition data A1, A2, and A3 within the preset range of the cluster center m1, and determine the selected target working condition data A1, A2, and A3 as a working condition data set. For the cluster center m2, the processor can determine the distances between the target working condition data A1, A2, A3, A4, and A5 and the cluster center m2. The processor can select the target working condition data A4 and A5 within the preset range of the cluster center m2, and determine the selected target working condition data A4 and A5 as a working condition data set. i

[0049] For the cluster center m1, the processor can extract the center point feature of the cluster center point m1, and determine the feature value of the center point feature as the class label of the working condition data set corresponding to the cluster center m1. After determining the class label of the working condition data set, the processor can determine the class label as the third label value of the second level label of the target working condition data A1, A2, and A3 included in the working condition data set.

[0050] For the cluster center m2, the processor can extract the center point feature of the cluster center point m2, and determine the feature value of the center point feature as the class label of the working condition data set corresponding to the cluster center m2. After determining the class label of the working condition data set, the processor can determine the class label as the third label value of the second level label of the target working condition data A4 and A5 included in the working condition data set.

[0051] For the working condition data set corresponding to the cluster center m1, the processor can generate the membership function f1(x) of the working condition data set according to the distribution rule of the target working condition data A1, A2, and A3 in the working condition data set and the constraint condition for the working condition data set. After generating the membership function f1(x), the processor can sequentially input the target working condition data A1, A2, and A3 in the working condition data set to the membership function f1(x) to respectively obtain the corresponding scores of the target working condition data A1, A2, and A3 output by the membership function f1(x) in the percentage evaluation set V. The processor can determine the target working condition data A1, A2, and A3 as the fourth label value of the third level label of the target working condition data A1, A2, and A3, respectively.

[0052] ​For the working condition data set corresponding to the cluster center m2, the processor generates a membership function f2(x) of the working condition data set according to the distribution rule of the target working condition data A4 and A5 in the working condition data set and the constraint condition of the working condition data set. After generating the membership function f2(x), the processor can input the target working condition data A4 and A5 in the working condition data set to the membership function f2(x) in turn to obtain the corresponding scores of the target working condition data A4 and A5 output by the membership function f2(x) in the percentage evaluation set V, respectively. The processor can determine the target working condition data A4 and A5 as the fourth label value of the third level label of the target working condition data A4 and A5, respectively.

[0053] In one embodiment, the method further includes: after describing each target working condition data according to the first label value, the second label value, the third label value and the fourth label value of each target working condition data, obtaining login information of a user; determining data authority of the user according to the login information, and determining a target label level corresponding to the data authority; in the case that a viewing instruction triggered by the user is received, returning the label value of the target label level of the target working condition data to the user according to the viewing instruction.

[0054] After describing each target working condition data according to the first label value, the second label value, the third label value and the fourth label value of each target working condition data, the processor can obtain login information of a user. After obtaining the login information of the user, the processor can determine data authority of the user according to the login information, and determine a target label level corresponding to the data authority. The processor can receive a viewing instruction triggered by the user. After receiving the viewing instruction triggered by the user, the processor can return the label value of the target label level of the target working condition data to the user according to the viewing instruction.

[0055] In one embodiment, determining the data authority of the user according to the login information and determining the target label level corresponding to the data authority includes: in the case that the login information is first identity information, determining that the data authority is to view the target label level corresponding to the first identity information, and determining that the target label level includes at least one of the initial label, the second level label and the third level label; in the case that the login information is second identity information, determining that the data authority is to view the target label level corresponding to the second identity information, and determining that the target label level includes at least one of the first level label and the third level label; in the case that the login information is third identity information, determining that the data authority is to view the target label level corresponding to the third identity information, and determining that the target label level is the second level label.

[0056] The processor can determine the data authority of the user according to the login information, and determine the target label level corresponding to the data authority. Specifically, the processor can determine whether the login information is the first identity information. In the case that the login information is the first identity information, the processor can determine that the data authority of the user is to view the target label level corresponding to the first identity information, and determine that the target label level includes at least one of the initial label, the second level label and the third level label. The processor can determine whether the login information is the second identity information. In the case that the login information is the second identity information, the processor can determine that the data authority of the user is to view the target label level corresponding to the second identity information, and determine that the target label level includes at least one of the first level label and the third level label. The processor can determine whether the login information is the third identity information. In the case that the login information is the third identity information, the processor can determine that the data authority of the user is to view the target label level corresponding to the third identity information, and determine that the target label level is the second level label.

[0057] In one embodiment, the method further comprises: after returning the label value of the target label level of the target working condition data to the user according to the viewing instruction, visualizing the label value through the display device; and / or in the case that the label value includes the second preset value, receiving an abnormal analysis instruction returned by the user, wherein the abnormal analysis instruction is obtained by the user analyzing the second preset value; and determining, according to the abnormal analysis instruction, that the target working condition data whose label value includes the second preset value is the target working condition data to be optimized.

[0058] After returning the label value of the target label level of the target working condition data to the user according to the viewing instruction, the processor can visualize the label value through the display device. The processor can also determine whether the returned label value includes the second preset value. In the case that the returned label value includes the second preset value, the processor can receive an abnormal analysis instruction returned by the user. The abnormal analysis instruction is obtained by the user analyzing the second preset value. After receiving the abnormal analysis instruction, the processor can determine, according to the abnormal analysis instruction, that the target working condition data whose label value includes the second preset value is the target working condition data to be optimized, so that the user can optimize and improve the working condition vehicle, which is helpful for the iterative upgrading of the engineering vehicle.

[0059] In one embodiment, as Figure 2As shown, the processor can determine a first level label, a second level label, a third level label and a fourth level label describing the working condition data of the device. For the data in the cloud platform database, the processor can first perform fourth level label acquisition. Specifically, the processor can acquire device parameters or working condition related data. After acquiring the related data, the processor can clean and preprocess the acquired data to obtain corresponding indicators. For the indicators obtained by preprocessing, the processor can filter out the indicators that need to be labeled according to business requirements, and determine the indicator values of the indicators as the label values of the fourth level labels of the indicators.

[0060] After the fourth level label acquisition, the processor can perform first level label acquisition. Specifically, the processor can determine whether each indicator is abnormal based on the Gaussian distribution anomaly detection model M. For any one indicator, the processor can input the indicator into the Gaussian distribution anomaly detection model M to output the probability of the indicator through the Gaussian distribution anomaly detection model M. The processor can compare the probability of the indicator with the probability threshold corresponding to the indicator. In the case that the probability of the indicator is greater than the probability threshold corresponding to the indicator, the processor can determine that the first level label of the indicator is normal. In the case that the probability of the indicator is less than the probability threshold corresponding to the indicator, the processor can determine that the first level label of the indicator is abnormal.

[0061] After the first level label acquisition, the processor can perform second level label acquisition. Specifically, the processor can use the K-means method to cluster historical data (i.e., indicators) to obtain K classes G i and the center point m i , i.e., K indicator sets G i are obtained, and the center point of each indicator set G i is the corresponding m i . For each center point m i , the processor can summarize the center point features to obtain a class label. For any one G i , the processor can compare the distance between the indicator values in the G i and the center point, and select the nearest class label as the second level label of each indicator in the G i .

[0062] After the second level label acquisition, the processor can perform third level label acquisition. Specifically, for the obtained K classes G i , for each G i , the processor can construct a membership function according to the data distribution and expert suggestions respectively. And each indicator value of the G i is substituted into the membership function to obtain the score of each indicator as the third level label of each indicator.

[0063] As shown in Figure 3 The processor can determine the fourth-level label of the original working condition data. After determining the fourth-level label of the original working condition data, the processor can perform anomaly detection on the original working condition data to determine the detection result: normal or abnormal as the first-level label of the original working condition data. After determining the first-level label, the processor can perform cluster analysis on the original working condition data to obtain the second-level label of the original working condition data. After obtaining the second-level label of the original working condition data, the processor can construct a score through fuzzy evaluation to determine the third-level label of the original working condition data.

[0064] After the fourth-level label, the first-level label, the second-level label and the third-level label of the original working condition data are determined, the processor can determine the data authority of the user according to the login information of the user.

[0065] For example, in the case that the login information of the user is a research and development personnel, the processor can determine that the data authority of the user is to be able to view at least one of the fourth-level label, the second-level label and the third-level label of the original working condition data. The fourth-level label is helpful for the research and development personnel to monitor the working condition of the equipment or to trace the label. The second-level label is helpful for the research and development personnel to finely manage the equipment and realize the overall quality control of the equipment. The third-level label is helpful for the research and development personnel to timely identify the health condition of the equipment to manage and optimize the equipment.

[0066] In the case that the login information of the user is at least one of a customer, an after-sales service, a quality personnel and a management, the processor can determine that the data authority of the user is to be able to view at least one of the first-level label and the third-level label of the original working condition data. The first-level label is helpful for the customer, the after-sales service, the quality personnel and the management to monitor the equipment for abnormality, quickly obtain the abnormal condition of the equipment and timely solve the problem of the equipment. The third-level label is helpful for the customer, the after-sales service, the quality personnel and the management to quantitatively score the working condition of the equipment or to make trend prediction, so that the development trend of the equipment can be clearly and objectively mastered.

[0067] In the case that the login information of the user is marketing, the processor can determine that the data authority of the user is to be able to view the second-level label of the original working condition data. The second-level label is helpful for the marketing personnel to analyze and compare between machine groups to obtain a suitable marketing strategy.

[0068] The technical solution described above determines a plurality of label levels describing the working condition data of the engineering vehicle, including an initial label, a first level label, a second level label, and a third level label; determines a plurality of target working condition data to be described based on business requirements, and determines an initial data value of each target working condition data as a first label value of the initial label of each target working condition data, wherein the initial data value includes the fuel consumption and the driving speed of the engineering vehicle; determines a second label value of the first level label of each target working condition data based on an anomaly detection model; divides all target working condition data into a plurality of working condition data sets through a preset classification algorithm, and determines a class label and a membership function of each working condition data set; determines a third label value of the second level label of each target working condition data according to the class label of each working condition data set; determines a function value of each target working condition data based on the membership function of each working condition data set, and determines a fourth label value of the third level label of each target working condition data according to the function value; and describes each target working condition data according to the first label value, the second label value, the third label value, and the fourth label value of each target working condition data. The technical solution described above can more objectively, more comprehensively, and more accurately describe each working condition data, and can distribute the working condition data according to the four level label values, so that the description of each data is more detailed, and different needs of users can be met.

[0069] Figure 1 、 2 FIG. 3 is a flowchart of an embodiment of a method for describing working condition data. It should be understood that although the steps in the flowchart of FIG. 3 are shown in a sequence following the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise explicitly stated herein, the execution of the steps is not necessarily limited to the order indicated by the arrows, and the steps can be executed in other orders. Moreover, Figure 1 、 2 The steps in the flowchart of FIG. 3 are not necessarily executed in the order indicated by the arrows. Unless otherwise explicitly stated herein, the execution of the steps is not necessarily limited to the order indicated by the arrows, and the steps can be executed in other orders. Moreover, Figure 1 、 2 At least some of the steps in FIG. 3 can include a plurality of sub-steps or a plurality of stages, which are not necessarily executed at the same time, but can be executed at different times. The execution order of the sub-steps or stages is not necessarily sequential, but can be alternated or rotated with at least a part of other steps or sub-steps or stages of other steps.

[0070] An embodiment of the present application provides a processor for running a program, wherein the processor is configured to execute the method for describing working condition data.

[0071] An embodiment of the present application provides a device for describing working condition data, comprising the processor described above.

[0072] The embodiment of the present application provides an engineering vehicle, comprising the above-described description device for working condition data.

[0073] The embodiment of the present application provides a storage medium, which stores a program, and the program is executed by a processor to implement the above-described description method for working condition data.

[0074] In one embodiment, a computer device can be a server, and an internal structure diagram of the computer device can be as shown in Figure 4 The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure) and a database (not shown in the figure) connected through a system bus. Wherein, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02 and a database (not shown in the figure). The internal memory A03 provides an environment for the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database of the computer device is used to store data of a label level, a label value and a function value. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. The computer program B02 is executed by the processor A01 to implement a description method for working condition data.

[0075] Those skilled in the art can understand that, Figure 4 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. Specifically, the computer device can include more or less components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0076] The embodiment of the application provides a device, the device comprises a processor, a memory and a program stored on the memory and executable on the processor, and the processor implements the following steps when executing the program: determining a plurality of label levels describing working condition data of an engineering vehicle, the plurality of label levels comprising an initial label, a first level label, a second level label and a third level label; determining a plurality of target working condition data to be described based on a business requirement, and determining an initial data value of each target working condition data as a first label value of the initial label of each target working condition data, wherein the initial data value comprises fuel consumption and a driving speed of the engineering vehicle; determining a second label value of the first level label of each target working condition data based on an anomaly detection model; dividing all the target working condition data into a plurality of working condition data sets through a preset classification algorithm, and determining a class label and a membership function of each working condition data set; determining a third label value of the second level label of each target working condition data according to the class label of each working condition data set; determining a function value of each target working condition data based on the membership function of each working condition data set, and determining a fourth label value of the third level label of each target working condition data according to the function value; and describing each target working condition data according to the first label value, the second label value, the third label value and the fourth label value of each target working condition data.

[0077] In one embodiment, determining the second label value of the first level label of each target working condition data based on the anomaly detection model comprises: sequentially inputting each target working condition data into the anomaly detection model to output a probability of each target working condition data through the anomaly detection model; for any one target working condition data, in a case where the probability of the target working condition data is greater than a probability threshold corresponding to the target working condition data, determining that the second label value is a first preset value; and for any one target working condition data, in a case where the probability of the target working condition data is less than the probability threshold corresponding to the target working condition data, determining that the second label value is a second preset value.

[0078] In one embodiment, the preset classification algorithm is a clustering algorithm, and dividing all the target working condition data into a plurality of working condition data sets through the preset classification algorithm comprises: determining a plurality of clustering centers of the clustering algorithm for all the target working condition data; for any one clustering center, determining a distance between each target working condition data and the clustering center, selecting target working condition data within a preset range of the clustering center, and determining all the selected target working condition data as one working condition data set.

[0079] In one embodiment, the determining the class label and the membership function of each working condition data set comprises: determining the center point feature of the cluster center corresponding to the working condition data set for any one working condition data set, and determining the feature value of the center point feature as the class label; and generating the membership function of the working condition data set according to the distribution law of all target working condition data of the working condition data set and the constraint condition for the working condition data set for any one working condition data set.

[0080] In one embodiment, the method further comprises: after describing each target working condition data according to the first label value, the second label value, the third label value and the fourth label value of each target working condition data, obtaining the login information of the user; determining the data authority of the user according to the login information, and determining the target label level corresponding to the data authority; in the case that the viewing instruction triggered by the user is received, returning the label value of the target label level of the target working condition data to the user according to the viewing instruction.

[0081] In one embodiment, the determining the data authority of the user according to the login information, and determining the target label level corresponding to the data authority comprises: in the case that the login information is the first identity information, determining that the data authority is to view the target label level corresponding to the first identity information, and determining that the target label level comprises at least one of the initial label, the second level label and the third level label; in the case that the login information is the second identity information, determining that the data authority is to view the target label level corresponding to the second identity information, and determining that the target label level comprises at least one of the first level label and the third level label; in the case that the login information is the third identity information, determining that the data authority is to view the target label level corresponding to the third identity information, and determining that the target label level is the second level label.

[0082] In one embodiment, the method further comprises: after returning the label value of the target label level of the target working condition data to the user according to the viewing instruction, visualizing the label value through the display device; and / or in the case that the label value comprises the second preset value, receiving the abnormal analysis instruction returned by the user, wherein the abnormal analysis instruction is obtained by the user analyzing the second preset value; and determining the target working condition data whose label value comprises the second preset value as the target working condition data to be optimized according to the abnormal analysis instruction.

[0083] The application also provides a computer program product adapted to execute the program initialized with the steps of the method for describing working condition data when executed on a data processing device.

[0084] Those skilled in the art will appreciate that embodiments of the application can be readily used as software, hardware, or a combination of software and hardware. In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0085] The present application is described in reference to the flowchart illustrations and / or block diagrams according to the embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing system, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0086] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0088] In one typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0089] The memory can include non-persistent memory, random access memory (RAM), and / or non-volatile memory, such as read only memory (ROM) or flash memory, among others. The memory is an example of computer-readable media.

[0090] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0091] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusions, so that a process, method, article or apparatus that includes a list of elements does not only include those elements, but also includes other elements not explicitly listed, or further includes elements inherent in such a process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0092] The above only is an embodiment of the present application, and is not used to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A method for describing operating condition data, characterized in that, The description method includes: Multiple label levels are identified to describe the operating data of engineering vehicles, including an initial label, a first-level label, a second-level label, and a third-level label. Based on business requirements, multiple target operating condition data to be described are determined, and the initial data value of each target operating condition data is determined as the first label value of the initial label of each target operating condition data, wherein the initial data value includes the fuel consumption and driving speed of the engineering vehicle; The second label value of the first-level label for each target operating condition data is determined based on the anomaly detection model. All target working condition data are divided into multiple working condition data sets by a preset classification algorithm, and the class label and membership function of each working condition data set are determined. The third label value of the second-level label for each target working condition data is determined based on the class label of each working condition data set; The function value of each target working condition data is determined based on the membership function of each working condition data set, and the fourth label value of the third-level label of each target working condition data is determined based on the function value. Each target working condition data is described based on its first, second, third, and fourth label values; The second label value for determining the first-level label of each target working condition data based on the anomaly detection model includes: Each target operating condition data is sequentially input into the anomaly detection model, so that the probability of each target operating condition data is output by the anomaly detection model; For any target working condition data, if the probability of the target working condition data is greater than the probability threshold corresponding to the target working condition data, the second label value is determined to be a first preset value; For any target operating condition data, if the probability of the target operating condition data is less than the probability threshold corresponding to the target operating condition data, the second label value is determined to be a second preset value.

2. The method for describing operating condition data according to claim 1, characterized in that, The preset classification algorithm is a clustering algorithm. Dividing all target operating condition data into multiple operating condition data sets using the preset classification algorithm includes: The clustering algorithm is used to determine multiple cluster centers for all target working condition data; For any cluster center, determine the distance between each target working condition data and the cluster center, select target working condition data whose distance is within a preset range of the cluster center, and determine all selected target working condition data as a working condition data set.

3. The method for describing operating condition data according to claim 2, characterized in that, Determining the class label and membership function for each set of operating condition data includes: For any set of working condition data, determine the centroid feature of the cluster center corresponding to the set of working condition data, and determine the feature value of the centroid feature as the class label; For any set of working condition data, a membership function for the set of working condition data is generated based on the distribution pattern of all target working condition data in the set of working condition data and the constraints on the set of working condition data.

4. The method for describing operating condition data according to claim 1, characterized in that, The description method further includes: After describing each target working condition data based on the first, second, third, and fourth label values, the user's login information is obtained. The user's data permissions are determined based on the login information, and the target tag level corresponding to the data permissions is determined. Upon receiving a viewing instruction triggered by the user, the system returns the tag value of the target tag level of the target operating condition data to the user according to the viewing instruction.

5. The method for describing operating condition data according to claim 4, characterized in that, The step of determining the user's data permissions based on the login information and determining the target tag level corresponding to the data permissions includes: If the login information is the first identity information, the data permission is determined to be viewing the target tag level corresponding to the first identity information, and the target tag level is determined to include at least one of the initial tag, the second level tag, and the third level tag; If the login information is a second identity information, the data permission is determined to be viewing the target tag level corresponding to the second identity information, and the target tag level is determined to include at least one of the first level tag and the third level tag; If the login information is third-party identity information, the data permission is determined to be viewing the target tag level corresponding to the third-party identity information, and the target tag level is determined to be the second-level tag.

6. The method for describing operating condition data according to claim 4, characterized in that, The description method further includes: After returning the tag values ​​of the target tag level of the target operating condition data to the user according to the viewing instruction, the tag values ​​are visualized through a display device; and / or If the tag value includes a second preset value, receive the anomaly analysis instruction returned by the user, wherein the anomaly analysis instruction is obtained by the user analyzing the second preset value; Based on the anomaly analysis instruction, the target operating condition data whose tag value includes the second preset value is determined to be the target operating condition data to be optimized.

7. A processor, characterized in that, It is configured to perform the method for describing operating condition data as described in any one of claims 1 to 6.

8. A device for describing operating condition data, characterized in that, The device includes the processor according to claim 7.

9. An engineering vehicle, characterized in that, Includes the device for describing operating condition data as described in claim 8.

10. A machine-readable storage medium storing instructions thereon, characterized in that, When executed by a processor, this instruction causes the processor to be configured to perform the method for describing operating condition data according to any one of claims 1 to 6.

Images