Device job control method and apparatus based on service attribute information, and electronic device

Abstract

Embodiments of the present disclosure disclose a device operation control method and device based on business attribute information and an electronic device. A specific implementation of the method includes: determining a pre-reference calculation value corresponding to each construction condition dimension; for each construction task record included in a construction task data table, performing the following steps: matching the pre-reference calculation value corresponding to the construction task record; linearly crossing and multiplying the actual task scale value in the construction task record with the pre-reference calculation value; training an initial post-model to obtain a solidified post-model; determining a calibrated characteristic value of a target business task; inputting the target calibrated characteristic value into the solidified post-model to obtain business attribute information; and performing operation control on a construction device executing the target business task. The implementation can improve the accuracy of the generated business attribute information, reduce the energy consumption and mechanical wear of the construction device, or slow down the speed of fatigue aging of the transmission components and sealing elements.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the field of computer technology, and more specifically to a device operation control method, apparatus, and electronic device based on business attribute information. Background Technology

[0002] In complex industrial forecasting and intelligent decision-making systems (such as multi-dimensional quota calculations for construction projects and production scheduling and cost forecasting in manufacturing), business attribute information is a crucial indicator for measuring task urgency and expected output. Higher business attribute information indicates an urgent task, high planned output, and the need for continuous and stable equipment operation to ensure the project schedule; conversely, lower business attribute information suggests a more relaxed task, a slower pace of operation, and less need for equipment to operate at full capacity for extended periods. Therefore, construction sites require refined control of the operating permissions and parameters of construction equipment based on business attribute information to achieve optimal matching between equipment resources and task load. Currently, the common approach to generating business attribute information for construction equipment operation control is as follows: the prediction model directly reads the raw data from the underlying database for feature extraction and model fitting, then generates the business attribute information through the fitted prediction model, thereby controlling the operation of the construction equipment.

[0003] However, when using the above method to generate business attribute information for operation control of construction equipment, the following technical problems often arise: The raw data entered into the underlying database often suffers from severe distortion. For example, in construction engineering scenarios, the construction period data entered by on-site personnel is significantly inconsistent with the actual construction period; a project that actually only takes 5 days is reported as 30 days. Existing data cleaning techniques typically employ simple statistical methods (such as removing outliers and taking averages). This approach requires multiple scans of the entire data table, leading to a significant increase in the number of input and output requests to the storage system, increasing the read / write load on the disk controller and the seek time of the read / write head. Furthermore, when predictive models directly use this distorted data as input features for training, the accuracy of the final generated business attribute information is low. This results in several problems when controlling construction equipment: an excessively long operating time window causes the equipment to idle for extended periods, increasing energy consumption and mechanical wear; an excessively short operating time window leads to frequent start-ups and shutdowns, accelerating the fatigue and aging of transmission components and sealing elements.

[0004] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not form prior art known to those skilled in the art. Summary of the Invention

[0005] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0006] Some embodiments of this disclosure provide a method, apparatus, electronic device, and computer-readable medium for controlling equipment operation based on business attribute information, in order to solve one or more of the technical problems mentioned in the background section above.

[0007] In a first aspect, some embodiments of this disclosure provide a device operation control method based on business attribute information. The method includes: in response to receiving an operation execution instruction for a target business task, determining, according to a target regression coefficient set and various construction condition dimensions, the preceding benchmark calculation values ​​corresponding to each of the aforementioned construction condition dimensions as a preceding benchmark calculation value set, wherein the preceding benchmark calculation values ​​are the construction period required per unit of work volume; for each construction task record included in the construction task data table, performing the following steps: matching the preceding benchmark calculation value corresponding to the aforementioned construction task record from the preceding benchmark calculation value set according to the construction condition dimension of the aforementioned construction task record; and comparing the actual task scale value in the aforementioned construction task record with the preceding benchmark calculation value set. The preceding benchmark calculation values ​​are linearly cross-multiplied to obtain calibrated feature values; each calibrated feature value is determined as a calibrated feature value series; based on the calibrated feature value series, the initial post-model is trained and its parameters are solidified to obtain a solidified post-model; based on the actual task scale of the target business task and the preceding benchmark calculation value set, the calibrated feature value of the target business task is determined as the target calibrated feature value; the target calibrated feature value is input into the solidified post-model to obtain the business attribute information corresponding to the target business task; based on the business attribute information, the construction equipment performing the target business task is controlled to drive the construction equipment to perform the operation.

[0008] Secondly, some embodiments of this disclosure provide a device for equipment operation control based on business attribute information. The device includes: a first determining unit configured to, in response to receiving an operation execution instruction for a target business task, determine, according to a target regression coefficient set and various construction condition dimensions, a set of pre-calculated benchmark values ​​corresponding to each of the construction condition dimensions, wherein the pre-calculated benchmark value is the construction period required per unit of work volume; and an execution unit configured to, for each construction task record included in a construction task data table, perform the following steps: matching the pre-calculated benchmark value corresponding to the construction task record from the set of pre-calculated benchmark values ​​according to the construction condition dimension of the construction task record; and performing a linear cross multiplication of the actual task scale value in the construction task record with the pre-calculated benchmark value. The system is configured to: obtain calibrated feature values; obtain a second determining unit; determine each calibrated feature value as a calibrated feature value sequence; obtain a parameter solidification unit; obtain a solidified post-model by training and parameter solidification of the initial post-model based on the calibrated feature value sequence; obtain a solidified post-model by training and parameter solidification of the initial post-model based on the calibrated feature value sequence; obtain a third determining unit; determine the calibrated feature value of the target business task as the target calibrated feature value based on the actual task scale value of the target business task and the set of pre-calculated benchmark values; obtain business attribute information corresponding to the target business task by inputting the target calibrated feature value into the solidified post-model; and obtain business attribute information corresponding to the target business task by inputting the target calibrated feature value into the solidified post-model.

[0009] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0010] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0011] The above-described embodiments of this disclosure have the following beneficial effects: The device operation control method based on business attribute information in some embodiments of this disclosure can reduce the number of input and output requests in the storage system, reduce the read / write load and head seek time of the disk controller, improve the accuracy of the final generated business attribute information, reduce the energy consumption and mechanical wear of construction equipment, or slow down the fatigue aging of transmission components and sealing elements. Specifically, the reason why the number of input and output requests in the storage system increases exponentially, increases the read / write load and head seek time of the disk controller, and leads to low accuracy of the final generated business attribute information, increases the energy consumption and mechanical wear of construction equipment, or accelerates the fatigue aging of transmission components and sealing elements is that the original data entered in the underlying database often has serious distortion problems. For example, in the scenario of construction engineering, the construction period data entered by on-site personnel is seriously inconsistent with the actual construction period; a project that actually only requires 5 days is entered as 30 days. Existing data cleaning techniques typically employ simple statistical methods (such as removing outliers and taking averages). This approach requires multiple scans of the entire data table, leading to a significant increase in the number of input and output requests to the storage system, increasing the read / write load on the disk controller and the seek time of the read / write head. Furthermore, when predictive models directly use this distorted data as input features for training, the accuracy of the resulting business attribute information is low. This results in several issues when controlling construction equipment: an excessively long operation time window causes the equipment to idle for extended periods, increasing energy consumption and mechanical wear; an excessively short operation time window leads to frequent start-ups and shutdowns, accelerating the fatigue and aging of transmission components and sealing elements. Therefore, the equipment operation control method based on business attribute information in some embodiments of this disclosure first, in response to receiving an operation execution instruction for the target business task, determines the preceding benchmark calculation values ​​corresponding to each of the aforementioned construction condition dimensions as a preceding benchmark calculation value set, based on the target regression coefficient set and each construction condition dimension. Thus, the preceding benchmark calculation value set corresponding to each construction condition dimension can be obtained. Next, for each construction task record included in the construction task data table, the following steps are performed: First, based on the construction condition dimension of the construction task record, the corresponding pre-benchmark calculation value for the construction task record is matched from the aforementioned pre-benchmark calculation value set. This yields the pre-benchmark calculation value for the construction task record. Next, the actual task scale value in the construction task record is linearly cross-multiplied with the aforementioned pre-benchmark calculation value to obtain calibrated feature values. This yields the calibrated feature values. Then, each obtained calibrated feature value is defined as a calibrated feature value column. This yields the calibrated feature value column. Next, based on the calibrated feature value column, the initial post-model is trained and its parameters are solidified to obtain the solidified post-model. This yields the solidified post-model after training.Next, based on the actual task scale of the target business task and the aforementioned set of pre-calculated benchmark values, the calibrated characteristic value of the target business task is determined as the target calibrated characteristic value. Thus, the calibrated characteristic value of the target business task can be obtained. Then, the calibrated characteristic value is input into the solidified post-model to obtain the business attribute information corresponding to the target business task. Thus, the business attribute information of the target business task can be obtained. Finally, based on the business attribute information, operation control is performed on the construction equipment executing the target business task to drive the construction equipment to perform the operation. Because it doesn't directly read raw distorted data from the underlying database for feature extraction, but instead uses a pre-model to perform benchmark extrapolation on all business data, generating pre-benchmark values ​​for each construction condition dimension, and then matching the corresponding pre-benchmark values ​​to the construction condition dimensions recorded in the construction task records, the actual task scale values ​​are linearly cross-multiplied with the pre-benchmark values ​​to obtain calibrated feature values. These calibrated feature values ​​are then written back to the construction task data table. Only one data cleaning operation is needed to complete the self-repair of all distorted data, reducing the number of input / output requests and disk head seek time in the storage system, thus improving system resource utilization. Furthermore, because it doesn't use static statistical methods (such as removing extreme values ​​or taking averages) for data cleaning, but instead generates calibrated feature values ​​by linearly cross-multiplying the pre-benchmark values ​​with the actual task scale values, which serve as input features for the subsequent model, it achieves dynamic adaptive repair of distorted data. This reduces the increase in model training iterations and wasted computational resources caused by data distortion, thereby shortening model training time and reducing CPU computational resource consumption. This sequential dependency of prior and subsequent iterations ensures that the subsequent model always uses high-quality, repaired data, reducing issues caused by data distortion leading to garbage data entering and leaving the system. This reduces the number of input and output requests to the storage system, decreases the read / write load on the disk controller and the head seek time, improves the accuracy of the final generated business attribute information, and reduces energy consumption and mechanical wear of construction equipment, or slows down the fatigue aging of transmission components and sealing elements. Attached Figure Description

[0012] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0013] Figure 1 These are flowcharts of some embodiments of the equipment operation control method based on business attribute information according to this disclosure; Figure 2These are schematic diagrams illustrating the structure of some embodiments of the equipment operation control device based on business attribute information according to this disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure.

[0014] Reference numerals: 200, Equipment operation control device based on business attribute information; 201, First determining unit; 202, Execution unit; 203, Second determining unit; 204, Parameter fixing unit; 205, Third determining unit; 206, Input unit; 207, Control unit; 300, Electronic device; 301, Processing device (e.g., central processing unit, graphics processing unit, etc.); 302, Read-only memory (ROM); 303, Random access memory (RAM); 304, Bus; 305, Input / output (I / O) interface; 306, Input device; 307, Output device; 308, Storage device; 309, Communication device. Detailed Implementation

[0015] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0016] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0017] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0018] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0019] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0020] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0021] Figure 1 A flow 100 of some embodiments of a device operation control method based on business attribute information according to this disclosure is shown. This device operation control method based on business attribute information includes the following steps: Step 101: In response to receiving the operation execution instruction for the target business task, determine the preceding benchmark calculation value corresponding to each construction condition dimension as the preceding benchmark calculation value set based on the target regression coefficient set and each construction condition dimension.

[0022] In some embodiments, in response to receiving a job execution instruction for a target business task, the execution subject (e.g., a computer device) of the equipment operation control method based on business attribute information can determine the preceding benchmark calculation values ​​corresponding to each of the above-mentioned construction condition dimensions as the preceding benchmark calculation value set, based on the target regression coefficient set and each construction condition dimension. The target business task can be a new task to be processed that requires prediction of business attribute information. For example, the target business task can be the concrete pouring task in the basement of Building 3 at a construction site in Beijing. The construction condition dimension of the target business task includes a construction area identifier of 1 (underground), an administrative division identifier of 110000 (used to indicate that the administrative division is Beijing), and an actual task scale value: the concrete pouring volume is 200 cubic meters. The target business task can include construction condition dimensions and actual task scale values. The construction condition dimensions can include a construction area identifier and an administrative division identifier. The construction area identifier can be the identifier corresponding to the construction area. The construction area identifier can be 1, 2, 3, 4, 5, or 6. 1 indicates the construction area is above ground. 2 indicates the construction area is underground. 3 indicates the construction area is outdoors. 4 indicates the construction area is a foundation pit. 5 indicates the construction area is a foundation. 6 indicates the construction area is a roof. The administrative division identifier mentioned above can be the identifier corresponding to an administrative division. For example, the administrative division identifier can be 110000 (Beijing) or 510100 (Chengdu). The construction area mentioned above can be above ground, underground, outdoors, foundation pit, foundation, or roof. For example, the construction condition dimension can be (construction area identifier: 1, administrative division identifier: 110000). The actual task scale value mentioned above is the workload of the target business task mentioned above. The operation execution instruction mentioned above can be a trigger instruction sent by a terminal device, used to instruct the execution entity to start predicting the business attribute information of the target business task mentioned above, and to execute the operation based on the obtained business attribute information. The terminal device mentioned above includes, but is not limited to, at least one of the following: smartphone, tablet, smartwatch, desktop computer, laptop, embedded industrial control computer. The aforementioned pre-calculated benchmark value can be the construction period required per unit of work volume. For example, the pre-calculated benchmark value can be 0.1 days / meter, which can indicate that it takes 0.1 days to lay 1 meter of cable. The aforementioned target regression coefficients can be intercept coefficients, weight coefficients, construction area coefficients, or administrative division coefficients. The intercept coefficient can be a baseline value representing the logarithmic total construction period when all input features are 0. The logarithmic total construction period can be the logarithm of the total construction period to the base 10. The total construction period can be the total number of days required to complete the aforementioned target business task. For example, if the formula is log(T) = β0 + β1x1 + β2x2, then the intercept coefficient can be β0. The weight coefficients can be regression coefficients of standard engineering quantities, representing the degree of influence of the aforementioned actual task scale on the total construction period. The standard engineering quantities can be pre-set quantities. For example, the standard engineering quantity can be 100 meters.The construction area coefficients mentioned above can be regression coefficients for construction areas, representing the degree of influence of the construction area on the total construction period. Each construction area corresponds to one regression coefficient. The administrative division coefficients mentioned above can be regression coefficients for administrative divisions, representing the degree of influence of administrative divisions on the total construction period. Each administrative division also corresponds to one regression coefficient.

[0023] In addressing the technical problems mentioned above, the following technical issues often arise in the second application scenario: calculating quotas for multiple regions in construction engineering and controlling construction equipment operations based on these quotas. The prediction model directly reads distorted data from the underlying database for feature extraction, requiring more iterations to converge. Furthermore, it struggles to account for multi-dimensional features under different construction areas and administrative divisions, resulting in inaccurate benchmark values ​​and quotas (business attribute information). Consequently, when controlling construction equipment operations, excessively long operation windows lead to prolonged idling, increasing energy consumption and mechanical wear; excessively short operation windows cause frequent start-ups and shutdowns, accelerating fatigue and aging of transmission components and sealing elements. Considering the following requirements for this application scenario: adaptability to multi-class variable combinations, high-precision quota requirements, and efficient energy-saving control of construction equipment, we have decided to adopt the following solution: In some optional implementations of certain embodiments, in response to receiving a job execution instruction for the target business task, the execution entity can determine the preceding benchmark calculation values ​​corresponding to each of the construction condition dimensions as the preceding benchmark calculation value set by following the steps of: The first step, for each of the above construction condition dimensions, is to perform the following steps based on the above set of construction area coefficients and the above set of administrative division coefficients: The first sub-step involves determining the target construction area coefficient and target administrative division coefficient for the aforementioned construction condition dimension, based on the aforementioned set of construction area coefficients, the aforementioned set of administrative division coefficients, and the construction area and administrative division identifiers included in the aforementioned construction condition dimension. Each construction area coefficient in the aforementioned set of construction area coefficients corresponds to a construction area identifier. Each administrative division coefficient in the aforementioned set of administrative division coefficients also corresponds to an administrative division identifier. The target construction area coefficient can be the regression coefficient of the construction area corresponding to the construction area identifier included in the aforementioned construction condition dimension, representing the degree of influence of the construction area on the total construction period. The target administrative division coefficient can be the regression coefficient of the administrative division corresponding to the administrative division identifier included in the aforementioned construction condition dimension. In practice, the implementing entity can obtain the construction area coefficient corresponding to the construction area identifier included in the aforementioned construction condition dimension from the aforementioned set of construction area coefficients as the target construction area coefficient, and obtain the administrative division coefficient corresponding to the administrative division identifier included in the aforementioned construction condition dimension from the aforementioned set of administrative division coefficients as the target administrative division coefficient.

[0024] The second sub-step involves determining the logarithmic planned construction period corresponding to the aforementioned construction condition dimension based on the target construction area coefficient, the target administrative division coefficient, the intercept term coefficient, and the weight coefficients included in the target regression coefficient set. The logarithmic planned construction period can represent the logarithm of the total construction period to base 10. In practice, firstly, the implementing entity can determine the sum of the intercept term coefficient, the target construction area coefficient, and the target administrative division coefficient as the first target value. Then, the logarithm of the standard engineering quantity to base 10 is determined as the second target value. Next, the product of the second target value and the weight coefficients is determined as the third target value. Finally, the sum of the third target value and the first target value is determined as the logarithmic planned construction period corresponding to the aforementioned construction condition dimension.

[0025] The third sub-step involves taking the antinomial of the logarithmic planned duration to obtain the total duration corresponding to the aforementioned construction condition dimension. In practice, the executing entity can use 10 as the base and take the antinomial of the logarithmic planned duration to obtain the total duration corresponding to the aforementioned construction condition dimension.

[0026] The fourth sub-step involves determining the ratio between the total construction period and the standard quantity of work under the aforementioned construction conditions as the unit construction period quota corresponding to the aforementioned construction conditions, which serves as the preliminary benchmark calculation value. The aforementioned unit construction period quota can be the construction period required to complete a unit quantity of work. For example, the unit construction period quota could be 0.1 days per meter.

[0027] The second step involves determining the pre-calculated benchmark values ​​corresponding to each construction condition dimension as a set of pre-calculated benchmark values, and then controlling the operation of the construction equipment performing the target business task based on this set of pre-calculated benchmark values ​​to drive the equipment to perform the operation. It should be noted that the specific implementation steps for controlling the operation of the construction equipment performing the target business task based on the set of pre-calculated benchmark values ​​to drive the equipment to perform the operation can be found in steps 102-107, and will not be repeated here.

[0028] The above-mentioned technical solution, as an inventive point of this disclosure, solves technical problem two: "increased energy consumption and mechanical wear of construction equipment or accelerated fatigue aging of transmission components and sealing elements." The reasons for increased energy consumption and mechanical wear of construction equipment or accelerated fatigue aging of transmission components and sealing elements are as follows: the prediction model directly reads distorted data from the underlying database for feature extraction, resulting in the prediction model requiring more iterations to converge, and making it difficult to take into account the multi-dimensional characteristics under different construction areas and different administrative division combinations, causing inaccurate benchmark calculation values. Consequently, when controlling the operation of construction equipment: an excessively long operation time window leads to the equipment being in an idling state for a long time, increasing the energy consumption and mechanical wear of the construction equipment; an excessively short operation time window leads to frequent start-stop of the construction equipment, accelerating the fatigue aging of transmission components and sealing elements. To achieve this effect, the equipment operation control method based on business attribute information disclosed in this disclosure first determines the target construction area coefficient and target administrative division coefficient for each construction condition dimension based on the set of construction area coefficients and the set of administrative division coefficients. Then, combining the intercept term coefficient and weight coefficient, the logarithmic planned construction period is determined, and the antilogarithm is then taken to obtain the standard planned construction period. Finally, the standard planned construction period is divided by the standard quantity of work to obtain the unit construction period quota for the construction condition dimension, which serves as the preliminary benchmark calculation value. This ensures the accuracy of the generated preliminary benchmark calculation value, reduces energy consumption and mechanical wear of construction equipment, and slows down the fatigue aging of transmission components and sealing elements.

[0029] In addressing the technical problems mentioned above, and specifically for scenario three: in construction engineering, when calculating quotas for small-sample construction areas (such as foundation pits and roofs) and controlling construction equipment operations based on these quotas, the following technical issues often arise: In construction engineering, some construction areas have extremely small sample sizes in historical data. Traditional prediction methods treat coefficients obtained from training with a small number of samples the same as coefficients from other construction areas with sufficient samples, failing to assess the reliability of the coefficients. This leads to highly unstable target construction area coefficients, resulting in large variance and low reliability of the output benchmark calculation values. Consequently, the accuracy of the final generated business attribute information is low, causing issues when controlling construction equipment operations: excessively long operation time windows lead to prolonged idling, increasing energy consumption and mechanical wear; excessively short operation time windows lead to frequent start-stop operations, accelerating fatigue aging of transmission components and sealing elements. Considering the following requirements for this application scenario—adaptability to small-sample data and efficient energy-saving control of construction equipment—we have decided to adopt the following solution: In some optional implementations of certain embodiments, the execution entity may determine the target construction area coefficient and target administrative division coefficient corresponding to the construction condition dimension by means of the following steps: based on the construction area coefficient set, the administrative division coefficient set, and the construction area identifier and administrative division identifier included in the construction condition dimension. The first step involves, in response to determining the aforementioned construction area identifier as the basic construction area identifier, setting a first preset value as the construction area coefficient corresponding to the aforementioned construction area identifier, and setting a second preset value as the first confidence score of the aforementioned construction area coefficient. The aforementioned basic construction area identifier can be a pre-specified identifier for a construction area. For example, the basic construction area identifier can be 1 (above ground). The aforementioned first preset value can be 1. The aforementioned second preset value can be 0. The aforementioned first confidence score can be the confidence score of the aforementioned construction area coefficient.

[0030] The second step involves determining the first sample size confidence base value based on each first sample corresponding to the aforementioned construction area identifier, in response to the determination that the construction area identifier is not the aforementioned foundation construction area identifier. Here, each first sample can be a sample whose construction area identifier is consistent with the aforementioned construction area identifier, where the dummy variable for each construction area in the sample set has a value of 1. For example, the foundation construction area identifier is 1 (above ground), the construction area dummy variable is [1,0,0,0,0], and the construction area identifier is 2 (underground). In practice, firstly, the executing entity can determine the variance of the residuals between the logarithmic predicted construction period and the corresponding logarithmic actual construction period of each of the aforementioned first samples predicted by the aforementioned target pre-model as the first fitting residual variance. Then, the product of the aforementioned first fitting residual variance and a preset variance penalty parameter is determined as the first product value. Here, the specific value of the aforementioned preset variance penalty parameter is not limited. For example, the preset variance penalty parameter can be 0.9. Next, the sum of the number of the aforementioned first samples and a preset sample size smoothing parameter is determined as the first sample size smoothing sum. Here, the specific value of the preset sample size smoothing parameter is not limited. For example, the preset sample size smoothing parameter can be 100. Then, the ratio between the number of each of the first samples and the smoothed sum of the first sample sizes is determined as the confidence base value of the first sample size.

[0031] The third step involves determining the target construction area coefficient and the first confidence score corresponding to the construction area identifier based on the aforementioned set of construction area coefficients and the aforementioned first sample size confidence base value. In practice, firstly, the executing entity can determine the construction area coefficient corresponding to the aforementioned construction area identifier in the aforementioned set of construction area coefficients as the target construction area coefficient. Next, the result of an exponential operation with the natural constant e (approximately 2.78) as the base and the negative of the aforementioned first product value as the exponent is determined as the first residual confidence decay factor. Finally, the product of the aforementioned first sample size confidence base value and the aforementioned first residual confidence decay factor is determined as the first confidence score of the aforementioned construction area identifier.

[0032] The fourth step involves determining the administrative division coefficient and the second confidence score corresponding to the administrative division identifier based on the aforementioned administrative division identifier, the aforementioned set of administrative division coefficients, and each second sample corresponding to the aforementioned administrative division identifier. The second sample in each of the aforementioned second samples can be a sample whose identifier matches the aforementioned administrative division identifier, provided that the dummy variable for each administrative division in the aforementioned sample set has a value of 1. The aforementioned second confidence score can be the confidence score of the aforementioned administrative division coefficient. In practice, firstly, in response to determining the aforementioned administrative division identifier as the basic administrative division identifier, the implementing entity can determine the aforementioned first preset value as the administrative division coefficient corresponding to the aforementioned administrative division identifier, and determine the aforementioned second preset value as the second confidence score of the aforementioned administrative division coefficient. The aforementioned basic administrative division identifier can be a pre-specified identifier of an administrative division. For example, the basic administrative division identifier can be 110000 (Beijing). In response to determining that the aforementioned administrative division identifier exists in the aforementioned set of administrative division coefficients, firstly, the implementing administrative division coefficient corresponding to the aforementioned administrative division identifier in the aforementioned set of administrative coefficients is determined as the target administrative division coefficient. Secondly, the variance of the residuals between the logarithmic predicted construction period and the corresponding logarithmic actual construction period of each of the second samples predicted by the aforementioned target pre-model is determined as the second fitting residual variance. Then, the product of the second fitting residual variance and the aforementioned preset variance penalty parameter is determined as the second product value. Next, the sum of the number of each of the second samples and the aforementioned preset sample size smoothing parameter is determined as the second sample size smoothing sum. Then, the ratio between the number of each of the second samples and the aforementioned second sample size smoothing sum is determined as the second sample size confidence base value. Next, a constant with the natural constant e (approximately 2.78) as the base and the negative of the aforementioned second product value as the exponent is determined as the second residual confidence decay factor. Finally, the product of the second sample size confidence base value and the aforementioned second residual confidence decay factor is determined as the second confidence score of the aforementioned administrative division identifier.

[0033] The fifth step is to determine the weighted construction area coefficient by multiplying the above-mentioned construction area coefficient and the above-mentioned first confidence score, and to determine the weighted administrative division coefficient by multiplying the above-mentioned administrative division coefficient and the above-mentioned second confidence score.

[0034] Step 6: Based on the preset global adjustment factor, the aforementioned weighted construction area coefficient, and the aforementioned weighted administrative division coefficient, determine the target construction area coefficient corresponding to the aforementioned construction area identifier and the target administrative division coefficient corresponding to the aforementioned administrative division identifier. Then, based on the aforementioned target construction area coefficient and the aforementioned target administrative division coefficient, perform operational control on the construction equipment executing the aforementioned target business task to drive the construction equipment to perform operations. Here, the specific value of the aforementioned preset global adjustment factor is not limited. For example, the preset global adjustment factor can be 0.95. In practice, firstly, the executing entity can determine the target construction area coefficient by multiplying the aforementioned preset global adjustment factor and the aforementioned weighted construction area coefficient. Then, the target administrative division coefficient is determined by multiplying the aforementioned preset global adjustment factor and the aforementioned weighted administrative division coefficient. It should be noted that the specific implementation steps for performing operational control on the construction equipment executing the aforementioned target business task based on the aforementioned target construction area coefficient and the aforementioned target administrative division coefficient to drive the construction equipment to perform operations can be referred to steps 101-107, and will not be repeated here.

[0035] The above-mentioned technical solution, as an inventive point of the embodiment of this disclosure, solves the third technical problem: "The predicted target construction area coefficient of the construction area is extremely unstable, the output pre-benchmark calculation value has a large variance and low reliability, which in turn leads to low accuracy of the final generated business attribute information, increases the energy consumption and mechanical wear of construction equipment or accelerates the fatigue aging of transmission components and sealing elements." The reasons why the predicted construction area coefficients are extremely unstable, the output baseline calculation values ​​have large variance and low reliability, and consequently the accuracy of the final generated business attribute information is low, increasing the energy consumption and mechanical wear of construction equipment or accelerating the fatigue aging of transmission components and sealing elements are as follows: In construction engineering, some construction areas have very few samples in historical data. Traditional prediction methods directly treat the coefficients obtained from training with a small number of samples the same as the coefficients of other construction areas with sufficient samples, which cannot assess the reliability of the coefficients. This leads to extremely unstable prediction results for these construction areas, with large variance and low reliability of the output results, resulting in low accuracy of the final generated business attribute information. Consequently, when controlling the operation of construction equipment: an excessively long operation time window causes the equipment to idle for a long time, increasing the energy consumption and mechanical wear of the construction equipment; an excessively short operation time window causes the construction equipment to start and stop frequently, accelerating the fatigue aging of transmission components and sealing elements. To achieve this effect, the equipment operation control method based on business attribute information disclosed herein first determines whether the construction area is a baseline area. If so, the coefficient is directly set to 0 and the confidence level to 1. If it is not a baseline area, a confidence level baseline value is calculated based on the sample size of the construction area in historical data (the smaller the sample size, the lower the baseline value). Next, the original coefficient is multiplied by the confidence level to obtain a weighted coefficient (the smaller the sample size, the closer the weighted coefficient is to 0, and the smaller the impact). Finally, a global adjustment factor is used to uniformly control the overall influence of all coefficients. This ensures that the predicted target construction area coefficients are stable, the variance of the output baseline calculation value is small, and the reliability is high, reducing energy consumption and mechanical wear of construction equipment or slowing down the fatigue aging of transmission components and sealing elements.

[0036] Optionally, the above set of target regression coefficients can be obtained through the following steps: The first step is to obtain a sample set. Each sample in the sample set can include a sample feature vector and the corresponding logarithmic actual construction period. The sample feature vector can be composed of dummy variables for construction area, administrative division, and the logarithm of the standard engineering quantity. The dummy variable for construction area can be a binary variable obtained by one-hot encoding of the construction area. There are 6 categories of construction areas, with one pre-defined category as the baseline, and the other 5 categories each corresponding to a dummy variable with a value of 0 or 1. The dummy variable for administrative division can be a binary variable obtained by one-hot encoding of the administrative division. There are 34 categories of administrative divisions, with one pre-defined category as the baseline, and the other 33 categories each corresponding to a dummy variable with a value of 0 or 1. For example, the pre-defined baseline for the construction area is above ground, the pre-defined baseline for the administrative division is Beijing, the construction area in the sample is underground, the administrative division is Shanghai, and the standard engineering quantity is 100 meters. The dummy variable for underground is 1 (the dummy variables for all construction areas except the benchmark construction area are 0), the dummy variable for the administrative division of Shanghai is 1 (the dummy variables for all administrative divisions except the benchmark administrative division are 0), and the logarithm of 100 (standard engineering quantity) to base 10 is 2. Therefore, the above sample feature vector can be represented as: [1,0,0,0,0,2.0,0,0,...,1,...,0] T The above logarithmic actual construction period can be the logarithm of the actual completed construction period of the above sample feature vectors, with base 10.

[0037] The second step, based on the above sample set, is to perform the following regression coefficient solidification steps: The first sub-step involves inputting the feature vector of at least one sample from the aforementioned sample set into the initial pre-model to obtain the logarithmic predicted construction period for each of the at least one sample. The initial pre-model can represent an untrained linear regression model. This initial pre-model can take the aforementioned sample feature vector as input and the predicted construction period corresponding to the sample as output. The logarithmic predicted construction period can be the logarithm (base 10) of the construction period predicted by the initial pre-model.

[0038] The second sub-step involves determining the loss value of the initial pre-model based on the logarithmic predicted duration and the logarithmic actual duration corresponding to each sample in at least one of the aforementioned samples. In practice, the executing entity can determine the mean square error between each obtained logarithmic predicted duration and the corresponding logarithmic actual duration as the loss value of the initial pre-model.

[0039] The third sub-step involves, in response to determining that the aforementioned loss value is less than a preset loss value, using the regression coefficients of the initial pre-model as the target regression coefficient set after training, and defining the initial pre-model as the target pre-model. The preset loss value can be 0.1.

[0040] The fourth sub-step involves adjusting the regression coefficients of the initial pre-model in response to the determination that the loss value is greater than or equal to the preset loss value. A new sample set is then created using unused samples, and the adjusted initial pre-model is used as the new initial pre-model. The regression coefficient solidification step is then executed again. In practice, the executing entity can use gradient descent to adjust the regression coefficients of the initial pre-model, obtain unused samples from the sample set to form a new sample set, and use the adjusted initial pre-model as the new initial pre-model to execute the regression coefficient solidification step again.

[0041] Step 102: For each construction task record included in the construction task data table, perform the following steps: Step 1021: Based on the construction condition dimension of the construction task record, match the corresponding baseline calculation value of the construction task record from the set of baseline calculation values.

[0042] In some embodiments, the executing entity can match the corresponding pre-benchmark calculation value for each construction task record from the aforementioned set of pre-benchmark calculation values ​​based on the construction condition dimension of the construction task record. The construction task data table can represent a table storing various construction task records. Each construction task record can be a row of data in the aforementioned construction task data table. The construction task record can include raw data such as the actually reported construction period and the actual task scale. The actual task scale can be the specific quantity of construction tasks in the construction task record; for example, the actual task scale can be the length of cable laid (100 meters). In practice, the executing entity can obtain the pre-benchmark calculation value corresponding to the construction condition dimension from the aforementioned set of pre-benchmark calculation values.

[0043] Step 1022: Perform a linear cross-multiplication of the actual task scale value in the construction task record with the previous benchmark calculation value to obtain the calibrated characteristic value.

[0044] In some embodiments, the executing entity may linearly cross-multiply the actual task scale value in the construction task record with the aforementioned pre-reference calculation value to obtain a calibrated feature value. The calibrated feature value represents the value obtained by multiplying the actual task scale value by the corresponding pre-reference calculation value, indicating the revised construction period.

[0045] Step 103: Determine the obtained calibrated feature values ​​as a calibrated feature value column.

[0046] In some embodiments, the aforementioned executing entity may determine the obtained calibrated feature values ​​as a calibrated feature value column.

[0047] Optionally, after step 103, the executing entity may also overwrite the calibrated feature value column back into the construction task data table to replace the original distorted feature column. The distorted feature column can characterize distorted data columns in the original data (such as manually entered incorrect construction periods).

[0048] Step 104: Based on the calibrated feature value column, train and solidify the parameters of the initial post-model to obtain the solidified post-model.

[0049] In some embodiments, the execution entity can train and solidify the initial post-model based on the calibrated feature value column to obtain a solidified post-model. The initial post-model can represent a linear regression model. The initial post-model can take the calibrated feature values ​​as input and business attribute information (predicted unit price) as output. The solidified post-model can represent the model obtained after training the initial post-model. The weights and biases of the initial post-model can be randomly initialized (e.g., random numbers between 0 and 0.1).

[0050] In some optional implementations of certain embodiments, the aforementioned execution entity may perform training and parameter solidification processing on the initial post-model based on the aforementioned calibrated feature value column to obtain the solidified post-model: The first step, based on the above-mentioned calibrated feature value column and the true unit price corresponding to each calibrated feature value in the above-mentioned calibrated feature value column, is to perform the following training steps: The first sub-step involves inputting at least one calibrated feature value from the aforementioned calibrated feature value column into the initial post-model to obtain the predicted unit price corresponding to each of the at least one calibrated feature value. Here, the actual unit price can represent the actual labor unit price corresponding to the aforementioned calibrated feature value. The predicted unit price can be the labor unit price predicted by the initial post-model.

[0051] The second sub-step involves determining the loss value of the initial post-model based on the predicted unit price and the actual unit price corresponding to each of the at least one calibrated feature values. In practice, the executing entity can determine the mean square error between each predicted unit price and its corresponding actual unit price as the loss value of the initial post-model.

[0052] The third sub-step involves determining that the aforementioned loss value is less than a preset loss threshold, and then identifying the initial post-model as the trained and solidified post-model. Here, the specific value of the preset loss threshold is not limited; for example, the preset loss threshold could be 0.15.

[0053] Optionally, in response to determining that the loss value is greater than or equal to the preset loss threshold, the training steps may further adjust the parameters of the initial post-model and use a calibrated feature value column composed of unused calibrated feature values, use the adjusted initial post-model as the initial post-model, and execute the training steps again.

[0054] Step 105: Based on the actual task size of the target business task and the set of previous benchmark calculation values, determine the calibrated feature value of the target business task as the target calibrated feature value.

[0055] In some embodiments, the executing entity may determine the calibrated feature value of the target business task as the target calibrated feature value based on the actual task size value of the target business task and the set of preceding benchmark calculation values.

[0056] In some optional implementations of certain embodiments, the execution entity may determine the calibrated characteristic value of the target business task as the target calibrated characteristic value by following the steps of: based on the actual task size value of the target business task and the aforementioned set of pre-calculated benchmark values. The first step is to match the corresponding pre-construction benchmark value from the aforementioned set of pre-construction benchmark values, based on the construction condition dimension of the target business task. In practice, the executing entity can determine the pre-construction benchmark value corresponding to the aforementioned construction condition dimension from the aforementioned set of pre-construction benchmark values ​​as the target pre-construction benchmark value.

[0057] The second step involves linearly cross-multiplying the actual task size of the target business task with the calculated target baseline value to obtain the calibrated characteristic value. This calibrated characteristic value can be the calibrated characteristic value corresponding to the target business task. In practice, the executing entity can determine the calibrated characteristic value as the product of the actual task size of the target business task and the calculated target baseline value.

[0058] Step 106: Input the target calibration feature values ​​into the solidified post-model to obtain the business attribute information corresponding to the target business task.

[0059] In some embodiments, the executing entity can input the calibrated feature values ​​of the target into the solidified post-model to obtain the business attribute information corresponding to the target business task. This business attribute information can characterize the unit cost corresponding to the target business task. For example, in a construction engineering quota pricing scenario, the business attribute information can be the predicted labor unit price, expressed in yuan / day. The level of this labor unit price can be used to adjust the operating time of construction equipment.

[0060] Step 107: Based on the business attribute information, perform operation control on the construction equipment that performs the target business task to drive the construction equipment to perform the operation.

[0061] In some embodiments, the aforementioned execution entity may, based on the aforementioned business attribute information, perform operation control on the construction equipment performing the aforementioned target business task, so as to drive the construction equipment to perform the operation.

[0062] In some optional implementations of certain embodiments, the aforementioned execution entity may perform operation control on the construction equipment executing the aforementioned target business task based on the aforementioned business attribute information through the following steps, so as to drive the construction equipment to perform the operation: The first step is to obtain the equipment efficiency information of the construction equipment. This construction equipment can be equipment that assists in performing the aforementioned target business task. For example, the construction equipment could be a concrete pump truck. The equipment efficiency information represents the amount of work that the construction equipment can complete per unit time. In practice, the executing entity can use the model number of the construction equipment as the query key to obtain the equipment efficiency information from the equipment parameter configuration table. This equipment parameter configuration table pre-stores equipment efficiency information for various models of construction equipment. For example, if the construction equipment is a concrete pump truck with model number "HB52", the equipment efficiency information for this model of pump truck read from the equipment parameter configuration table is 40 cubic meters per hour.

[0063] The second step is to determine the initial operating time of the construction equipment based on the actual workload of the target task and the equipment efficiency information. The actual workload can be the total amount of work required to complete the target task. The initial operating time represents the time required to complete the actual workload under the working efficiency corresponding to the equipment efficiency information. In practice, the executing entity can determine the initial operating time of the construction equipment as the ratio between the actual workload and the equipment efficiency information. For example, if the actual workload is 200 cubic meters and the equipment efficiency is 40 cubic meters per hour, the initial operating time is 5 hours.

[0064] The third step is to determine the duration adjustment coefficient for the construction equipment based on the aforementioned business attribute information. This duration adjustment coefficient can be a multiplier for adjusting the initial operation duration. In practice, the executing entity can query a pre-defined adjustment coefficient mapping table, using the aforementioned business attribute information as the query key, to match the corresponding duration adjustment coefficient. If a match is successful, the matched duration adjustment coefficient is determined as the duration adjustment coefficient for the construction equipment; if a match fails, the default adjustment coefficient of 1.0 is used. The pre-defined adjustment coefficient mapping table stores duration adjustment coefficients corresponding to multiple business attribute information value ranges. For example, a preset adjustment coefficient mapping table could be: {If business attribute information is greater than or equal to 300 (yuan / day), the corresponding duration adjustment coefficient is 1.2; if business attribute information is greater than or equal to 200 (yuan / day) and less than 300 (yuan / day), the corresponding duration adjustment coefficient is 1.0; if business attribute information is greater than or equal to 150 (yuan / day) and less than 200 (yuan / day), the corresponding duration adjustment coefficient is 0.8; if business attribute information is less than 150 (yuan / day), the corresponding duration adjustment coefficient is 0.5}. It should be noted that the above division of numerical ranges and the corresponding duration adjustment coefficient values ​​are only examples. The specific values ​​of the above range thresholds and duration adjustment coefficients can be adjusted according to the actual construction scenario (such as equipment type, project urgency, cost control strategy, etc.).

[0065] The fourth step is to determine the target operating time for the construction equipment based on the preliminary operating time and the time adjustment coefficient mentioned above. The target operating time can be the actual operating time required for the construction equipment to perform the target task. In practice, the executing entity can determine the target operating time of the construction equipment by multiplying the preliminary operating time by the time adjustment coefficient. For example, if the preliminary operating time is 5 hours and the time adjustment coefficient is 1.2, then the target operating time is 6 hours.

[0066] Fifth, based on the target operation duration, generate the corresponding operation control instruction for the construction equipment. This operation control instruction can be a data instruction containing the target operation duration and equipment identifier, used to control the construction equipment to perform operations according to the target operation duration. In practice, the executing entity assembles the equipment identifier of the construction equipment and the target operation duration into a data frame according to a preset communication protocol format to obtain the operation control instruction. The operation control instruction can include a frame header, equipment identifier field, instruction type field, target operation duration field, and verification field. The instruction type field can be used to identify this instruction as an operation duration control instruction. The verification field can be used to verify the integrity of the operation control instruction in subsequent steps. The preset communication protocol format can be the MODBUS communication protocol format.

[0067] The sixth step involves sending the aforementioned operation control commands to the controller of the construction equipment to control the equipment to perform the operation. The controller can be a built-in control unit (such as a programmable logic controller or microcontroller system) within the construction equipment, used to receive external commands and control the actions of the actuators. In practice, the actuator sends the operation control commands to the controller of the construction equipment via a communication network. This communication network can be a wired network (such as industrial Ethernet or CAN bus) or a wireless network (such as 4G / 5G or Wi-Fi). The actuators can include at least one of the following: a drive motor (for driving wheels or a pumping mechanism), a hydraulic pump (for driving a hydraulic cylinder or hydraulic motor), a solenoid valve (for controlling the on / off and reversing of the hydraulic circuit), and a relay (for controlling the on / off of the main circuit power supply).

[0068] The above-described embodiments of this disclosure have the following beneficial effects: The device operation control method based on business attribute information in some embodiments of this disclosure can reduce the number of input and output requests in the storage system, reduce the read / write load and head seek time of the disk controller, improve the accuracy of the final generated business attribute information, reduce the energy consumption and mechanical wear of construction equipment, or slow down the fatigue aging of transmission components and sealing elements. Specifically, the reason why the number of input and output requests in the storage system increases exponentially, increases the read / write load and head seek time of the disk controller, and leads to low accuracy of the final generated business attribute information, increases the energy consumption and mechanical wear of construction equipment, or accelerates the fatigue aging of transmission components and sealing elements is that the original data entered in the underlying database often has serious distortion problems. For example, in the scenario of construction engineering, the construction period data entered by on-site personnel is seriously inconsistent with the actual construction period; a project that actually only requires 5 days is entered as 30 days. Existing data cleaning techniques typically employ simple statistical methods (such as removing outliers and taking averages). This approach requires multiple scans of the entire data table, leading to a significant increase in the number of input and output requests to the storage system, increasing the read / write load on the disk controller and the seek time of the read / write head. Furthermore, when predictive models directly use this distorted data as input features for training, the accuracy of the resulting business attribute information is low. This results in several issues when controlling construction equipment: an excessively long operation time window causes the equipment to idle for extended periods, increasing energy consumption and mechanical wear; an excessively short operation time window leads to frequent start-ups and shutdowns, accelerating the fatigue and aging of transmission components and sealing elements. Therefore, the equipment operation control method based on business attribute information in some embodiments of this disclosure first, in response to receiving an operation execution instruction for the target business task, determines the preceding benchmark calculation values ​​corresponding to each of the aforementioned construction condition dimensions as a preceding benchmark calculation value set, based on the target regression coefficient set and each construction condition dimension. Thus, the preceding benchmark calculation value set corresponding to each construction condition dimension can be obtained. Next, for each construction task record included in the construction task data table, the following steps are performed: First, based on the construction condition dimension of the construction task record, the corresponding pre-benchmark calculation value for the construction task record is matched from the aforementioned pre-benchmark calculation value set. This yields the pre-benchmark calculation value for the construction task record. Next, the actual task scale value in the construction task record is linearly cross-multiplied with the aforementioned pre-benchmark calculation value to obtain calibrated feature values. This yields the calibrated feature values. Then, each obtained calibrated feature value is defined as a calibrated feature value column. This yields the calibrated feature value column. Next, based on the calibrated feature value column, the initial post-model is trained and its parameters are solidified to obtain the solidified post-model. This yields the solidified post-model after training.Next, based on the actual task scale of the target business task and the aforementioned set of pre-calculated benchmark values, the calibrated characteristic value of the target business task is determined as the target calibrated characteristic value. Thus, the calibrated characteristic value of the target business task can be obtained. Then, the calibrated characteristic value is input into the solidified post-model to obtain the business attribute information corresponding to the target business task. Thus, the business attribute information of the target business task can be obtained. Finally, based on the business attribute information, operation control is performed on the construction equipment executing the target business task to drive the construction equipment to perform the operation. Because it doesn't directly read raw distorted data from the underlying database for feature extraction, but instead uses a pre-model to perform benchmark extrapolation on all business data, generating pre-benchmark values ​​for each construction condition dimension, and then matching the corresponding pre-benchmark values ​​to the construction condition dimensions recorded in the construction task records, the actual task scale values ​​are linearly cross-multiplied with the pre-benchmark values ​​to obtain calibrated feature values. These calibrated feature values ​​are then written back to the construction task data table. Only one data cleaning operation is needed to complete the self-repair of all distorted data, reducing the number of input / output requests and disk head seek time in the storage system, thus improving system resource utilization. Furthermore, because it doesn't use static statistical methods (such as removing extreme values ​​or taking averages) for data cleaning, but instead generates calibrated feature values ​​by linearly cross-multiplying the pre-benchmark values ​​with the actual task scale values, which serve as input features for the subsequent model, it achieves dynamic adaptive repair of distorted data. This reduces the increase in model training iterations and wasted computational resources caused by data distortion, thereby shortening model training time and reducing CPU computational resource consumption. This sequential dependency of prior and subsequent iterations ensures that the subsequent model always uses high-quality, repaired data, reducing issues caused by data distortion leading to garbage data entering and leaving the system. This reduces the number of input and output requests to the storage system, decreases the read / write load on the disk controller and the head seek time, improves the accuracy of the final generated business attribute information, and reduces energy consumption and mechanical wear of construction equipment, or slows down the fatigue aging of transmission components and sealing elements.

[0069] Further reference Figure 2 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a device operation control method based on business attribute information. These device embodiments are similar to... Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0070] like Figure 2As shown, some embodiments of the equipment operation control device 200 based on business attribute information include: a first determining unit 201, an execution unit 202, a second determining unit 203, a parameter fixing unit 204, a third determining unit 205, an input unit 206, and a control unit 207. The first determining unit 201 is configured to, in response to receiving an operation execution instruction for a target business task, determine the preceding benchmark calculation values ​​corresponding to each construction condition dimension as a preceding benchmark calculation value set, based on the target regression coefficient set and each construction condition dimension, wherein the preceding benchmark calculation value is the construction period required per unit of project volume; the execution unit 202 is configured to, for each construction task record included in the construction task data table, perform the following steps: matching the preceding benchmark calculation value corresponding to the construction task record from the preceding benchmark calculation value set according to the construction condition dimension of the construction task record; linearly cross-multiplying the actual task scale value in the construction task record with the preceding benchmark calculation value to obtain a calibrated feature value; the second determining unit 203 is configured to... The obtained calibrated feature values ​​are determined as a calibrated feature value series; the parameter solidification unit 204 is configured to train and solidify the initial post-model according to the above-mentioned calibrated feature value series to obtain a solidified post-model; the third determination unit 205 is configured to determine the calibrated feature value of the above-mentioned target business task as the target calibrated feature value according to the actual task scale value of the above-mentioned target business task and the above-mentioned set of pre-reference calculation values; the input unit 206 is configured to input the above-mentioned target calibrated feature value into the above-mentioned solidified post-model to obtain the business attribute information corresponding to the above-mentioned target business task; the control unit 207 is configured to perform operation control on the construction equipment performing the above-mentioned target business task according to the above-mentioned business attribute information to drive the construction equipment to perform the operation.

[0071] It is understandable that the units recorded in the equipment operation control device 200 based on business attribute information are related to the reference... Figure 1 The steps in the described method correspond accordingly. Therefore, the operations, features, and beneficial effects described above for the method also apply to the equipment operation control device 200 based on business attribute information and the units contained therein, and will not be repeated here.

[0072] The following is for reference. Figure 3 It shows a schematic diagram of the structure of an electronic device (such as a computing device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0073] like Figure 3As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0074] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0075] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0076] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0077] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0078] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: in response to receiving a job execution instruction for a target business task, determine, based on the target regression coefficient set and each construction condition dimension, the preceding benchmark calculation value corresponding to each of the aforementioned construction condition dimensions as a preceding benchmark calculation value set, wherein the preceding benchmark calculation value is the construction period required per unit of project volume; for each construction task record included in the construction task data table, perform the following steps: based on the construction condition dimension of the aforementioned construction task record, match the preceding benchmark calculation value corresponding to the aforementioned construction task record from the preceding benchmark calculation value set; and set the actual task scale in the aforementioned construction task record... The numerical value is linearly cross-multiplied with the aforementioned pre-benchmark calculation value to obtain the calibrated feature value; each of the obtained calibrated feature values ​​is determined as a calibrated feature value series; based on the aforementioned calibrated feature value series, the initial post-model is trained and its parameters are solidified to obtain the solidified post-model; based on the actual task scale of the aforementioned target business task and the aforementioned pre-benchmark calculation value set, the calibrated feature value of the aforementioned target business task is determined as the target calibrated feature value; the aforementioned target calibrated feature value is input into the aforementioned solidified post-model to obtain the business attribute information corresponding to the aforementioned target business task; based on the aforementioned business attribute information, the construction equipment performing the aforementioned target business task is controlled to drive the construction equipment to perform the operation.

[0079] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0080] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0081] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including a first determining unit, an execution unit, a second determining unit, a parameter fixing unit, a third determining unit, an input unit, and a control unit. The names of these units do not necessarily limit the unit itself. For example, the first determining unit may also be described as a unit that, "in response to receiving a job execution instruction for a target business task, determines the preceding benchmark calculation values ​​corresponding to each of the aforementioned construction condition dimensions as a preceding benchmark calculation value set, based on the target regression coefficient set and each construction condition dimension."

[0082] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0083] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A method for equipment operation control based on business attribute information, characterized in that, include: In response to receiving an operation execution instruction for the target business task, the system determines the preceding benchmark calculation value corresponding to each construction condition dimension as the preceding benchmark calculation value set based on the target regression coefficient set and each construction condition dimension, wherein the preceding benchmark calculation value is the construction period required per unit of project volume. For each construction task record included in the construction task data table, perform the following steps: Based on the construction condition dimension of the construction task record, the corresponding pre-benchmark calculation value of the construction task record is matched from the set of pre-benchmark calculation values. The actual task scale value in the construction task record is linearly cross-multiplied with the previous benchmark calculation value to obtain the calibrated feature value; Each calibrated feature value obtained is defined as a calibrated feature value column; Based on the calibrated feature value column, the initial post-model is trained and its parameters are solidified to obtain the solidified post-model; Based on the actual task size of the target business task and the set of preceding benchmark calculation values, the calibrated feature value of the target business task is determined as the target calibrated feature value. The calibrated feature values ​​of the target are input into the solidified post-model to obtain the business attribute information corresponding to the target business task; Based on the business attribute information, the construction equipment performing the target business task is controlled to drive the construction equipment to perform the operation.

2. The method according to claim 1, characterized in that, The method further includes: The calibrated feature value column is overwritten back into the construction task data table to replace the original distorted feature column.

3. The method according to claim 1, characterized in that, The step of training and parameter solidification of the initial post-model based on the calibrated feature value column to obtain the solidified post-model includes: Based on the calibrated feature value column and the true unit price corresponding to each calibrated feature value in the calibrated feature value column, perform the following training steps: Input at least one calibrated feature value from the calibrated feature value column into the initial post-model to obtain the predicted unit price corresponding to each calibrated feature value in the at least one calibrated feature value; Based on the predicted unit price and the actual unit price corresponding to each of the at least one calibrated feature values, the loss value of the initial post-model is determined. In response to determining that the loss value is less than a preset loss threshold, the initial post-model is determined as the solidified post-model after training is completed.

4. The method according to claim 3, characterized in that, The training steps also include: In response to determining that the loss value is greater than or equal to the preset loss threshold, the parameters of the initial post-model are adjusted, and a calibrated feature value column composed of unused calibrated feature values ​​is used. The adjusted initial post-model is then used as the initial post-model, and the training step is executed again.

5. The method according to claim 1, characterized in that, The step of determining the calibrated feature value of the target business task as the target calibrated feature value based on the actual task size value of the target business task and the set of previous benchmark calculation values ​​includes: Based on the construction condition dimension of the target business task, the corresponding preceding benchmark calculation value is matched from the preceding benchmark calculation value set as the target preceding benchmark calculation value; The actual task size of the target business task is linearly cross-multiplied with the target pre-benchmark calculation value to obtain the target calibrated feature value.

6. The method according to claim 1, characterized in that, The step of controlling the construction equipment performing the target business task based on the business attribute information to drive the construction equipment to perform the operation includes: Obtain equipment efficiency information of construction equipment, wherein the equipment efficiency information is the amount of work that the construction equipment can complete per unit time; Based on the actual workload of the target business task and the equipment efficiency information, determine the initial operating time of the construction equipment; Based on the business attribute information, determine the duration adjustment coefficient of the construction equipment; Based on the preliminary operation time and the time adjustment coefficient, the target operation time of the construction equipment is determined; Based on the target operation duration, generate operation control instructions corresponding to the construction equipment; The operation control command is sent to the controller of the construction equipment to control the construction equipment to perform the operation.

7. A device for controlling equipment operation based on business attribute information, characterized in that, include: The first determining unit is configured to, in response to receiving a job execution instruction for a target business task, determine the preceding benchmark calculation value corresponding to each construction condition dimension as a preceding benchmark calculation value set based on the target regression coefficient set and each construction condition dimension, wherein the preceding benchmark calculation value is the construction period required per unit of project volume; The execution unit is configured to perform the following steps for each construction task record included in the construction task data table: matching the corresponding pre-benchmark calculation value of the construction task record from the pre-benchmark calculation value set according to the construction condition dimension of the construction task record; and performing linear cross multiplication between the actual task scale value in the construction task record and the pre-benchmark calculation value to obtain the calibrated feature value. The second determining unit is configured to determine the obtained calibrated feature values ​​as a calibrated feature value column; The parameter solidification unit is configured to train and solidify the initial post-model based on the calibrated feature value column to obtain the solidified post-model. The third determining unit is configured to determine the calibrated feature value of the target business task as the target calibrated feature value based on the actual task size value of the target business task and the set of preceding benchmark calculation values. The input unit is configured to input the target calibrated feature value into the solidified post-model to obtain the business attribute information corresponding to the target business task; The control unit is configured to perform operation control on the construction equipment executing the target business task based on the business attribute information, so as to drive the construction equipment to perform the operation.

8. An electronic device, characterized in that, include: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 6.

9. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 6.

Images