Device operation policy recommendation method and apparatus, device, and storage medium

Abstract

The present disclosure provides a device operation strategy recommendation method and device, equipment and storage medium, which are applied to the technical field of big data and the technical field of finance. The method comprises the following steps: inputting operation value time sequence information of a target device in a historical period into an initial random process model, outputting a first parameter and a first function corresponding to the first parameter; correcting the first function according to time sequence information of an operation value influencing factor to obtain a second function; inputting a target moment for which operation value prediction is to be performed into the second function to output device operation value prediction candidate information; performing model transformation on the initial random process model by using the second function to obtain a target random process model; inputting the operation value time sequence information into the target random process model to output a second parameter and a third function corresponding to the second parameter; and in the case that the third function meets a first preset condition, recommending an operation strategy for the target device according to the device operation value prediction candidate information.

Description

Technical Field

[0001] This disclosure relates to the fields of big data technology and financial technology, and in particular to a method, apparatus, device, medium and program product for recommending equipment operation strategies. Background Technology

[0002] Because numerous factors influence equipment lifespan, and the timing of these factors is somewhat random, equipment operation is often accompanied by a degree of randomness, making it difficult to formulate relatively consistent operational strategies. Traditional equipment operation strategies are typically developed based on expert diagnosis when equipment malfunctions. However, this relies on the subjective judgment of experts, and the resulting strategies may contain omissions, leading to operational risks. Furthermore, manually inspecting equipment for potential hazards is usually performed periodically, and adjusting the operation strategy based on the results of these inspections is not only time-consuming and labor-intensive but also inherently delayed and inefficient. Summary of the Invention

[0003] In view of the above problems, this disclosure provides methods, apparatus, equipment, media and program products for recommending equipment operation strategies.

[0004] According to one aspect of this disclosure, a method for recommending equipment operation strategies is provided, comprising:

[0005] The time-series information of the operational value of the target equipment in the historical period is input into the initial stochastic process model, and the first parameter and the first function corresponding to the first parameter are output. The first function represents the correlation between the operational value of the equipment and time.

[0006] The first function is modified based on the time-series information of the factors influencing the operational value of the target equipment in the historical period to obtain the second function; the target time for which operational value prediction is to be performed is input into the second function, and candidate information for equipment operational value prediction is output.

[0007] The initial stochastic process model is transformed using the second function to obtain the target stochastic process model; the operational value time series information is input into the target stochastic process model, and the second parameter and the third function corresponding to the second parameter are output.

[0008] If the third function satisfies the first preset condition, an operation strategy for the target device is recommended based on the device operation value prediction candidate information.

[0009] According to embodiments of this disclosure, the operational value time-series information includes actual operational value information of the equipment at m time points. The first function is modified based on the time-series information of the operational value influencing factors of the target equipment within a historical period to obtain a second function, which includes:

[0010] Based on the actual operating value information of the equipment at time i and the first predicted operating value information of the equipment at time i, the first prediction deviation is determined, wherein the first predicted operating value information of the equipment is obtained by inputting the first function at time i.

[0011] If the first prediction deviation between the actual operating value information of the equipment at m time points and the predicted operating value information of the equipment at m time points meets the first preset threshold, the first function and the time series information of the factors affecting the operating value are input into the generalized linear model for multiple regression analysis, and the second function is output, where m and i are positive integers, and 1≤i≤m.

[0012] According to embodiments of this disclosure, a first prediction deviation is determined based on the actual operating value information of the equipment at time i and the first predicted operating value information of the equipment at time i, including:

[0013] The first prediction deviation value is determined based on the difference between the actual operating value information of the equipment at time i and the predicted operating value information of the first equipment at time i.

[0014] The first prediction deviation is determined based on the percentage of the first prediction deviation value and the actual operating value information of the equipment at time i.

[0015] According to embodiments of this disclosure, the operational value time-series information includes actual operational value information of the equipment at m time points. When the third function satisfies a first preset condition, an operational strategy for the target equipment is recommended based on the equipment operational value prediction candidate information, including:

[0016] The second prediction deviation is determined based on the actual operating value information of the equipment at time i and the second equipment operating value prediction information at time i. The second equipment operating value prediction information is obtained by inputting the third function at time i.

[0017] Input the target time into the third function, and output the third equipment operation value prediction information corresponding to the target time;

[0018] Based on the equipment prediction candidate information and the third equipment operation value prediction information at the target time, the third prediction deviation is determined. The third equipment operation value prediction information is obtained by inputting the target time into the third function.

[0019] If the second prediction deviation between the actual operating value information of the equipment at m time points and the predicted operating value information of the equipment at m time points and the third prediction deviation at the target time satisfy the second preset threshold, an operating strategy for the target equipment is recommended based on the candidate information for predicting the operating value of the equipment, where m and i are positive integers, and 1≤i≤m.

[0020] According to embodiments of this disclosure, determining a second prediction deviation based on the actual operating value information of the equipment at time i and the second predicted operating value information of the equipment at time i includes:

[0021] The second prediction deviation value is determined based on the difference between the actual operating value information of the equipment at time i and the predicted operating value information of the second equipment at time i.

[0022] The second prediction deviation is determined based on the second prediction deviation value and the actual operating value information of the equipment at time i.

[0023] According to embodiments of this disclosure, a third prediction deviation is determined based on candidate equipment prediction information at a target time and third equipment operating value prediction information, including:

[0024] The third prediction deviation value is determined based on the difference between the candidate equipment prediction information and the third equipment operation value prediction information at the target time.

[0025] The third prediction deviation is determined based on the third prediction deviation value and the equipment prediction candidate information at the target time.

[0026] According to embodiments of this disclosure, the time-series information of operational value influencing factors includes time-series information of n operational value influencing factors, and further includes:

[0027] For the time series information of the j-th operational value influencing factor, examine the correlation between the time series information of the j-th operational value influencing factor and the operational value of the equipment;

[0028] If the correlation between the time series information of the j-th operational value influencing factor and the equipment operational value meets the third preset condition, the time series information of the j-th operational value influencing factor is determined as the input information of the generalized linear model, where n is a positive integer greater than 1, and 1≤j≤m, and j is a positive integer.

[0029] According to embodiments of this disclosure, the above-mentioned equipment operation strategy recommendation method further includes:

[0030] Based on the first parameter being within a preset adjustment range, k sets of third parameters are randomly determined;

[0031] Based on the k sets of third parameters, determine k first functions, where k is a positive integer greater than 1.

[0032] According to embodiments of this disclosure, operational value time-series information is input into an initial stochastic process model, and a first parameter and a first function corresponding to the first parameter are output, including:

[0033] The operational value time series information is input into the initial stochastic process model, and the first parameter is calculated using the differential equation of the initial process function;

[0034] The first parameter and the operational value time series information are input into the initial process function, and iterative calculations are performed to obtain the first function.

[0035] According to embodiments of this disclosure, operational value time-series information is input into a target stochastic process model, and a second parameter and a third function corresponding to the second parameter are output, including:

[0036] The operational value time series information is input into the target stochastic process model, and the second parameter is calculated using the differential equation of the target process function;

[0037] The second parameter and the operational value time series information are input into the target process function for iterative calculation to obtain the third function.

[0038] Another aspect of this disclosure provides an equipment operation strategy recommendation device, comprising: a first fitting module, a correction module, a second fitting module, and a recommendation module. The first fitting module is used to input the time-series information of the operational value of the target equipment within a historical period into an initial stochastic process model, and output a first parameter and a first function corresponding to the first parameter, wherein the first function characterizes the correlation between the operational value of the equipment and time. The correction module is used to correct the first function based on the time-series information of the factors influencing the operational value of the target equipment within a historical period, obtaining a second function; and input the target time for which operational value prediction is to be performed into the second function, outputting candidate information for equipment operational value prediction. The second fitting module is used to transform the initial stochastic process model using the second function to obtain a target stochastic process model; and input the time-series information of operational value into the target stochastic process model, outputting a second parameter and a third function corresponding to the second parameter. The recommendation module is used to recommend an operation strategy for the target equipment based on the candidate information for equipment operational value prediction, provided that the third function satisfies a first preset condition.

[0039] According to embodiments of this disclosure, the correction module includes a first determining unit and a first output unit. The first determining unit is used to determine a first prediction deviation based on the actual operating value information of the equipment at time i and the first predicted operating value information of the equipment at time i. The first output unit is used to, when the first prediction deviation between the actual operating value information of the equipment at time m and the predicted operating value information at time m satisfies a first preset threshold, input the time-series information of the first function and the influencing factors of operating value into a generalized linear model, perform multiple regression analysis, and output a second function, where m is a positive integer, 1 ≤ i ≤ m.

[0040] According to embodiments of this disclosure, the first determining unit includes a first determining subunit and a second determining subunit. The first determining subunit is configured to determine a first prediction deviation value based on the difference between the actual operating value information of the equipment at time i and the first predicted operating value information of the equipment at time i. The second determining subunit is configured to determine a first prediction deviation degree based on the percentage of the first prediction deviation value to the actual operating value information of the equipment at time i.

[0041] According to embodiments of this disclosure, the recommendation module includes a second output unit, a second determination unit, a third output unit, a third determination unit, and a recommendation unit. The second output unit is used to input the i-th time moment into a third function and output second equipment operation value prediction information corresponding to the i-th time moment. The second determination unit is used to determine a second prediction deviation based on the actual equipment operation value information at the i-th time moment and the second equipment operation value prediction information at the i-th time moment. The third output unit is used to input the target time moment into the third function and output third equipment operation value prediction information corresponding to the target time moment. The third determination unit is used to determine a third prediction deviation based on the equipment prediction candidate information at the target time and the third equipment operation value prediction information. The recommendation unit is used to recommend an operation strategy for the target equipment based on the equipment operation value prediction candidate information when the second prediction deviation between the actual equipment operation value information at m times and the equipment operation value prediction information at m times, and the third prediction deviation at the target time, satisfy a second preset threshold, where m is a positive integer, 1 ≤ i ≤ m.

[0042] According to embodiments of this disclosure, the second determining unit includes a third determining subunit and a fourth determining subunit. The third determining subunit is configured to determine a second prediction deviation value based on the difference between the actual operating value information of the equipment at time i and the second predicted operating value information of the equipment at time i. The fourth determining subunit is configured to determine a second prediction deviation degree based on the second prediction deviation value and the actual operating value information of the equipment at time i.

[0043] According to embodiments of this disclosure, the third determining unit includes a fifth determining subunit and a sixth determining subunit. The fifth determining subunit is used to determine a third prediction deviation value based on the difference between the equipment prediction candidate information at the target time and the third equipment operating value prediction information. The sixth determining subunit is used to determine a third prediction deviation degree based on the third prediction deviation value and the equipment prediction candidate information at the target time.

[0044] According to embodiments of this disclosure, the above-mentioned equipment operation strategy recommendation device further includes a verification module and a first determination module. The verification module is used to verify the correlation between the time-series information of the j-th operational value influencing factor and the equipment operational value. The first determination module is used to determine the time-series information of the j-th operational value influencing factor as the input information of the generalized linear model when the correlation between the time-series information of the j-th operational value influencing factor and the equipment operational value meets a third preset condition, where n is a positive integer greater than 1, and 1 ≤ j ≤ m.

[0045] According to embodiments of this disclosure, the above-mentioned equipment operation strategy recommendation device further includes a second determining module and a third determining module. The second determining module is used to randomly determine k sets of third parameters within a preset adjustment range based on the first parameters. The third determining module is used to determine k first functions based on the k sets of third parameters, where k is a positive integer greater than 1.

[0046] According to embodiments of this disclosure, the first fitting module includes a first calculation unit and a second calculation unit. The first calculation unit is used to input operational value time-series information into an initial stochastic process model and calculate first parameters using the differential equation of the initial process function. The second calculation unit is used to input the first parameters and operational value time-series information into the initial process function and perform iterative calculations to obtain a first function.

[0047] According to embodiments of this disclosure, the second fitting module includes a third calculation unit and a fourth calculation unit. The third calculation unit is used to input operational value time-series information into the target stochastic process model and calculate the second parameter using the differential equation of the target process function. The fourth calculation unit is used to input the second parameter and operational value time-series information into the target process function and perform iterative calculation to obtain the third function.

[0048] Another aspect of this disclosure provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors perform the methods described above.

[0049] Another aspect of this disclosure provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the methods described above.

[0050] Another aspect of this disclosure provides a computer program product including a computer program that, when executed by a processor, implements the methods described above.

[0051] According to the equipment operation strategy recommendation method, apparatus, equipment, medium, and program products provided in this disclosure, by inputting the time-series information of the target equipment's operational value over a historical period into an initial stochastic process model, a first function characterizing the equipment's operational value versus time is obtained using the initial stochastic process model. By modifying the first function using the time-series information of operational value influencing factors, and then transforming the initial stochastic process model using the modified function, a third function that accurately reflects the change in equipment's operational value over time is objectively fitted based on the actual operational value time-series data and the actual operational value influencing factors. Based on the equipment operational value prediction candidate information at the target time, an operation strategy for the target equipment is recommended. Therefore, this at least partially solves the problem in related technologies where reliance on subjective human experience leads to certain lags and omissions in operation strategies, achieving the technical effect of accurately recommending operation strategies for the entire lifecycle of the target equipment. Attached Figure Description

[0052] The foregoing contents, as well as other objects, features, and advantages of this disclosure, will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0053] Figure 1 The illustration schematically depicts application scenarios of equipment operation strategy recommendation methods, apparatus, devices, media, and program products according to embodiments of this disclosure;

[0054] Figure 2 A flowchart illustrating a device operation strategy recommendation method according to an embodiment of the present disclosure is shown schematically.

[0055] Figure 3 A flowchart illustrating a method for modifying a first function according to an embodiment of the present disclosure is shown schematically.

[0056] Figure 4 A flowchart illustrating the recommendation of operational strategies for a target device based on device operational value prediction candidate information according to an embodiment of the present disclosure is shown.

[0057] Figure 5 A schematic diagram illustrating a structural block diagram of an equipment operation strategy recommendation device according to an embodiment of the present disclosure; and

[0058] Figure 6 A block diagram of an electronic device suitable for implementing a device operation strategy recommendation method according to an embodiment of the present disclosure is illustrated schematically. Detailed Implementation

[0059] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0060] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0061] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0062] When using expressions such as "at least one of A, B, and C", they should generally be interpreted in accordance with the meaning that is commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0063] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision, disclosure, and application of user personal information comply with the provisions of relevant laws and regulations, necessary confidentiality measures have been taken, and there is no violation of public order and good morals.

[0064] This disclosure provides a method for recommending equipment operation strategies, comprising: inputting time-series information of the operational value of a target device within a historical period into an initial stochastic process model, outputting a first parameter and a first function corresponding to the first parameter, wherein the first function characterizes the correlation between the operational value of the device and time; modifying the first function according to time-series information of factors influencing the operational value of the target device within a historical period to obtain a second function; inputting the target time for which operational value prediction is to be performed into the second function, outputting candidate information for equipment operational value prediction; performing a model transformation on the initial stochastic process model using the second function to obtain a target stochastic process model; inputting the time-series information of operational value into the target stochastic process model, outputting a second parameter and a third function corresponding to the second parameter; and recommending an operation strategy for the target device based on the candidate information for equipment operational value prediction when the third function satisfies a first preset condition.

[0065] Figure 1 The diagram illustrates an application scenario recommended by the device operation strategy according to an embodiment of the present disclosure.

[0066] like Figure 1 As shown, application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0067] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, such as sending device operation strategy recommendation requests to the server. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (this is just an example).

[0068] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0069] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or determined according to user requests) to the terminal devices.

[0070] It should be noted that the device operation strategy recommendation method provided in this embodiment can generally be executed by server 105. Correspondingly, the device operation strategy recommendation device provided in this embodiment can generally be located in server 105. The device operation strategy recommendation method provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the device operation strategy recommendation device provided in this embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0071] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0072] The following will be based on Figure 1 The described scene, through Figures 2-6 The method for recommending equipment operation strategies according to the disclosed embodiments is described in detail.

[0073] Figure 2 A flowchart illustrating a device operation strategy recommendation method according to an embodiment of the present disclosure is shown schematically.

[0074] like Figure 2 As shown, the equipment operation strategy recommendation method in this embodiment includes operations S210 to S240.

[0075] In operation S210, the time-series information of the operational value of the target equipment within the historical period is input into the initial stochastic process model, and the first parameter and the first function corresponding to the first parameter are output. The first function represents the correlation between the operational value of the equipment and time.

[0076] According to embodiments of this disclosure, operational value can characterize the residual value that a target device is expected to recover during its service life, also known as residual value. The operational value time-series information Xt can be obtained from the maintenance records of the target device over a historical period. The operational value time-series information may include the initial operational value information of the target device before it is used, the operational value information of the target device after its first maintenance in year t / day / month, and the operational value information of the target device after its nth maintenance in year k / day / month. For example, the historical period can be 100 days, the initial operational value of the target device M is X0, and the operational value information of the target device after its first maintenance on day 35 can be Xt. 35 The operational value information of the target equipment after its second maintenance on day 80 can be X. 80 .

[0077] According to embodiments of this disclosure, the initial stochastic process model can be a standard OU process function (Ornstein-Uhlenbeck process):

[0078] dλ=c(k-λ)t+σdWt (1)

[0079] Where λ=X t The function represents the operational value over time; c and k represent parameters; t represents the usage time of the target equipment; and σdWt represents the random fluctuation value.

[0080] For example: The operational value time-series information (X0, X...) of the target equipment... 35 X 80 By inputting the above OU process function, the differential equation can be used to approximate the solution by substituting the above operational value time series information into equation (1) to obtain the first parameters c0 and k0. Then, the first parameters c0 and k0 can be substituted into equation (2) for iterative calculation to obtain the first function.

[0081] X t+1 -X t =c0(k0-X) t )t+σW t (2)

[0082] In operation S220, the first function is modified based on the time series information of the factors affecting the operational value of the target equipment in the historical period to obtain the second function; the target time for which operational value prediction is to be performed is input into the second function, and candidate information for equipment operational value prediction is output.

[0083] According to embodiments of this disclosure, operational value influencing factors may include equipment operating environment information, such as equipment operating temperature information, equipment operating humidity information, etc. They may also include equipment operation and maintenance cost information, such as water and electricity costs, repair costs, etc. All of the above operational value influencing factors are time-related factors, and the time-series information of these operational value influencing factors can be used to modify the first function.

[0084] According to embodiments of this disclosure, the target device's operating environment information and operation and maintenance cost information over a historical period can be used as time-series data with multiple dimensions. Each dimension can represent an influencing factor, and the time-series data of each influencing factor can be a scatter plot of time data. The higher the prediction accuracy of the second function, the more time-series data of each influencing factor is added. The time-series data of each influencing factor can be used as a function with time as the independent variable. For example, the time-series information of the device's operating temperature can be C1(t), the time-series information of the device's operating humidity can be C2(t), the time-series information of the device's operation and maintenance costs can be C3(t), and so on.

[0085] According to an embodiment of this disclosure, the first function is modified using the time-series information of the factors influencing operational value, and the second function is obtained as shown in equation (3).

[0086] X t =m1 C1(t)+m2C2(t)+...+m3C3(t) (3)

[0087] According to the embodiments of this disclosure, the target time for the proposed operational value prediction can be T. Substituting the target time T into the above equation (3) yields the candidate information X for equipment operational value prediction. T .

[0088] Since the curve shape of the modified second function differs somewhat from that of the initial first function, it is necessary to verify the goodness of fit of the second function again using the time series information of operating value. Traditionally, goodness-of-fit verification involves fitting data to data. However, this method is not suitable for the random fluctuation of equipment operating value over time. Therefore, this disclosure fits the function of equipment operating value versus time using a function of the factors influencing equipment operating value, ensuring that the resulting fitted function guarantees a slow decline in equipment operating value over time and exhibits the properties of a stochastic process and a Markov process.

[0089] In operation S230, the initial stochastic process model is transformed using the second function to obtain the target stochastic process model; the operational value time series information is input into the target stochastic process model, and the second parameter and the third function corresponding to the second parameter are output.

[0090] According to an embodiment of this disclosure, the initial stochastic process model is transformed using a second function. This can be achieved by substituting equation (3) into equation (1) to obtain equation (4), thus obtaining the target stochastic process model. Operational value time-series information is input into the target stochastic process model, and a second parameter and a third function corresponding to the second parameter are output.

[0091] d(mlC1(t)+...+mnCn(t))=c(k-(mlC1(t)+...+mnCn(t)))t+σdWt (4)

[0092] Where m1, ..., mn represent the weights of the factors influencing the overall operational value of the target equipment; c and k represent parameters; t represents the usage time of the target equipment; and σdWt represents the random fluctuation value.

[0093] For example: The operational value time-series information (X0, X...) of the target equipment... 35 X 80 The OU process function of the input target stochastic process can be approximated by substituting the above operational value time series information into equation (4) using differential equations to obtain the first parameters c1 and k1. The first parameters c1 and k1 are then substituted into equation (2) for iterative calculation to obtain the third function.

[0094] In operation S240, if the third function meets the first preset condition, an operation strategy for the target equipment is recommended based on the equipment operation value prediction candidate information.

[0095] According to an embodiment of this disclosure, the first preset condition can be the neighborhood formed by the curve of the third function passing through the points representing the time-series information of operational value and the points representing the candidate information of the equipment operational value at the target time.

[0096] For example, the points representing the time-series information of operational value can be (0, X0), (35, X...). 35 (80, X) 80 The points representing candidate information of equipment operational value at the target time can be (T, X). T The neighborhood can be represented by a threshold range, for example, it can be the function value Y obtained at t=35 in the curve of the third function when ΔX=20. 35 X in the operational value time series information 35 The difference is less than 20, and so on, for the other points mentioned above, the corresponding Y... 80 Y T With the corresponding X 80 X T If the difference between the values ​​is less than 20, it means that the third function satisfies the first preset condition.

[0097] According to embodiments of this disclosure, an operational strategy for a target device is recommended based on candidate device operation value prediction information. For example, the target time period could be 1080 days, and the corresponding candidate device operation value prediction information could be X. 1080 Based on the candidate information of the equipment's operational value at the current time, an operational strategy can be recommended for the target equipment. For example, if the equipment's operational value at the target time is less than 10% of its initial value, the recommended operational strategy is to scrap it without further maintenance. If the equipment's operational value at the target time is high, the recommended operational strategy is to maintain the target equipment.

[0098] According to embodiments of this disclosure, since the operational value influencing factors used in modifying the first function may include operating costs and maintenance expenses, the operating costs, maintenance expenses, operating environment, and other information of the target equipment can also be obtained from the second function, thereby comprehensively recommending an operational strategy for the target equipment.

[0099] According to embodiments of this disclosure, by inputting the time-series information of the operational value of the target equipment over a historical period into an initial stochastic process model, a first function characterizing the operational value of the equipment over time is obtained using the initial stochastic process model. Since the first function is modified using the time-series information of factors influencing operational value, and the modified function is used to transform the initial stochastic process model, a third function that accurately reflects the change in operational value of the equipment over time is objectively fitted based on the actual time-series data of the equipment's operational value and the actual time-series information of factors influencing operational value. Based on the candidate information predicting the operational value of the target equipment at the target time, an operational strategy for the target equipment is recommended. Therefore, this at least partially solves the problem in related technologies where reliance on subjective human experience leads to certain lags and omissions in operational strategies, achieving the technical effect of accurately recommending operational strategies for the entire lifecycle of the target equipment.

[0100] According to embodiments of this disclosure, operational value time-series information is input into an initial stochastic process model, and a first parameter and a first function corresponding to the first parameter are output, including:

[0101] The operational value time series information is input into the initial stochastic process model, and the first parameter is calculated using the differential equation of the initial process function;

[0102] The first parameter and the operational value time series information are input into the initial process function, and iterative calculations are performed to obtain the first function.

[0103] According to embodiments of this disclosure, for example, the operational value time-series information may include: the initial operational value X0 of the target equipment at t=0, and the operational value X after the first maintenance at the end of the second year of use. 730The operating value of the target equipment when it is sold at the end of year 10 is X. 3650 The initial process function is shown in equation (1). By substituting the initial process function into the equation using the differential method, c0 and k0 are approximated. Since the initial operating value of the target equipment is known, the initial operating value X0 can be substituted into equation (2) for iterative calculation. The iterative calculation process is as follows:

[0104] X2-X1=c0(k0-X1)×1+σW1;

[0105] X3-X2=c0(k0-X2)×2+σW2;

[0106] …

[0107] X t+1 -X t =c0(k0-X) t )×t+σW t ;

[0108] Among them, W1, W2, ... W t The variables representing the Wiener process, whose increments within each time interval follow a Gaussian distribution, are σW1, σW2, ..., σW t These are fluctuation values ​​automatically generated through a random normal distribution.

[0109] According to embodiments of this disclosure, by utilizing the time-series information of equipment operating value through a preliminary stochastic process model and undergoing the aforementioned iterative calculations, a first function can be obtained. This enables the fitting of a function relating equipment operating value and time using relatively little basic data, thus solving the problem in related technologies where the accuracy of recommended equipment operating schemes is low due to the small amount of operating data for the target equipment.

[0110] Figure 3 A flowchart illustrating a method for modifying a first function according to an embodiment of the present disclosure is shown.

[0111] like Figure 3 As shown, the method for modifying the first function in this embodiment includes operations S310 to S320.

[0112] In operation S310, the first prediction deviation is determined based on the actual operating value information of the equipment at time i and the first predicted operating value information of the equipment at time i.

[0113] According to embodiments of this disclosure, the operational value time-series information includes actual operational value information of the equipment at m time points, which can be X1, X2, X... i ...X m The actual operational value of the equipment at time i can be X. iThe first equipment operating value prediction information is obtained by inputting the i-th time step into the first function, which can be X. i’ The first deviation can be X. i With X i’ difference.

[0114] In operation S320, if the first prediction deviation between the actual operating value information of the equipment at m time points and the predicted operating value information of the equipment at m time points meets the first preset threshold, the first function and the time series information of the operating value influencing factors are input into the generalized linear model to perform multiple regression analysis and output the second function, where m and i are positive integers, and 1≤i≤m.

[0115] According to embodiments of this disclosure, for example, if the first prediction deviation is 10 and the first preset threshold is 20, then the first prediction deviation is less than the first preset threshold. The first preset threshold can be a single value or a range of thresholds. When the first preset deviation is within the preset threshold range, the first function and the time-series information of the operational value influencing factors can be input into a generalized linear model for multiple regression analysis, outputting a second function. Using a generalized linear model to perform multiple regression analysis on time-series data is a relatively mature technology and will not be elaborated upon here.

[0116] According to the embodiments of this disclosure, since the factors affecting operational value are all time-series data, regression analysis of multivariate time series is used to establish the correlation between operational value factors and time functions and operational value and time functions, with time as the bridge. This achieves the purpose of fitting functions with functions and solves the problem of subjectivity defects in related technologies that rely on expert experience to manually construct models.

[0117] If the first prediction deviation does not meet the first preset threshold, it means that the fit of the first function obtained by the current fitting does not meet the fluctuation of the actual operating value of the equipment over time, so the first parameter needs to be adjusted.

[0118] According to embodiments of this disclosure, the above-mentioned equipment operation strategy recommendation method further includes:

[0119] Based on the first parameter being within a preset adjustment range, k sets of third parameters are randomly determined;

[0120] Based on the k sets of third parameters, determine k first functions, where k is a positive integer greater than 1.

[0121] According to embodiments of this disclosure, for example, the first parameter (c0, k0) can have a preset adjustment range of [c0-Δc, c0+Δc], [k0-Δk, k0+Δk]. K sets of third parameters can be randomly determined from the aforementioned preset adjustment range. Since subsequent processes continuously consume data, k can be on the order of hundreds of thousands or more.

[0122] According to embodiments of this disclosure, for example, the k groups of third parameters can be (c1, k1), (c2, k2), ..., (c k k k Substituting the third parameter into equation (2), the first function corresponding to each set of third parameters can be obtained through iterative calculation. The iterative calculation process is the same as described above and will not be repeated here.

[0123] According to embodiments of this disclosure, by adjusting parameters within a preset adjustment range, multiple first functions that can be used for generalized linear verification are obtained. This can be applied to models that have a high degree of fit with the actual value fluctuations of equipment operation, even when there is limited basic data on the operation of the target equipment.

[0124] According to embodiments of this disclosure, a first prediction deviation is determined based on the actual operating value information of the equipment at time i and the first predicted operating value information of the equipment at time i, including:

[0125] The first prediction deviation value is determined based on the difference between the actual operating value information of the equipment at time i and the predicted operating value information of the first equipment at time i.

[0126] The first prediction deviation is determined based on the percentage of the first prediction deviation value and the actual operating value information of the equipment at time i.

[0127] According to embodiments of this disclosure, the operational value time-series information includes actual operational value information of the equipment at m time points, which can be X1, X2, X... i ...X m The actual operational value of the equipment at time i can be X. i The first equipment operating value prediction information is obtained by inputting the i-th time step into the first function, which can be X. i’ The first prediction deviation can be X. i With X i’ The difference ΔX i .

[0128] According to embodiments of this disclosure, the first prediction deviation can be a first prediction deviation value ΔX. i Information X of the actual operational value of the equipment at time i i Percentage: ΔX i / X i .

[0129] According to embodiments of this disclosure, by using the time-series information of operational value to verify the fit of the fitted first function with a first preset deviation, the fluctuation of equipment operational value represented by the first function over time can be made more consistent with the actual fluctuation of equipment operational value over time, thereby improving the accuracy of equipment operation strategy recommendations.

[0130] According to embodiments of this disclosure, operational value time-series information is input into a target stochastic process model, and a second parameter and a third function corresponding to the second parameter are output, including:

[0131] The operational value time series information is input into the target stochastic process model, and the second parameter is calculated using the differential equation of the target process function;

[0132] The second parameter and the operational value time series information are input into the target process function for iterative calculation to obtain the third function.

[0133] According to embodiments of this disclosure, for example, the operational value time-series information may include: the initial operational value X0 of the target equipment at t=0, and the operational value X after the first maintenance at the end of the second year of use. 730 The operating value of the target equipment when it is sold at the end of year 10 is X. 3650 The initial process function is shown in equation (4). By substituting the initial process function into the equation using the differential method, c1 and k1 are obtained. Since the initial operating value of the target equipment is known, the initial operating value X0 can be substituted into equation (2) for iterative calculation. The iterative calculation process is the same as described above and will not be repeated here.

[0134] According to embodiments of this disclosure, through multiple linear regression analysis, the time-series information of each influencing factor has been transformed into a function with time as the independent variable, and the weight information of each influencing factor is a known quantity.

[0135] According to embodiments of this disclosure, by modifying the second function after adjusting for factors affecting equipment operating value, and verifying its goodness of fit using time-series information on operating value, the fluctuation of equipment operating value over time in the resulting third function will better reflect the actual fluctuation of equipment operating value over time, thereby improving the accuracy of recommending equipment operating strategies for the target equipment.

[0136] Figure 4 A flowchart illustrating a process for recommending an operational strategy for a target device based on device operational value prediction candidate information is shown in accordance with an embodiment of the present disclosure.

[0137] like Figure 4 As shown, this embodiment includes operations S410 to S430.

[0138] In operation S410, the second prediction deviation is determined based on the actual operating value information of the equipment at time i and the second equipment operating value prediction information at time i. The second equipment operating value prediction information is obtained by inputting the third function at time i.

[0139] According to embodiments of this disclosure, the actual operational value of the device at time i can be X. i The second piece of equipment's operational value prediction information can be used for X i” The second prediction deviation can be X. i” With X i The difference.

[0140] In operation S420, the third prediction deviation is determined based on the equipment prediction candidate information and the third equipment operation value prediction information at the target time. The third equipment operation value prediction information is obtained by inputting the target time into the third function.

[0141] According to embodiments of this disclosure, the device prediction candidate information for the target device can be X. T The third equipment operation value prediction information can be used for X T’ The third prediction deviation can be X. T’ With X T The difference.

[0142] In operation S430, if the second prediction deviation between the actual operating value information of the equipment at m time points and the predicted operating value information of the equipment at m time points and the third prediction deviation at the target time satisfy the second preset threshold, an operating strategy for the target equipment is recommended based on the candidate information for predicting the operating value of the equipment, where m and i are positive integers, and 1≤i≤m.

[0143] According to embodiments of this disclosure, the second preset threshold can be a single value or a threshold range. For example, if the second preset threshold is 20, the second prediction deviation is 10, and the third prediction deviation is 15, then both the second and third prediction deviations are less than the second preset threshold. This indicates that the fluctuation of equipment operating value and time represented by the current third function matches the actual fluctuation of equipment operating value and time. Therefore, an operating strategy for the target equipment can be recommended based on the current equipment operating value prediction candidate information.

[0144] According to embodiments of this disclosure, the fluctuation of equipment operating value and time represented by the third function can also be reflected by the probability of equipment operating value, so that the target equipment can be targeted to obtain the operating strategy at the target time, such as the probability of the target equipment being repaired after 200 days, etc.

[0145] According to embodiments of this disclosure, by utilizing equipment operation value time-series information and equipment operation value prediction information at the target time to verify the third function, new data that can be used to verify the third function can be continuously generated in each application process, thereby achieving the goal of continuously improving recommendation accuracy in application.

[0146] According to embodiments of this disclosure, determining a second prediction deviation based on the actual operating value information of the equipment at time i and the second predicted operating value information of the equipment at time i includes:

[0147] The second prediction deviation value is determined based on the difference between the actual operating value information of the equipment at time i and the predicted operating value information of the second equipment at time i.

[0148] The second prediction deviation is determined based on the second prediction deviation value and the actual operating value information of the equipment at time i.

[0149] According to embodiments of this disclosure, for example, the operational value time-series information includes actual operational value information of the equipment at m time points, which can be X1, X2, X... i ...X m The actual operational value of the equipment at time i can be X. i The second piece of equipment's operational value prediction information is obtained by inputting the i-th time step into the third function, and can be represented as X. i” The second prediction deviation can be X. i With X i” The difference ΔX i '.

[0150] According to embodiments of this disclosure, the second prediction deviation can be a percentage of the second prediction deviation value and the actual operating value information of the device at time i: ΔX i’ / X i .

[0151] According to embodiments of this disclosure, a third prediction deviation is determined based on candidate equipment prediction information at a target time and third equipment operating value prediction information, including:

[0152] The third prediction deviation value is determined based on the difference between the candidate equipment prediction information and the third equipment operation value prediction information at the target time.

[0153] The third prediction deviation is determined based on the third prediction deviation value and the equipment prediction candidate information at the target time.

[0154] According to embodiments of this disclosure, for example: the predicted candidate operational value of the equipment at a target time can be X. T The third equipment operation value prediction information is obtained by inputting the target time T into the third function, which can be X. T’The third prediction deviation can be X. T With X T’ The difference ΔX T .

[0155] According to embodiments of this disclosure, the third prediction deviation can be a third prediction deviation value and a percentage of the predicted candidate operational value of the device at the target time T: ΔX T / X T .

[0156] According to embodiments of this disclosure, by utilizing the time-series information of equipment operation value and the third function obtained by fitting the candidate equipment operation value verification of the target time, the fluctuation of equipment operation value represented by the third function over time can be made more consistent with reality, thereby improving the accuracy of the recommended equipment operation strategy.

[0157] Because numerous factors influence the operational value of equipment, some factors obtained from equipment operation and maintenance records may not exhibit regular fluctuations over time, or may have a relatively small impact on the fluctuations in operational value over time. The presence of these factors can actually affect the accuracy of the final recommendation results.

[0158] In view of this, the above-mentioned recommended methods for equipment operation strategies also include:

[0159] The time-series information of factors influencing operational value includes the time-series information of n factors influencing operational value. For the time-series information of the j-th factor influencing operational value, we examine the correlation between the time-series information of the j-th factor influencing operational value and the operational value of the equipment.

[0160] If the correlation between the time series information of the j-th operational value influencing factor and the equipment operational value meets the third preset condition, the time series information of the j-th operational value influencing factor is determined as the input information of the generalized linear model, where n is a positive integer greater than 1, and 1≤j≤m, and j is a positive integer.

[0161] According to embodiments of this disclosure, the third preset condition can be a threshold range of correlation. The Analytic Hierarchy Process (AHP) can be used to test the correlation between the time series information of the j-th operational value influencing factor and the operational value of the equipment. If the correlation meets the threshold range, it can be used as input information for the generalized linear model to correct the first function. This can effectively avoid the problem of low accuracy of the final recommendation result due to the introduction of too many interference factors.

[0162] For example, the time-series information of equipment operating temperature, tested using the analytic hierarchy process (AHP), shows a correlation of 10 with the equipment's operational value. Similarly, the time-series information of equipment maintenance costs, tested using the AHP, shows a correlation of 15 with the equipment's operational value. The preset threshold for this correlation can be 5. Therefore, both the time-series information of equipment operating temperature and equipment maintenance costs have a significant impact on the equipment's operational value and can be used as input information for a generalized linear model.

[0163] According to embodiments of this disclosure, by examining the factors influencing the operational value of equipment, and if the correlation meets the threshold range, these factors are then used as input information for a generalized linear model to correct the first function. This effectively avoids the problem of introducing too many interfering factors that lead to low accuracy of the final recommendation results.

[0164] Based on the above-described equipment operation strategy recommendation method, this disclosure also provides an equipment operation strategy recommendation device. The following will be combined with... Figure 5 The device is described in detail.

[0165] Figure 5 A schematic block diagram of a device for recommending equipment operation strategies according to an embodiment of the present disclosure is shown.

[0166] like Figure 5 As shown, the equipment operation strategy recommendation device 500 of this embodiment includes a first fitting module 510, a correction module 520, a second fitting module 530, and a recommendation module 540.

[0167] The first fitting module 510 is used to input the time-series information of the operational value of the target equipment within a historical period into an initial stochastic process model, and output a first parameter and a first function corresponding to the first parameter. The first function characterizes the correlation between the operational value of the equipment and time. In one embodiment, the first fitting module 510 can be used to perform the operation S210 described above, which will not be repeated here.

[0168] The correction module 520 is used to correct the first function based on the time-series information of the factors influencing the operational value of the target equipment in the historical period, thereby obtaining a second function; the target time for which operational value prediction is to be performed is input into the second function, and candidate information for equipment operational value prediction is output. In one embodiment, the correction module 520 can be used to perform the operation S220 described above, which will not be repeated here.

[0169] The second fitting module 530 is used to transform the initial stochastic process model using the second function to obtain the target stochastic process model; it inputs the operational value time series information into the target stochastic process model and outputs the second parameter and the third function corresponding to the second parameter. In one embodiment, the second fitting module 530 can be used to perform the operation S230 described above, which will not be repeated here.

[0170] The recommendation module 540 is used to recommend an operational strategy for the target device based on the device operational value prediction candidate information, provided that the third function meets the first preset condition. In one embodiment, the recommendation module 540 can be used to perform the operation S240 described above, which will not be repeated here.

[0171] According to embodiments of this disclosure, the correction module includes a first determining unit and a first output unit. The first determining unit is used to determine a first prediction deviation based on the actual operating value information of the equipment at time i and the first predicted operating value information of the equipment at time i. The first output unit is used to, when the first prediction deviation between the actual operating value information of the equipment at time m and the predicted operating value information at time m satisfies a first preset threshold, input the time-series information of the first function and the influencing factors of operating value into a generalized linear model, perform multiple regression analysis, and output a second function, where m is a positive integer, 1 ≤ i ≤ m.

[0172] According to embodiments of this disclosure, the first determining unit includes a first determining subunit and a second determining subunit. The first determining subunit is configured to determine a first prediction deviation value based on the difference between the actual operating value information of the equipment at time i and the first predicted operating value information of the equipment at time i. The second determining subunit is configured to determine a first prediction deviation degree based on the percentage of the first prediction deviation value to the actual operating value information of the equipment at time i.

[0173] According to embodiments of this disclosure, the recommendation module includes a second output unit, a second determination unit, a third output unit, a third determination unit, and a recommendation unit. The second output unit is used to input the i-th time moment into a third function and output second equipment operation value prediction information corresponding to the i-th time moment. The second determination unit is used to determine a second prediction deviation based on the actual equipment operation value information at the i-th time moment and the second equipment operation value prediction information at the i-th time moment. The third output unit is used to input the target time moment into the third function and output third equipment operation value prediction information corresponding to the target time moment. The third determination unit is used to determine a third prediction deviation based on the equipment prediction candidate information at the target time and the third equipment operation value prediction information. The recommendation unit is used to recommend an operation strategy for the target equipment based on the equipment operation value prediction candidate information when the second prediction deviation between the actual equipment operation value information at m times and the equipment operation value prediction information at m times, and the third prediction deviation at the target time, satisfy a second preset threshold, where m is a positive integer, 1 ≤ i ≤ m.

[0174] According to embodiments of this disclosure, the second determining unit includes a third determining subunit and a fourth determining subunit. The third determining subunit is configured to determine a second prediction deviation value based on the difference between the actual operating value information of the equipment at time i and the second predicted operating value information of the equipment at time i. The fourth determining subunit is configured to determine a second prediction deviation degree based on the second prediction deviation value and the actual operating value information of the equipment at time i.

[0175] According to embodiments of this disclosure, the third determining unit includes a fifth determining subunit and a sixth determining subunit. The fifth determining subunit is used to determine a third prediction deviation value based on the difference between the equipment prediction candidate information at the target time and the third equipment operating value prediction information. The sixth determining subunit is used to determine a third prediction deviation degree based on the third prediction deviation value and the equipment prediction candidate information at the target time.

[0176] According to embodiments of this disclosure, the above-mentioned equipment operation strategy recommendation device further includes a verification module and a first determination module. The verification module is used to verify the correlation between the time-series information of the j-th operational value influencing factor and the equipment operational value. The first determination module is used to determine the time-series information of the j-th operational value influencing factor as the input information of the generalized linear model when the correlation between the time-series information of the j-th operational value influencing factor and the equipment operational value meets a third preset condition, where n is a positive integer greater than 1, and 1 ≤ j ≤ m.

[0177] According to embodiments of this disclosure, the above-mentioned equipment operation strategy recommendation device further includes a second determining module and a third determining module. The second determining module is used to randomly determine k sets of third parameters within a preset adjustment range based on the first parameters. The third determining module is used to determine k first functions based on the k sets of third parameters, where k is a positive integer greater than 1.

[0178] According to embodiments of this disclosure, the first fitting module includes a first calculation unit and a second calculation unit. The first calculation unit is used to input operational value time-series information into an initial stochastic process model and calculate first parameters using the differential equation of the initial process function. The second calculation unit is used to input the first parameters and operational value time-series information into the initial process function and perform iterative calculations to obtain a first function.

[0179] According to embodiments of this disclosure, the second fitting module includes a third calculation unit and a fourth calculation unit. The third calculation unit is used to input operational value time-series information into the target stochastic process model and calculate the second parameter using the differential equation of the target process function. The fourth calculation unit is used to input the second parameter and operational value time-series information into the target process function and perform iterative calculation to obtain the third function.

[0180] According to embodiments of this disclosure, any plurality of modules among the first fitting module 510, correction module 520, second fitting module 530, and recommendation module 540 may be combined into one module, or any one of these modules may be split into multiple modules. Alternatively, at least a portion of the functionality of one or more of these modules may be combined with at least a portion of the functionality of other modules and implemented in one module. According to embodiments of this disclosure, at least one of the first fitting module 510, correction module 520, second fitting module 530, and recommendation module 540 may be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging the circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, at least one of the first fitting module 510, the correction module 520, the second fitting module 530, and the recommendation module 540 may be implemented at least partially as a computer program module, which can perform corresponding functions when the computer program module is run.

[0181] Figure 6 A block diagram of an electronic device suitable for implementing a device operation strategy recommendation method according to an embodiment of the present disclosure is illustrated schematically.

[0182] like Figure 6 As shown, an electronic device 600 according to an embodiment of this disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage portion 608 into a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this disclosure.

[0183] RAM 603 stores various programs and data required for the operation of electronic device 600. Processor 601, ROM 602, and RAM 603 are interconnected via bus 604. Processor 601 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 602 and / or RAM 603. It should be noted that the programs may also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0184] According to embodiments of this disclosure, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to a bus 604. The electronic device 600 may also include one or more of the following components connected to the I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 610 as needed so that computer programs read from it can be installed into the storage section 608 as needed.

[0185] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0186] According to embodiments of this disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this disclosure, the computer-readable storage medium may include ROM 602 and / or RAM 603 and / or one or more memories other than ROM 602 and RAM 603 described above.

[0187] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to cause the computer system to implement the item recommendation method provided in the embodiments of this disclosure.

[0188] When the computer program is executed by the processor 601, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0189] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and downloaded and installed via the communication section 609, and / or installed from the removable medium 611. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0190] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, it performs the functions defined in the system of this disclosure embodiment. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0191] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0192] 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 a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may 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.

[0193] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0194] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A method for recommending equipment operation strategies, comprising: The time-series information of the operational value of the target equipment within a historical period is input into an initial stochastic process model, and a first parameter and a first function corresponding to the first parameter are output. The first function characterizes the correlation between the operational value of the equipment and time. The time-series information of the operational value includes the actual operational value information of the equipment at m time points. The time-series information of the operational value is obtained from the maintenance records of the target equipment within a historical period. The operational value of the equipment is used to reflect the lifespan of the equipment. The first function is modified based on the time-series information of the factors influencing the operational value of the target equipment during the historical period to obtain the second function, which includes: Based on the actual operating value information of the equipment at time i and the first equipment operating value prediction information at time i, a first prediction deviation is determined, wherein the first equipment operating value prediction information is obtained by inputting the first function at time i. When the first prediction deviation between the actual operating value information of the equipment at m time points and the predicted operating value information of the equipment at m time points meets the first preset threshold, the first function and the time series information of the operating value influencing factors are input into the generalized linear model, and multiple regression analysis is performed to output the second function, where m and i are positive integers, 1≤i≤m, and the time series information of operating value includes the actual operating value information of the equipment at m time points. The target time for predicting the operational value is input into the second function, which outputs candidate information for predicting the operational value of the equipment. Among them, the factors affecting the operational value include equipment operating environment information and equipment operation and maintenance cost information. The initial stochastic process model is transformed using the second function to obtain the target stochastic process model; the operational value time series information is input into the target stochastic process model, and the second parameter and the third function corresponding to the second parameter are output, wherein the third function contains the weight of the impact of operational value influencing factors on the overall operational value of the target equipment; When the third function satisfies the first preset condition, an operational strategy for the target device is recommended based on the device operation value prediction candidate information, including: Based on the actual operating value information of the equipment at the i-th time and the second equipment operating value prediction information at the i-th time, a second prediction deviation is determined, wherein the second equipment operating value prediction information is obtained by inputting the i-th time into the third function; Based on the equipment prediction candidate information and the third equipment operation value prediction information at the target time, a third prediction deviation is determined, wherein the third equipment operation value prediction information is obtained by inputting the target time into the third function; If the second prediction deviation between the actual operating value information of the equipment at m time points and the predicted operating value information of the equipment at m time points and the third prediction deviation at the target time satisfy a second preset threshold, an operating strategy for the target equipment is recommended based on the candidate information for predicted operating value of the equipment. The operating strategy includes strategies for equipment scrapping or equipment maintenance.

2. The method according to claim 1, wherein, The step of determining the first prediction deviation based on the actual operating value information of the equipment at time i and the first predicted operating value information of the equipment at time i includes: The first prediction deviation value is determined based on the difference between the actual operating value information of the equipment at the i-th time and the predicted operating value information of the first equipment at the i-th time. The first prediction deviation is determined based on the percentage of the first prediction deviation value and the actual operating value information of the equipment at the i-th time point.

3. The method according to claim 1, wherein, The step of determining the second prediction deviation based on the actual operating value information of the equipment at the i-th time moment and the second predicted operating value information of the equipment at the i-th time moment includes: The second prediction deviation value is determined based on the difference between the actual operating value information of the equipment at the i-th time and the predicted operating value information of the second equipment at the i-th time. The second prediction deviation is determined based on the second prediction deviation value and the actual operating value information of the equipment at the i-th time point.

4. The method according to claim 1, wherein, The step of determining the third prediction deviation based on the equipment prediction candidate information at the target time and the third equipment operating value prediction information includes: The third prediction deviation value is determined based on the difference between the candidate equipment prediction information at the target time and the third equipment operation value prediction information. The third prediction deviation is determined based on the third prediction deviation value and the device prediction candidate information at the target time.

5. The method according to claim 1, wherein, The time-series information of the operational value influencing factors includes the time-series information of n operational value influencing factors, and also includes: For the time series information of the j-th operational value influencing factor, examine the correlation between the time series information of the j-th operational value influencing factor and the operational value of the equipment; If the correlation between the time series information of the j-th operational value influencing factor and the equipment operational value meets the third preset condition, the time series information of the j-th operational value influencing factor is determined as the input information of the generalized linear model, where n is a positive integer greater than 1, and 1≤j≤m, and j is a positive integer.

6. The method according to claim 1, further comprising: Based on the first parameter being within a preset adjustment range, k sets of third parameters are randomly determined; Based on the k sets of third parameters, determine k first functions, where k is a positive integer greater than 1.

7. The method according to claim 1, wherein, The step of inputting the operational value time-series information into an initial stochastic process model and outputting a first parameter and a first function corresponding to the first parameter includes: The operational value time series information is input into the initial stochastic process model, and the first parameter is calculated using the differential equation of the initial process function; The first parameter and the operational value time series information are input into the initial process function, and iterative calculations are performed to obtain the first function.

8. The method according to claim 1, wherein, The step of inputting the operational value time-series information into the target stochastic process model and outputting a second parameter and a third function corresponding to the second parameter includes: The operational value time series information is input into the target stochastic process model, and the second parameter is calculated using the differential equation of the target process function; The second parameter and the operational value time series information are input into the target process function for iterative calculation to obtain the third function.

9. A device for recommending equipment operation strategies, comprising: The first fitting module is used to input the time series information of the operational value of the target equipment in the historical period into the initial stochastic process model, and output the first parameter and the first function corresponding to the first parameter. The first function represents the correlation between the operational value of the equipment and time. The operational value time series information includes the actual operational value information of the equipment at m time points. The operational value time series information is obtained from the maintenance records of the target equipment in the historical period. The operational value of the equipment is used to reflect the life of the equipment. The correction module is used to correct the first function based on the time-series information of the factors affecting the operational value of the target equipment in the historical period, so as to obtain a second function; the target time for which operational value prediction is to be performed is input into the second function, and the candidate information for equipment operational value prediction is output; wherein, the factors affecting operational value include equipment operating environment information and equipment operation and maintenance cost information; The correction module includes a first determining unit and a first output unit; The first determining unit is used to determine the first prediction deviation based on the actual operating value information of the equipment at the i-th time and the first equipment operating value prediction information at the i-th time, wherein the first equipment operating value prediction information is obtained by inputting the i-th time into the first function; The first output unit is used to input the time series information of the first function and the operational value influencing factors into a generalized linear model, perform multiple regression analysis, and output a second function when the first prediction deviation between the actual operational value information of the equipment at m times and the predicted operational value information at m times meets a first preset threshold. Here, m and i are positive integers, 1≤i≤m, and the operational value time series information includes the actual operational value information of the equipment at m times. The second fitting module is used to transform the initial stochastic process model using the second function to obtain the target stochastic process model; input the operational value time series information into the target stochastic process model, and output the second parameter and the third function corresponding to the second parameter, wherein the third function contains the influence weight of operational value influencing factors on the overall operational value of the target equipment; The recommendation module is used to recommend an operation strategy for the target equipment based on the equipment operation value prediction candidate information when the third function satisfies the first preset condition. The operation strategy includes a strategy for equipment scrapping or equipment maintenance. The recommendation module includes a second determination unit, a third determination unit, and a recommendation unit. The second determining unit is used to determine a second prediction deviation based on the actual operating value information of the equipment at the i-th time and the second equipment operating value prediction information at the i-th time, wherein the second equipment operating value prediction information is obtained by inputting the i-th time into the third function; The third determining unit is used to determine the third prediction deviation based on the equipment prediction candidate information and the third equipment operation value prediction information at the target time, wherein the third equipment operation value prediction information is obtained by inputting the target time into the third function; The recommendation unit is used to recommend an operation strategy for the target device based on the device operation value prediction candidate information when the second prediction deviation between the actual operation value information of the device at m times and the predicted operation value information of the device at m times and the third prediction deviation at the target time meet a second preset threshold.

10. An electronic device, comprising: One or more processors; Storage device for storing one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors perform the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the method according to any one of claims 1 to 8.

12. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images