Method and device for determining steady-state parameters

Abstract

The invention discloses a steady-state parameter determination method and device, which are applied to the field of data processing, and the method comprises the steps: determining iteration variable information and dependent variable information under a target scene configured by a user, the iteration variable information comprises the name of an iteration variable and the initial value of the iteration variable, and the dependent variable information comprises the name of the iteration variable and the initial value of the iteration variable; the dependent variable information comprises a name of a dependent variable and a target value of the dependent variable, constructing a relation equation of the target scene according to the iterative variable information and the dependent variable information, and if a loss function of the relation equation reaches a minimum value, determining a current initial value of the iterative variable in the relation equation as a steady-state parameter, and if the loss function of the relation equation does not reach the minimum value, according to a preset initial value selection rule, re-determining the target initial value to iterate the relation equation until the loss function reaches the minimum value or the number of iterations reaches an iteration number threshold, and determining the corresponding target initial value as a steady-state parameter. Therefore, the steady-state parameter can be automatically determined, and the steady-state problem in the system is solved.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a method and device for determining steady-state parameters. Background Art

[0002] Steady-state balancing is often used to describe a system, especially a dynamic system, where various forces or variables reach a state of equilibrium and no longer change significantly over time. This concept has different applications in many fields, including physics, engineering, economics, etc.

[0003] A stable equilibrium state represents the stable behavior of a system over a long period of time and is critical for stable performance and evaluation. If a system has stability issues, simulation will not be able to find a solution, so steady-state issues should be solved first to ensure that the system can operate normally under all conditions. Summary of the invention

[0004] The present application provides a method for determining steady-state parameters to solve steady-state problems, and the present application also provides a device for determining steady-state parameters.

[0005] In a first aspect, the present application provides a method for determining a steady-state parameter, comprising:

[0006] Determine the iteration variable information and dependent variable information under the target scenario configured by the user, wherein the iteration variable information includes at least: the name of the iteration variable and the initial value of the iteration variable; the dependent variable information includes at least: the name of the dependent variable and the target value of the dependent variable;

[0007] Constructing a relational equation of a target scenario according to the iterative variable information and the dependent variable information;

[0008] If the loss function of the relational equation reaches a minimum value, determining the current initial value of the iterative variable in the relational equation as a steady-state parameter;

[0009] If the loss function of the relationship equation has not reached the minimum value, the target initial value is determined according to the preset initial value selection rule, and the relationship equation is iterated using the target initial value until the loss function reaches the minimum value or the number of iterations reaches the iteration number threshold, and the corresponding target initial value is determined as the steady-state parameter.

[0010] Optionally, the iteration variable information further includes a value range of the iteration variable, and the step of determining a target initial value according to a preset initial value selection rule, and iterating the relationship equation using the target initial value includes:

[0011] The target initial value is determined from the value interval of the iteration variable by means of a normally distributed random number, and the relationship equation is iterated by using the target initial value.

[0012] Optionally, determining a target initial value according to a preset initial value selection rule, and iterating the relationship equation using the target initial value includes:

[0013] A first multiple of the initial value is randomly selected as a target initial value and the relationship equation is iterated using the target initial value, wherein the first multiple is 0 to 10 times.

[0014] Optionally, when the number of iterations reaches a target number of times, determining a target initial value according to a preset initial value selection rule, and iterating the relationship equation using the target initial value includes:

[0015] Select the minimum initial value among multiple initial values ​​corresponding to multiple iterations;

[0016] Determine the minimum initial value of the second multiple as the target initial value and iterate the relationship equation using the target initial value, wherein the second multiple is less than 1;

[0017] or,

[0018] Select the maximum initial value among the multiple initial values ​​corresponding to the multiple iterations;

[0019] Determine the maximum initial value of the third multiple as the target initial value and iterate the relationship equation using the target initial value, wherein the third multiple is greater than 1;

[0020] or,

[0021] Select the maximum initial value and the minimum initial value from the multiple initial values ​​corresponding to the multiple iterations;

[0022] A target initial value is determined from the interval between the maximum initial value and the minimum initial value by using a binary search method, and the relational equation is iterated by using the target initial value.

[0023] Optionally, determining the corresponding target initial value as a steady-state parameter includes:

[0024] According to a preset verification rule, verifying the target initial value corresponding to when the loss function reaches a minimum value or the number of iterations reaches an iteration number threshold;

[0025] When the verification rules are met, the corresponding target initial value is determined as the steady-state parameter.

[0026] Optionally, the method further includes:

[0027] Presenting a parameter configuration interface, the parameter configuration interface including a scene selection option, an iteration variable information column, and a dependent variable information column;

[0028] The step of determining the iteration variable information and dependent variable information in the target scenario configured by the user includes:

[0029] The target scene is determined according to the user's selection operation on the scene selection option, and the iteration variable information and the dependent variable information under the target scene are determined according to the information input by the user in the iteration variable information column and the dependent variable information column.

[0030] Optionally, the method further includes:

[0031] Display the determined steady-state parameters and the number of iterations used to determine the steady-state parameters;

[0032] Generate code files and store the process of determining steady-state parameters

[0033] In a second aspect, the present application further provides a device for determining a steady-state parameter, the device comprising:

[0034] A first determining unit is used to determine iterative variable information and dependent variable information in a target scenario configured by a user, wherein the iterative variable information at least includes: a name of the iterative variable and an initial value of the iterative variable; and the dependent variable information at least includes: a name of the dependent variable and a target value of the dependent variable;

[0035] A construction unit, used to construct a relational equation of a target scenario according to the iterative variable information and the dependent variable information;

[0036] A second determining unit is used to determine the current initial value of the iterative variable in the relational equation as a steady-state parameter if the loss function of the relational equation reaches a minimum value;

[0037] The third determination unit is used to determine the target initial value according to a preset initial value selection rule if the loss function of the relationship equation has not reached the minimum value, and to iterate the relationship equation using the target initial value until the loss function reaches the minimum value or the number of iterations reaches an iteration number threshold, and to determine the corresponding target initial value as a steady-state parameter.

[0038] Optionally, the iteration variable information further includes a value range of the iteration variable, and the third determination unit is specifically configured to:

[0039] The target initial value is determined from the value interval of the iteration variable by means of a normally distributed random number, and the relationship equation is iterated by using the target initial value.

[0040] Optionally, the third determining unit is specifically configured to:

[0041] A first multiple of the initial value is randomly selected as a target initial value and the relationship equation is iterated using the target initial value, wherein the first multiple is 0 to 10 times.

[0042] Optionally, when the number of iterations reaches the target number, the third determining unit is specifically configured to:

[0043] Select the minimum initial value among multiple initial values ​​corresponding to multiple iterations;

[0044] Determine the minimum initial value of the second multiple as the target initial value and iterate the relationship equation using the target initial value, wherein the second multiple is less than 1;

[0045] or,

[0046] Select the maximum initial value among the multiple initial values ​​corresponding to the multiple iterations;

[0047] Determine the maximum initial value of the third multiple as the target initial value and iterate the relationship equation using the target initial value, wherein the third multiple is greater than 1;

[0048] or,

[0049] Select the maximum initial value and the minimum initial value from the multiple initial values ​​corresponding to the multiple iterations;

[0050] A target initial value is determined from the interval between the maximum initial value and the minimum initial value by using a binary search method, and the relational equation is iterated by using the target initial value.

[0051] Optionally, the third determining unit is specifically configured to:

[0052] According to a preset verification rule, verifying the target initial value corresponding to when the loss function reaches a minimum value or the number of iterations reaches an iteration number threshold;

[0053] When the verification rules are met, the corresponding target initial value is determined as the steady-state parameter.

[0054] Optionally, the device further comprises:

[0055] A presentation unit, used to present a parameter configuration interface, wherein the parameter configuration interface includes a scene selection option, an iteration variable information column, and a dependent variable information column;

[0056] The first determining unit is specifically configured to:

[0057] The target scene is determined according to the user's selection operation on the scene selection option, and the iteration variable information and the dependent variable information under the target scene are determined according to the information input by the user in the iteration variable information column and the dependent variable information column.

[0058] Optionally, the device further comprises:

[0059] A display unit, used for displaying the determined steady-state parameters and the number of iterations for determining the steady-state parameters;

[0060] The fourth determining unit is used to generate a code file for the process of determining the steady-state parameters and store the code file.

[0061] In a third aspect, an embodiment of the present application provides a device, comprising a memory and a processor, wherein the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the device executes any method described in the first aspect.

[0062] In a fourth aspect, an embodiment of the present application provides a computer storage medium, in which a code is stored. When the code is executed, a device executing the code implements the method described in any one of the first aspects above.

[0063] Compared with the prior art, this application has the following beneficial effects:

[0064] In the present application, the iterative variable information and dependent variable information under the target scenario configured by the user are determined, wherein the iterative variable information at least includes: the name of the iterative variable and the initial value of the iterative variable, and the dependent variable information at least includes: the name of the dependent variable and the target value of the dependent variable. The relational equation of the target scenario is constructed according to the iterative variable information and the dependent variable information. If the loss function of the relational equation reaches the minimum value, the current initial value of the iterative variable in the relational equation is determined to be a steady-state parameter. If the loss function of the relational equation does not reach the minimum value, the target initial value is determined according to the preset initial value selection rule, and the relational equation is iterated using the target initial value until the loss function reaches the minimum value or the number of iterations reaches the iteration number threshold, and the corresponding target initial value is determined to be a steady-state parameter. In other words, if the loss function of the relational equation does not reach the minimum value, the target initial value is reselected for iteration until the loss function reaches the minimum value or the number of iterations reaches the iteration number threshold, so that the steady-state parameters can be automatically determined, thereby solving the steady-state problem in the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions in this embodiment or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0066] Figure 1 A flow chart of a method for determining steady-state parameters provided in an embodiment of the present application;

[0067] Figure 2 A schematic diagram of a parameter configuration interface provided in an embodiment of the present application;

[0068] Figure 3 A schematic diagram of a display interface provided in an embodiment of the present application;

[0069] Figure 4 A schematic diagram of a file storage interface provided in an embodiment of the present application;

[0070] Figure 5 A schematic structural diagram of a specific implementation of a device for determining steady-state parameters provided in an embodiment of the present application. DETAILED DESCRIPTION

[0071] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0072] It should be noted that the method and device for determining steady-state parameters provided by the present application are used in the field of data processing technology. The above is only an example and does not limit the application field of the method and device provided by the present application.

[0073] Steady-state balancing is often used to describe a system, especially a dynamic system, where various forces or variables reach a state of equilibrium and no longer change significantly over time. This concept has different applications in many fields, including physics, engineering, economics, etc.

[0074] A stable equilibrium state represents the stable behavior of a system over a long period of time and is critical for stable performance and evaluation. If a system has stability issues, simulation will not be able to find a solution, so steady-state issues should be solved first to ensure that the system can operate normally under all conditions.

[0075] In view of this, the present application provides a method for determining steady-state parameters, including: determining iterative variable information and dependent variable information under a target scenario configured by a user, wherein the iterative variable information includes at least: the name of the iterative variable and the initial value of the iterative variable, and the dependent variable information includes at least: the name of the dependent variable and the target value of the dependent variable, constructing a relational equation for the target scenario according to the iterative variable information and the dependent variable information, and if the loss function of the relational equation reaches a minimum value, determining the current initial value of the iterative variable in the relational equation as a steady-state parameter, and if the loss function of the relational equation does not reach a minimum value, determining the target initial value according to a preset initial value selection rule, and iterating the relational equation using the target initial value until the loss function reaches a minimum value or the number of iterations reaches an iteration number threshold, determining the corresponding target initial value as a steady-state parameter. In other words, if the loss function of the relational equation does not reach a minimum value, reselecting the target initial value for iteration until the loss function reaches a minimum value or the number of iterations reaches an iteration number threshold, so that the steady-state parameters can be automatically determined, thereby solving the steady-state problem in the system.

[0076] The method provided in the embodiment of the present application can be executed by software on a computing device. The computing device can be, for example, a server, a mobile phone, a tablet computer, a computer, etc. The software can be, for example, system software.

[0077] In order to make the technical personnel in this field better understand the present application, the present application is further described in detail below in combination with the drawings and specific implementation methods. The following is an example of the method provided in the present application embodiment being executed by a computing device.

[0078] Figure 1 A flow chart of a method for determining a steady-state parameter provided in an embodiment of the present application. Figure 1 As shown, the method includes:

[0079] S101: Determine iterative variable information and dependent variable information in a target scenario configured by a user.

[0080] The computing device determines the iteration variable information and dependent variable information in the target scenario configured by the user, wherein the iteration variable information includes at least: the name of the iteration variable and the initial value of the iteration variable, and the dependent variable information includes at least: the name of the dependent variable and the target value of the dependent variable.

[0081] Exemplarily, the computing device may present a parameter configuration interface, such as Figure 2 As shown, the parameter configuration interface may include a scenario selection option 201, an iteration variable information column 202, and a dependent variable information column 203, wherein the scenario selection option 201 may include a circuit scenario option and a car driving scenario option, etc.

[0082] For example, in Figure 2 In the example, the name of the iteration variable, the initial value of the iteration variable, the maximum value of the iteration variable's value interval, and the minimum value of the iteration variable's value interval can be input in the iteration variable information column 202. The name of the dependent variable and the target value of the dependent variable can be input in the dependent variable information column 203.

[0083] Specifically, the computing device may determine the target scene according to the user's selection operation on the scene selection option 201 .

[0084] The iteration variable information and dependent variable information under the target scene are determined according to the information input by the user in the iteration variable information column 202 and the dependent variable information column 203. For example, if the target scene is determined to be a car driving scene, the information input by the user in the iteration variable information column is that the iteration variable is traction force F, and the corresponding initial value is 1000N, and the information input in the dependent variable information column is that the dependent variable is acceleration a, and the corresponding initial value is 0.

[0085] The computing device may call the getTrimValue() function to determine the value of the dependent variable acceleration a, and create the SetInitValue() function to determine the initial value of the iteration variable traction force F.

[0086] S102: Construct a relational equation for the target scenario according to the iterative variable information and the dependent variable information.

[0087] The computing device can construct a relational equation for the target scenario based on the iterative variable information and the dependent variable information.

[0088] For example, if the determined independent variable is the speed of the car, which is 30 m / s, the friction force can be determined according to the speed of the car using the formula as follows:

[0089]

[0090] Among them, F d is the friction force, C d is the air resistance coefficient, which is related to many factors such as the shape of the car and the smoothness of the surface. For example, the value here is 0.15. A is the frontal area in front of the car, which is related to the model and size of the car, and generally ranges from 1.5 to 2.5. The unit is square meters. For example, the value here is 2. ρ is the air density, which varies at different temperatures and altitudes. Under standard conditions (sea level, 20°C), the air density is about 1.225kg / m 3. For example, the air density is 1. V is the speed of the car. Then Fd = 0.5*1*2*0.15*V. The trim setting requires the acceleration of the car to be 0 (the car is traveling at a constant speed); we need to solve the traction F; we construct the equation based on the relationship between the dependent variable and the iteration variable as follows, create the function interface getTrimValue() to obtain the value of acceleration a, create the SetInitValue() interface to assign an initial value to F, and the specific relationship equation can be shown as follows:

[0091]

[0092] S103: If the loss function of the relational equation reaches a minimum value, determine the current initial value of the iterative variable in the relational equation as a steady-state parameter.

[0093] If the loss function of the relational equation (here, the residual value) reaches a minimum value, the current initial value of the iterative variable in the relational equation is determined as a steady-state parameter.

[0094] S104: If the loss function of the relationship equation has not reached the minimum value, determine the target initial value according to the preset initial value selection rule, and iterate the relationship equation using the target initial value until the loss function reaches the minimum value or the number of iterations reaches the iteration number threshold, and determine the corresponding target initial value as the steady-state parameter.

[0095] Exemplarily, if the loss function of the relationship equation has not reached the minimum value, the computing device can use the Levenberg-Marquardt method to determine the target initial value according to a preset initial value selection rule, and use the target initial value to iterate the relationship equation until the loss function reaches the minimum value or the number of iterations reaches an iteration number threshold, and determine that the corresponding target initial value is a steady-state parameter, wherein the iteration number threshold can be set by technicians in this field as needed, for example, set to 10 times, which is not limited here.

[0096] In some possible implementations, the iteration variable information also includes a value range of the iteration variable. The computing device can determine the target initial value (i.e., generate a minimum value x in the value range) from the value range of the iteration variable by using a normally distributed random number. min The maximum value x of the value interval max That is, multiply the range by a random number between 0 and 1 and then add x min , you will get a min and x max and use the target initial value to iterate the relationship equation.

[0097] The specific formula is as follows:

[0098]

[0099] Among them, X min is the minimum value of the iteration variable, and Xmax is the maximum value of the iteration variable. The rand() function represents the output value of a random number generator. Rand_MAX: This is a constant that represents the maximum value that the rand() function can return.

[0100] In some possible implementations, the computing device may randomly select a first multiple of the initial value to determine as a target initial value and iterate the relationship equation using the target initial value, and the first multiple may be 0 to 10 times.

[0101] The specific formula can be as follows:

[0102]

[0103] Among them, -inf represents infinitesimal, inf represents infinitesimal, Xmin=-inf xmax=inf means the user has not specified the interval range. rand() / Rand_Max represents the generation of random numbers between 0 and 1.

[0104] (rand() / Rand_Max)*10 represents the generation of a direct random number between 0 and 10.

[0105] In some possible implementation methods, when the number of iterations reaches the target number (which can be set according to actual needs, for example, 10 times, not limited here), that is, the number of iterations using the above two methods reaches the target number, and the steady-state parameters are still not determined, the changing trend of the initial value and the loss function in each iteration process can be judged.

[0106] If it is determined that the initial value decreases and the loss function decreases, the minimum initial value among the multiple initial values ​​corresponding to the multiple iterations can be selected, the minimum initial value of the second multiple can be determined as the target initial value, and the target initial value can be used to iterate the relationship equation, wherein the second multiple is less than 1, for example, it can be 0.1, which is not limited here.

[0107] If it is determined that the initial value decreases and the loss function increases, the computing device can select the maximum initial value among the corresponding multiple initial values ​​in the multiple iterations, determine the maximum initial value of the third multiple as the target initial value and use the target initial value to iterate the relationship equation, where the third multiple is greater than 1, for example, it can be 10, which is not limited here.

[0108] Except for the two cases where the initial value decreases, the loss function decreases, and the initial value decreases, the loss function increases, in other cases (such as the initial value increases, the loss function increases), the computing device can select the maximum initial value and the minimum initial value from the corresponding multiple initial values ​​in the multiple iterations, use the dichotomy method to determine the target initial value from the interval from the maximum initial value to the minimum initial value, and use the target initial value to iterate the relationship equation.

[0109] In some possible implementations, the target initial value is determined according to a preset initial value selection rule, and the relationship equation is iterated using the target initial value. If the loss function reaches the minimum value or the number of iterations reaches an iteration threshold, the corresponding target initial value can also be verified according to a preset verification rule.

[0110] Exemplarily, for example, it can be verified whether the corresponding target initial value is within the value range of the iteration variable set by the user. It is verified whether the target initial value makes the difference between the value of the dependent variable and the target value within a preset range. It should be noted that the preset range can be set according to actual needs and is not limited here.

[0111] Verify that the computing device fails to determine the steady-state parameters according to the initial values ​​configured by the user for the first time, and whether to continue to transform the initial values ​​and try to determine the steady-state parameters again.

[0112] If the relationship equation is iterated using the target initial value and the loss function reaches the minimum value, it can also be verified whether the number of iterations reaches the iteration number threshold.

[0113] If it is determined that the corresponding target initial value is within the value range of the iteration variable set by the user, and the target initial value makes the difference between the value of the dependent variable and the target value within the preset range, and the steady-state parameters are not determined according to the initial value configured by the user for the first time, the initial value continues to be transformed, and an attempt is made to determine the steady-state parameters again, and when the relationship equation is iterated using the target initial value and the loss function reaches the minimum value, it is determined that the number of iterations does not reach the iteration number threshold, then it can be determined that the verification rules are met and the corresponding target initial value is determined to be a steady-state parameter.

[0114] If any one of them is not satisfied, the iteration can be continued according to the iteration method in step S104 until the verification condition is satisfied, and the corresponding target initial value is determined to be the steady-state parameter.

[0115] The present application can determine the iterative variable information and dependent variable information under the target scenario configured by the user, wherein the iterative variable information at least includes: the name of the iterative variable and the initial value of the iterative variable, and the dependent variable information at least includes: the name of the dependent variable and the target value of the dependent variable. The relational equation of the target scenario is constructed according to the iterative variable information and the dependent variable information. If the loss function of the relational equation reaches the minimum value, the current initial value of the iterative variable in the relational equation is determined to be a steady-state parameter. If the loss function of the relational equation does not reach the minimum value, the target initial value is determined according to the preset initial value selection rule, and the relational equation is iterated using the target initial value until the loss function reaches the minimum value or the number of iterations reaches the iteration number threshold, and the corresponding target initial value is determined to be a steady-state parameter. In other words, if the loss function of the relational equation does not reach the minimum value, the target initial value is reselected for iteration until the loss function reaches the minimum value or the number of iterations reaches the iteration number threshold, so that the steady-state parameters can be automatically determined, thereby solving the steady-state problem in the system.

[0116] The above embodiment may be referred to as embodiment 1. Based on embodiment 1, the present application further provides another embodiment, which may be referred to as embodiment 2. Based on embodiment 1, embodiment 2 may further display the determined steady-state parameters and the number of iterations for determining the steady-state parameters. For example, Figure 3 As shown, Figure 3 The determined steady-state parameters, i.e. the initial value of the last iteration variable, are shown as 135 and the number of iterations is 7. This is for the relevant personnel to view.

[0117] In some possible implementations, such as Figure 4 As shown, the process of determining the steady-state parameters can also be generated into a code file and stored, thereby increasing the readability of the code and making it easier for relevant personnel to understand the entire process of determining the steady-state parameters.

[0118] The above are some specific implementations of the method for determining steady-state parameters provided in the embodiments of the present application. Based on this, the present application also provides a corresponding device. The device provided in the embodiments of the present application will be introduced from the perspective of functional modularization. The device and the method for determining steady-state parameters described above can be referred to each other.

[0119] Figure 5 The structural block diagram provided for the embodiment of the present invention is referred to as the specific implementation mode three, and the Figure 5 The device may include:

[0120] A first determining unit is used to determine iterative variable information and dependent variable information in a target scenario configured by a user, wherein the iterative variable information at least includes: a name of the iterative variable and an initial value of the iterative variable; and the dependent variable information at least includes: a name of the dependent variable and a target value of the dependent variable;

[0121] A construction unit, used to construct a relational equation of a target scenario according to the iterative variable information and the dependent variable information;

[0122] A second determining unit is used to determine the current initial value of the iterative variable in the relational equation as a steady-state parameter if the loss function of the relational equation reaches a minimum value;

[0123] The third determination unit is used to determine the target initial value according to a preset initial value selection rule if the loss function of the relationship equation has not reached the minimum value, and to iterate the relationship equation using the target initial value until the loss function reaches the minimum value or the number of iterations reaches an iteration number threshold, and to determine the corresponding target initial value as a steady-state parameter.

[0124] Optionally, the iteration variable information further includes a value range of the iteration variable, and the third determination unit is specifically configured to:

[0125] The target initial value is determined from the value interval of the iteration variable by means of a normally distributed random number, and the relationship equation is iterated by using the target initial value.

[0126] Optionally, the third determining unit is specifically configured to:

[0127] A first multiple of the initial value is randomly selected as a target initial value and the relationship equation is iterated using the target initial value, wherein the first multiple is 0 to 10 times.

[0128] Optionally, when the number of iterations reaches the target number, the third determining unit is specifically configured to:

[0129] Select the minimum initial value among multiple initial values ​​corresponding to multiple iterations;

[0130] Determine the minimum initial value of the second multiple as the target initial value and iterate the relationship equation using the target initial value, wherein the second multiple is less than 1;

[0131] or,

[0132] Select the maximum initial value among the multiple initial values ​​corresponding to the multiple iterations;

[0133] Determine the maximum initial value of the third multiple as the target initial value and iterate the relationship equation using the target initial value, wherein the third multiple is greater than 1;

[0134] or,

[0135] Select the maximum initial value and the minimum initial value from the multiple initial values ​​corresponding to the multiple iterations;

[0136] A target initial value is determined from the interval between the maximum initial value and the minimum initial value by using a binary search method, and the relational equation is iterated by using the target initial value.

[0137] Optionally, the third determining unit is specifically configured to:

[0138] According to a preset verification rule, verifying the target initial value corresponding to when the loss function reaches a minimum value or the number of iterations reaches an iteration number threshold;

[0139] When the verification rules are met, the corresponding target initial value is determined as the steady-state parameter.

[0140] Optionally, the device further comprises:

[0141] A presentation unit, used to present a parameter configuration interface, wherein the parameter configuration interface includes a scene selection option, an iteration variable information column, and a dependent variable information column;

[0142] The first determining unit is specifically configured to:

[0143] The target scene is determined according to the user's selection operation on the scene selection option, and the iteration variable information and the dependent variable information under the target scene are determined according to the information input by the user in the iteration variable information column and the dependent variable information column.

[0144] Optionally, the device further comprises:

[0145] A display unit, used for displaying the determined steady-state parameters and the number of iterations for determining the steady-state parameters;

[0146] The fourth determining unit is used to generate a code file for the process of determining the steady-state parameters and store the code file.

[0147] The embodiments of the present application also provide corresponding devices and computer storage media for implementing the solutions provided by the embodiments of the present application.

[0148] The device includes a memory and a processor, the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the device executes the method described in any embodiment of the present application.

[0149] The computer storage medium stores codes, and when the codes are executed, a device executing the codes implements the method described in any embodiment of the present application.

[0150] The "first" and "second" in the names such as "first" and "second" (if any) mentioned in the embodiments of the present application are only used as name identifiers and do not represent the first or second in order.

[0151] Through the description of the above implementation methods, it can be known that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus a general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a storage medium, such as a read-only memory (ROM) / RAM, a magnetic disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network communication device such as a router) to execute the methods described in each embodiment of the present application or some parts of the embodiments.

[0152] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0153] The above description is merely an exemplary embodiment of the present application and is not intended to limit the protection scope of the present application.

Claims

1. A method for determining steady-state parameters, characterized in that: include: Determine the iteration variable information and dependent variable information under the target scenario configured by the user, wherein the iteration variable information includes at least: the name of the iteration variable and the initial value of the iteration variable; the dependent variable information includes at least: the name of the dependent variable and the target value of the dependent variable; Constructing a relational equation of a target scenario according to the iterative variable information and the dependent variable information; If the loss function of the relational equation reaches a minimum value, determining the current initial value of the iterative variable in the relational equation as a steady-state parameter; If the loss function of the relationship equation has not reached the minimum value, the target initial value is determined according to the preset initial value selection rule, and the relationship equation is iterated using the target initial value until the loss function reaches the minimum value or the number of iterations reaches the iteration number threshold, and the corresponding target initial value is determined as the steady-state parameter.

2. The method according to claim 1, characterized in that The iteration variable information also includes a value range of the iteration variable. The step of determining a target initial value according to a preset initial value selection rule and iterating the relationship equation using the target initial value includes: The target initial value is determined from the value interval of the iteration variable by means of a normally distributed random number, and the relationship equation is iterated by using the target initial value.

3. The method according to claim 1, characterized in that The step of determining a target initial value according to a preset initial value selection rule, and iterating the relationship equation using the target initial value, comprises: A first multiple of the initial value is randomly selected to be determined as a target initial value and the relationship equation is iterated using the target initial value, wherein the first multiple is 0 to 10 times.

4. The method according to claim 1, characterized in that: When the number of iterations reaches the target number of times, determining the target initial value according to the preset initial value selection rule, and iterating the relationship equation using the target initial value, including: Select the minimum initial value among multiple initial values ​​corresponding to multiple iterations; Determine the minimum initial value of the second multiple as the target initial value and iterate the relationship equation using the target initial value, wherein the second multiple is less than 1; or, Select the maximum initial value among the multiple initial values ​​corresponding to the multiple iterations; Determine the maximum initial value of the third multiple as the target initial value and iterate the relationship equation using the target initial value, wherein the third multiple is greater than 1; or, Select the maximum initial value and the minimum initial value from the multiple initial values ​​corresponding to the multiple iterations; A target initial value is determined from the interval between the maximum initial value and the minimum initial value by using a binary search method, and the relational equation is iterated by using the target initial value.

5. The method according to claim 1, characterized in that Determining the corresponding target initial value as a steady-state parameter includes: According to a preset verification rule, verifying the target initial value corresponding to when the loss function reaches a minimum value or the number of iterations reaches an iteration number threshold; When the verification rules are met, the corresponding target initial value is determined as the steady-state parameter.

6. The method according to claim 1, characterized in that The method further comprises: Presenting a parameter configuration interface, the parameter configuration interface including a scene selection option, an iteration variable information column, and a dependent variable information column; The step of determining the iteration variable information and dependent variable information in the target scenario configured by the user includes: The target scene is determined according to the user's selection operation on the scene selection option, and the iteration variable information and the dependent variable information under the target scene are determined according to the information input by the user in the iteration variable information column and the dependent variable information column.

7. The method according to claim 1, characterized in that The method further comprises: Display the determined steady-state parameters and the number of iterations used to determine the steady-state parameters; The process of determining steady-state parameters generates a code file and stores it.

8. A device for determining steady-state parameters, characterized in that: include: A first determining unit is used to determine iterative variable information and dependent variable information in a target scenario configured by a user, wherein the iterative variable information at least includes: a name of the iterative variable and an initial value of the iterative variable; and the dependent variable information at least includes: a name of the dependent variable and a target value of the dependent variable; A construction unit, used to construct a relational equation of a target scenario according to the iterative variable information and the dependent variable information; A second determining unit is used to determine the current initial value of the iterative variable in the relational equation as a steady-state parameter if the loss function of the relational equation reaches a minimum value; The third determination unit is used to determine the target initial value according to a preset initial value selection rule if the loss function of the relationship equation has not reached the minimum value, and to iterate the relationship equation using the target initial value until the loss function reaches the minimum value or the number of iterations reaches an iteration number threshold, and to determine the corresponding target initial value as a steady-state parameter.

9. The device according to claim 8, characterized in that The iteration variable information also includes a value range of the iteration variable. The third determination unit is specifically configured to: The target initial value is determined from the value interval of the iteration variable by means of a normally distributed random number, and the relationship equation is iterated by using the target initial value.

10. The device according to claim 8, characterized in that The third determining unit is specifically configured to: A first multiple of the initial value is randomly selected to be determined as a target initial value and the relationship equation is iterated using the target initial value, wherein the first multiple is 0 to 10 times.

Images