Object state category conversion strategy generation method and device, equipment and medium

Abstract

The invention relates to an object state category conversion strategy generation method and device, equipment and a medium, and the method comprises the steps: inputting a preset parameter combination into a conversion tree, carrying out the traversal of a corresponding leaf branch, so as to determine a plurality of conversion strategies, and calculating and determining the goodness corresponding to each conversion strategy, the conversion strategy represents a combination constructed by selectable values corresponding to the adjustable parameters and the non-adjustable parameters; sorting the plurality of conversion strategies according to the goodness corresponding to each conversion strategy to determine a goodness sequence, detecting whether the conversion strategies ranked in a preset threshold range in the goodness sequence accord with an expected result or not, if so, outputting the conversion strategy according with the expected result as an alternative conversion strategy, and if not, outputting the alternative conversion strategy. Therefore, the generation of the object state category conversion strategy is completed. The scheme generated by the invention can better adapt to data mining of structured and unstructured data sets in various scenes.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a method for generating a transaction status category conversion strategy, a corresponding device, an electronic device, and a computer-readable storage medium. Background Art

[0002] In today's data-driven era, data mining, as an important technical means to extract valuable information and knowledge from massive and complex data, has been widely used in all walks of life, from business intelligence to scientific research, demonstrating its huge potential and value. However, with the explosive growth of data scale and the increasing complexity of data structure, traditional data mining methods are facing unprecedented challenges. Although current research and practice mainly focus on the two major areas of optimal solution mining and full parameter data mining, these efforts have undoubtedly revealed the deep laws and potential value of data for us, but the breadth and depth of data mining still need to be further expanded.

[0003] Specifically, existing optimal solution mining methods focus on automatically discovering optimal or near-optimal solutions from data, providing strong support for decision-making. However, these solutions often exist in isolation, lacking a comprehensive comparison and in-depth analysis of the performance, applicable conditions, and pros and cons of different solutions. In terms of functions, they are mainly based on classification and prediction, and the knowledge of intelligent adjustment of parameters to dynamically change the state of things has not yet attracted attention. In addition, although full-parameter data mining can explore all dimensions of data in detail, it often ignores the important impact of parameter adjustability on mining results, and achieves more flexible and efficient data analysis through segmented classification, focusing on improving the accuracy of classification, and ignoring the analysis of intelligently changing label results through parameter adjustment.

[0004] To sum up, the solutions in the existing technology often exist in isolation, lacking a comprehensive comparison and in-depth analysis of the performance, applicable conditions, advantages and disadvantages of different solutions, often ignoring the important impact of parameter adjustability on mining results, and ignoring the analysis of intelligently changing label results through parameter adjustment. In order to solve this problem, the applicant has made corresponding explorations. Summary of the invention

[0005] The purpose of the present application is to solve the above-mentioned problems and to provide a method for generating a thing state category conversion strategy, a corresponding device, an electronic device and a computer-readable storage medium.

[0006] In order to meet the various objectives of this application, this application adopts the following technical solutions:

[0007] A method for generating a strategy for converting a state of matter category proposed to meet one of the purposes of this application includes:

[0008] In response to the thing state category conversion strategy generation instruction, a plurality of parameters in the sample data set, an optional value of each parameter, and a target frequency reached and a target frequency not reached corresponding to the optional value are obtained, wherein the parameters include adjustable parameters and non-adjustable parameters;

[0009] Calculate and determine the expected conversion rate of each adjustable parameter according to the target frequency that has been reached and the target frequency that has not been reached corresponding to the optional value of each adjustable parameter;

[0010] The non-adjustable parameter is set as a root node, a transformation tree is constructed according to the expected conversion rates of the adjustable parameters and their corresponding optional values, and the transformation tree is pruned and optimized, wherein each leaf branch of the transformation tree represents a selection of an adjustable parameter, and a leaf node of the transformation tree represents a parameter combination;

[0011] Input a preset parameter combination into the transformation tree, traverse the corresponding leaf branches to determine a plurality of transformation strategies, and calculate and determine the corresponding goodness of each transformation strategy, wherein the transformation strategy represents a combination constructed by the optional values ​​corresponding to the adjustable parameters and the non-adjustable parameters;

[0012] The multiple conversion strategies are sorted according to the corresponding excellence of each conversion strategy to determine the excellence sequence, and the conversion strategies ranked within the preset threshold range in the excellence sequence are detected to see whether they meet the expected results. If so, the conversion strategies that meet the expected results are output as alternative conversion strategies to complete the generation of the thing state category conversion strategy.

[0013] Optionally, the step of setting the non-adjustable parameter as a root node, constructing a transformation tree according to the expected conversion rates of the adjustable parameters and their corresponding optional values, and performing pruning optimization on the transformation tree includes:

[0014] Acquire each root node to construct a root node group, and sort the expected conversion rates of each adjustable parameter in ascending order to construct an adjustable parameter sequence;

[0015] Selecting an adjustable parameter in order from the adjustable parameter sequence as a first adjustable parameter;

[0016] deriving a corresponding child node from each root node in the root node group according to an optional value of the first adjustable parameter;

[0017] The derived child nodes are used as a new root node group, the first adjustable parameter is replaced with a second adjustable parameter, and the step of deriving corresponding child nodes from each root node in the root node group according to the optional value of the second adjustable parameter is executed until each adjustable parameter in the adjustable parameter sequence is traversed, so as to construct the transformation tree and perform pruning optimization on the transformation tree.

[0018] Optionally, the steps of inputting a preset parameter combination into the transformation tree, traversing the corresponding leaf branches to determine a plurality of transformation strategies, and calculating and determining the corresponding optimality of each transformation strategy include:

[0019] Step S401: taking the leaf node of the leaf branch corresponding to the preset parameter combination as the second node;

[0020] Step S402: Use the parent node corresponding to the second node as the third node; remove the second node from the child nodes of the third node, and use the remaining nodes as a child node group;

[0021] Step S403, determining whether the child node group is empty, if the child node group is not empty, executing step S404; if the child node group is empty, executing step S406;

[0022] Step S404: Select a node from the child node group as the first node, and replace the optional value of the parameter corresponding to the second node with the optional value of the parameter corresponding to the first node to form a new strategy;

[0023] Step S405: After processing the first node, remove the first node from the child node group, and return to step S403;

[0024] Step S406, determining whether the third node is a root node; if the third node is a root node, executing step S408; if the third node is not a root node, executing step S407;

[0025] Step S407: take the third node as the new second node, and take the parent node of the third node as the new third node; readjust the child node group, remove the new second node, and use the remaining nodes as the new child node group, and return to step S403;

[0026] Step S408: When the third node is a root node, the finally generated strategy is used as a conversion strategy to determine multiple conversion strategies.

[0027] Optionally, the step of inputting a preset parameter combination into the transformation tree and traversing its corresponding leaf branches to determine a plurality of transformation strategies includes:

[0028] Detecting whether the number of the transformation strategies reaches a preset number threshold, and if so, continuing to execute the steps after inputting the preset parameter combination into the transformation tree and traversing the corresponding leaf branches to determine multiple transformation strategies;

[0029] If not reached, increase the optional values ​​of non-adjustable parameters and / or adjustable parameters, and return to execute the steps of obtaining multiple parameters in the sample data set, the optional value of each parameter, and the target frequency reached and the target frequency not reached corresponding to the optional value, until the number of conversion strategies reaches the preset quantity threshold.

[0030] Optionally, the expression of the goodness corresponding to each conversion strategy is:

[0031] O=α1k1+α2k2,

[0032] Among them, O represents goodness, α1 and α2 represent weights, k1 represents the conversion cost correlation, and k2 represents the expected conversion rate;

[0033] The calculation formula of conversion cost correlation is as follows:

[0034]

[0035] Wherein, k1(x) represents the conversion cost correlation, ρ represents the extension distance calculation operation, which is used to calculate the distance or difference between elements, D represents the extension position value calculation operation, which is used to calculate the position or sorting of elements, x0 represents the minimum conversion cost, x represents the conversion cost, X represents the range where the conversion cost meets the requirements, and X0 represents several ranges in X with smaller conversion costs. represents X and the range of requirements that are met in a particular case, Represents the selectable range for all conversion costs.

[0036] Optionally, the step of calculating and determining the expected conversion rate of each adjustable parameter according to the target frequency that has been reached and the target frequency that has not been reached corresponding to the optional value of each adjustable parameter includes:

[0037] The calculation formula of the expected conversion rate includes:

[0038] E(A)=Average(E + (A i )),

[0039]

[0040] Where i≠j, for parameter A, E(A) represents the expected conversion rate, Average(E + (A i )) represents all non-negative E(Ai ), E(A i →A j ) is the expected conversion rate after the parameter is adjusted from the i-th optional value to the j-th optional value, P(A i ) is the frequency of the i-th optional value, P(A i →B) is the target frequency of the i-th optional value that has been reached, is the confidence of the jth optional value, is the target frequency of the i-th optional value that has not been reached.

[0041] Optionally, the non-adjustable parameter is a main dish, and the optional values ​​corresponding to the non-adjustable parameter include one or more categories of main dishes; the adjustable parameters include side dishes and desserts, and the optional values ​​corresponding to the side dishes include one or more categories of side dishes; the optional values ​​corresponding to the desserts include one or more categories of side dishes.

[0042] A device for generating a strategy for converting a state category of a thing provided for another purpose of the present application includes:

[0043] A parameter acquisition module is configured to respond to the thing state category conversion strategy generation instruction, obtain multiple parameters in the sample data set, the optional value of each parameter, and the target frequency reached and the target frequency not reached corresponding to the optional value, wherein the parameters include adjustable parameters and non-adjustable parameters;

[0044] An expected conversion rate determination module is configured to calculate and determine the expected conversion rate of each adjustable parameter according to the target frequency that has been reached and the target frequency that has not been reached corresponding to the optional value of each adjustable parameter;

[0045] a conversion tree construction module, configured to set the non-adjustable parameter as a root node, construct a conversion tree according to the expected conversion rates of the adjustable parameters and their corresponding optional values, and perform pruning optimization on the conversion tree, wherein each leaf branch of the conversion tree represents a selection of an adjustable parameter, and a leaf node of the conversion tree represents a parameter combination;

[0046] A transformation strategy goodness determination module is configured to input a preset parameter combination into the transformation tree, traverse the corresponding leaf branches to determine multiple transformation strategies, and calculate and determine the goodness corresponding to each transformation strategy, wherein the transformation strategy represents the optional value combination corresponding to each parameter;

[0047] The conversion strategy determination module is configured to sort the multiple conversion strategies according to the corresponding excellence of each conversion strategy to determine the excellence sequence, detect whether the conversion strategies ranked within a preset threshold range in the excellence sequence meet the expected results, and if so, output the conversion strategies that meet the expected results as alternative conversion strategies to complete the generation of the thing state category conversion strategies.

[0048] An electronic device provided to meet another purpose of the present application includes a central processing unit and a memory, wherein the central processing unit is used to call and run a computer program stored in the memory to execute the steps of the method for generating a transaction status category conversion strategy described in the present application.

[0049] A computer-readable storage medium is provided to meet another purpose of the present application, which stores a computer program implemented according to the method for generating a state category conversion strategy for a thing in the form of computer-readable instructions. When the computer program is called and executed by a computer, the steps included in the corresponding method are executed.

[0050] Compared with the prior art, the present application aims at the problems that the solutions in the prior art often exist in isolation, lack comprehensive comparison and in-depth analysis of the performance, applicable conditions and advantages and disadvantages of different solutions, often ignore the important influence of parameter adjustability on mining results, and ignore the analysis of intelligently changing label results through parameter adjustment. The present application includes but is not limited to the following beneficial effects:

[0051] First, the method for generating a strategy for transforming the state of things in the present application can not only systematically compare the similarities and differences between different schemes, reveal the internal connections and transformation rules between them, but also distinguish the parameter adjustability, so as to flexibly adjust the mining strategy according to the specific application scenario and data characteristics, thereby obtaining a more accurate and comprehensive state change analysis result;

[0052] Secondly, the method for generating transformation strategies for the state categories of things in this application constructs a transformation tree and then arranges the importance of parameter improvements. By traversing the transformation tree, new transformation plans are generated; this application introduces a goodness ranking, which enables a comprehensive consideration of the cost and efficiency between plans, and extracts alternative transformation strategies (plans). In general, the plans generated by this application can better adapt to data mining of structured and unstructured data sets in a variety of scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0054] Figure 1 Schematic diagram of the process of generating a method for converting a state category of a thing in an embodiment of the present application;

[0055] Figure 2 This is a principle block diagram of a device for generating a strategy for converting a state category of a thing in an embodiment of the present application;

[0056] Figure 3 It is a schematic diagram of the structure of the computer device in the embodiment of the present application. DETAILED DESCRIPTION

[0057] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present application.

[0058] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0059] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with those in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0060] It will be understood by those skilled in the art that the "client", "terminal" and "terminal device" used herein include both devices with wireless signal receivers, which are devices with only wireless signal receivers without transmission capabilities, and devices with receiving and transmitting hardware, which are devices with receiving and transmitting hardware capable of two-way communication on a two-way communication link. Such devices may include: cellular or other communication devices such as personal computers, tablet computers, which have single-line displays or multi-line displays or cellular or other communication devices without multi-line displays; PCS (Personal Communications Service, personal communication system), which can combine voice, data processing, fax and / or data communication capabilities; PDA (Personal Digital Assistant, personal digital assistant), which may include a radio frequency receiver, pager, Internet / intranet access, web browser, notepad, calendar and / or GPS (Global Positioning System, global positioning system) receiver; conventional laptop and / or palmtop computers or other devices, which have and / or include a conventional laptop and / or palmtop computer or other device with and / or including a radio frequency receiver. The "client", "terminal" and "terminal device" used herein may be portable, transportable, installed in a vehicle (air, sea and / or land), or suitable for and / or configured to run locally, and / or in a distributed form, at any other location on the earth and / or in space. The "client", "terminal" and "terminal device" used herein may also be a communication terminal, an Internet terminal, a music / video playing terminal, for example, a PDA, a MID (Mobile Internet Device) and / or a mobile phone with a music / video playing function, or a smart TV, a set-top box and other devices.

[0061] The hardware referred to by the names such as "server", "client", and "service node" in this application is essentially an electronic device with the equivalent capabilities of a personal computer. It is a hardware device with the necessary components revealed by the von Neumann principle, such as a central processing unit (including an arithmetic unit and a controller), a memory, an input device, and an output device. The computer program is stored in its memory, and the central processing unit calls the program stored in the external memory into the internal memory for execution, executes the instructions in the program, and interacts with the input and output devices to complete specific functions.

[0062] It should be pointed out that the concept of "server" referred to in this application can also be extended to the case of server clusters. According to the network deployment principle understood by those skilled in the art, the servers should be logically divided. In physical space, these servers can be independent of each other but can be called through interfaces, or integrated into a physical computer or a set of computer clusters. Those skilled in the art should understand this flexibility, and should not use it to restrict the implementation of the network deployment method of this application.

[0063] Unless expressly specified, one or more technical features of the present application can be deployed on a server for implementation and accessed by a client through a remote call to obtain an online service interface provided by the server, or can be directly deployed and run on a client for access.

[0064] The neural network models referenced or may be referenced in this application, unless expressly specified, can be deployed on a remote server and remotely called on the client, or can be deployed and directly called on a client with sufficient device capabilities. In some embodiments, when it runs on the client, its corresponding intelligence can be obtained through transfer learning to reduce the requirements for the client's hardware operating resources and avoid excessive occupation of the client's hardware operating resources.

[0065] Unless explicitly specified, the various data involved in this application can be stored remotely on a server or on a local terminal device, as long as it is suitable for being called by the technical solution of this application.

[0066] Those skilled in the art should be aware that, although the various methods of the present application are described based on the same concept and thus present commonality to each other, unless otherwise specified, these methods can be independently executed. Similarly, for each embodiment disclosed in the present application, they are all proposed based on the same inventive concept, therefore, concepts with the same expression, and concepts that are appropriately changed for convenience despite different expressions, should be understood as equivalent.

[0067] Unless the mutually exclusive relationship between the embodiments to be disclosed in this application is explicitly stated, the relevant technical features involved in each embodiment can be cross-combined to flexibly construct a new embodiment, as long as such combination does not deviate from the creative spirit of this application and can meet the needs of the prior art or solve certain deficiencies in the prior art. Those skilled in the art should be aware of this flexibility.

[0068] See also Figure 1 In one embodiment, the method for generating a transaction status category conversion strategy of the present application includes:

[0069] Step S10, in response to the thing state category conversion strategy generation instruction, obtain multiple parameters in the sample data set, the optional value of each parameter, and the target frequency reached and the target frequency not reached corresponding to the optional value, wherein the parameters include adjustable parameters and non-adjustable parameters;

[0070] The thing state category conversion strategy generation system can respond to the thing state category conversion strategy generation instruction, obtain multiple parameters in the sample data set, the optional value of each parameter, and the target frequency reached and the target frequency not reached corresponding to the optional value, wherein the parameters include adjustable parameters and non-adjustable parameters;

[0071] In some embodiments, the target frequency that has been reached refers to the number of samples that meet the predetermined target or standard. The target frequency that has not been reached refers to the number of samples that have failed to reach the predetermined target or standard; adjustable parameters refer to parameters that can be adjusted to optimize the system or model; non-adjustable parameters refer to parameters that cannot be adjusted and are determined by external conditions or other limiting factors.

[0072] Specifically, the present application can combine and extract different conversion strategies from mixed parameters, and the conversion strategies are screened to meet actual business needs.

[0073] In some embodiments, the method of the present application is applied to the scenario of a machining database, the goal is whether the machined workpiece is qualified, and the multiple parameters include feed distance, rotation speed, surface roughness, machining temperature parameters, etc. The adjustable parameters include feed distance, rotation speed, machining temperature, etc., and the non-adjustable parameters include surface roughness, etc.

[0074] In some embodiments, the method of the present application is applied to the scenario of a health analysis database, where the goal is to determine whether the subject is healthy. The multiple parameters include gender, age, work and rest time, blood pressure, heart rate parameters, etc. The adjustable parameters include work and rest time, blood pressure, heart rate parameters, etc., and the non-adjustable parameters include gender, age, etc.

[0075] In some embodiments, the method of the present application is applied to a material analysis database, with the goal of determining whether the material meets performance requirements, and the multiple parameters include the amounts of different components, the mixing order, the mixing method, etc.

[0076] In some embodiments, if there are multiple non-adjustable parameters, the information gain rate of the non-adjustable parameters can be calculated, and the non-adjustable parameters are arranged in descending order according to the information gain rate to construct a root node. The calculation formula of the information gain rate is expressed as follows:

[0077]

[0078] The information gain rate of the non-adjustable parameters can be obtained through the above calculation formula, and the non-adjustable parameters are arranged in descending order according to the information gain rate to construct a root node.

[0079] Furthermore, after dividing the multiple parameters into adjustable parameters and setting the degree of difficulty of conversion, it also includes making a discreteness judgment on the adjustable parameters. If the adjustable parameters are continuous values, a parameter discretization operation is performed.

[0080] In some embodiments, the method is applied to a beverage preparation database, with the goal of determining whether the beverage is accepted. The database is extracted to determine whether the raw materials are used and the mixing ratio of different ingredients. A discrete value index is established for the ratio, the mixing ratio is used as a separate variable, and the mixing ratio value is used as a discrete optional value.

[0081] Step S20, calculating and determining the expected conversion rate of each adjustable parameter according to the target frequency that has been reached and the target frequency that has not been reached corresponding to the optional value of each adjustable parameter;

[0082] After obtaining multiple parameters in the sample data set, the optional value of each parameter, and the target frequency that has been reached and the target frequency that has not been reached corresponding to the optional value, the expected conversion rate of each adjustable parameter is calculated and determined according to the target frequency that has been reached and the target frequency that has not been reached corresponding to the optional value of each adjustable parameter;

[0083] In some embodiments, the calculation formula for the expected conversion rate includes:

[0084] E(A)=Average(E + (A i )),

[0085]

[0086] Where i≠j, for parameter A, E(A) represents the expected conversion rate, Average(E + (A i )) represents all non-negative E(A i ), E(A i →A j ) is the expected conversion rate after the parameter is adjusted from the i-th optional value to the j-th optional value, P(A i ) is the frequency of the i-th optional value, P(A i →S) is the target frequency of the i-th optional value that has been reached, is the confidence of the jth optional value, is the target frequency of the i-th optional value that has not been reached.

[0087] Step S30, setting the non-adjustable parameter as a root node, constructing a transformation tree according to the expected conversion rates of the adjustable parameters and their corresponding optional values, and performing pruning optimization on the transformation tree, wherein each leaf branch of the transformation tree represents a selection of an adjustable parameter, and a leaf node of the transformation tree represents a parameter combination;

[0088] After calculating and determining the expected conversion rate of each adjustable parameter, the non-adjustable parameter is set as a root node, a conversion tree is constructed according to the expected conversion rate of each adjustable parameter and its corresponding optional value, and the conversion tree is pruned and optimized, wherein each leaf branch of the conversion tree represents a selection of an adjustable parameter, and the leaf node of the conversion tree represents a parameter combination;

[0089] In some embodiments, the steps of setting the non-adjustable parameter as a root node, constructing a transformation tree according to the expected conversion rates of the adjustable parameters and their corresponding optional values, and performing pruning optimization on the transformation tree include:

[0090] Step S301: Acquire each root node to construct a root node group, and sort the expected conversion rates of each adjustable parameter in ascending order to construct an adjustable parameter sequence;

[0091] Step S302: Select an adjustable parameter from the adjustable parameter sequence in order as a first adjustable parameter;

[0092] Step S303: derive a corresponding child node from each root node in the root node group according to the optional value of the first adjustable parameter;

[0093] Step S304: Use the derived child nodes as a new root node group, replace the first adjustable parameter with a second adjustable parameter, and execute the step of deriving corresponding child nodes from each root node in the root node group according to the optional value of the second adjustable parameter, until each adjustable parameter in the adjustable parameter sequence is traversed, so as to construct the transformation tree and perform pruning optimization on the transformation tree.

[0094] Step S40: input a preset parameter combination into the transformation tree, traverse the corresponding leaf branches to determine a plurality of transformation strategies, and calculate and determine the corresponding goodness of each transformation strategy, wherein the transformation strategy represents a combination constructed by the optional values ​​corresponding to the adjustable parameters and the non-adjustable parameters;

[0095] The non-adjustable parameter is set as a root node, a transformation tree is constructed according to the expected conversion rate of each adjustable parameter and its corresponding optional value, and after pruning and optimizing the transformation tree, a preset parameter combination is input into the transformation tree, and its corresponding leaf branches are traversed to determine a plurality of transformation strategies, and the corresponding goodness of each transformation strategy is calculated and determined, wherein the transformation strategy represents the combination constructed by the adjustable parameter and the optional value corresponding to the non-adjustable parameter;

[0096] In some embodiments, the expression of the goodness corresponding to each conversion strategy is:

[0097] O=α1k1+α2k2,

[0098] Among them, O represents goodness, α1 and α2 represent weights, k1 represents the conversion cost correlation, and k2 represents the expected conversion rate;

[0099] The calculation formula of the conversion cost correlation is as follows:

[0100]

[0101] Wherein, k1(x) represents the conversion cost correlation, ρ represents the extension distance calculation operation, which is used to calculate the distance or difference between elements, D represents the extension position value calculation operation, which is used to calculate the position or sorting of elements, x0 represents the minimum conversion cost, x represents the conversion cost, X represents the range where the conversion cost meets the requirements, and X0 represents several ranges in X with smaller conversion costs. represents X and the range of requirements that are met in a particular case, Represents the selectable range for all conversion costs.

[0102] In a specific embodiment, it is necessary to ensure that k1∈[-1,1] and k2∈[-1,1], therefore, k1 and k2 need to be normalized, and the specific formula is as follows:

[0103]

[0104]

[0105] In a specific embodiment, the calculation operation of the extension distance is as follows:

[0106] Assume that the extension distance is ρ(x,x0,N), N is the interval [a,b] of axis x, then the minimum conversion cost x0 can be regarded as a point in axis x.

[0107] When x0 is to the left of the midpoint of the interval:

[0108]

[0109] When x0=a:

[0110]

[0111] When x0 is to the right of the midpoint of the interval:

[0112]

[0113] When x0=b:

[0114]

[0115] When x0 is at the midpoint of the interval:

[0116]

[0117] The calculation operation of the extension bit value is as follows:

[0118] D(x,x0,N,M)=ρ(x,x0,M)-ρ(x,x0,N).

[0119] In a specific embodiment, if the minimum conversion cost x0 = 2900, the conversion cost range X0 is [2700, 3100], the conversion cost meets the required range X0 is set to [1900, 3400], and the conversion cost meets the required range and the required range in specific cases is [1400,3900], then:

[0120]

[0121]

[0122]

[0123] k1(2900)=0.5.

[0124] In some embodiments, the steps of inputting a preset parameter combination into the transformation tree, traversing the corresponding leaf branches to determine a plurality of transformation strategies, and calculating and determining the corresponding goodness of each transformation strategy include:

[0125] Step S401: taking the leaf node of the leaf branch corresponding to the preset parameter combination as the second node;

[0126] Step S402: Use the parent node corresponding to the second node as the third node; remove the second node from the child nodes of the third node, and use the remaining nodes as a child node group;

[0127] Step S403, determining whether the child node group is empty, if the child node group is not empty, executing step S404; if the child node group is empty, executing step S406;

[0128] Step S404: Select a node from the child node group as the first node, and replace the optional value of the parameter corresponding to the second node with the optional value of the parameter corresponding to the first node to form a new strategy;

[0129] Step S405: After processing the first node, remove the first node from the child node group, and return to step S403;

[0130] Step S406, determining whether the third node is a root node; if the third node is a root node, executing step S408; if the third node is not a root node, executing step S407;

[0131] Step S407: take the third node as the new second node, and take the parent node of the third node as the new third node; readjust the child node group, remove the new second node, and use the remaining nodes as the new child node group, and return to step S403;

[0132] Step S408: When the third node is a root node, the finally generated strategy is used as a conversion strategy to determine multiple conversion strategies.

[0133] In some embodiments, the method is applied to a sub-health analysis database, and the goal is whether the object is in a healthy state. It is assumed that the expected conversion rates of work and rest time, eating habits, and exercise frequency increase in sequence, and a conversion tree is constructed thereby. Input a parameter combination of 2 categories of work and rest time, 1 category of eating habits, and 3 categories of exercise frequency as the improved scheme, and record it as (2,1,3). During reverse traversal, first adjust the leaf node parameter, that is, the exercise frequency, and modify it to 2 categories to obtain a new scheme (2,1,2). Similarly, when the modification of the exercise frequency is completed, reverse traverse to adjust the eating habits to 0 categories, forming a new scheme (2,0,3). And so on, until all adjustable parameter modifications are completed.

[0134] More specifically, the goal is to determine whether a subject is healthy based on changes in three factors (work and rest time, eating habits, and exercise frequency). The categories of each factor are as follows: Work and rest time: 2 categories (assuming good work and rest time and bad work and rest time respectively), eating habits: 1 category (assuming good eating habits), exercise frequency: 3 categories (representing low frequency, medium frequency, and high frequency respectively)

[0135] Suppose we build a transformation tree where each node represents a factor (sleep schedule, eating habits, exercise frequency) and each node can adjust its category. The transformation tree is a structured representation that can be used for reverse traversal, that is, starting from the leaf node (the farthest factor) and adjusting each factor until the desired result is achieved.

[0136] Further, reverse traversal and adjustment steps: the initial parameter combination is (2,1,3), which means: the work and rest time is category 2 (bad work and rest time), the eating habits are category 1 (good diet) and the exercise frequency is category 3 (high frequency).

[0137] First, adjust the exercise frequency: Assume that the reverse traversal starts with the exercise frequency, and first change the exercise frequency from 3 to 2. Assume that this means that the exercise frequency is reduced, which may lead to changes in sub-health status. The new solution is (2,1,2), that is: the work and rest time is 2 categories, the eating habits are 1 category, and the exercise frequency is 2 categories (medium frequency).

[0138] Next, modify the eating habits. Modify the eating habits from category 1 (good) to category 0 (poor), assuming that this represents a change in eating habits that may affect health status.

[0139] The new plan is (2,0,2), that is: the work and rest time is category 2, the eating habits are category 0 (poor), and the exercise frequency is category 2 (medium frequency).

[0140] Finally, adjust the work and rest schedule from Category 2 (bad work and rest schedule) to Category 1 (good work and rest schedule). This is an operation to improve the work and rest schedule.

[0141] The new plan is (1,0,2), that is: the work and rest time is category 1 (good work and rest time), the eating habits are category 0 (poor), and the exercise frequency is category 2 (moderate frequency).

[0142] According to the logic of reverse traversal, other factors can be adjusted or the categories of each factor can be adjusted recursively to find the optimal solution. The purpose of reverse traversal is to gradually change each factor and eventually find the parameter combination that optimizes the health status.

[0143] In some embodiments, this method is used in a menu design database, with the goal of whether the user accepts the set meal. It is assumed that the expected conversion rate of desserts is lower than that of side dishes. The main dish parameters are non-adjustable parameters that cannot be modified, and a conversion tree is constructed accordingly. A parameter combination of 3 categories of main dishes, 2 categories of desserts, and 1 category of side dishes is selected as a solution and recorded as (3,2,1). When traversing in reverse, first adjust the leaf node parameters, that is, the side dishes, and modify them to 2 categories to obtain a new solution (3,2,2). Similarly, when the modification of the side dishes is completed, reverse traverse to adjust the desserts to 3 categories, forming a new solution (3,3,1). And so on, until all adjustable parameters are modified.

[0144] Furthermore, the non-adjustable parameter is a main dish, and the optional values ​​corresponding to the non-adjustable parameter include one or more categories of main dishes; the adjustable parameters include side dishes and desserts, and the optional values ​​corresponding to the side dishes include one or more categories of side dishes; the optional values ​​corresponding to the desserts include one or more categories of side dishes.

[0145] Specifically, first, clarify the different options for each parameter: Main course: There are 3 categories to choose from (for example: A, B, C), and this parameter cannot be adjusted; Dessert: There are 2 categories to choose from (for example: X, Y), the conversion rate of this parameter is lower than that of side dishes, and it can be adjusted; Side dishes: There is 1 category to choose from (for example: S), the conversion rate of this parameter is higher, so it needs to be adjusted. The initial solution is (3,2,1), that is: choose 1 of the 3 categories for the main course, 1 of the 2 categories for the dessert, and 1 of the side dishes.

[0146] When traversing in reverse, start with the side dishes and make adjustments. The initial side dish option is 1 category, first increase it to 2 categories, and get a new solution (3,2,2). If there are more side dish options, continue to make adjustments until all possible side dish optional values ​​are traversed.

[0147] Next, adjust the dessert parameters. After adjusting the side dish parameters, continue to adjust the dessert categories. Starting from the initial solution (3,2,1), adjust the desserts from 2 categories to 3 categories, and get a new solution (3,3,1). If there are more dessert options, you can continue to adjust and form different solutions such as (3,3,2).

[0148] Working backwards means starting with the most detailed parameters (i.e., side dishes) and then working your way up to the parameters for desserts and main courses. Here’s how this process unfolds:

[0149] The initial solution is (3,2,1) (the main course is fixed, the dessert is of 2 categories, and the side dishes are of 1 category); the side dishes are adjusted from 1 category to 2 categories, and the solution is (3,2,2); the dessert parameters are continued to be adjusted: the desserts are adjusted from 2 categories to 3 categories, and the solution is (3,3,1); the side dishes are adjusted from 1 category to 2 categories, and the solution is (3,3,2); the traversal is continued, and finally all the parameters are adjusted, forming all the leaf nodes of the transformation tree.

[0150] To better understand the construction of the transformation tree, consider all combinations of adjustable parameters (desserts and side dishes). The complete steps of the reverse traversal are as follows: Scheme 1: Start from (3,2,1); Side dishes: 1 category → 2 categories, get (3,2,2); Desserts: 2 categories → 3 categories, get (3,3,1); Side dishes: 1 category → 2 categories, get (3,3,2); The final set of solutions is: (3,2,1), (3,2,2), (3,3,1), (3,3,2).

[0151] It can be seen from the above embodiments that by reverse traversal and gradually adjusting the adjustable parameters (such as desserts and side dishes), a conversion tree that can reflect user acceptance is constructed. This can not only effectively analyze the conversion effects of different plans, but also optimize the package design according to the conversion rate of each parameter, thereby improving user satisfaction and acceptance of the choice.

[0152] In some embodiments, the step of inputting a preset parameter combination into the transformation tree and traversing its corresponding leaf branches to determine a plurality of transformation strategies includes:

[0153] Step S4001, detecting whether the number of the conversion strategies reaches a preset number threshold, and if so, continuing to execute the steps after inputting a preset parameter combination into the conversion tree and traversing its corresponding leaf branches to determine multiple conversion strategies;

[0154] Step S4002: If not reached, increase the optional values ​​of the non-adjustable parameters and / or adjustable parameters, and return to execute the step of obtaining multiple parameters in the sample data set, the optional value of each parameter, and the target frequency reached and the target frequency not reached corresponding to the optional value, until the number of conversion strategies reaches the preset quantity threshold.

[0155] Step S50, sorting the multiple conversion strategies according to the corresponding excellence of each conversion strategy to determine a excellence sequence, detecting whether the conversion strategies ranked within a preset threshold range in the excellence sequence meet the expected results, and if so, outputting the conversion strategies that meet the expected results as alternative conversion strategies to complete the generation of the thing state category conversion strategies.

[0156] A preset parameter combination is input into the transformation tree, and its corresponding leaf branches are traversed to determine multiple transformation strategies. After calculating and determining the corresponding optimality of each transformation strategy, the multiple transformation strategies are sorted according to the corresponding optimality of each transformation strategy to determine a optimality sequence, and it is detected whether the transformation strategies ranked within a preset threshold range in the optimality sequence meet the expected results. If so, the transformation strategies that meet the expected results are output as alternative transformation strategies to complete the generation of the thing state category transformation strategy.

[0157] Specifically, all conversion strategies will be sorted according to the goodness value of each conversion strategy. Strategies with high goodness will be ranked first, and strategies with low goodness will be ranked last. This can help quickly identify which strategies may be optimal or most in line with the expected results. The expected result refers to the target state or standard that is expected to be achieved during the conversion process. The expected result can be a specific target state or a certain optimization goal (such as minimizing costs, maximizing effects, etc.). By testing the conversion strategies after goodness sorting, determine which conversion strategies can meet the expected results. If the results of certain strategies meet expectations, these strategies are considered feasible.

[0158] The alternative transformation strategies, i.e., those transformation strategies that meet the expected results, are considered effective and can be used as candidate strategies for subsequent decision-making or further analysis.

[0159] Ultimately, the expected conversion strategy will be output as an optimized alternative for further decision-making or execution.

[0160] It can be seen from the above embodiments that, compared with the prior art, the solutions in the prior art are often isolated, lack a comprehensive comparison and in-depth analysis of the performance, applicable conditions and advantages and disadvantages of different solutions, often ignore the important influence of parameter adjustability on mining results, and ignore the analysis of intelligently changing label results through parameter adjustment. The present application includes but is not limited to the following beneficial effects:

[0161] First, the method for generating a strategy for transforming the state of things in the present application can not only systematically compare the similarities and differences between different schemes, reveal the internal connections and transformation rules between them, but also distinguish the parameter adjustability, so as to flexibly adjust the mining strategy according to the specific application scenario and data characteristics, thereby obtaining a more accurate and comprehensive state change analysis result;

[0162] Secondly, the method for generating transformation strategies for the state categories of things in this application constructs a transformation tree and then arranges the importance of parameter improvements. By traversing the transformation tree, new transformation plans are generated; this application introduces a goodness ranking, which enables a comprehensive consideration of the cost and efficiency between plans, and extracts alternative transformation strategies (plans). In general, the plans generated by this application can better adapt to data mining of structured and unstructured data sets in a variety of scenarios.

[0163] See also Figure 2 , a device for generating a transformation strategy for a state of thing category provided to meet one of the purposes of the present application, comprises a parameter acquisition module 1100, an expected transformation rate determination module 1200, a transformation tree construction module 1300, a transformation strategy goodness determination module 1400 and a transformation strategy determination module 1500. The parameter acquisition module 1100 is configured to respond to a transformation strategy generation instruction for a state of thing category, obtain multiple parameters in a sample data set, an optional value for each parameter, and the target frequency reached and the target frequency not reached corresponding to the optional value, wherein the parameters include adjustable parameters and non-adjustable parameters; the expected transformation rate determination module 1200 is configured to calculate and determine the expected transformation rate of each adjustable parameter according to the target frequency reached and the target frequency not reached corresponding to the optional value of each adjustable parameter; the transformation tree construction module 1300 is configured to set the non-adjustable parameter as a root node, construct a transformation tree according to the expected transformation rate of each adjustable parameter and its corresponding optional value, and perform pruning optimization on the transformation tree, wherein the transformation tree Each leaf branch represents a selection of an adjustable parameter, and the leaf node of the transformation tree represents a parameter combination; the transformation strategy goodness determination module 1400 is configured to input a preset parameter combination into the transformation tree, traverse the corresponding leaf branches to determine multiple transformation strategies, and calculate and determine the corresponding goodness of each transformation strategy, wherein the transformation strategy represents the combination of optional values ​​corresponding to each parameter; the transformation strategy determination module 1500 is configured to sort the multiple transformation strategies according to the goodness corresponding to each transformation strategy to determine a goodness sequence, detect whether the transformation strategies ranked within a preset threshold range in the goodness sequence meet the expected results, and if so, output the transformation strategy that meets the expected results as an alternative transformation strategy to complete the generation of the thing state category transformation strategy.

[0164] Based on any embodiment of this application, please refer to Figure 3 Another embodiment of the present application further provides an electronic device, which can be implemented by a computer device, such as Figure 3As shown, a schematic diagram of the internal structure of a computer device. The computer device includes a processor, a computer-readable storage medium, a memory, and a network interface connected via a system bus. Among them, the computer-readable storage medium of the computer device stores an operating system, a database, and computer-readable instructions. The database may store a control information sequence. When the computer-readable instructions are executed by the processor, the processor may implement a method for generating a thing state category conversion strategy. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The memory of the computer device may store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor may execute the thing state category conversion strategy generation method of the present application. The network interface of the computer device is used to connect and communicate with a terminal. Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0165] In this embodiment, the processor is used to execute Figure 2 The memory stores the program code and various data required to execute the above modules or submodules. The network interface is used to transmit data between user terminals or servers. The memory in this embodiment stores the program code and data required to execute all modules / submodules in the thing state category conversion strategy generation device of this application, and the server can call the program code and data of the server to execute the functions of all submodules.

[0166] The present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the method for generating a transaction status category conversion strategy described in any embodiment of the present application.

[0167] The present application also provides a computer program product, including a computer program / instruction, which, when executed by one or more processors, implements the steps of the method for generating a transaction status category conversion strategy described in any embodiment of the present application.

[0168] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments of the present application can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a computer-readable storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0169] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for generating a strategy for converting a state of things, characterized in that: include: In response to the thing state category conversion strategy generation instruction, a plurality of parameters in the sample data set, an optional value of each parameter, and a target frequency reached and a target frequency not reached corresponding to the optional value are obtained, wherein the parameters include adjustable parameters and non-adjustable parameters; Calculate and determine the expected conversion rate of each adjustable parameter according to the target frequency that has been reached and the target frequency that has not been reached corresponding to the optional value of each adjustable parameter; The non-adjustable parameter is set as a root node, a transformation tree is constructed according to the expected conversion rates of the adjustable parameters and their corresponding optional values, and the transformation tree is pruned and optimized, wherein each leaf branch of the transformation tree represents a selection of an adjustable parameter, and a leaf node of the transformation tree represents a parameter combination; Input a preset parameter combination into the transformation tree, traverse the corresponding leaf branches to determine a plurality of transformation strategies, and calculate and determine the corresponding goodness of each transformation strategy, wherein the transformation strategy represents a combination constructed by the optional values ​​corresponding to the adjustable parameters and the non-adjustable parameters; The multiple conversion strategies are sorted according to the corresponding excellence of each conversion strategy to determine the excellence sequence, and the conversion strategies ranked within the preset threshold range in the excellence sequence are detected to see whether they meet the expected results. If so, the conversion strategies that meet the expected results are output as alternative conversion strategies to complete the generation of the thing state category conversion strategy.

2. The method for generating a thing state category conversion strategy according to claim 1, characterized in that: The steps of setting the non-adjustable parameter as a root node, constructing a transformation tree according to the expected conversion rates of the adjustable parameters and their corresponding optional values, and performing pruning optimization on the transformation tree include: Acquire each root node to construct a root node group, and sort the expected conversion rates of each adjustable parameter in ascending order to construct an adjustable parameter sequence; Selecting an adjustable parameter in order from the adjustable parameter sequence as a first adjustable parameter; deriving a corresponding child node from each root node in the root node group according to an optional value of the first adjustable parameter; The derived child nodes are used as a new root node group, the first adjustable parameter is replaced with a second adjustable parameter, and the step of deriving corresponding child nodes from each root node in the root node group according to the optional value of the second adjustable parameter is executed until each adjustable parameter in the adjustable parameter sequence is traversed, so as to construct the transformation tree and perform pruning optimization on the transformation tree.

3. The method for generating a thing state category conversion strategy according to claim 1, characterized in that: The steps of inputting a preset parameter combination into the transformation tree, traversing the corresponding leaf branches to determine a plurality of transformation strategies, and calculating and determining the corresponding goodness of each transformation strategy include: Step S401: taking the leaf node of the leaf branch corresponding to the preset parameter combination as the second node; Step S402: Use the parent node corresponding to the second node as the third node; remove the second node from the child nodes of the third node, and use the remaining nodes as a child node group; Step S403, determining whether the child node group is empty, if the child node group is not empty, executing step S404; if the child node group is empty, executing step S406; Step S404: Select a node from the child node group as the first node, and replace the optional value of the parameter corresponding to the second node with the optional value of the parameter corresponding to the first node to form a new strategy; Step S405: After processing the first node, remove the first node from the child node group, and return to step S403; Step S406, determining whether the third node is a root node; if the third node is a root node, executing step S408; if the third node is not a root node, executing step S407; Step S407: take the third node as the new second node, and take the parent node of the third node as the new third node; readjust the child node group, remove the new second node, and use the remaining nodes as the new child node group, and return to step S403; Step S408: When the third node is a root node, the finally generated strategy is used as a conversion strategy to determine multiple conversion strategies.

4. The method for generating a thing state category conversion strategy according to claim 1, characterized in that: The steps of inputting a preset parameter combination into the transformation tree and traversing the corresponding leaf branches to determine a plurality of transformation strategies include: Detecting whether the number of the transformation strategies reaches a preset number threshold, and if so, continuing to execute the steps after inputting the preset parameter combination into the transformation tree and traversing the corresponding leaf branches to determine multiple transformation strategies; If not reached, increase the optional values ​​of non-adjustable parameters and / or adjustable parameters, and return to execute the steps of obtaining multiple parameters in the sample data set, the optional value of each parameter, and the target frequency reached and the target frequency not reached corresponding to the optional value, until the number of conversion strategies reaches the preset quantity threshold.

5. The method for generating a thing state category conversion strategy according to claim 1, characterized in that: The expression of the goodness corresponding to each transformation strategy is: O=α1k1+α2k2, Among them, O represents goodness, α1 and α2 represent weights, k1 represents the conversion cost correlation, and k2 represents the expected conversion rate; The calculation formula of conversion cost correlation is as follows: Wherein, k1(x) represents the conversion cost correlation, ρ represents the extension distance calculation operation, which is used to calculate the distance or difference between elements, D represents the extension position value calculation operation, which is used to calculate the position or sorting of elements, x0 represents the minimum conversion cost, x represents the conversion cost, X represents the range where the conversion cost meets the requirements, and X0 represents several ranges in X with smaller conversion costs. represents X and the range of requirements that are met in a particular case, Represents the selectable range for all conversion costs.

6. The method for generating a thing state category conversion strategy according to claim 1, characterized in that: The step of calculating and determining the expected conversion rate of each adjustable parameter according to the target frequency that has been reached and the target frequency that has not been reached corresponding to the optional value of each adjustable parameter includes: The calculation formula of the expected conversion rate includes: E(A)=Average(E + (TO i )), Where i≠j, for parameter A, E(A) represents the expected conversion rate, Average(E + (A i )) represents all non-negative E(A i ), E(A i →A j ) is the expected conversion rate after the parameter is adjusted from the i-th optional value to the j-th optional value, P(A i ) is the frequency of the i-th optional value, P(A i →B) is the target frequency of the i-th optional value that has been reached, is the confidence of the jth optional value, is the target frequency of the i-th optional value that has not been reached.

7. The method for generating a thing state category conversion strategy according to any one of claims 1 to 6, characterized in that: The non-adjustable parameter is the main dish, and the optional values ​​corresponding to the non-adjustable parameter include one or more categories of main dishes; the adjustable parameters include side dishes and desserts, and the optional values ​​corresponding to the side dishes include one or more categories of side dishes; the optional values ​​corresponding to the desserts include one or more categories of side dishes.

8. A device for generating a strategy for converting a state of things, characterized in that: include: A parameter acquisition module is configured to respond to the thing state category conversion strategy generation instruction, obtain multiple parameters in the sample data set, the optional value of each parameter, and the target frequency reached and the target frequency not reached corresponding to the optional value, wherein the parameters include adjustable parameters and non-adjustable parameters; An expected conversion rate determination module is configured to calculate and determine the expected conversion rate of each adjustable parameter according to the target frequency that has been reached and the target frequency that has not been reached corresponding to the optional value of each adjustable parameter; a conversion tree construction module, configured to set the non-adjustable parameter as a root node, construct a conversion tree according to the expected conversion rates of the adjustable parameters and their corresponding optional values, and perform pruning optimization on the conversion tree, wherein each leaf branch of the conversion tree represents a selection of an adjustable parameter, and a leaf node of the conversion tree represents a parameter combination; A transformation strategy goodness determination module is configured to input a preset parameter combination into the transformation tree, traverse the corresponding leaf branches to determine multiple transformation strategies, and calculate and determine the goodness corresponding to each transformation strategy, wherein the transformation strategy represents the optional value combination corresponding to each parameter; The conversion strategy determination module is configured to sort the multiple conversion strategies according to the corresponding excellence of each conversion strategy to determine the excellence sequence, detect whether the conversion strategies ranked within a preset threshold range in the excellence sequence meet the expected results, and if so, output the conversion strategies that meet the expected results as alternative conversion strategies to complete the generation of the thing state category conversion strategies.

9. An electronic device, comprising a central processing unit and a memory, characterized in that: The central processing unit is used to call and run the computer program stored in the memory to execute the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: It stores a computer program implemented according to the method described in any one of claims 1 to 7 in the form of computer-readable instructions, and when the computer program is called and executed by a computer, the steps included in the corresponding method are executed.

Images