A power marketing data processing method based on big data and machine learning

Abstract

The present application discloses a method for processing power marketing data based on big data and machine learning, belonging to the field of computer technology. Through the technical solution provided by the embodiments of the present application, the first power marketing data, the second power marketing data, the marketing behavior data, and the marketing environment data of the target power marketing behavior are obtained. The set of marketed objects, the set of object data, and the marketing behavior feedback data corresponding to the target power marketing behavior are obtained. The obtained data is processed through the first evaluation model, the second evaluation model, and the third evaluation model to obtain the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter, realizing the distributed processing of power marketing data. Based on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter, the target marketing effect parameter of the target power marketing behavior is determined, completing the processing of the power marketing data of the target power marketing behavior, and the processing efficiency is relatively high.

Description

Technical Field

[0001] This application relates to the field of computer technology, and particularly to a method for processing power marketing data based on big data and machine learning. Background Art

[0002] With the development of society, power enterprises also need to carry out power marketing activities to promote enterprise business and expand the scope of enterprise business. After carrying out power marketing activities, corresponding power marketing data can be obtained, and the power marketing data needs to be processed and analyzed in order to evaluate the effect of power marketing activities, so as to facilitate the organization of subsequent power marketing activities.

[0003] In the related art, the analysis of power marketing data is usually carried out manually. When there is a large amount of power marketing data, a large number of personnel are required to process and analyze it, resulting in low processing efficiency of power marketing data.

[0004] Therefore, how to improve the processing efficiency of power marketing data is a research hotspot for power enterprises. Summary of the Invention

[0005] An embodiment of this application provides a method for processing power marketing data based on big data and machine learning, which can improve the processing efficiency of power marketing data. The technical solution is as follows:

[0006] On the one hand, a method for processing power marketing data based on big data and machine learning is provided. The method includes:

[0007] Obtain the first power marketing data, the second power marketing data, the marketing behavior data, and the marketing environment data of the target power marketing activity, and obtain the object data set of the set of objects to be marketed corresponding to the target power marketing activity and the marketing behavior feedback data. The first power marketing data is the estimated power marketing data before implementing the target power marketing activity, and the second power marketing data is the actual power marketing data after implementing the target power marketing activity;

[0008] Through the first evaluation model, based on the first power marketing data and the second power marketing data, determine the first marketing effect parameter of the target power marketing activity;

[0009] Through the second evaluation model, based on the second power marketing data and the marketing environment data, determine the second marketing effect parameter of the target power marketing activity;

[0010] Through the third evaluation model, based on the marketing behavior data, the object data set, and the marketing behavior feedback data, determine the third marketing effect parameter of the target power marketing activity;

[0011] Determine the target marketing effect parameter of the target power marketing behavior based on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter of the target power marketing behavior.

[0012] In a possible implementation manner, the determining the first marketing effect parameter of the target power marketing behavior based on the first power marketing data and the second power marketing data includes:

[0013] Based on the first power marketing data, determine the first marketing sub-data of the target power marketing behavior in multiple dimensions;

[0014] Based on the second power marketing data, determine the second marketing sub-data of the target power marketing behavior in the multiple dimensions;

[0015] Based on the first marketing sub-data and the second marketing sub-data of the target power marketing behavior in multiple dimensions, determine the first marketing effect parameter of the target power marketing behavior.

[0016] In a possible implementation manner, the determining the first marketing effect parameter of the target power marketing behavior based on the first marketing sub-data and the second marketing sub-data of the target power marketing behavior in multiple dimensions includes:

[0017] Based on the first marketing sub-data and the second marketing sub-data of the target power marketing behavior in multiple dimensions, determine the marketing data difference data of the target power marketing behavior in each dimension;

[0018] Based on the weights of each dimension and the marketing data difference data of the target power marketing behavior in each dimension, determine the first marketing effect parameter of the target power marketing behavior.

[0019] In a possible implementation manner, the method for determining the weights of each dimension includes:

[0020] For any one of the multiple dimensions, obtain the dimension description information of the dimension;

[0021] Based on the dimension description information of the dimension, the marketing environment data, and the object data set, determine the weight of the dimension.

[0022] In a possible implementation manner, the determining the second marketing effect parameter of the target power marketing behavior based on the second power marketing data and the marketing environment data includes:

[0023] Based on the second power marketing data, determine the second marketing sub-data of the target power marketing behavior in the multiple dimensions;

[0024] Based on the marketing environment data, determine the benchmark marketing sub-data for the multiple dimensions, where the benchmark marketing sub-data is the mean of the marketing sub-data corresponding to multiple power marketing behaviors;

[0025] Based on the second marketing sub-data and the benchmark marketing sub-data of the target power marketing behavior in the multiple dimensions, determine the second marketing effect parameter.

[0026] In a possible implementation manner, determining the third marketing effect parameter of the target power marketing behavior based on the marketing behavior data, the object data set, and the marketing behavior feedback data includes:

[0027] Based on the marketing behavior data and the object data set, determine the matching parameter between the target marketing behavior and the marketed object set;

[0028] Based on the object data set and the marketing behavior feedback data, determine the evaluation parameter of the marketed object set for the target marketing behavior;

[0029] Based on the matching parameter and the evaluation parameter, determine the third marketing effect parameter.

[0030] In a possible implementation manner, determining the matching parameter between the target marketing behavior and the marketed object set based on the marketing behavior data and the object data set includes:

[0031] Based on the marketing behavior data, determine multiple target object types corresponding to the target marketing behavior;

[0032] Based on the object data set, determine multiple reference object types corresponding to the marketed object set, where the reference object type is the object type of the marketed objects in the marketed object set;

[0033] Based on the multiple target object types and the multiple reference object types, determine the matching parameter between the target marketing behavior and the marketed object set.

[0034] In a possible implementation manner, determining the evaluation parameter of the marketed object set for the target marketing behavior based on the object data set and the marketing behavior feedback data includes:

[0035] Based on the object data set, determine the feedback credibility of multiple marketed objects in the marketed object set;

[0036] Based on the feedback credibility of multiple marketed objects in the set of marketed objects, filter out target feedback data from the marketing behavior feedback data, where the target feedback data includes sub-feedback data provided by marketed objects whose feedback credibility is greater than or equal to the credibility threshold;

[0037] Based on the target feedback data, determine the evaluation parameters of the set of marketed objects for the target marketing behavior.

[0038] In one possible implementation manner, the determining the target marketing effect parameter of the target power marketing behavior based on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter of the target power marketing behavior includes:

[0039] Perform weighted fusion on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter of the target power marketing behavior to obtain the target marketing effect parameter of the target power marketing behavior.

[0040] In one possible implementation manner, after determining the target marketing effect parameter of the target power marketing behavior based on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter of the target power marketing behavior, the method further includes:

[0041] Based on the marketing behavior data, the marketing environment data, and the target marketing effect parameter, generate a modification suggestion for the target marketing behavior.

[0042] On the one hand, a power marketing data processing device based on big data and machine learning is provided, and the device includes:

[0043] An acquisition module, configured to acquire the first power marketing data, the second power marketing data, the marketing behavior data, and the marketing environment data of the target power marketing behavior, and acquire the object data set and the marketing behavior feedback data of the set of marketed objects corresponding to the target power marketing behavior, where the first power marketing data is the estimated power marketing data before implementing the target power marketing behavior, and the second power marketing data is the actual power marketing data after implementing the target power marketing behavior;

[0044] A first marketing effect parameter determination module, configured to determine the first marketing effect parameter of the target power marketing behavior based on the first power marketing data and the second power marketing data through a first evaluation model;

[0045] A second marketing effect parameter determination module, configured to determine the second marketing effect parameter of the target power marketing behavior based on the second power marketing data and the marketing environment data through a second evaluation model;

[0046] A third marketing effect parameter determination module, configured to determine a third marketing effect parameter of the target power marketing behavior based on the marketing behavior data, the object data set, and the marketing behavior feedback data through a third evaluation model;

[0047] A target marketing effect parameter determination module, configured to determine a target marketing effect parameter of the target power marketing behavior based on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter of the target power marketing behavior.

[0048] In a possible implementation manner, the first marketing effect parameter determination module is configured to determine first marketing sub-data of the target power marketing behavior in multiple dimensions based on the first power marketing data; determine second marketing sub-data of the target power marketing behavior in the multiple dimensions based on the second power marketing data; and determine a first marketing effect parameter of the target power marketing behavior based on the first marketing sub-data and the second marketing sub-data of the target power marketing behavior in multiple dimensions.

[0049] In a possible implementation manner, the first marketing effect parameter determination module is configured to determine marketing data difference data of the target power marketing behavior in each dimension based on the first marketing sub-data and the second marketing sub-data of the target power marketing behavior in multiple dimensions; and determine a first marketing effect parameter of the target power marketing behavior based on the weights of each dimension and the marketing data difference data of the target power marketing behavior in each dimension.

[0050] In a possible implementation manner, the device further includes a weight determination module, configured to obtain dimension description information of any dimension in the multiple dimensions; and determine a weight of the dimension based on the dimension description information of the dimension, the marketing environment data, and the object data set.

[0051] In a possible implementation manner, the second marketing effect parameter determination module is configured to determine second marketing sub-data of the target power marketing behavior in the multiple dimensions based on the second power marketing data; determine benchmark marketing sub-data of the multiple dimensions based on the marketing environment data, where the benchmark marketing sub-data is an average value of marketing sub-data corresponding to multiple power marketing behaviors; and determine the second marketing effect parameter based on the second marketing sub-data and the benchmark marketing sub-data of the target power marketing behavior in the multiple dimensions.

[0052] In a possible implementation, the third marketing effect parameter determination module is configured to determine a matching parameter between the target marketing behavior and the set of marketed objects based on the marketing behavior data and the object data set; determine an evaluation parameter of the set of marketed objects for the target marketing behavior based on the object data set and the marketing behavior feedback data; and determine the third marketing effect parameter based on the matching parameter and the evaluation parameter.

[0053] In a possible implementation, the third marketing effect parameter determination module is configured to determine multiple target object types corresponding to the target marketing behavior based on the marketing behavior data; determine multiple reference object types corresponding to the set of marketed objects based on the object data set, where the reference object type is the object type of the marketed objects in the set of marketed objects; and determine a matching parameter between the target marketing behavior and the set of marketed objects based on the multiple target object types and the multiple reference object types.

[0054] In a possible implementation, the third marketing effect parameter determination module is configured to determine the feedback credibility of multiple marketed objects in the set of marketed objects based on the object data set; screen out target feedback data from the marketing behavior feedback data based on the feedback credibility of the multiple marketed objects in the set of marketed objects, where the target feedback data includes sub-feedback data provided by marketed objects with a feedback credibility greater than or equal to a credibility threshold; and determine an evaluation parameter of the set of marketed objects for the target marketing behavior based on the target feedback data.

[0055] In a possible implementation, the target marketing effect parameter determination module is configured to perform weighted fusion on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter of the target power marketing behavior to obtain the target marketing effect parameter of the target power marketing behavior.

[0056] In a possible implementation, the device further includes:

[0057] A modification suggestion generation module, configured to generate a modification suggestion for the target marketing behavior based on the marketing behavior data, the marketing environment data, and the target marketing effect parameter.

[0058] On the one hand, a computer device is provided. The computer device includes one or more processors and one or more memories. At least one computer program is stored in the one or more memories, and the computer program is loaded and executed by the one or more processors to implement the power marketing data processing method based on big data and machine learning.

[0059] On the one hand, a computer-readable storage medium is provided, in which at least one computer program is stored, and the computer program is loaded and executed by a processor to implement the power marketing data processing method based on big data and machine learning.

[0060] On the one hand, a computer program product or a computer program is provided. The computer program product or the computer program includes program code, and the program code is stored in a computer-readable storage medium. A processor of a computer device reads the program code from the computer-readable storage medium, and the processor executes the program code, so that the computer device executes the above-mentioned power marketing data processing method based on big data and machine learning.

[0061] Through the technical solution provided by the embodiments of the present application, first power marketing data, second power marketing data, marketing behavior data, and marketing environment data of a target power marketing behavior are obtained. A set of marketed objects, an object data set corresponding to the target power marketing behavior, and marketing behavior feedback data are obtained. The obtained data is processed through a first evaluation model, a second evaluation model, and a third evaluation model to obtain a first marketing effect parameter, a second marketing effect parameter, and a third marketing effect parameter, realizing distributed processing of power marketing data. Based on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter, a target marketing effect parameter of the target power marketing behavior is determined, completing the processing of the power marketing data of the target power marketing behavior, and the processing efficiency is relatively high. Description of the Drawings

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0063] Figure 1 It is a schematic diagram of an implementation environment of a power marketing data processing method based on big data and machine learning provided by the embodiments of the present application;

[0064] Figure 2 It is a flowchart of a power marketing data processing method based on big data and machine learning provided by the embodiments of the present application;

[0065] Figure 3 It is a flowchart of another power marketing data processing method based on big data and machine learning provided by the embodiments of the present application;

[0066] Figure 4It is a schematic structural diagram of a power marketing data processing device provided by an embodiment of the present application based on big data and machine learning;

[0067] Figure 5 It is a schematic structural diagram of a server provided by an embodiment of the present application. Specific embodiments

[0068] To make the objectives, technical solutions, and advantages of the present application clearer, the following will further describe the embodiments of the present application in detail with reference to the accompanying drawings.

[0069] In the present application, terms such as "first" and "second" are used to distinguish identical or similar items with basically the same functions and effects. It should be understood that there is no logical or chronological dependency between "first", "second", and "nth", nor are the quantity and execution order limited.

[0070] Artificial Intelligence (AI) is to use a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, a theory, method, technology, and application system that perceives the environment, acquires knowledge, and uses knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a way similar to human intelligence. Artificial intelligence also studies the design principles and implementation methods of various intelligent machines, enabling the machines to have the functions of perception, reasoning, and decision-making.

[0071] Machine Learning (ML) is an interdisciplinary subject that involves multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory. It specifically studies how a computer simulates or realizes human learning behaviors to acquire new knowledge or skills and reorganize the existing knowledge sub-models to continuously improve its own performance. Machine learning is the core of artificial intelligence and the fundamental way to make a computer intelligent, and its applications cover all fields of artificial intelligence. Machine learning and deep learning usually include technologies such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and teaching learning.

[0072] Semantic feature: A feature used to represent the semantics expressed by text. Different texts can correspond to the same semantic feature. For example, the texts "What's the weather like today" and "How's the weather today" can correspond to the same semantic feature. A computer device can map the characters in the text into character vectors, and based on the relationships between the characters, combine and operate on the character vectors to obtain the semantic feature of the text. For example, the computer device can adopt the Bidirectional Encoder Representations from Transformers (BERT) of the codec.

[0073] Normalization: Maps a sequence of numbers with different value ranges to the interval (0, 1) for easy data processing. In some cases, the normalized values can be directly implemented as probabilities.

[0074] Embedded Coding: Embedded Coding represents a correspondence relationship mathematically, that is, maps the data in the X space to the Y space through a function F, where the function F is an injective function, and the result of the mapping is structure preservation. The injective function means that the data after mapping corresponds uniquely to the data before mapping, and structure preservation means that the size relationship of the data before mapping is the same as that of the data after mapping. For example, there are data X1 and X2 before mapping, and Y1 corresponding to X1 and Y2 corresponding to X2 are obtained after mapping. If the data X1 > X2 before mapping, then correspondingly, the data Y1 after mapping is greater than Y2. For words, it is to map the words to another space for subsequent machine learning and processing.

[0075] Attention weight: Can represent the importance of a certain data during the training or prediction process. Importance represents the magnitude of the influence of the input data on the output data. The data with high importance has a higher corresponding attention weight value, and the data with low importance has a lower corresponding attention weight value. In different scenarios, the importance of the data is not the same, and the process of training the attention weight of the model is also the process of determining the importance of the data.

[0076] Figure 1 It is a schematic diagram of the implementation environment of a power marketing data processing method provided by an embodiment of the present application. Refer to Figure 1 In this implementation environment, a terminal 110 and a server 140 can be included.

[0077] The terminal 110 is connected to the server 140 through a wireless network or a wired network. Optionally, the terminal 110 is a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal 110 installs and runs an application program that supports power marketing data processing.

[0078] The server 140 is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery network (CDN), and big data and artificial intelligence platforms. The server 140 provides background services for application programs running on the terminal 110.

[0079] Figure 2 It is a flowchart of a power marketing data processing method based on big data and machine learning provided by an embodiment of the present application. Refer to Figure 2 Taking the server as the execution subject as an example, the method includes the following steps.

[0080] 201. The server obtains the first power marketing data, the second power marketing data, the marketing behavior data, and the marketing environment data of the target power marketing behavior, and obtains the object data set of the set of marketed objects corresponding to the target power marketing behavior and the marketing behavior feedback data. The first power marketing data is the estimated power marketing data before implementing the target power marketing behavior, and the second power marketing data is the actual power marketing data after implementing the target power marketing behavior.

[0081] Among them, the target power marketing behavior refers to a power marketing behavior that has been implemented and is to be analyzed. The power marketing behavior refers to a marketing behavior related to electricity or power enterprises. For example, a power enterprise promoting power business belongs to a power marketing behavior. The power marketing data is data representing the marketing result of the power marketing behavior. The first power marketing data is the estimated power marketing data before implementing the target power marketing behavior, and thus can represent the estimated marketing result of the target power marketing behavior; the second power marketing data is the actual power marketing data after implementing the target power marketing behavior, and thus can represent the actual marketing result of the target power marketing behavior. The marketing behavior data is used to represent the behavior situation of the target power marketing behavior, that is, to reflect the situation of multiple marketing measures in the target power marketing behavior. The marketing environment data is used to represent the situation of the power marketing environment. Generally speaking, it is determined according to the results of multiple power marketing behaviors. The set of marketed objects includes multiple marketed objects, the object data set includes the object data of multiple marketed objects, and the object data is used to represent the object situation of the marketed objects. The marketing behavior feedback data includes the feedback data of multiple marketed objects and is used to represent the evaluation of the target power marketing behavior by the marketed objects. In some embodiments, the marketed object refers to the marketed user.

[0082] 202. The server determines a first marketing effect parameter of the target power marketing behavior based on the first power marketing data and the second power marketing data through a first evaluation model.

[0083] Among them, the first marketing effect parameter is used to represent the marketing effect evaluation of the target power marketing behavior in the first aspect, and the first evaluation model is a machine learning model used to determine the first marketing effect parameter.

[0084] 203. The server determines a second marketing effect parameter of the target power marketing behavior based on the second power marketing data and the marketing environment data through a second evaluation model.

[0085] Among them, the second marketing effect parameter is used to represent the marketing effect evaluation of the target power marketing behavior in the second aspect, and the second evaluation model is a machine learning model used to determine the second marketing effect parameter.

[0086] 204. The server determines a third marketing effect parameter of the target power marketing behavior based on the marketing behavior data, the object data set, and the marketing behavior feedback data through a third evaluation model.

[0087] Among them, the third marketing effect parameter is used to represent the marketing effect evaluation of the target power marketing behavior in the third aspect, and the third evaluation model is a machine learning model used to determine the third marketing effect parameter.

[0088] 205. The server determines a target marketing effect parameter of the target power marketing behavior based on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter of the target power marketing behavior.

[0089] Among them, the target marketing effect parameter is the finally obtained marketing effect parameter, which can be regarded as the processing result of the marketing data of the target power marketing behavior.

[0090] Through the technical solution provided by the embodiments of the present application, the first power marketing data, the second power marketing data, the marketing behavior data, and the marketing environment data of the target power marketing behavior are obtained. The set of marketed objects, the object data set, and the marketing behavior feedback data corresponding to the target power marketing behavior are obtained. The first evaluation model, the second evaluation model, and the third evaluation model are used to process the obtained data to obtain the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter, realizing the distributed processing of power marketing data. Based on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter, the target marketing effect parameter of the target power marketing behavior is determined, completing the processing of the power marketing data of the target power marketing behavior, and the processing efficiency is relatively high.

[0091] The above steps 201-205 are a brief description of the technical solution provided by the embodiments of the present application. Next, some examples will be combined to more clearly illustrate the technical solution provided by the embodiments of the present application. See Figure 3 , taking the execution entity as the server as an example, the method includes the following steps.

[0092] 301. The server obtains the first power marketing data, the second power marketing data, the marketing behavior data, and the marketing environment data of the target power marketing behavior, and obtains the object data set of the target power marketing behavior corresponding to the set of marketed objects and the marketing behavior feedback data. The first power marketing data is the estimated power marketing data before implementing the target power marketing behavior, and the second power marketing data is the actual power marketing data after implementing the target power marketing behavior.

[0093] Among them, the target power marketing behavior refers to a power marketing behavior that has been implemented and is to be analyzed. The power marketing behavior refers to a marketing behavior related to electricity or power enterprises. For example, a power enterprise promoting power business belongs to a power marketing behavior. The power marketing data is data representing the marketing result of the power marketing behavior. The first power marketing data is the estimated power marketing data before implementing the target power marketing behavior, and thus can represent the estimated marketing result of the target power marketing behavior. In some embodiments, the first power marketing data is estimated by marketing personnel. The second power marketing data is the actual power marketing data after implementing the target power marketing behavior, and thus can represent the actual marketing result of the target power marketing behavior. The marketing behavior data is used to represent the behavior situation of the target power marketing behavior, that is, to reflect the situation of multiple marketing measures in the target power marketing behavior. The marketing environment data is used to represent the situation of the power marketing environment. Generally speaking, it is determined according to the results of multiple power marketing behaviors. The set of marketed objects includes multiple marketed objects, the object data set includes the object data of multiple marketed objects, and the object data is used to represent the object situation of the marketed object. The marketing behavior feedback data includes the feedback data of multiple marketed objects and is used to represent the evaluation of the target power marketing behavior by the marketed objects. In some embodiments, the marketed object refers to the marketed user.

[0094] In a possible implementation manner, the server obtains the first power marketing data, the second power marketing data, the marketing behavior data, and the marketing environment data of the target power marketing behavior from the terminal. The server obtains the object data set of the target power marketing behavior corresponding to the set of marketed objects and the marketing behavior feedback data from the terminal.

[0095] 302. The server determines the first marketing effect parameter of the target power marketing behavior through the first evaluation model based on the first power marketing data and the second power marketing data.

[0096] Among them, the first marketing effect parameter is used to represent the marketing effect evaluation of the target power marketing behavior in the first aspect, and the first evaluation model is a machine learning model used to determine the first marketing effect parameter.

[0097] In a possible implementation manner, the server determines the first marketing sub-data of the target power marketing behavior in multiple dimensions based on the first power marketing data. The server determines the second marketing sub-data of the target power marketing behavior in the multiple dimensions based on the second power marketing data. The server determines the first marketing effect parameter of the target power marketing behavior based on the first marketing sub-data and the second marketing sub-data of the target power marketing behavior in multiple dimensions.

[0098] Among them, the multiple dimensions refer to multiple effect dimensions of the target marketing behavior. For example, one dimension is the marketing amount, and another dimension is the marketing revenue. The multiple dimensions are set by technicians according to the actual situation, and the embodiments of the present application do not limit this. The first marketing sub-data of the multiple dimensions includes the first marketing sub-data of each dimension, that is, one dimension corresponds to one first marketing sub-data. Correspondingly, the second marketing sub-data of the multiple dimensions includes the second marketing sub-data of each dimension, that is, one dimension corresponds to one second marketing sub-data. The first marketing effect parameter is an evaluation of the target marketing behavior from the aspect of the difference between the estimated effect and the actual effect.

[0099] In this implementation manner, the first power marketing data is used to obtain the first marketing sub-data in multiple dimensions, the second power marketing data is used to obtain the second marketing sub-data in multiple dimensions, and the first marketing sub-data and the second marketing sub-data in multiple dimensions are used to determine the first marketing effect parameter, so as to realize the evaluation of the target marketing behavior from the perspectives of the estimated effect and the actual effect.

[0100] To illustrate the above implementation manner more clearly, the above implementation manner will be described in several parts below.

[0101] The first part: The server determines the first marketing sub-data of the target power marketing behavior in multiple dimensions based on the first power marketing data.

[0102] In a possible implementation manner, the server splits the first power marketing data using multiple dimensions to obtain the first marketing sub-data of each dimension.

[0103] The second part: The server determines the second marketing sub-data of the target power marketing behavior in the multiple dimensions based on the second power marketing data.

[0104] In a possible implementation manner, the server splits the second power marketing data using multiple dimensions to obtain the second marketing sub-data of each dimension.

[0105] Part III. The server determines the first marketing effect parameter of the target power marketing behavior based on the first marketing sub-data and the second marketing sub-data of the target power marketing behavior in multiple dimensions.

[0106] In a possible implementation manner, the server determines the first marketing data difference of the target power marketing behavior in each dimension based on the first marketing sub-data and the second marketing sub-data of the target power marketing behavior in multiple dimensions. The server determines the first marketing effect parameter of the target power marketing behavior based on the weights of each dimension and the first marketing data difference of the target power marketing behavior in each dimension.

[0107] For example, the server subtracts the first marketing sub-data and the second marketing sub-data of the target power marketing behavior in each dimension to obtain the first marketing data difference of the target power marketing behavior in each dimension. The server uses the weights of each dimension to perform weighted fusion on the first marketing data difference of the target power marketing behavior in each dimension to obtain the first marketing effect parameter of the target power marketing behavior.

[0108] To illustrate the above implementation manner more clearly, the method for determining the weights of each dimension will be described below.

[0109] In a possible implementation manner, for any dimension in the multiple dimensions, the server obtains the dimension description information of the dimension. The server determines the weight of the dimension based on the dimension description information of the dimension, the marketing environment data, and the object data set.

[0110] The dimension description information is a descriptive text that introduces the dimension.

[0111] For example, for any dimension in the multiple dimensions, the server obtains the dimension description information of the dimension from the terminal. The server determines the marketing environment weight of the dimension based on the dimension description information of the dimension and the marketing environment data. The server determines the object weight of the dimension based on the dimension description information of the dimension and the object data set. The server fuses the marketing environment weight and the object weight of the dimension to obtain the weight of the dimension.

[0112] The marketing environment weight is used to represent the importance degree of the dimension in the marketing environment indicated by the marketing environment data, and the object weight is used to represent the importance degree of the dimension in the set of objects to be marketed.

[0113] For example, for any one of the multiple dimensions, the server obtains the dimension description information of this dimension from the terminal. The server inputs the dimension description information of this dimension and the marketing environment data into the first weight determination model, and processes the dimension description information of this dimension and the marketing environment data through the first weight determination model to obtain the marketing environment weight of this dimension. The server inputs the dimension description information of this dimension and the object data set into the second weight determination model, and processes the dimension description information of this dimension and the object data set through the second weight determination model to obtain the object weight of this dimension. The server fuses the marketing environment weight and the object weight of this dimension to obtain the weight of this dimension.

[0114] Among them, both the first weight determination model and the second weight determination model are obtained through training and respectively have the ability to determine the marketing environment weight and the object weight.

[0115] 303. The server determines the second marketing effect parameter of the target power marketing behavior based on the second power marketing data and the marketing environment data through the second evaluation model.

[0116] Among them, the second marketing effect parameter is used to represent the marketing effect evaluation of the target power marketing behavior in the second aspect, and the second evaluation model is a machine learning model used to determine the second marketing effect parameter.

[0117] In a possible implementation manner, the server determines the second marketing sub-data of the target power marketing behavior in the multiple dimensions based on the second power marketing data. The server determines the benchmark marketing sub-data of the multiple dimensions based on the marketing environment data, and the benchmark marketing sub-data is the average value of the marketing sub-data corresponding to multiple power marketing behaviors. The server determines the second marketing effect parameter based on the second marketing sub-data and the benchmark marketing sub-data of the target power marketing behavior in the multiple dimensions.

[0118] Among them, the multiple power marketing behaviors are the implemented power marketing behaviors, and the implementation time of the multiple power marketing behaviors is in the same time period as the implementation time of the target power marketing behavior.

[0119] To more clearly illustrate the above implementation manner, the above implementation manner will be described in several parts below.

[0120] The first part: The server determines the second marketing sub-data of the target power marketing behavior in the multiple dimensions based on the second power marketing data.

[0121] In a possible implementation manner, the server splits the second power marketing data using multiple dimensions to obtain the second marketing sub-data of each dimension.

[0122] In the second part, the server determines the benchmark marketing sub-data for the multiple dimensions based on the marketing environment data, and the benchmark marketing sub-data is the average value of the marketing sub-data corresponding to various power marketing behaviors.

[0123] In a possible implementation, the server splits the marketing environment data using multiple dimensions to obtain the marketing sub-data corresponding to various power marketing behaviors under each dimension. The server determines the average value of the marketing sub-data corresponding to various power marketing behaviors under each dimension as the benchmark marketing sub-data for each dimension.

[0124] In the third part, the server determines the second marketing effect parameter based on the second marketing sub-data and the benchmark marketing sub-data of the target power marketing behavior in the multiple dimensions.

[0125] In a possible implementation, the server determines the second marketing data difference of the target power marketing behavior in each dimension based on the benchmark marketing sub-data and the second marketing sub-data of the target power marketing behavior in the multiple dimensions. The server determines the first marketing effect parameter of the target power marketing behavior based on the weight of each dimension and the second marketing data difference of the target power marketing behavior in each dimension.

[0126] For example, the server subtracts the benchmark marketing sub-data from the second marketing sub-data of the target power marketing behavior in each dimension to obtain the second marketing data difference of the target power marketing behavior in each dimension. The server uses the weights of each dimension to perform weighted fusion on the second marketing data difference of the target power marketing behavior in each dimension to obtain the second marketing effect parameter of the target power marketing behavior.

[0127] 304. The server determines the third marketing effect parameter of the target power marketing behavior through a third evaluation model based on the marketing behavior data, the object data set, and the marketing behavior feedback data.

[0128] Among them, the third marketing effect parameter is used to represent the marketing effect evaluation of the target power marketing behavior in the third aspect, and the third evaluation model is a machine learning model used to determine the third marketing effect parameter.

[0129] In a possible implementation, the server determines the matching parameter between the target marketing behavior and the set of marketed objects based on the marketing behavior data and the object data set. The server determines the evaluation parameter of the set of marketed objects for the target marketing behavior based on the object data set and the marketing behavior feedback data. The server determines the third marketing effect parameter based on the matching parameter and the evaluation parameter.

[0130] Among them, the matching parameter includes the matching parameters between the target marketing behavior and each marketed object in the set of marketed objects.

[0131] To more clearly illustrate the above embodiments, the above embodiments will be described in several parts below.

[0132] First part: The server determines the matching parameter between the target marketing behavior and the set of marketed objects based on the marketing behavior data and the set of object data.

[0133] In a possible implementation, the server determines multiple target object types corresponding to the target marketing behavior based on the marketing behavior data. The server determines multiple reference object types corresponding to the set of marketed objects based on the set of object data, where the reference object type is the object type of the marketed objects in the set of marketed objects. The server determines the matching parameter between the target marketing behavior and the set of marketed objects based on the multiple target object types and the multiple reference object types.

[0134] Among them, the target object type is the object type with a high degree of matching with the target power marketing behavior. The reference object type is the object type of the marketed objects in the set of marketed objects. The matching parameter is used to reflect the degree of matching. In some embodiments, the matching parameter is positively correlated with the degree of matching, that is, the larger the matching parameter, the higher the degree of matching; the smaller the matching parameter, the lower the degree of matching.

[0135] For example, the server inputs the marketing behavior data into the object type prediction model, extracts the feature of the marketing behavior data through the object type prediction model to obtain the behavior data feature of the marketing behavior data. The server determines the multiple target object types based on the behavior data feature through the object type prediction model. The server inputs the set of object data into the object classification model, extracts the features of the set of object data through the object classification model to obtain multiple object data features, and one object data feature corresponds to one marketed object. The server determines the reference object type of each marketed object based on the multiple object data features through the object classification model. The server determines the matching parameter between the target marketing behavior and the set of marketed objects based on the object type overlap degree between the multiple target object types and the multiple reference object types.

[0136] Among them, the object type prediction model is trained based on multiple sample marketing behavior data and multiple labeled object types corresponding to each sample marketing behavior data, and has the ability to predict the object type corresponding to the marketing behavior data. The object classification model is trained based on multiple sample object data and the labeled object types corresponding to each sample object data, and has the ability to predict the object type based on the object data. In some embodiments, the object type prediction model and the object classification model are jointly trained using a set of labeled data.

[0137] Part Two: The server determines the evaluation parameter of the target marketing behavior for the set of objects to be marketed based on the set of object data and the marketing behavior feedback data.

[0138] In a possible implementation manner, the server determines the feedback credibility of multiple objects to be marketed in the set of objects to be marketed based on the set of object data. The server filters out the target feedback data from the marketing behavior feedback data based on the feedback credibility of multiple objects to be marketed in the set of objects to be marketed, and the target feedback data includes the sub-feedback data provided by the objects to be marketed whose feedback credibility is greater than or equal to the credibility threshold. The server determines the evaluation parameter of the target marketing behavior for the set of objects to be marketed based on the target feedback data.

[0139] Wherein, the credibility threshold is set by technicians according to the actual situation, and the embodiments of the present application do not limit this.

[0140] For example, the server inputs the set of object data into the credibility prediction model, extracts features of the set of object data through the credibility prediction model to obtain multiple object data features. The server performs credibility prediction based on the multiple object data features through the credibility prediction model to obtain the feedback credibility of each object to be marketed. The server determines multiple target objects to be marketed from multiple objects to be marketed based on the feedback credibility of multiple objects to be marketed in the set of objects to be marketed, and the target objects to be marketed are the objects to be marketed whose feedback credibility is greater than or equal to the credibility threshold. The server filters out the target feedback data of the target objects to be marketed from the marketing behavior feedback data. The server inputs the target feedback data into the semantic recognition model, extracts semantic features of the target feedback data through the semantic recognition model to obtain the semantic features of the target feedback data. The server maps the semantic features of the target feedback data to obtain the evaluation parameter.

[0141] For example, the server inputs the object data set into a credibility prediction model, extracts features from the object data set through the credibility prediction model, and obtains multiple object data features. The server performs full connection and normalization on the basis of the multiple object data features through the credibility prediction model to obtain the feedback credibility of each marketed object. The server determines multiple target marketed objects from the multiple marketed objects based on the feedback credibility of the multiple marketed objects in the marketed object set, where the target marketed objects are the marketed objects whose feedback credibility is greater than or equal to the credibility threshold. The server filters out the target feedback data of the target marketed objects from the marketing behavior feedback data. The server inputs the target feedback data into a semantic recognition model, extracts semantic features from the target feedback data through the semantic recognition model, and obtains the semantic features of the target feedback data. The server performs full connection and normalization on the semantic features of the target feedback data to obtain the evaluation parameter.

[0142] Part Three: The server determines the third marketing effect parameter based on the matching parameter and the evaluation parameter.

[0143] In a possible implementation manner, the server fuses the matching parameter and the evaluation parameter to obtain the third marketing effect parameter.

[0144] 305. The server determines the target marketing effect parameter of the target power marketing behavior based on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter of the target power marketing behavior.

[0145] Among them, the target marketing effect parameter is the finally obtained marketing effect parameter, which can be regarded as the processing result of the marketing data of the target power marketing behavior.

[0146] In a possible implementation manner, the server performs weighted fusion on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter of the target power marketing behavior to obtain the target marketing effect parameter of the target power marketing behavior.

[0147] Among them, the weights for weighted fusion are set by technicians according to actual situations, and the embodiments of the present application do not limit this.

[0148] 306. The server generates a modification suggestion for the target marketing behavior based on the marketing behavior data, the marketing environment data, and the target marketing effect parameter.

[0149] In a possible implementation manner, the server determines marketing adjustment data based on the marketing environment data and the target marketing effect parameter. The server generates the modification suggestion based on the marketing adjustment data and the marketing behavior data.

[0150] For example, the server inputs the marketing environment data and the target marketing effect parameters into an adjustment data determination model. The adjustment data determination model extracts features from the marketing environment data and the target marketing effect parameters to obtain marketing adjustment data prediction features. The server determines the marketing adjustment data based on the marketing adjustment data prediction features through the adjustment data determination model. The server inputs the marketing adjustment data and the marketing behavior data into a recommendation generation model. The recommendation generation model extracts features from the marketing adjustment data and the marketing behavior data to obtain modification recommendation determination features. The server generates the modification recommendation based on the modification recommendation determination features through the recommendation generation model.

[0151] For example, the server inputs the marketing environment data and the target marketing effect parameters into an adjustment data determination model. The adjustment data determination model encodes the marketing environment data and the target marketing effect parameters based on an attention mechanism to obtain marketing adjustment data prediction features. The server performs multiple rounds of iterative decoding on the marketing adjustment data prediction features based on the attention mechanism through the adjustment data determination model to obtain the marketing adjustment data. The server inputs the marketing adjustment data and the marketing behavior data into a recommendation generation model. The recommendation generation model encodes the marketing adjustment data and the marketing behavior data based on the attention mechanism to obtain modification recommendation determination features. The server performs multiple rounds of iterative decoding on the modification recommendation determination features based on the attention mechanism through the recommendation generation model to obtain the modification recommendation.

[0152] Any combination of the above optional technical solutions can form an optional embodiment of the present application, which will not be elaborated here one by one.

[0153] Through the technical solution provided by the embodiment of the present application, the first power marketing data, the second power marketing data, the marketing behavior data, and the marketing environment data of the target power marketing behavior are obtained. The set of marketed objects, the set of object data, and the marketing behavior feedback data corresponding to the target power marketing behavior are obtained. The first evaluation model, the second evaluation model, and the third evaluation model are used to process the obtained data to obtain the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter, realizing the distributed processing of the power marketing data. Based on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter, the target marketing effect parameter of the target power marketing behavior is determined, completing the processing of the power marketing data of the target power marketing behavior, and the processing efficiency is relatively high.

[0154] Figure 4 It is a structural schematic diagram of a power marketing data processing device based on big data and machine learning provided by the embodiment of the present application. Refer to Figure 4 , the device includes:

[0155] An acquisition module 401, configured to acquire first power marketing data, second power marketing data, marketing behavior data, and marketing environment data of a target power marketing behavior, and acquire an object data set of a set of objects to be marketed corresponding to the target power marketing behavior and marketing behavior feedback data, where the first power marketing data is estimated power marketing data before implementing the target power marketing behavior, and the second power marketing data is actual power marketing data after implementing the target power marketing behavior.

[0156] A first marketing effect parameter determination module 402, configured to determine a first marketing effect parameter of the target power marketing behavior based on the first power marketing data and the second power marketing data through a first evaluation model.

[0157] A second marketing effect parameter determination module 403, configured to determine a second marketing effect parameter of the target power marketing behavior based on the second power marketing data and the marketing environment data through a second evaluation model.

[0158] A third marketing effect parameter determination module 404, configured to determine a third marketing effect parameter of the target power marketing behavior based on the marketing behavior data, the object data set, and the marketing behavior feedback data through a third evaluation model.

[0159] A target marketing effect parameter determination module 405, configured to determine a target marketing effect parameter of the target power marketing behavior based on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter of the target power marketing behavior.

[0160] In a possible implementation manner, the first marketing effect parameter determination module 402 is configured to determine first marketing sub-data of the target power marketing behavior in multiple dimensions based on the first power marketing data. Determine second marketing sub-data of the target power marketing behavior in the multiple dimensions based on the second power marketing data. Determine a first marketing effect parameter of the target power marketing behavior based on the first marketing sub-data and the second marketing sub-data of the target power marketing behavior in multiple dimensions.

[0161] In a possible implementation manner, the first marketing effect parameter determination module 402 is configured to determine marketing data difference data of the target power marketing behavior in each dimension based on the first marketing sub-data and the second marketing sub-data of the target power marketing behavior in multiple dimensions. Determine a first marketing effect parameter of the target power marketing behavior based on the weights of each dimension and the marketing data difference data of the target power marketing behavior in each dimension.

[0162] In a possible implementation, the device further includes a weight determination module, which is configured to, for any one of the multiple dimensions, obtain the dimension description information of the dimension. Based on the dimension description information of the dimension, the marketing environment data, and the object data set, determine the weight of the dimension.

[0163] In a possible implementation, the second marketing effect parameter determination module 403 is configured to determine the second marketing sub-data of the target power marketing behavior in the multiple dimensions based on the second power marketing data. Based on the marketing environment data, determine the benchmark marketing sub-data of the multiple dimensions, where the benchmark marketing sub-data is the average value of the marketing sub-data corresponding to multiple power marketing behaviors. Based on the second marketing sub-data and the benchmark marketing sub-data of the target power marketing behavior in the multiple dimensions, determine the second marketing effect parameter.

[0164] In a possible implementation, the third marketing effect parameter determination module 404 is configured to determine the matching parameter between the target marketing behavior and the set of marketed objects based on the marketing behavior data and the object data set. Based on the object data set and the marketing behavior feedback data, determine the evaluation parameter of the set of marketed objects for the target marketing behavior. Based on the matching parameter and the evaluation parameter, determine the third marketing effect parameter.

[0165] In a possible implementation, the third marketing effect parameter determination module 404 is configured to determine multiple target object types corresponding to the target marketing behavior based on the marketing behavior data. Based on the object data set, determine multiple reference object types corresponding to the set of marketed objects, where the reference object type is the object type of the marketed objects in the set of marketed objects. Based on the multiple target object types and the multiple reference object types, determine the matching parameter between the target marketing behavior and the set of marketed objects.

[0166] In a possible implementation, the third marketing effect parameter determination module 404 is configured to determine the feedback credibility of multiple marketed objects in the set of marketed objects based on the object data set. Based on the feedback credibility of multiple marketed objects in the set of marketed objects, screen out the target feedback data from the marketing behavior feedback data, where the target feedback data includes the sub-feedback data provided by the marketed objects with a feedback credibility greater than or equal to the credibility threshold. Based on the target feedback data, determine the evaluation parameter of the set of marketed objects for the target marketing behavior.

[0167] In a possible implementation, the target marketing effect parameter determination module 405 is configured to perform weighted fusion on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter of the target power marketing behavior to obtain the target marketing effect parameter of the target power marketing behavior.

[0168] In a possible implementation, the device further includes:

[0169] A modification suggestion generation module, configured to generate a modification suggestion for the target marketing behavior based on the marketing behavior data, the marketing environment data, and the target marketing effect parameter.

[0170] It should be noted that: when the power marketing data processing device based on big data and machine learning provided in the above embodiment processes power marketing data, only the division of the above functional modules is used for illustration. In actual application, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the power marketing data processing device based on big data and machine learning provided in the above embodiment and the embodiment of the power marketing data processing method based on big data and machine learning belong to the same concept. For the specific implementation process, please refer to the method embodiment, which will not be elaborated here.

[0171] Through the technical solution provided in the embodiment of the present application, the first power marketing data, the second power marketing data, the marketing behavior data, and the marketing environment data of the target power marketing behavior are obtained. The set of marketed objects, the object data set, and the marketing behavior feedback data corresponding to the target power marketing behavior are obtained. The obtained data is processed through the first evaluation model, the second evaluation model, and the third evaluation model to obtain the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter, realizing the distributed processing of power marketing data. Based on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter, the target marketing effect parameter of the target power marketing behavior is determined, completing the processing of the power marketing data of the target power marketing behavior, and the processing efficiency is relatively high.

[0172] Figure 5 FIG. is a schematic structural diagram of a computer device provided in an embodiment of the present application. The computer device 500 may vary greatly due to configuration or performance, and may include one or more processors (Central Processing Units, CPUs) 501 and one or more memories 502. Among them, at least one computer program is stored in the one or more memories 502, and the at least one computer program is loaded and executed by the one or more processors 501 to implement the methods provided in the above various method embodiments. Of course, the computer device 500 may also have components such as wired or wireless network interfaces, keyboards, and input / output interfaces for input and output. The computer device 500 may further include other components for implementing device functions, which will not be elaborated here.

[0173] In an exemplary embodiment, a computer-readable storage medium is further provided, such as a memory including a computer program. The computer program can be executed by a processor to complete the power marketing data processing method based on big data and machine learning in the above embodiment. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0174] In an exemplary embodiment, a computer program product or a computer program is further provided. The computer program product or the computer program includes program code, and the program code is stored in a computer-readable storage medium. The processor of the computer device reads the program code from the computer-readable storage medium, and the processor executes the program code, so that the computer device executes the power marketing data processing method based on big data and machine learning described above.

[0175] In some embodiments, the computer program involved in the embodiments of the present application can be deployed to be executed on a computer device, or on multiple computer devices located at one place. Or, it can be executed on multiple computer devices distributed at multiple locations and interconnected through a communication network. The multiple computer devices distributed at multiple locations and interconnected through a communication network can form a blockchain system.

[0176] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above embodiments can be completed by hardware, or can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium, and the storage medium mentioned above can be a read-only memory, a magnetic disk, an optical disc, etc.

[0177] The above are only optional embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A power marketing data processing method based on big data and machine learning, characterized in that, The method includes: Obtaining first power marketing data, second power marketing data, marketing behavior data, and marketing environment data of a target power marketing behavior, and obtaining an object data set of the set of objects to be marketed corresponding to the target power marketing behavior and marketing behavior feedback data. The first power marketing data is the estimated power marketing data before implementing the target power marketing behavior, the second power marketing data is the actual power marketing data after implementing the target power marketing behavior, the marketing environment data is used to represent the situation of the power marketing environment and is determined based on the results of multiple power marketing behaviors, and the marketing behavior feedback data is used to represent the evaluation of the target power marketing behavior by the objects to be marketed; Determining a first marketing effect parameter of the target power marketing behavior through a first evaluation model based on the first power marketing data and the second power marketing data; The determining the first marketing effect parameter of the target power marketing behavior based on the first power marketing data and the second power marketing data includes: Based on the first power marketing data, determining first marketing sub-data of the target power marketing behavior in multiple dimensions; based on the second power marketing data, determining second marketing sub-data of the target power marketing behavior in the multiple dimensions; based on the first marketing sub-data and the second marketing sub-data of the target power marketing behavior in multiple dimensions, determining the first marketing effect parameter of the target power marketing behavior; The determining the first marketing effect parameter of the target power marketing behavior based on the first marketing sub-data and the second marketing sub-data of the target power marketing behavior in multiple dimensions includes: Based on the first marketing sub-data and the second marketing sub-data of the target power marketing behavior in multiple dimensions, determining marketing data difference data of the target power marketing behavior in each dimension; based on the weights of each dimension and the marketing data difference data of the target power marketing behavior in each dimension, determining the first marketing effect parameter of the target power marketing behavior; The determining the first marketing effect parameter of the target power marketing behavior based on the first marketing sub-data and the second marketing sub-data of the target power marketing behavior in multiple dimensions includes: Based on the first marketing sub-data and the second marketing sub-data of the target power marketing behavior in multiple dimensions, determining marketing data difference data of the target power marketing behavior in each dimension; based on the weights of each dimension and the marketing data difference data of the target power marketing behavior in each dimension, determining the first marketing effect parameter of the target power marketing behavior; Wherein, the method for determining the weights of each dimension includes: For any one of the multiple dimensions, obtaining the dimension description information of the dimension; based on the dimension description information of the dimension, the marketing environment data, and the object data set, determining the weight of the dimension; The determining the weight of the dimension based on the dimension description information of the dimension, the marketing environment data, and the object data set includes: Determine the marketing environment weight of the dimension based on the dimension description information of the dimension and the marketing environment data; determine the object weight of the dimension based on the dimension description information of the dimension and the object data set; fuse the marketing environment weight and the object weight of the dimension to obtain the weight of the dimension. Determine the second marketing effect parameter of the target power marketing behavior based on the second power marketing data and the marketing environment data through a second evaluation model. Determine the third marketing effect parameter of the target power marketing behavior based on the marketing behavior data, the object data set, and the marketing behavior feedback data through a third evaluation model. Perform weighted fusion on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter of the target power marketing behavior to obtain the target marketing effect parameter of the target power marketing behavior.

2. The method according to claim 1, wherein The determining of the second marketing effect parameter of the target power marketing behavior based on the second power marketing data and the marketing environment data includes: Determine the second marketing sub-data of the target power marketing behavior in the multiple dimensions based on the second power marketing data. Determine the benchmark marketing sub-data of the multiple dimensions based on the marketing environment data, where the benchmark marketing sub-data is the mean of the marketing sub-data corresponding to multiple power marketing behaviors. Determine the second marketing effect parameter based on the second marketing sub-data and the benchmark marketing sub-data of the target power marketing behavior in the multiple dimensions.

3. The method according to claim 1, characterized in that The determining of the third marketing effect parameter of the target power marketing behavior based on the marketing behavior data, the object data set, and the marketing behavior feedback data includes: Determine the matching parameter between the target marketing behavior and the set of marketed objects based on the marketing behavior data and the object data set. Determine the evaluation parameter of the set of marketed objects for the target marketing behavior based on the object data set and the marketing behavior feedback data. Determine the third marketing effect parameter based on the matching parameter and the evaluation parameter.

4. The method according to claim 3, wherein The determining of the matching parameter between the target marketing behavior and the set of marketed objects based on the marketing behavior data and the object data set includes: Determine multiple target object types corresponding to the target marketing behavior based on the marketing behavior data. Determine multiple reference object types corresponding to the set of marketed objects based on the object data set, where the reference object type is the object type of the marketed objects in the set of marketed objects. Determine the matching parameter between the target marketing behavior and the set of marketed objects based on the multiple target object types and the multiple reference object types.

5. The method according to claim 3, wherein The determining of the evaluation parameter of the set of marketed objects for the target marketing behavior based on the object data set and the marketing behavior feedback data includes: Determine the feedback credibility of multiple marketed objects in the set of marketed objects based on the object data set. Based on the feedback credibility of multiple marketed objects in the set of marketed objects, filter out target feedback data from the marketing behavior feedback data, where the target feedback data includes sub-feedback data provided by marketed objects with a feedback credibility greater than or equal to the credibility threshold; Based on the target feedback data, determine the evaluation parameters of the set of marketed objects for the target marketing behavior.

6. The method according to claim 1, wherein, After determining the target marketing effect parameter of the target power marketing behavior based on the first marketing effect parameter, the second marketing effect parameter, and the third marketing effect parameter of the target power marketing behavior, the method further includes: Generate a modification suggestion for the target marketing behavior based on the marketing behavior data, the marketing environment data, and the target marketing effect parameter.

Images