Data processing method, device and electronic equipment

Abstract

The present application provides a data processing method, device and electronic device, the method comprising: obtaining first data, the first data comprising at least attribute information and behavior data of a first object; based on the first data, obtaining second data, the second data comprising at least label data of the first object; obtaining third data from the first data and the second data, the third data comprising at least clue information of the second object, the second object being an object valuable to the target object; inputting the third data into a machine learning model to obtain a value assessment result of the clue information of the second object determined by the machine learning model, the value assessment result representing the effectiveness of the clue information.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a data processing method, device and electronic equipment. Background Art

[0002] Leads are commonly used indicators in enterprise management, and enterprise platforms often evaluate the value of leads. However, how to process data to ensure the accuracy of lead value assessment results becomes a problem. Summary of the invention

[0003] This application provides the following technical solutions:

[0004] On one hand, the present application provides a data processing method, including:

[0005] Obtaining first data, wherein the first data at least includes attribute information and behavior data of a first object;

[0006] Based on the first data, obtaining second data, where the second data at least includes label data of the first object;

[0007] Obtaining third data from the first data and the second data, wherein the third data at least includes clue information of a second object, and the second object is an object valuable to the target object;

[0008] The third data is input into a machine learning model to obtain a value assessment result of the clue information of the second object determined by the machine learning model, wherein the value assessment result represents the effectiveness of the clue information.

[0009] The obtaining of the first data comprises:

[0010] First data is acquired from a first data set, where the first data set at least includes the first data, and the first data comes from a business system.

[0011] The obtaining of third data from the first data and the second data comprises:

[0012] Acquire data related to clue information value assessment from the first data and the second data;

[0013] Based on the data related to the clue information value assessment, third data is obtained.

[0014] The step of acquiring data related to clue information value assessment from the first data and the second data includes:

[0015] Acquire data representing the contribution value of the second object from the first data and the second data;

[0016] and / or,

[0017] Acquire data representing the value contributed by the target object to the second object from the first data and the second data;

[0018] and / or,

[0019] Data representing the degree of matching between the needs of the second object and the services provided by the target object is obtained from the first data and the second data.

[0020] The third data also includes:

[0021] Behavior data and label data related to the clue information of the second object.

[0022] The machine learning model is determined by:

[0023] Acquire first training data, where the first training data includes first attribute information and first behavior data of the first object;

[0024] Based on the first training data, obtaining second training data, where the second training data at least includes first label data of the first object;

[0025] Obtaining third training data from the first training data and the second training data, wherein the third training data at least includes first clue information of the second object;

[0026] Inputting the third training data into a machine learning model to obtain a value evaluation result of the first clue information of the second object obtained by the machine learning model;

[0027] If the difference between the value assessment result of the first clue information of the second object and the set value assessment result does not meet the set conditions, the parameters of the machine learning model are updated, and the step of obtaining the first training data is returned to execute.

[0028] The obtaining third training data from the first training data and the second training data comprises:

[0029] Acquire first target data and second target data related to target clue value assessment from the first training data and the second training data, wherein the first target data and the second target data are different;

[0030] Based on the first target data, fourth training data is obtained, and based on the second target data, fifth training data is obtained, and the fourth training data and the fifth training data constitute the third training data.

[0031] The step of inputting the third training data into the machine learning model to obtain a value evaluation result of the first clue information of the second object obtained by the machine learning model includes:

[0032] Inputting the fourth training data and the fifth training data into the machine learning model respectively, and determining a first evaluation result and a second evaluation result of the machine learning model, wherein the first evaluation result and the second evaluation result respectively represent evaluation performance of the machine learning model;

[0033] Comparing the first evaluation result and the second evaluation result to obtain a comparison result, and determining the target data to be used from the first target data and the second target data based on the comparison result;

[0034] updating the first training data and the second training data, and acquiring third target data corresponding to the target data to be used from the updated first training data and the second training data;

[0035] The third target data is input into the machine learning model to obtain a value assessment result of the first clue information of the second object obtained by the machine learning model.

[0036] Another aspect of the present application provides a data processing device, comprising:

[0037] A first obtaining module, used to obtain first data, wherein the first data at least includes attribute information and behavior data of a first object;

[0038] A second obtaining module, configured to obtain second data based on the first data, wherein the second data at least includes label data of the first object;

[0039] A third obtaining module, configured to obtain third data from the first data and the second data, wherein the third data at least includes clue information of a second object, and the second object is an object valuable to the target object;

[0040] A determination module is used to input the third data into a machine learning model to obtain a value assessment result of the clue information of the second object determined by the machine learning model, wherein the value assessment result represents the effectiveness of the clue information.

[0041] A third aspect of the present application provides an electronic device, including:

[0042] Memory and processor;

[0043] The memory is used to store at least one set of instruction sets;

[0044] The processor is used to call and execute the instruction set in the memory, and execute any one of the data processing methods described above by executing the instruction set.

[0045] In the present application, by obtaining first data, the first data at least includes attribute information and behavior data of the first object, so as to ensure the richness of the data. On this basis, based on the first data, second data is obtained, and the second data at least includes label data of the first object, so as to further enrich the data required by the machine learning model. The third data is obtained from the first data and the second data, so as to obtain the third data from richer data, ensure the comprehensiveness and accuracy of the third data, and then input the third data into the machine learning model to ensure the accuracy of the value assessment results of the clue information of the second object determined by the machine learning model. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0047] Figure 1 It is a flowchart of a data processing method provided in Example 1 of the present application;

[0048] Figure 2 It is a schematic diagram of a mapping relationship between clue information of a second object and a set clue conversion model provided by the present application;

[0049] Figure 3 It is a flowchart of a data processing method provided in Example 2 of the present application;

[0050] Figure 4 It is a flowchart of a data processing method provided in Example 2 of the present application;

[0051] Figure 5 It is a flowchart of a data processing method provided in Example 2 of the present application;

[0052] Figure 6 It is a structural schematic diagram of a data processing device provided by the present application;

[0053] Figure 7 It is a structural schematic diagram of an electronic device provided by this application. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0055] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0056] Reference Figure 1 , is a flow chart of a data processing method provided in Example 1 of the present application. The method can be applied to electronic devices. The present application does not limit the product type of the electronic device. For example, Figure 1 As shown, the method may include but is not limited to the following steps:

[0057] Step S101: Obtain first data, where the first data at least includes attribute information and behavior data of a first object.

[0058] In this embodiment, the business system that can generate the first data can be directly connected to obtain the first data from the business system. Of course, the first data can also be obtained in other ways, such as user uploading or downloading from the network.

[0059] The attribute information of the first object may include but is not limited to: basic information of the first object, department information related to the first object, and company information related to the first object.

[0060] The basic information of the first object may include, but is not limited to: an identifier (eg, name) and contact information (eg, at least one or more of a mobile phone number, a landline number, and an email address) of the first object.

[0061] The department information related to the first object may include but is not limited to: position role information related to the first object.

[0062] The company information related to the first object may include but is not limited to: at least one or more of the company name, the region where the company is located, the industry field to which the company belongs, the company size, the company's registered assets, and the company's main products.

[0063] The behavioral data of the first object may include but is not limited to: browsing behavior data (such as opening marketing content, opening public account articles, watching live broadcasts), comment behavior data, activity behavior data (such as participating in survey questionnaires, participating in activities), registration behavior data, forwarding behavior data and downloading behavior data (such as downloading materials). At least one or more.

[0064] The attribute information and behavior data of the first object may be obtained through the following channels: at least one or more of an official website, activities, public accounts, success stories, and media promotions.

[0065] Step S102: Based on the first data, obtain second data, where the second data at least includes label data of the first object.

[0066] It will be appreciated that the second data is different from the first data.

[0067] Based on the first data, obtaining the second data may include but is not limited to:

[0068] S1021. Based on the first data, search for second data matching the first data from a set data mapping relationship, where the second data at least includes label data of the first object.

[0069] The set data mapping relationship can be determined in the following ways:

[0070] S10211, determine the second data from the target data of the first object, and establish a mapping relationship between the target data and the second data to obtain a set data mapping relationship. The target data of the first object is different from the second data.

[0071] The target data of the first object may include but is not limited to: target attribute information and target behavior data of the first object, wherein the target attribute information of the first object is at least partially identical to the attribute information of the first object, and the target behavior data of the first object is at least partially identical to the behavior data of the first object.

[0072] The present application also provides another implementation method for obtaining the second data based on the first data, which may specifically include:

[0073] S1022. Determine second data from the first data.

[0074] Determining the second data from the first data may specifically include:

[0075] Based on the attribute information and / or behavior data of the first object, at least one or more of the type of the first object, the content that the first object is interested in, and the purchase intention of the first object are determined. The type of the first object, the content that the first object is interested in, or the purchase intention of the first object are all tag data of the first object.

[0076] Step S103: obtaining third data from the first data and the second data, wherein the third data at least includes clue information of the second object, and the second object is an object valuable to the target object.

[0077] Obtaining the third data from the first data and the second data may include:

[0078] S1031, obtaining first data to be used related to the second object from the first data, where the first data to be used at least includes attribute information and behavior data of the second object;

[0079] S1032, obtaining second data to be used related to the second object from the second data, where the second data to be used at least includes first label data of the second object;

[0080] S1033. If it is determined that the second object is valuable to the target object based on the first data to be used and the second data to be used, third data is obtained from the attribute information of the second object, and the third data at least includes clue information of the second object.

[0081] Alternatively, obtaining the third data from the first data and the second data may include:

[0082] S1034, obtaining first data to be used related to the second object from the first data, where the first data to be used at least includes attribute information and behavior data of the second object;

[0083] S1035. Determine third data to be used related to the second object based on the first data to be used, where the third data to be used at least includes: second label data of the second object;

[0084] S1036, obtaining second data to be used related to the second object from the second data, where the second data to be used at least includes first label data of the second object;

[0085] S1037. If the second object is determined to be valuable to the target object based on the first data to be used, the second data to be used and the third data to be used, third data is obtained from the attribute information of the second object, and the third data at least includes clue information of the second object.

[0086] In this embodiment, the clue information of the second object can be used to reach the second object. The clue information of the second object can include but is not limited to: at least one or more of the second object's mobile phone number, landline number, email address, and communication software identifier.

[0087] The target object may be, but is not limited to, an enterprise; accordingly, the second object may be, but is not limited to, a customer of the enterprise.

[0088] Step S104: input the third data into the machine learning model to obtain a value assessment result of the clue information of the second object determined by the machine learning model, wherein the value assessment result represents the effectiveness of the clue information.

[0089] Machine learning models can be determined by, but are not limited to, the following methods:

[0090] S1041. Acquire first training data, where the first training data includes first attribute information and first behavior data of the first object;

[0091] The first attribute information and the second behavior data of the first object specifically include the same types of information and data as the attribute information and behavior data of the first object, but it should be noted that the first attribute information and the first behavior data of the first object are different from the attribute information and behavior data of the first object.

[0092] S1042. Obtain second training data based on the first training data, where the second training data at least includes first label data of the first object;

[0093] The specific method for obtaining the second training data based on the first training data can refer to the specific method for obtaining the second data based on the first data, but it should be noted that the first training data is different from the first data, and the second training data is different from the second data.

[0094] S1043: Obtain third training data from the first training data and the second training data, where the third training data at least includes first clue information of the second object.

[0095] S1044, inputting the third training data into the machine learning model to obtain a value assessment result of the first clue information of the second object obtained by the machine learning model;

[0096] S1045. If the difference between the value assessment result of the first clue information of the second object and the set value assessment result does not meet the set conditions, update the parameters of the machine learning model and return to execute step S1041.

[0097] In this application, the setting conditions can be set as needed, and there is no restriction on the setting of the setting conditions. It should be noted that the setting conditions can at least ensure that the machine learning model can accurately determine the value assessment result.

[0098] Among them, the machine learning model may include but is not limited to: a neural network model, a decision tree model or a regression analysis model.

[0099] In this embodiment, the clue information of the second object can be mapped to a set clue conversion model based on the value evaluation result, for example, Figure 2As shown, the set lead conversion model includes: IQL (effective retention) layer, MQL (leads recognized by the marketing department) layer, SQL (leads recognized by the sales department) layer, business opportunity layer and order layer. The lead effectiveness of the MQL layer is higher than that of the IQL layer, and the lead effectiveness of the SQL layer is higher than that of the MQL layer. The business opportunity layer can generate sales opportunities based on the SQL layer, and the order layer can generate orders based on the sales opportunities of the business opportunity layer. Corresponding to the set lead conversion model, if the lead information of the second object is mapped to the SQL layer based on the value assessment result, the lead information representing the second object is a lead recognized by the sales department, and the sales department follows up the second object based on the lead information of the second object, and in the case that the SQL layer has the lead information mapped, the business opportunity layer generates sales opportunities based on the result of following up the second object in the SQL layer, and the order layer can generate orders based on the sales opportunities, then sales opportunities and orders can be generated, and efficient conversion from lead information to business opportunities to orders can be achieved.

[0100] In this embodiment, by obtaining first data, the first data at least includes attribute information and behavior data of the first object, thereby ensuring the richness of the data. On this basis, based on the first data, second data is obtained, and the second data at least includes label data of the first object, thereby further enriching the data required by the machine learning model. The third data is obtained from the first data and the second data, thereby achieving the goal of obtaining the third data from richer data, thereby ensuring the comprehensiveness and accuracy of the third data, and then inputting the third data into the machine learning model to ensure the accuracy of the value assessment results of the clue information of the second object determined by the machine learning model.

[0101] As another optional embodiment of the present application, refer to Figure 3 , is a flow chart of a data processing method provided in Example 2 of the present application. This embodiment is mainly a detailed solution of the data processing method described in Example 1 above, such as Figure 3 As shown, the method may include but is not limited to the following steps:

[0102] Step S201: Acquire first data from a first data set, where the first data set includes at least first data, the first data comes from a business system, and the first data includes at least attribute information and behavior data of a first object.

[0103] Different from the method of directly connecting to the business system, obtaining the first data from the first data set can be understood as connecting at the data layer, and there is no need to establish a dependency relationship with the business system.

[0104] In this embodiment, the first data set may be determined by, but is not limited to, the following methods:

[0105] The data collection device collects first data from the business system, stores the first data in a data set, and obtains a first data set;

[0106] Alternatively, the business system stores the first data in a data set to obtain a first data set.

[0107] Step S201 is a specific implementation of step S101 in Example 1.

[0108] Step S202: Based on the first data, obtain second data, where the second data at least includes label data of the first object.

[0109] Step S203: Obtain third data from the first data and the second data, where the third data at least includes clue information of the second object, and the second object is an object that is valuable to the target object.

[0110] Step S204: input the third data into the machine learning model to obtain a value assessment result of the clue information of the second object determined by the machine learning model, wherein the value assessment result represents the effectiveness of the clue information.

[0111] The detailed process of steps S202-S204 can refer to the relevant introduction of steps S102-S104 in Example 1, which will not be repeated here.

[0112] In this embodiment, the first data is obtained from the first data set without establishing a dependency relationship with the business system, thereby ensuring the independence of obtaining the first data and the implementation of subsequent steps. In addition, the first data at least includes the attribute information and behavior data of the first object, thereby ensuring the richness of the data. On this basis, the second data is obtained based on the first data, and the second data at least includes the label data of the first object, thereby further enriching the data required by the machine learning model. The third data is obtained from the first data and the second data, thereby achieving the goal of obtaining the third data from richer data, thereby ensuring the comprehensiveness and accuracy of the third data. The third data is then input into the machine learning model, thereby ensuring the accuracy of the value assessment result of the clue information of the second object determined by the machine learning model.

[0113] As another optional embodiment of the present application, refer to Figure 3 , is a flow chart of a data processing method provided in Example 3 of the present application. This embodiment is mainly a detailed solution of the data processing method described in the above Example 1, such as Figure 3 As shown, the method may include but is not limited to the following steps:

[0114] Step S301: Obtain first data, where the first data at least includes attribute information and behavior data of a first object.

[0115] Step S302: Based on the first data, obtain second data, where the second data at least includes label data of the first object.

[0116] The detailed process of steps S301-S302 can refer to the relevant introduction of steps S101-S102 in Example 1, which will not be repeated here.

[0117] Step S303: Acquire data related to clue information value assessment from the first data and the second data.

[0118] The data related to the clue information value assessment does not include at least one or more of the following: data of a third object whose value to the target object is lower than a threshold (e.g., the target object is an enterprise and the third object is an employee of the enterprise), information related to the way of obtaining the attribute information and behavior data of the first object, and suspicious clue information (e.g., clue information of an object that has a loss impact on the target object).

[0119] The clue information value assessment can be set as needed and is not limited in this application.

[0120] This step may include but is not limited to:

[0121] S3031. Obtain data representing the contribution value of the second object from the first data and the second data.

[0122] The data representing the contribution value of the second object may include, but is not limited to, at least one or more of: data related to the second object's participation in activities, the second object's purchase data, the second object's consultation data, and the second object's order data.

[0123] Alternatively, this step may include:

[0124] S3032. Obtain data representing the value contributed by the target object to the second object from the first data and the second data.

[0125] The data representing the value contributed by the target object to the second object may include, but is not limited to, data related to the service provided by the target object to the second object.

[0126] Alternatively, this step may include:

[0127] S3033. Obtain data representing the degree of matching between the needs of the second object and the services provided by the target object from the first data and the second data.

[0128] Acquiring data representing the degree of matching between the second object's requirements and the services provided by the target object from the first data and the second data may include:

[0129] S30331. Acquire data related to the second object requirement from the first data and the second data;

[0130] S30332. Acquire data related to the service provided by the target object from the first data and the second data;

[0131] S30333. Calculate the degree of matching between the data related to the needs of the second object and the data related to the services provided by the target object, and obtain data representing the degree of matching between the needs of the second object and the services provided by the target object.

[0132] Of course, this step may also include:

[0133] At least two or more of steps S3031, S3032 and S3033.

[0134] Step S304: Obtain third data based on data related to clue information value assessment.

[0135] This step may include but is not limited to:

[0136] S3041. If, based on data related to clue information value assessment, it is determined that the second object is an object valuable to the target object, third data is obtained from the first data, and the third data at least includes clue information of the second object.

[0137] Steps S303-S304 are a specific implementation of step S103 in Example 1.

[0138] Step S305: input the third data into the machine learning model to obtain a value assessment result of the clue information of the second object determined by the machine learning model, wherein the value assessment result represents the effectiveness of the clue information.

[0139] In this embodiment, the machine learning model can be determined by, but is not limited to, the following methods:

[0140] S3051. Acquire first training data, where the first training data includes first attribute information and first behavior data of a first object.

[0141] S3052: Based on the first training data, obtain second training data, where the second training data at least includes first label data of the first object;

[0142] The detailed process of steps S3051-S3052 can refer to the relevant introduction of steps S1041-S1042 in Example 1, which will not be repeated here.

[0143] S3053. Obtain first target data and second target data related to target clue value assessment from the first training data and the second training data, where the first target data and the second target data are different.

[0144] S3054: Obtain fourth training data based on the first target data, and obtain fifth training data based on the second target data, the fourth training data and the fifth training data forming third training data.

[0145] S3055. Input the fourth training data and the fifth training data into the machine learning model respectively, and determine a first evaluation result and a second evaluation result of the machine learning model, wherein the first evaluation result and the second evaluation result respectively represent the evaluation performance of the machine learning model.

[0146] S3056: Compare the first evaluation result and the second evaluation result to obtain a comparison result, and determine the target data to be used from the first target data and the second target data based on the comparison result.

[0147] Determining the target data to be used from the first target data and the second target data based on the comparison result may include:

[0148] If the comparison result is that the evaluation performance represented by the first evaluation result is higher than the evaluation performance represented by the second evaluation result, the first target data is determined as the target data to be used;

[0149] If the comparison result is that the evaluation performance represented by the second evaluation result is higher than the evaluation performance represented by the first evaluation result, the second target data is determined as the target data to be used.

[0150] S3057: Update the first training data and the second training data, and obtain third target data corresponding to the target data to be used from the updated first training data and the second training data.

[0151] In this embodiment, training data may be acquired from a data source to update the first training data and the second training data.

[0152] Corresponding to the implementation method of determining the first target data as the target data to be used, this step may include: acquiring third target data of the same type as the first target data from the updated first training data and the second training data.

[0153] Corresponding to the implementation method of determining the second target data as the target data to be used, this step may include:

[0154] Third target data having the same data type as the second target data is obtained from the updated first training data and second training data.

[0155] S3058. Input the third target data into the machine learning model to obtain a value assessment result of the first clue information of the second object obtained by the machine learning model.

[0156] S3058. If the difference between the value assessment result of the first clue information of the second object and the set value assessment result does not meet the set conditions, update the parameters of the machine learning model and return to execute step S3057.

[0157] In this embodiment, steps S3051-S3058 are used to respectively determine the evaluation performance of the machine learning model based on the two sets of training data, and based on the evaluation performance, determine a set of training data that can guarantee higher evaluation performance from the two sets of training data, namely, the target data to be used. Based on the target data to be used, the third target data is obtained from the updated first training data and the second training data, and the machine learning model is continuously trained based on the third target data to improve the accuracy of the machine learning model training and ensure that the trained machine learning model can more accurately determine the value evaluation results of the clue information.

[0158] In this embodiment, by obtaining first data, the first data at least includes attribute information and behavior data of the first object, thereby ensuring the richness of the data. On this basis, based on the first data, second data is obtained, and the second data at least includes label data of the first object, thereby further enriching the data required by the machine learning model. Data related to clue value assessment is obtained from the first data and the second data, thereby achieving the goal of obtaining data related to clue value assessment from richer data. Based on the data related to clue information value assessment, third data is obtained, thereby reducing workload and ensuring the comprehensiveness and accuracy of the third data. The third data is then input into the machine learning model to ensure the accuracy and efficiency of the value assessment results of the clue information of the second object determined by the machine learning model.

[0159] As another optional embodiment of the present application, refer to Figure 4 , is a flow chart of a data processing method provided in Example 4 of the present application. This embodiment is mainly an extended solution of the data processing method described in Example 1 above, such as Figure 4 As shown, the method may include but is not limited to the following steps:

[0160] Step S401: Obtain first data, where the first data at least includes attribute information and behavior data of a first object.

[0161] Step S402: Based on the first data, obtain second data, where the second data at least includes label data of the first object.

[0162] The detailed process of steps S401-S402 can refer to the relevant introduction of steps S101-S102 in Example 1, which will not be repeated here.

[0163] Step S403: Obtain third data from the first data and the second data, wherein the third data at least includes clue information of the second object, behavior data and label data related to the clue information of the second object, and the second object is an object valuable to the target object.

[0164] This step may include but is not limited to:

[0165] S4031. Obtain first data to be used related to the second object from the first data, where the first data to be used includes at least attribute information and behavior data of the second object;

[0166] S1032, obtaining second data to be used related to the second object from the second data, where the second data to be used at least includes first label data of the second object;

[0167] S1033. If, based on the first data to be used and the second data to be used, it is determined that the second object is an object that is valuable to the target object, clue information of the second object is obtained from the attribute information of the second object, behavior data related to the clue information of the second object is obtained from the behavior data of the second object, and label data related to the clue information of the second object is obtained from the first label data of the second object.

[0168] Step S404: input the third data into the machine learning model to obtain a value assessment result of the clue information of the second object determined by the machine learning model, wherein the value assessment result represents the effectiveness of the clue information.

[0169] It can be understood that the training data on which the machine learning model in this embodiment is based includes at least the first clue information of the second object, behavior data related to the first clue information of the second object, and label data.

[0170] The machine learning model is trained based on the first clue information of the second object, the behavioral data and label data related to the first clue information of the second object, so that the machine learning model can learn more features related to the first clue information of the second object, thereby improving the accuracy of the value assessment results of the clue information of the second object determined by the machine learning model.

[0171] The method for obtaining the training data based on the machine learning model can refer to the method for obtaining the third data, which will not be described in detail here. However, it should be noted that the training data is different from the third data.

[0172] In this embodiment, by obtaining first data, the first data at least includes attribute information and behavior data of the first object, thereby ensuring the richness of the data. On this basis, based on the first data, second data is obtained, and the second data at least includes label data of the first object, thereby further enriching the data required by the machine learning model. The third data is obtained from the first data and the second data, thereby achieving the goal of obtaining the third data from richer data, thereby ensuring the comprehensiveness and accuracy of the third data, and then inputting the third data into the machine learning model to ensure the accuracy of the value assessment results of the clue information of the second object determined by the machine learning model.

[0173] In addition, the third data includes clue information of the second object, behavioral data related to the clue information of the second object, and label data. Inputting the clue information of the second object, behavioral data related to the clue information of the second object, and label data into the machine learning model can further improve the accuracy of the value assessment results of the clue information of the second object.

[0174] Corresponding to the above-mentioned data processing method embodiment provided by the present application, the present application also provides an embodiment of a data processing device.

[0175] See also Figure 6 The data processing device includes: a first obtaining module 100, a second obtaining module 200, a third obtaining module 300 and a determining module 400.

[0176] A first obtaining module 100 is used to obtain first data, where the first data at least includes attribute information and behavior data of a first object;

[0177] A second obtaining module 200 is used to obtain second data based on the first data, where the second data at least includes label data of the first object;

[0178] A third obtaining module 300 is used to obtain third data from the first data and the second data, where the third data at least includes clue information of the second object, where the second object is an object valuable to the target object;

[0179] The determination module 400 is used to input the third data into the machine learning model to obtain a value assessment result of the clue information of the second object determined by the machine learning model, and the value assessment result represents the effectiveness of the clue information.

[0180] In this embodiment, the first obtaining module 100 may be specifically used for:

[0181] First data is obtained from a first data set, where the first data set at least includes first data, and the first data comes from a business system.

[0182] In this embodiment, the third obtaining module 300 may be specifically used for:

[0183] Acquire data related to clue information value assessment from the first data and the second data;

[0184] Based on the data related to the clue information value assessment, third data is obtained.

[0185] In this embodiment, the third obtaining module 300 may be specifically used for:

[0186] Acquire data representing the contribution value of the second object from the first data and the second data;

[0187] and / or,

[0188] Acquire data representing the value contributed by the target object to the second object from the first data and the second data;

[0189] and / or,

[0190] Data representing the degree of matching between the needs of the second object and the services provided by the target object is obtained from the first data and the second data.

[0191] In this embodiment, the third data may also include: behavior data and label data related to the clue information of the second object.

[0192] In this embodiment, the data processing device may further include:

[0193] Training modules for:

[0194] Acquire first training data, where the first training data includes first attribute information and first behavior data of the first object;

[0195] Based on the first training data, obtaining second training data, the second training data at least including first label data of the first object;

[0196] Obtaining third training data from the first training data and the second training data, wherein the third training data at least includes first clue information of the second object;

[0197] Inputting the third training data into the machine learning model to obtain a value assessment result of the first clue information of the second object obtained by the machine learning model;

[0198] If the difference between the value assessment result of the first clue information of the second object and the set value assessment result does not meet the set conditions, the parameters of the machine learning model are updated and the step of obtaining the first training data is returned to be executed.

[0199] In this embodiment, the training module obtains the third training data from the first training data and the second training data, which may specifically include:

[0200] Acquire first target data and second target data related to target clue value assessment from the first training data and the second training data, the first target data and the second target data being different;

[0201] Based on the first target data, fourth training data is obtained, and based on the second target data, fifth training data is obtained, and the fourth training data and the fifth training data constitute the third training data.

[0202] In this embodiment, the training module inputs the third training data into the machine learning model to obtain a value assessment result of the first clue information of the second object obtained by the machine learning model, which may specifically include:

[0203] Inputting the fourth training data and the fifth training data into the machine learning model respectively, and determining a first evaluation result and a second evaluation result of the machine learning model, wherein the first evaluation result and the second evaluation result respectively represent evaluation performance of the machine learning model;

[0204] Comparing the first evaluation result and the second evaluation result to obtain a comparison result, and determining the target data to be used from the first target data and the second target data based on the comparison result;

[0205] The first training data and the second training data are updated, and third target data corresponding to the target data to be used are acquired from the updated first training data and the second training data;

[0206] The third target data is input into the machine learning model to obtain a value assessment result of the first clue information of the second object obtained by the machine learning model.

[0207] Corresponding to the above-mentioned data processing method embodiment provided by the present application, the present application also provides an electronic device embodiment applying the data processing method.

[0208] like Figure 7 The figure is a schematic diagram of the structure of an electronic device embodiment 1 provided by the present application, and the electronic device may include the following structure:

[0209] The memory 10 and the processor 20 .

[0210] A memory 10, used to store at least one set of instruction sets;

[0211] The processor 20 is used to call and execute the instruction set in the memory 10, and execute the data processing method introduced in any one of the above method embodiments 1-5 by executing the instruction set.

[0212] Corresponding to the above-mentioned control method embodiment provided by the present application, the present application also provides an embodiment of a storage medium.

[0213] In this embodiment, the storage medium stores a computer program for implementing the data processing method introduced in any of the aforementioned method embodiments, and the computer program is executed by the processor to implement the data processing method introduced in any of the aforementioned embodiments.

[0214] It should be noted that each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0215] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0216] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0217] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0218] The above is a detailed introduction to a data processing method, device and electronic device provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A data processing method, comprising: Obtaining first data, wherein the first data at least includes attribute information and behavior data of a first object; Based on the first data, obtaining second data, where the second data at least includes label data of the first object; Obtaining third data from the first data and the second data, wherein the third data at least includes clue information of a second object, and the second object is an object valuable to the target object; Inputting the third data into a machine learning model to obtain a value evaluation result of the clue information of the second object determined by the machine learning model, wherein the value evaluation result represents the effectiveness of the clue information; The machine learning model is determined by: Acquire first training data, where the first training data includes first attribute information and first behavior data of the first object; Based on the first training data, obtaining second training data, where the second training data at least includes first label data of the first object; Acquire first target data and second target data related to target clue value assessment from the first training data and the second training data, wherein the first target data and the second target data are different; Based on the first target data, fourth training data is obtained, and based on the second target data, fifth training data is obtained, the fourth training data and the fifth training data constitute third training data, and the third training data at least includes the first clue information of the second object; The third training data is input into the machine learning model to obtain a value assessment result of the first clue information of the second object obtained by the machine learning model.

2. The method according to claim 1, wherein obtaining the first data comprises: First data is acquired from a first data set, where the first data set at least includes the first data, and the first data comes from a business system.

3. The method according to claim 1, wherein obtaining third data from the first data and the second data comprises: Acquire data related to clue information value assessment from the first data and the second data; Based on the data related to the clue information value assessment, third data is obtained.

4. The method according to claim 3, wherein obtaining data related to clue information value assessment from the first data and the second data comprises: Acquire data representing the contribution value of the second object from the first data and the second data; and / or, Acquire data representing the value contributed by the target object to the second object from the first data and the second data; and / or, Data representing the degree of matching between the needs of the second object and the services provided by the target object is obtained from the first data and the second data.

5. The method according to claim 1, wherein the third data further comprises: Behavior data and label data related to the clue information of the second object.

6. The method according to claim 1, During the process of determining the machine learning model, if the difference between the value assessment result of the first clue information of the second object and the set value assessment result does not meet the set conditions, the parameters of the machine learning model are updated, and the step of obtaining the first training data during the process of determining the machine learning model is returned.

7. The method according to claim 1, wherein inputting the third training data into the machine learning model to obtain a value assessment result of the first clue information of the second object obtained by the machine learning model comprises: Inputting the fourth training data and the fifth training data into the machine learning model respectively, and determining a first evaluation result and a second evaluation result of the machine learning model, wherein the first evaluation result and the second evaluation result respectively represent evaluation performance of the machine learning model; Comparing the first evaluation result and the second evaluation result to obtain a comparison result, and determining the target data to be used from the first target data and the second target data based on the comparison result; updating the first training data and the second training data, and acquiring third target data corresponding to the target data to be used from the updated first training data and the second training data; The third target data is input into the machine learning model to obtain a value assessment result of the first clue information of the second object obtained by the machine learning model.

8. A data processing device, comprising: A first obtaining module, used to obtain first data, wherein the first data at least includes attribute information and behavior data of a first object; A second obtaining module, configured to obtain second data based on the first data, wherein the second data at least includes label data of the first object; A third obtaining module, configured to obtain third data from the first data and the second data, wherein the third data at least includes clue information of a second object, and the second object is an object valuable to the target object; a determination module, configured to input the third data into a machine learning model to obtain a value assessment result of the clue information of the second object determined by the machine learning model, wherein the value assessment result represents the effectiveness of the clue information; The machine learning model is determined by: Acquire first training data, where the first training data includes first attribute information and first behavior data of the first object; Based on the first training data, obtaining second training data, where the second training data at least includes first label data of the first object; Acquire first target data and second target data related to target clue value assessment from the first training data and the second training data, wherein the first target data and the second target data are different; Based on the first target data, fourth training data is obtained, and based on the second target data, fifth training data is obtained, the fourth training data and the fifth training data constitute third training data, and the third training data at least includes the first clue information of the second object; The third training data is input into the machine learning model to obtain a value assessment result of the first clue information of the second object obtained by the machine learning model.

9. An electronic device, comprising: Memory and processor; The memory is used to store at least one set of instruction sets; The processor is used to call and execute the instruction set in the memory, and execute the data processing method according to any one of claims 1 to 7 by executing the instruction set.

Images