Interaction qualification level determination method, device, equipment and storage medium

Abstract

The present application discloses a method, device, equipment and storage medium for determining an interaction qualification level, the method comprising: obtaining the first-stage behavior data of a target user, determining a corresponding first target prediction model, predicting the order rate of the target user in the first stage, and obtaining a first order rate prediction result; determining the first interaction qualification level of the target user in the first stage based on the first order rate prediction result, obtaining the second-stage behavior data of the target user determined based on the first interaction qualification level; determining the second target prediction model of the second-stage behavior data based on the second-stage behavior data, predicting the order rate of the target user in the second stage, and determining the second interaction qualification level of the target user in the second stage based on the second order rate prediction result, wherein the second stage is a time-series continuous stage with the first stage. The present application solves the technical problem of low accuracy in determining the user interaction qualification level in the prior art.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology in financial technology (Fintech), and in particular to a method, device, equipment and storage medium for determining an interaction qualification level. Background Art

[0002] With the continuous development of financial technology, especially Internet technology finance, more and more technologies are applied in the financial field, but the financial industry also puts forward higher requirements for technology. For example, the financial industry also has higher requirements for the determination of interactive qualification levels.

[0003] At present, user behavior is usually predicted, for example, predicting the user's click rate, purchase rate and order rate for a certain item, etc. However, in most scenarios, the distribution of user behavior feature dimensions is dynamic, and in the prior art, the user's order rate is predicted only based on the neural network model obtained by determining the feature dimensions, resulting in inaccurate user order rate prediction results. The user's interaction qualification level is determined based on the user's order rate prediction result. The inaccurate order rate prediction result makes it difficult to accurately determine the user's interaction qualification level. Summary of the invention

[0004] The main purpose of the present application is to provide a method, device, equipment and storage medium for determining an interaction qualification level, aiming to solve the technical problem in the prior art that it is difficult to accurately determine the interaction qualification level of a user.

[0005] To achieve the above object, the present application provides a method for determining an interaction qualification level, the method comprising:

[0006] Acquire the first-stage behavior data of the target user, determine the first target prediction model of the first-stage behavior data, perform the first-stage order rate prediction for the target user, and obtain the first order rate prediction result;

[0007] Determine a first interaction qualification level of a target user in the first phase based on the first order rate prediction result, and obtain second phase behavior data of the target user determined based on the first interaction qualification level;

[0008] Based on the second-stage behavior data, a second target prediction model of the second-stage behavior data is determined, and a second-stage order rate prediction is performed on the target user to determine a second interaction qualification level of the second-stage target user based on the second order rate prediction result, wherein the second stage is a time-series continuous stage with the first stage.

[0009] Optionally, the step of acquiring the first-stage behavior data of the target user, determining the first target prediction model of the first-stage behavior data, performing the first-stage order rate prediction for the target user, and obtaining the first order rate prediction result includes:

[0010] Acquire the first-stage behavior data of the target user, and determine the first-stage characteristics of the first-stage behavior data;

[0011] A first target prediction model of the first stage features is selected from a preset model set, and based on the first target prediction model, a first stage order rate prediction is performed on the target user to obtain a first order rate prediction result.

[0012] Optionally, before the step of selecting the first target prediction model of the first stage features from the preset model set, the method includes:

[0013] Obtain the combined features of each stage, and obtain the training data corresponding to the combined features of each stage;

[0014] Based on the training data, the preset models to be trained are iteratively trained to obtain target models corresponding to the combined features of each stage, so as to obtain a preset model set.

[0015] Optionally, the step of determining a first interaction qualification level of a target user in the first phase based on the first order placement rate prediction result, and acquiring second phase behavior data of the target user determined based on the first interaction qualification level includes:

[0016] Determining a first interaction qualification level of the target user in the first phase based on the numerical value of the first order rate prediction result;

[0017] A first interaction file of the first interaction qualification level is determined, and the first interaction file is parsed to determine second-stage behavior data.

[0018] Optionally, the step of determining the first interaction file of the first interaction qualification level, parsing the first interaction file, and determining the second-stage behavior data includes:

[0019] a first interaction profile for determining said first interaction qualification level;

[0020] The channel type of the target user is determined, and the second-stage behavior data is determined based on the channel type and the first interaction file.

[0021] Optionally, the step of determining a second target prediction model for the second stage behavior data based on the second stage behavior data, predicting the order rate of the target user in the second stage, and determining a second interaction qualification level of the target user in the second stage based on the second order rate prediction result includes:

[0022] Acquire the second-stage behavior data of the target user, and determine the second-stage characteristics of the second-stage behavior data;

[0023] Selecting a second target prediction model of the second stage features from the preset model set, and performing a second stage order rate prediction for the target user based on the second target prediction model to obtain a second order rate prediction result;

[0024] Based on the second order rate prediction result, a second interaction qualification level of the target user in the second stage is determined, a second interaction file is determined, and an interaction mode in the second stage is determined based on the second interaction file, so that the target user can perform behavioral operations in the next stage based on the interaction mode in the second stage.

[0025] Optionally, after the step of predicting the order rate of the target user in the second stage to determine the second interaction qualification level of the target user in the second stage based on the second order rate prediction result, the method further comprises:

[0026] Obtain the behavior prediction results of the target user in multiple continuous time stages;

[0027] If it is detected that the behavior prediction results of the target user in multiple time-series continuous stages are all greater than the preset value, a preset special identification process is performed on the target user;

[0028] A preset targeted recommendation process is executed for the target user after the preset special identification processing.

[0029] Optionally, the step of determining a first interaction qualification level of a target user in the first phase based on the first order placement rate prediction result, and acquiring second phase behavior data of the target user determined based on the first interaction qualification level includes:

[0030] Determining a first interaction qualification level of a first-stage target user based on the first order rate prediction result;

[0031] Obtaining a channel type corresponding to the first interaction qualification level;

[0032] If the channel type is a public account channel, outputting preset selected articles to the target user based on the public account channel;

[0033] The second-stage behavior data of the target user determined based on the preset selected articles is obtained.

[0034] The present application also provides an interactive qualification level determination device, the interactive qualification level determination device comprising:

[0035] A first acquisition module is used to acquire the first-stage behavior data of the target user, determine the first target prediction model of the first-stage behavior data, perform a first-stage order rate prediction on the target user, and obtain a first order rate prediction result;

[0036] A first determination module is used to determine a first interaction qualification level of a target user in the first phase based on the first order placement rate prediction result, and obtain second phase behavior data of the target user determined based on the first interaction qualification level;

[0037] The second determination module is used to determine a second target prediction model of the second stage behavior data based on the second stage behavior data, and predict the second stage order rate of the target user, so as to determine the second interaction qualification level of the second stage target user based on the second order rate prediction result, wherein the second stage is a time-series continuous stage with the first stage.

[0038] Optionally, the first acquisition module includes:

[0039] A first acquisition unit, configured to acquire first-stage behavior data of a target user and determine first-stage features of the first-stage behavior data;

[0040] The first prediction unit is used to select a first target prediction model of the first stage characteristics from a preset model set, and based on the first target prediction model, perform a first stage order rate prediction on the target user to obtain a first order rate prediction result.

[0041] Optionally, the interaction qualification level determination device further includes:

[0042] The second acquisition module is used to acquire the combined features of each stage and the training data corresponding to the combined features of each stage;

[0043] The third acquisition module is used to iteratively train the preset models to be trained based on the training data, obtain the target models corresponding to the combined features of each stage, and obtain a preset model set.

[0044] Optionally, the first determining module includes:

[0045] A second acquisition unit, configured to determine a first interaction qualification level of the target user in the first phase based on a numerical value of the first order placement rate prediction result;

[0046] The first determining unit is configured to determine a first interaction file of the first interaction qualification level, parse the first interaction file, and determine second-stage behavior data.

[0047] Optionally, the first determining unit includes:

[0048] A first determining subunit, configured to determine a first interaction file of the first interaction qualification level;

[0049] The second determining subunit is used to determine the channel type of the target user, and determine the second-stage behavior data based on the channel type and the first interaction file.

[0050] Optionally, the second determining module includes:

[0051] A third acquisition unit is used to acquire the second-stage behavior data of the target user and determine the second-stage characteristics of the second-stage behavior data;

[0052] A second prediction unit is used to select a second target prediction model of the second stage characteristics from a preset model set, and perform a second stage order rate prediction for the target user based on the second target prediction model to obtain a second order rate prediction result;

[0053] The second determination unit is used to determine the second interaction qualification level of the target user in the second stage based on the second order rate prediction result, determine the second interaction file, and determine the interaction mode of the second stage based on the second interaction file, so that the target user can perform the next stage of behavior operation based on the interaction mode of the second stage.

[0054] Optionally, the interaction qualification level determination device further includes:

[0055] The identification model is used to perform a preset special identification process on the target user if it is detected that the behavior prediction results of the target user in multiple time-series continuous stages are all greater than a preset value;

[0056] The execution model is used to execute a preset targeted recommendation process for the target user after the preset special identification processing.

[0057] Optionally, the first determining module further includes:

[0058] A third determining unit, configured to determine a first interaction qualification level of a target user in the first phase based on the first order placement rate prediction result;

[0059] A fourth acquiring unit, configured to acquire a channel type corresponding to the first interaction qualification level;

[0060] A fourth determining unit, configured to output preset selected articles to the target user based on the official account channel if the channel type is an official account channel;

[0061] The fifth acquisition unit is used to acquire the second-stage behavior data of the target user determined based on the preset selected articles.

[0062] The present application also provides an interaction qualification level determination device, which is a physical device, and includes: a memory, a processor, and a program of the interaction qualification level determination method stored in the memory and executable on the processor. When the program of the interaction qualification level determination method is executed by the processor, the steps of the interaction qualification level determination method as described above can be implemented.

[0063] The present application also provides a storage medium, on which is stored a program for implementing the above-mentioned interaction qualification level determination method. When the program of the interaction qualification level determination method is executed by a processor, the steps of the above-mentioned interaction qualification level determination method are implemented.

[0064] The present application provides a method, device, equipment and storage medium for determining an interaction qualification level. Compared with the prior art that predicts the order rates of users in all stages based on a neural network model obtained by determining feature dimensions, and then obtains the interaction qualification levels of target users in different stages, the present application obtains the first-stage behavior data of the target user, determines the first target prediction model of the first-stage behavior data, predicts the order rate of the target user in the first stage, and obtains the first order rate prediction result; determines the first interaction qualification level of the target user in the first stage based on the first order rate prediction result, obtains the second-stage behavior data of the target user determined based on the first interaction qualification level; determines the second-stage behavior data based on the second-stage behavior data. The second target prediction model of the behavioral data predicts the order rate of the target user in the second stage, so as to determine the second interaction qualification level of the target user in the second stage based on the second order rate prediction result, wherein the second stage and the first stage are stages that are continuous in time series, and it is possible to obtain the user order rate prediction results of the corresponding stage in stages or grades, and then obtain the interaction qualification level of the target user, which can reduce the difference in the order rate prediction process, thereby overcoming the defect of low prediction accuracy of the order rate result caused by predicting the order rate of users in all stages based on the neural network model obtained based on the determined feature dimension in the prior art, which leads to inaccurate determination of the user interaction qualification level, and improves the accuracy of determining the user interaction qualification level. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0066] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0067] Figure 1 This is a flow chart of the first embodiment of the interactive qualification level determination method of the present application;

[0068] Figure 2 This is a schematic diagram of the detailed steps of step S20 in the interactive qualification level determination method of this application;

[0069] Figure 3 A schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present application;

[0070] Figure 4 This is a flow chart of iterative training of a preset model to be trained in the interactive qualification level determination method of this application.

[0071] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0072] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0073] The present application embodiment provides a method for determining an interaction qualification level. In the first embodiment of the method for determining an interaction qualification level of the present application, refer to Figure 1 , the interaction qualification level determination method includes:

[0074] Step S10, obtaining the first-stage behavior data of the target user, determining the first target prediction model of the first-stage behavior data, performing the first-stage order rate prediction for the target user, and obtaining the first order rate prediction result;

[0075] Step S20, determining a first interaction qualification level of a target user in the first phase based on the first order rate prediction result, and obtaining second phase behavior data of the target user determined based on the first interaction qualification level;

[0076] Step S30, based on the second-stage behavior data, determine a second target prediction model for the second-stage behavior data, predict the second-stage order rate for the target user, and determine the second interaction qualification level of the second-stage target user based on the second order rate prediction result, wherein the second stage is a time-series continuous stage with the first stage.

[0077] The specific steps are as follows:

[0078] Step S10, obtaining the first-stage behavior data of the target user, determining the first target prediction model of the first-stage behavior data, performing the first-stage order rate prediction for the target user, and obtaining the first order rate prediction result;

[0079] It should be noted that the interaction qualification level is determined based on the size of the user's order rate. In order to accurately obtain the interaction qualification level, it is necessary to accurately predict the target user's order rate. In this embodiment, the interaction qualification level determination method can be applied to the interaction qualification level determination system. The interaction qualification level determination system is subordinate to the interaction qualification level determination device. For the interaction qualification level determination system, it has a communication connection relationship with an organization such as an enterprise. Therefore, as long as the user has an operation behavior on the enterprise's associated web page, the interaction qualification level determination system can obtain the user's operation behavior, and predict the user's order possibility or purchase possibility based on the user's operation behavior, that is, obtain the order rate prediction result, and then obtain the user's interaction qualification level. Then the enterprise provides feedback service based on the interaction qualification level (or provides first feedback information in a targeted manner). The feedback service can be carried out through various channels such as through official accounts, WeChat, APP, etc., wherein the channel can also be subdivided, and the channel of the feedback service is associated with the channel corresponding to the user's operation behavior. For enterprises, no matter what channel they use, there are industry characteristics (business scope characteristics), and industry characteristics include business characteristics, and business characteristics include different product characteristics, etc., that is, therefore, for enterprises, they provide multi-layer deep serial and parallel path services for user operations. It should be noted that the company's feedback service or path service is different for different users' different operating behaviors on the company's website. Although enterprises can interact with users through different methods such as apps, mini-programs, official accounts or sharing links, and enterprises provide multi-layer deep serial and parallel path services, but overall, the user's interaction with the enterprise includes serial paths such as enterprise, business, portal, page, etc. After the serial path, there is a parallel path, such as: article path, problem path, dialogue path, contact path, such as adding WeChat, making a phone call, etc. Among them, the serial path is the operating behavior path that all users have, while the parallel path is not available to all users, or for a certain user at a certain stage, there may be only one parallel path.

[0080] Specifically, the enterprise and the user (user end) can interact through multiple entrances or channels, such as interacting through an app, interacting through a mini-program, interacting through a public account, or interacting through a sharing link. After the enterprise has respectively recorded the operation behavior data on the app, mini-program, public account, or sharing link, for example, after the enterprise obtains the operation behavior data of each user at different depths through the operation data records of each operation button, the operation behavior data of each user at different depths is sent to the interaction qualification level determination system to predict whether the user will purchase or place an order. In this embodiment, it should be noted that the operation behavior data recorded by the enterprise includes at least one user behavior, for example, the user clicks to read the article, adds the customer service WeChat, , answered the customer service call, then each user behavior is clicked to read the article, added WeChat and answered the call, and each user behavior is staged. The staged here can refer to: after the first user behavior, the user receives services from the enterprise based on the first user behavior feedback, such as the feedback WeChat public account article (the first user behavior is different, the WeChat public account article is different), and subsequently generates user behavior based on the feedback service such as the feedback WeChat public account article (such as click to read behavior), then the subsequent behavior is different from the first user behavior stage. In this embodiment, prediction is performed based on the data corresponding to the changed behavior, and after obtaining the corresponding prediction result or the second order rate prediction result, the second interaction qualification level is determined, so that the enterprise can dynamically adjust the service level and the corresponding service.

[0081] The first-stage behavior data of the target user is obtained, a first target prediction model of the first-stage behavior data is determined, and a first-stage order rate prediction is performed on the target user to obtain a first order rate prediction result; specifically, the first-stage behavior data of the target user is obtained, and a first target prediction model of the first-stage behavior data is selected from a preset model set, so as to determine a first-stage order rate prediction result for the target user based on the first target prediction model, and then further obtain a first interaction qualification level, wherein, with reference to Figure 2 The steps of acquiring the first-stage behavior data of the target user, determining the first target prediction model of the first-stage behavior data, predicting the order rate of the target user in the first stage, and obtaining the first order rate prediction result include:

[0082] Step S11, obtaining the first-stage behavior data of the target user, and determining the first-stage characteristics of the first-stage behavior data;

[0083] Acquire the first-stage behavior data of the target user, and determine the first-stage features of the first-stage behavior data. The first-stage features may include only features x1, x2, x3, and x4, or only features x1, x2, x3, x4, and x5, or only features x1, x2, x3, x4, and x6, or only features x1, x2, x3, x4, x5, and x7, or only features x1, x2, x3, x4, x5, x6, and x7, etc.

[0084] The method of obtaining the first-stage behavior data of the target user and determining the first-stage characteristics of the first-stage behavior data includes:

[0085] Method 1:

[0086] After obtaining the first-stage behavior data of the target user, the serial-parallel path of the first-stage behavior data is obtained through the first-stage behavior data, and the first-stage characteristics of the first-stage behavior data are determined through the serial-parallel path of the first-stage behavior data.

[0087] Method 2: After obtaining the first-stage behavior data of the target user, obtain the path channel, path level, path depth, etc. of the first-stage behavior data through the first-stage behavior data, and determine the first-stage characteristics of the first-stage behavior data through the path channel, path level, path depth, etc.

[0088] Among them, the first-stage characteristics corresponding to the first-stage behavior data can be expressed by encoding different feature variables as 0 or 1.

[0089] Step S12, selecting a first target prediction model of the first stage features from a preset model set, and based on the first target prediction model, performing a first stage order rate prediction for the target user to obtain a first order rate prediction result.

[0090] Specifically, if the first-stage features only include features x1, x2, x3 and x4, then from the preset model set, a first target prediction model obtained by training with training data corresponding to features only including features x1, x2, x3 and x4 is selected, and the first-stage order rate prediction is performed on the target user to obtain a first order rate prediction result; or if the first-stage features only include features x1, x2, x3, x4 and x5, then from the preset model set, a first target prediction model obtained by training with training data corresponding to features only including features x1, x2, x3, x4 and x5 is selected, and the first-stage order rate prediction is performed on the target user to obtain a first order rate prediction result; or if the first-stage features only include features x1, x2, x3, x4 and x6, then from the preset model set, a first target prediction model obtained by training with training data corresponding to features only including features x1, x2, x3, x4 and x6 is selected. or if the first stage features only include the features of x1, x2, x3, x4, x5 and x7, then from the preset model set, the first target prediction model obtained by training with the training data corresponding to the features only including x1, x2, x3, x4, x5 and x7 is selected, and the first stage order rate prediction is performed on the target user to obtain the first order rate prediction result; or if the first stage features only include the features of x1, x2, x3, x4, x5, x6 and x7, then from the preset model set, the first target prediction model obtained by training with the training data corresponding to the features only including x1, x2, x3, x4, x5, x6 and x7 is selected, and the first stage order rate prediction is performed on the target user to obtain the first order rate prediction result.

[0091] It should be noted that, since the first target prediction model has been trained, it is possible to accurately predict the order rate of the target user in the first stage and obtain the first order rate prediction result.

[0092] Before the step of selecting the first target prediction model of the first stage features from the preset model set, the method includes:

[0093] Step S01, obtaining the combined features of each stage, and obtaining the training data corresponding to the combined features of each stage;

[0094] Step S02, based on the training data, iteratively train the preset models to be trained respectively, obtain the target models corresponding to the combined features of each stage, so as to obtain a preset model set.

[0095] In this embodiment, each model in the preset model set has been trained before application. By obtaining each training data corresponding to the combined features of each stage, specifically, by obtaining each training data with corresponding labels corresponding to the combined features of each stage, the preset models to be trained are iteratively trained to obtain the target models corresponding to the combined features of each stage, so as to obtain the preset model set.

[0096] like Figure 4 As shown, for example, a model is trained by training data with a first preset label including only features x1, x2, x3 and x4, and the model is only used to predict the probability of placing an order when the user has only features x1, x2, x3 and x4;

[0097] A model is trained by using training data with a second preset label that only includes features x1, x2, x3, x4, and x5, and the model is only used to predict the probability of placing an order when the user has only features x1, x2, x3, x4, and x5;

[0098] A model is trained by training data with a third preset label including only features x1, x2, x3, x4, x5, x6 and x7, and the model is only used to predict the probability of placing an order when the user has only features x1, x2, x3, x4, x5, x6 and x7;

[0099] A model is trained by using training data with a fourth preset label that only includes features x1, x2, x3, x4, x5 and x7. The model is only used to predict the probability of placing an order when the user only has feature behaviors of x1, x2, x3, x4, x5 and x7.

[0100] Step S20, determining a first interaction qualification level of a target user in the first phase based on the first order rate prediction result, and obtaining second phase behavior data of the target user determined based on the first interaction qualification level;

[0101] Based on the first order rate prediction result, the first interaction qualification level of the target user in the first stage is determined to determine the first feedback data of the first order rate prediction result, so as to obtain the second stage behavior data of the target user determined based on the first interaction qualification level. For example, the first order rate prediction result, i.e., the order rate, is 0.3. At this time, the pre-stored first interaction qualification level is level A, and the corresponding first feedback information is common questions and answers (pre-stored). After obtaining the first feedback information, the second stage behavior data determined by the target user based on the first feedback information is obtained. Specifically, if the user generates a (click or read common questions and answers) behavior based on the first feedback information, the generated (click or read common questions and answers) behavior and the first stage behavior data together constitute the second stage behavior data.

[0102] The step of determining the first interaction qualification level of the first interaction qualification level determination result comprises:

[0103] Step S21, determining a first interaction qualification level of a target user in the first phase based on the numerical value of the first order placement rate prediction result;

[0104] Based on the numerical value of the first order rate prediction result (order rate size), such as 0.3, the threshold interval of the first order rate prediction result is determined, and the first interaction qualification level of the target user in the first stage is determined based on the threshold interval. Specifically, if the order rate is divided into three threshold intervals in the interaction qualification level determination system, wherein the order rate range of the first threshold interval is (0, 0.33), the order rate range of the second threshold interval is (0.33-0.66), and the order rate range of the third threshold interval is (0.66-1), then the first interaction qualification level of the target user in the first stage is the first level corresponding to the first threshold interval.

[0105] Step S22: determining a first interaction file of the first target level, and determining a first interaction qualification level based on the first interaction file.

[0106] A first interaction file of the first target level is determined, and the first interaction file is parsed to obtain an interaction method (by machine or manual, etc.) and first feedback information, and then the first interaction file is determined to determine a first interaction qualification level.

[0107] Specifically, for example, the interaction file may be: a preset common marketing article, a pure machine interaction mode, and the first feedback information output after the interaction is a common question and answer;

[0108] Or the interaction file can be: preset machine-selected articles, machine-first then human interaction, and the first feedback information output after the interaction is the popular questions and answers;

[0109] Or the interaction file may be: preset manually selected articles, pure manual interaction mode, the first feedback information output after the interaction is manually selected questions and answers, etc.

[0110] After obtaining the first interaction qualification level, the user generates further behavior based on the first feedback information corresponding to the first interaction qualification level, and obtains second-stage behavior data based on the further behavior and the first-stage behavior data.

[0111] Step S30, based on the second-stage behavior data, determine a second target prediction model for the second-stage behavior data, predict the second-stage order rate for the target user, and determine the second interaction qualification level of the second-stage target user based on the second order rate prediction result, wherein the second stage is a time-series continuous stage with the first stage.

[0112] In this embodiment, based on the second-stage behavior data, a second target prediction model of the second-stage behavior data (second-stage features) is determined from a preset model set, and the second-stage order rate prediction result is determined for the target user, and the second interaction qualification level is further determined, wherein the second stage and the first stage are time-series continuous stages. Since the second stage and the first stage are time-series continuous stages, that is, based on the order rate in the previous stage, the first interaction qualification level is determined (the service content or the first feedback information, the first interaction file is further determined), and the order rate in the subsequent stage is determined based on the first interaction qualification level. That is, in this embodiment, the user's interaction level can be determined according to the prediction result (the order rate in the previous stage), and the user further obtains the service content or the first feedback information on the basis of the interaction level. When the user further generates behavior, the prediction of the next stage is performed. Since the corresponding prediction model is selected in a targeted manner in stages, that is, the target prediction model of the corresponding stage is obtained in stages or grades in this application to predict user behavior, the accuracy of order rate prediction is improved, and then the accuracy of interaction qualification level determination is improved.

[0113] The present application discloses a method, device, equipment and storage medium for determining an interaction qualification level. Compared with the prior art which predicts the order rates of users in all stages based on a neural network model obtained by determining feature dimensions, and then obtains the interaction qualification levels of target users in different stages, the present application obtains the first-stage behavior data of the target user, determines a first target prediction model for the first-stage behavior data, predicts the order rate of the target user in the first stage, and obtains a first order rate prediction result; determines a first interaction qualification level of the target user in the first stage based on the first order rate prediction result, obtains the second-stage behavior data of the target user determined based on the first interaction qualification level; determines the second-stage behavior data based on the second-stage behavior data; A second target prediction model for data is used to predict the order rate of the target user in the second stage, so as to determine the second interaction qualification level of the target user in the second stage based on the second order rate prediction result, wherein the second stage and the first stage are stages that are continuous in time series, and it is possible to obtain the user order rate prediction results of the corresponding stage in stages or grades, and then obtain the interaction qualification level of the target user, which can reduce the difference in the order rate prediction process, thereby overcoming the defect of low prediction accuracy of the order rate result caused by predicting the order rate of users in all stages based on the neural network model obtained based on the determined feature dimension in the prior art, thereby leading to inaccurate determination of the user interaction qualification level, and improving the accuracy of determining the user interaction qualification level.

[0114] Further, based on the first embodiment of the present application, the step of determining the first interaction file of the first target level and determining the first interaction qualification level based on the first interaction file includes:

[0115] Step A1, determining a first interaction file of the first target level;

[0116] Step A2: determine the channel type of the target user, and determine the second-stage behavior data based on the channel type and the first interaction file.

[0117] Determine the first interaction file of the first target level. After determining the first interaction file, determine the channel type of the target user, such as through WeChat, APP, phone, text message, etc. The channel can also be subdivided into a public account channel. Based on the channel type and the first interaction file, determine the first feedback information (service content). Specifically, if the channel type is a certain a business text message, then based on the a business text message and the first interaction file, determine that the first feedback information is a manually output preset a business ordinary marketing article. The target user further generates behavior based on the first interaction file, and further obtains the second stage behavior data.

[0118] In this embodiment, the first interaction qualification level is also determined by the channel type and the first interaction file, thereby avoiding resource consumption caused by attempting to output the first feedback information through multiple channels to obtain the second-stage behavior data.

[0119] The step of determining a second target prediction model of the second stage behavior data based on the second stage behavior data, determining a second interaction qualification level for the target user of the second stage, and obtaining a second interaction qualification level determination result includes:

[0120] Step B1, obtaining the second-stage behavior data of the target user, and determining the second-stage characteristics of the second-stage behavior data;

[0121] In this embodiment, the second-stage behavior data of the target user is obtained. Specifically, the second-stage characteristics of the second-stage behavior data are determined by the first interaction qualification level. For example, if the first-stage behavior data includes x1 (enterprise), x2 (business), x3 (entry) and x4 (page) characteristics, then the second-stage behavior data may include x1 (enterprise), x2 (business), x3 (entry), x4 (page) and X5 (WeChat) characteristics.

[0122] Step B2, selecting a second target prediction model of the second stage features from the preset model set, and performing a second stage order rate prediction on the target user based on the second target prediction model to obtain a second order rate prediction result;

[0123] A second target prediction model of the second stage characteristics is selected from the preset model set (obtained by training with training data with second preset labels that only includes x1, x2, x3, x4 and x5 features), and a second order rate prediction result is obtained based on the second target prediction model.

[0124] Step B3, determining the second interaction qualification level of the target user in the second stage based on the second order rate prediction result, determining the second interaction file, and determining the interaction mode of the second stage based on the second interaction file, so that the target user can perform the next stage of behavior operations based on the interaction mode of the second stage.

[0125] Based on the result of determining the second interaction qualification level, a second interaction file is determined, and based on the second interaction file, the interaction mode of the second stage (such as machine interaction mode or manual interaction mode) and the second feedback information are determined, so that the target user can perform the next stage of behavioral operations based on the interaction mode of the second stage and the second feedback information, such as performing the third stage of behavioral operations based on the interaction mode of the second stage and the second output data.

[0126] In this embodiment, the second-stage characteristics of the second-stage behavior data are determined by acquiring the second-stage behavior data of the target user; the second target prediction model of the second-stage characteristics is selected from the preset model set, and based on the second target prediction model, the second-stage order rate prediction of the target user is performed to obtain the second order rate prediction result; based on the second order rate prediction result, the second interaction qualification level of the target user in the second stage is determined, the second interaction file is determined, and the second-stage interaction mode is determined based on the second interaction file, so that the target user can perform the next-stage behavior operation based on the second-stage interaction mode. In this embodiment, the target user performs the next-stage behavior operation based on the second-stage interaction mode and the second feedback information, that is, the hierarchical determination of the target user's interaction qualification level at different stages is realized.

[0127] Further, based on the first embodiment and the second embodiment of the present application, after the step of determining the second interaction qualification level of the target user in the second stage and obtaining the second interaction qualification level determination result, the following steps are included:

[0128] Step C1: if it is detected that the behavior prediction results of the target user in multiple time-series continuous stages are all greater than a preset value, a preset special identification process is performed on the target user;

[0129] In this embodiment, if it is detected that the behavior prediction results of the target user in multiple time-series continuous stages are all greater than the preset value, it indicates that the target user is a user who needs to be recommended, and thus a preset special identification processing is performed on the target user.

[0130] Step C2, executing a preset targeted recommendation process for the target user after the preset special identification processing.

[0131] A preset targeted recommendation process is executed for the target users who have been processed with the preset special identification. The preset targeted recommendation process may include: fixed-point push to the target users who have been processed with the preset special identification, or telephone push to the target users who have been processed with the preset special identification. To avoid causing user disgust, if no user feedback is received after a preset number of fixed-point pushes or telephone pushes, no push will be made within a preset time period.

[0132] In this embodiment, if it is detected that the behavior prediction results of the target user in multiple time-series continuous stages are greater than the preset value, the target user is processed with a preset special mark; and a preset targeted recommendation process is executed for the target user after the preset special mark processing. In this embodiment, targeted services are provided to users with preset special mark processing to improve user experience.

[0133] Further, based on the above embodiments in the present application, another embodiment of the present application is provided. In this embodiment, the step of determining the first interaction qualification level of the target user in the first stage based on the first order placement rate prediction result, and obtaining the second stage behavior data of the target user determined based on the first interaction qualification level includes:

[0134] Step a1, determining a first interaction qualification level of a target user in the first phase based on the first order rate prediction result;

[0135] Step a2, obtaining the channel type corresponding to the first interaction qualification level;

[0136] Step a3: if the channel type is a public account channel, outputting preset selected articles to the target user based on the public account channel;

[0137] Step a4, obtaining the second-stage behavior data of the target user determined based on the preset selected articles.

[0138] Specifically, for example, the first order rate prediction result, i.e., the order rate, is 0.3. At this time, the pre-stored first interaction qualification level is level A, the channel information of the target user is obtained as the public account channel, and it is determined to output the preset selected articles to the target user, and the second-stage behavior data determined by the target user based on the preset selected articles is obtained. Specifically, the user generates a (click to read, read for half an hour) behavior based on the preset selected articles, and the generated (click to read, read for half an hour) behavior and the first-stage behavior data constitute the second-stage behavior data. After determining the second-stage behavior data, the second feedback information is further fed back based on the second-stage behavior data.

[0139] In this embodiment, the first interaction qualification level of the target user in the first stage is determined based on the first order rate prediction result; the channel type corresponding to the first interaction qualification level is obtained; if the channel type is a public account channel, the preset selected articles are output to the target user based on the public account channel; and the second stage behavior data determined by the target user based on the preset selected articles is obtained. Thus, the second stage behavior data is accurately determined.

[0140] Reference Figure 3 , Figure 3 It is a schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present application.

[0141] like Figure 3As shown, the interactive qualification level determination device may include: a processor 1001, such as a CPU, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to realize the connection and communication between the processor 1001 and the memory 1005. The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0142] Optionally, the interactive qualification level determination device may also include a rectangular user interface, a network interface, a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module, etc. The rectangular user interface may include a display screen (Display), an input submodule such as a keyboard (Keyboard), and the optional rectangular user interface may also include a standard wired interface and a wireless interface. The network interface may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0143] Those skilled in the art will understand that Figure 3 The structure of the interactive qualification level determination device shown in the figure does not constitute a limitation on the interactive qualification level determination device, and may include more or less components than those shown in the figure, or combine certain components, or arrange the components differently.

[0144] like Figure 3 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module and an interactive qualification level determination program. The operating system is a program that manages and controls the hardware and software resources of the interactive qualification level determination device, and supports the operation of the interactive qualification level determination program and other software and / or programs. The network communication module is used to realize the communication between the components inside the memory 1005, and the communication with other hardware and software in the interactive qualification level determination system.

[0145] exist Figure 3 In the interactive qualification level determination device shown, the processor 1001 is used to execute the interactive qualification level determination program stored in the memory 1005 to implement the steps of any of the interactive qualification level determination methods described above.

[0146] The specific implementation of the interactive qualification level determination device of the present application is basically the same as the embodiments of the interactive qualification level determination method described above, and will not be repeated here.

[0147] The present application also provides an interactive qualification level determination device, the interactive qualification level determination device comprising:

[0148] A first acquisition module is used to acquire the first-stage behavior data of the target user, determine the first target prediction model of the first-stage behavior data, perform a first-stage order rate prediction on the target user, and obtain a first order rate prediction result;

[0149] A first determination module is used to determine a first interaction qualification level of a target user in the first phase based on the first order placement rate prediction result, and obtain second phase behavior data of the target user determined based on the first interaction qualification level;

[0150] The second determination module is used to determine a second target prediction model of the second stage behavior data based on the second stage behavior data, and predict the second stage order rate of the target user, so as to determine the second interaction qualification level of the second stage target user based on the second order rate prediction result, wherein the second stage is a time-series continuous stage with the first stage.

[0151] Optionally, the first acquisition module includes:

[0152] A first acquisition unit, configured to acquire first-stage behavior data of a target user and determine first-stage features of the first-stage behavior data;

[0153] The first prediction unit is used to select a first target prediction model of the first stage characteristics from a preset model set, and based on the first target prediction model, perform a first stage order rate prediction on the target user to obtain a first order rate prediction result.

[0154] Optionally, the interaction qualification level determination device further includes:

[0155] The second acquisition module is used to acquire the combined features of each stage and the training data corresponding to the combined features of each stage;

[0156] The third acquisition module is used to iteratively train the preset models to be trained based on the training data, obtain the target models corresponding to the combined features of each stage, and obtain a preset model set.

[0157] Optionally, the first determining module includes:

[0158] A second acquisition unit, configured to determine a first interaction qualification level of the target user in the first phase based on a numerical value of the first order placement rate prediction result;

[0159] The first determining unit is configured to determine a first interaction file of the first interaction qualification level, parse the first interaction file, and determine second-stage behavior data.

[0160] Optionally, the first determining unit includes:

[0161] A first determining subunit, configured to determine a first interaction file of the first interaction qualification level;

[0162] The second determining subunit is used to determine the channel type of the target user, and determine the second-stage behavior data based on the channel type and the first interaction file.

[0163] Optionally, the second determining module includes:

[0164] A third acquisition unit is used to acquire the second-stage behavior data of the target user and determine the second-stage characteristics of the second-stage behavior data;

[0165] A second prediction unit is used to select a second target prediction model of the second stage characteristics from a preset model set, and perform a second stage order rate prediction for the target user based on the second target prediction model to obtain a second order rate prediction result;

[0166] The second determination unit is used to determine the second interaction qualification level of the target user in the second stage based on the second order rate prediction result, determine the second interaction file, and determine the interaction mode of the second stage based on the second interaction file, so that the target user can perform the next stage of behavior operation based on the interaction mode of the second stage.

[0167] Optionally, the interaction qualification level determination device further includes:

[0168] The identification model is used to perform a preset special identification process on the target user if it is detected that the behavior prediction results of the target user in multiple time-series continuous stages are all greater than a preset value;

[0169] The execution model is used to execute a preset targeted recommendation process for the target user after the preset special identification processing.

[0170] Optionally, the first determining module further includes:

[0171] A third determining unit, configured to determine a first interaction qualification level of a target user in the first phase based on the first order placement rate prediction result;

[0172] A fourth acquiring unit, configured to acquire a channel type corresponding to the first interaction qualification level;

[0173] A fourth determining unit, configured to output preset selected articles to the target user based on the official account channel if the channel type is an official account channel;

[0174] The fifth acquisition unit is used to acquire the second-stage behavior data of the target user determined based on the preset selected articles.

[0175] The specific implementation of the interactive qualification level determination device of the present application is basically the same as the various embodiments of the interactive qualification level determination method described above, and will not be repeated here.

[0176] An embodiment of the present application provides a storage medium, and the storage medium stores one or more programs, and the one or more programs can also be executed by one or more processors to implement the steps of any of the above-mentioned methods for determining the interaction qualification level.

[0177] The specific implementation of the storage medium of the present application is basically the same as the above-mentioned embodiments of the interaction qualification level determination method, and will not be repeated here.

[0178] It should be noted that, in this article, the terms "include", "comprises" or any other variations 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, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0179] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0180] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0181] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for determining an interaction qualification level, characterized in that: The interactive qualification level determination method comprises: Acquire the first-stage behavior data of the target user, determine the first target prediction model of the first-stage behavior data, perform the first-stage order rate prediction for the target user, and obtain the first order rate prediction result; the first-stage behavior data includes the recorded operation behavior of the user; Based on the first order rate prediction result, determine the first interaction qualification level of the target user in the first stage, and obtain the second stage behavior data of the target user determined based on the first interaction qualification level; the second stage behavior data includes the service for which the user receives feedback after the first stage behavior, and the user behavior generated based on the feedback service later; Based on the second-stage behavior data, determine a second target prediction model for the second-stage behavior data, and perform a second-stage order rate prediction for the target user, so as to determine a second interaction qualification level of the second-stage target user based on the second order rate prediction result, wherein the second stage is a time-series continuous stage with the first stage; The step of determining a first interaction qualification level of a target user in the first phase based on the first order rate prediction result, and acquiring second phase behavior data of the target user determined based on the first interaction qualification level comprises: Determining a first interaction qualification level of the target user in the first phase based on the numerical value of the first order rate prediction result; Determine a first interaction file of the first interaction qualification level, parse the first interaction file, and determine second-stage behavior data; The step of determining a first interaction qualification level of a target user in the first phase based on the first order rate prediction result, and acquiring second phase behavior data of the target user determined based on the first interaction qualification level, further includes: Determining a first interaction qualification level of a first-stage target user based on the first order rate prediction result; Obtaining a channel type corresponding to the first interaction qualification level; If the channel type is a public account channel, outputting preset selected articles to the target user based on the public account channel; The second-stage behavior data of the target user determined based on the preset selected articles is obtained.

2. The interactive qualification level determination method according to claim 1, characterized in that: The step of acquiring the first-stage behavior data of the target user, determining the first target prediction model of the first-stage behavior data, performing the first-stage order rate prediction for the target user, and obtaining the first order rate prediction result includes: Acquire the first-stage behavior data of the target user, and determine the first-stage characteristics of the first-stage behavior data; A first target prediction model of the first stage features is selected from a preset model set, and based on the first target prediction model, a first stage order rate prediction is performed on the target user to obtain a first order rate prediction result.

3. The interactive qualification level determination method according to claim 2, characterized in that: Before the step of selecting the first target prediction model of the first stage features from the preset model set, the method includes: Obtain the combined features of each stage, and obtain the training data corresponding to the combined features of each stage; Based on the training data, the preset models to be trained are iteratively trained to obtain target models corresponding to the combined features of each stage, so as to obtain a preset model set.

4. The interactive qualification level determination method according to claim 1, characterized in that: The step of determining the first interaction file of the first interaction qualification level, parsing the first interaction file, and determining the second-stage behavior data comprises: a first interaction profile for determining said first interaction qualification level; The channel type of the target user is determined, and the second-stage behavior data is determined based on the channel type and the first interaction file.

5. The interactive qualification level determination method according to claim 1, characterized in that: The step of determining a second target prediction model of the second stage behavior data based on the second stage behavior data, predicting the second stage order rate of the target user, and determining the second interaction qualification level of the second stage target user based on the second order rate prediction result includes: Acquire the second-stage behavior data of the target user, and determine the second-stage characteristics of the second-stage behavior data; Selecting a second target prediction model of the second stage features from the preset model set, and performing a second stage order rate prediction for the target user based on the second target prediction model to obtain a second order rate prediction result; Based on the second order rate prediction result, a second interaction qualification level of the target user in the second stage is determined, a second interaction file is determined, and an interaction mode in the second stage is determined based on the second interaction file, so that the target user can perform behavioral operations in the next stage based on the interaction mode in the second stage.

6. The interactive qualification level determination method according to claim 1, characterized in that: After the step of predicting the order rate of the target user in the second stage to determine the second interaction qualification level of the target user in the second stage based on the second order rate prediction result, the method further comprises: Obtain the behavior prediction results of the target user in multiple continuous time stages; If it is detected that the behavior prediction results of the target user in multiple time-series continuous stages are all greater than the preset value, a preset special identification process is performed on the target user; A preset targeted recommendation process is executed for the target user after the preset special identification processing.

7. An interactive qualification level determination device, characterized in that: The interactive qualification level determination device comprises: A first acquisition module is used to acquire the first-stage behavior data of the target user, determine the first target prediction model of the first-stage behavior data, perform the first-stage order rate prediction for the target user, and obtain the first order rate prediction result; the first-stage behavior data includes the recorded operation behavior of the user; A first determination module is used to determine a first interaction qualification level of a target user in the first stage based on the first order rate prediction result, and obtain second stage behavior data of the target user determined based on the first interaction qualification level; the second stage behavior data includes a service for which the user receives feedback after the first stage behavior, and a subsequent user behavior generated based on the feedback service; a second determination module, configured to determine a second target prediction model of the second-stage behavior data based on the second-stage behavior data, and to predict the order rate of the target user in the second stage, so as to determine a second interaction qualification level of the target user in the second stage based on the second order rate prediction result, wherein the second stage is a stage that is sequentially continuous with the first stage; The first determination module is used to implement: Determining a first interaction qualification level of the target user in the first phase based on the numerical value of the first order rate prediction result; Determine a first interaction file of the first interaction qualification level, parse the first interaction file, and determine second-stage behavior data; The first determining module is further used to implement: Determining a first interaction qualification level of a first-stage target user based on the first order rate prediction result; Obtaining a channel type corresponding to the first interaction qualification level; If the channel type is a public account channel, outputting preset selected articles to the target user based on the public account channel; The second-stage behavior data of the target user determined based on the preset selected articles is obtained.

8. An interactive qualification level determination device, characterized in that: The interactive qualification level determination device comprises: a memory, a processor, and a program stored in the memory for implementing the interactive qualification level determination method. The memory is used to store a program for implementing the interactive qualification level determination method; The processor is used to execute a program for implementing the interaction qualification level determination method, so as to implement the steps of the interaction qualification level determination method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a program for implementing the interactive qualification level determination method, and the program for implementing the interactive qualification level determination method is executed by a processor to implement the steps of the interactive qualification level determination method according to any one of claims 1 to 6.

Images