User portrait index heat prediction method, device, equipment and storage medium

Abstract

The present application relates to the field of data processing technology, and provides a method, device, equipment and storage medium for predicting the heat of user portrait indicators. The method responds to a user's query operation, determines a user category to be predicted and a time to be predicted according to the query operation; obtains page click data of the user category to be predicted; processes the page click data according to a preset time series dimension and a preset category dimension, and establishes an interface for data to be counted; obtains data to be counted through the interface for data to be counted according to the time to be predicted; performs heat analysis on the data to obtain the index heat of the user category to be predicted within the time to be predicted, reduces the impact on the efficiency of online database operations, speeds up the data statistics rate, dynamically obtains accurate index heat according to different prediction time ranges, and improves the accuracy of user portrait indicator heat.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for predicting the heat of user portrait indicators. Background Art

[0002] User portraits, also known as user roles, are an effective tool for outlining target users and linking user demands with design directions. User portraits have been widely used in various fields. In the era of big data, user information is flooding the Internet. Each specific information of the user is abstracted into a label, and these labels are used to concretize the user image, so as to provide users with targeted services. In the actual operation process, the user's attributes, behaviors and expected data are often linked in the most simple and life-like words. The heat of different indicators of user portraits can reflect the user's activity for different services, and targeted services can be provided to users based on the heat of user portrait indicators.

[0003] In related technologies, page click operations are usually stored in online databases. When staff members perform popularity statistics on user portrait indicators, they usually process the data directly in the online database. They use complex logic to count the usage of portrait indicators through the page click operations stored in the online database, combined with the historical data and other experience mastered by the staff.

[0004] However, the statistical methods in the existing technology will affect the efficiency of online operations, have low statistical efficiency, and the staff can only perform statistics based on historical data and cannot accurately predict the popularity of user portrait indicators. Summary of the invention

[0005] The present application provides a method, device, equipment and storage medium for predicting the heat of user portrait indicators, thereby solving the technical problems that the statistical methods in the prior art will affect the efficiency of online operations, the statistical efficiency is low, and the staff can only perform statistics based on historical data and cannot accurately predict the heat of user portrait indicators.

[0006] In a first aspect, the present application provides a method for predicting the popularity of user portrait indicators, including:

[0007] In response to a query operation of a user, determining a user category to be predicted and a time to be predicted according to the query operation;

[0008] Obtaining page click data of the user category to be predicted;

[0009] According to the preset time series dimension and the preset category dimension, the page click data is processed and an interface for the data to be counted is established;

[0010] According to the time to be predicted, obtaining the statistical data to be counted through the statistical data interface;

[0011] Perform heat analysis on the to-be-predicted data to obtain the index heat of the to-be-predicted user category within the to-be-predicted time.

[0012] Here, an embodiment of the present application provides a method for predicting the heat of user portrait indicators. Users can customize the prediction time range. For the user category that needs to be queried, the page click data of the user category to be predicted is first obtained. There is no need to perform data operations and statistical processing in the online database, which reduces the impact on the efficiency of online database operations and speeds up the data statistics rate. After obtaining the page click data, a public statistical method interface can be established on the time series and category dimensions. Through this interface, page click data within a preset time, business types, business indicators, etc. can be accurately obtained, so as to dynamically obtain accurate indicator heat according to different prediction time ranges, thereby improving the accuracy of user portrait indicator heat.

[0013] Optionally, performing heat analysis on the to-be-stated data to obtain the index heat of the to-be-predicted user category within the to-be-predicted time period includes:

[0014] Establishing a prediction model based on the data to be counted;

[0015] According to the prediction results of the prediction model, the probability of different user portrait indicators of the user category to be predicted within the prediction time is obtained;

[0016] The probabilities of the different user portrait indicators are sorted to obtain the indicator heat of the user category to be predicted.

[0017] Here, when determining the heat of user portrait indicators, the embodiment of the present application can dynamically build different prediction models according to different prediction time ranges through the interface of customizing the prediction time range, so that the user portrait system is more flexible. There is no need to store every possible prediction situation. The prediction model can adapt to different application scenarios, which improves the flexibility of indicator heat prediction and saves system space. At the same time, through the prediction model method, the accuracy of user portrait indicator prediction is further improved.

[0018] Optionally, obtaining page click data of the to-be-predicted user category includes:

[0019] In the online database, the page click data of the user category to be predicted is obtained.

[0020] Here, when predicting the heat of user portrait indicators, the embodiment of the present application can obtain real-time and accurate page click data through the online database, thereby improving the accuracy and real-time performance of the prediction results. In addition, there is no need to perform data processing in the online database, which reduces the resource usage of the online database and improves the data processing rate.

[0021] Optionally, the preset time series dimensions include the current day, the past week, the past two weeks, and the current quarter;

[0022] The preset category dimensions include a primary category dimension, a secondary category dimension, and a tertiary category dimension;

[0023] The establishing of the interface for statistics to be collected includes:

[0024] Establish the time dimension + category dimension + portrait indicator click count interface;

[0025] or,

[0026] Establish the time dimension + portrait indicator click count interface;

[0027] or,

[0028] Establish category dimension + portrait indicator click count interface.

[0029] Here, the embodiment of the present application can obtain the click status of user portrait indicators within a future time range through a customized time range (for example, the next week, the next month, the next quarter), and enable users to flexibly grasp the type of popularity indicators through the category dimension. Different interfaces for data to be counted are established through the above two dimensions. The data to be counted can be obtained quickly, conveniently and accurately through the access interface, without downloading a large amount of data for training, thereby further improving the prediction efficiency and prediction accuracy.

[0030] Optionally, after performing heat analysis processing on the to-be-stated data to obtain the index heat of the to-be-predicted user category within the to-be-predicted time, the method further includes:

[0031] Displays the heat of the indicator.

[0032] Among them, the user portrait indicator heat prediction method provided in the embodiment of the present application can display the indicator heat to the user, realize the visualization of the indicator heat, facilitate the user to understand the various business needs of the target user category, and improve the user experience.

[0033] Optionally, after performing heat analysis processing on the to-be-stated data to obtain the index heat of the to-be-predicted user category within the to-be-predicted time, the method further includes:

[0034] Generate service push information for the user category to be predicted according to the indicator heat.

[0035] Here, the embodiment of the present application can intelligently and automatically generate service push information based on the indicator heat of the user portrait, further improving the user experience.

[0036] Optionally, the performing data processing on the page click data according to a preset time series dimension and a preset category dimension includes:

[0037] According to the preset time series dimension and the preset category dimension, the page click data is processed by using the AWK text processing tool.

[0038] Here, compared with using complex logic to process large amounts of data in an online database, the embodiment of the present application uses AWK, a powerful text analysis tool, to speed up data processing efficiency, while reducing resource usage of the connected database, avoiding interference with the online transaction processing speed, and improving the prediction efficiency of user portrait indicator heat.

[0039] In a second aspect, an embodiment of the present application provides a user portrait index heat prediction device, comprising:

[0040] A determination module, configured to respond to a user's query operation and determine a user category to be predicted and a time to be predicted according to the query operation;

[0041] A first acquisition module, used to acquire page click data of the user category to be predicted;

[0042] A first processing module is used to process the page click data according to a preset time series dimension and a preset category dimension, and establish an interface for statistical data;

[0043] A second acquisition module is used to acquire the to-be-predicted statistical data through the to-be-stated data interface according to the to-be-predicted time;

[0044] The second processing module is used to perform heat analysis on the to-be-predicted data to obtain the index heat of the to-be-predicted user category within the to-be-predicted time.

[0045] Optionally, the second processing module is specifically configured to:

[0046] Establishing a prediction model based on the data to be counted;

[0047] According to the prediction results of the prediction model, the probability of different user portrait indicators of the user category to be predicted within the prediction time is obtained;

[0048] The probabilities of the different user portrait indicators are sorted to obtain the indicator heat of the user category to be predicted.

[0049] Optionally, the first acquisition module is specifically used to:

[0050] In the online database, the page click data of the user category to be predicted is obtained.

[0051] Optionally, the preset time series dimensions include the current day, the past week, the past two weeks, and the current quarter;

[0052] The preset category dimensions include a primary category dimension, a secondary category dimension, and a tertiary category dimension;

[0053] The first processing module is specifically used for:

[0054] Establish the time dimension + category dimension + portrait indicator click count interface;

[0055] or,

[0056] Establish the time dimension + portrait indicator click count interface;

[0057] or,

[0058] Establish category dimension + portrait indicator click count interface.

[0059] Optionally, after the second processing module performs heat analysis processing on the to-be-stated data to obtain the index heat of the to-be-predicted user category within the to-be-predicted time, the above-mentioned device further includes:

[0060] The display module is used to display the heat of the indicator.

[0061] Optionally, after the second processing module performs heat analysis processing on the to-be-stated data to obtain the index heat of the to-be-predicted user category within the to-be-predicted time, the above-mentioned device further includes:

[0062] A generation module is used to generate service push information for the user category to be predicted according to the indicator heat.

[0063] Optionally, the first processing module is specifically configured to:

[0064] According to the preset time series dimension and the preset category dimension, the page click data is processed by using the AWK text processing tool.

[0065] In a third aspect, the present application provides a user portrait index heat prediction device, including: at least one processor and a memory;

[0066] The memory stores computer-executable instructions;

[0067] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the user portrait indicator heat prediction method described in the first aspect and various possible designs of the first aspect.

[0068] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer execution instructions. When a processor executes the computer execution instructions, the user portrait indicator heat prediction method described in the first aspect and various possible designs of the first aspect is implemented.

[0069] In a fifth aspect, the present invention provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the user portrait indicator heat prediction method described in the first aspect and various possible designs of the first aspect.

[0070] The present application provides a method, device, equipment and storage medium for predicting the heat of user portrait indicators, wherein the method allows users to customize the prediction time range. For the user category that needs to be queried, the page click data of the user category to be predicted is first obtained, without the need to perform data operations and statistical processing in the online database, thereby reducing the impact on the operating efficiency of the online database and speeding up the data statistics rate. After obtaining the page click data, a public statistical method interface can be established on the time series and category dimensions. Through this interface, the page click data within the preset time, as well as the business type, business indicators, etc. can be accurately obtained, thereby dynamically obtaining accurate indicator heat according to different prediction time ranges, thereby improving the accuracy of the user portrait indicator heat. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] 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, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0072] Figure 1 A schematic diagram of a user portrait index heat prediction system architecture provided in an embodiment of the present application;

[0073] Figure 2 A flowchart of a method for predicting the popularity of user portrait indicators provided in an embodiment of the present application;

[0074] Figure 3 A flowchart of another method for predicting the popularity of user portrait indicators provided in an embodiment of the present application;

[0075] Figure 4A schematic diagram of the structure of a user portrait index heat prediction device provided in an embodiment of the present application;

[0076] Figure 5 A schematic diagram of the structure of a user portrait index heat prediction device provided in an embodiment of the present application.

[0077] The above drawings show clear embodiments of the present disclosure, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present disclosure in any way, but to illustrate the concepts of the present disclosure to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0078] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0079] The terms "first", "second", "third", and "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0080] It should be noted that the collection, storage, use, processing, transmission, provision and disclosure of financial data or personal data involved in the technical solution of this application are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0081] First, the terms in the embodiments of the present application are explained:

[0082] AWK: A language for processing text files and a text analysis tool.

[0083] Linear regression: A type of regression analysis that models the relationship between one or more independent variables and a dependent variable using a least-squares function of an equation that is a linear combination of one or more model parameters called the regression coefficients.

[0084] The user portrait system needs to be based on an effective behavior screening method. The staff can sort, classify and analyze the recent clicks on the user portrait indicators to provide the staff with a range of recently active user groups. The staff can provide targeted services to users based on the analysis of historical data. For example, in the user portrait system of a bank, there are various portrait indicators with a wide variety and a large amount of data. With the increase in demand, the popularity of user portrait indicators is expected to have a comprehensive ranking result, which is used to analyze the active user groups in the near future and formulate targeted business plans for these user groups. Therefore, a relatively efficient and portable method is needed to adapt to the development of different business needs. Due to the limitations of frequent business transactions in banks every day, page click operations are stored in online databases. Using complex logic statistics directly in online databases to count the usage of portrait indicators may affect the efficiency of online operations, and the statistical efficiency is also relatively low. From the staff's perspective, due to the lack of experience in data analysis, it is difficult to obtain an estimate of the active user trends in the near future. Differentiating different groups of users based only on historical portrait popularity cannot represent the popularity dynamics of portrait indicators in the near future, which may lead to deviations in customized marketing strategies. In addition, the existing system predicts that the popularity of user portrait indicator clicks is relatively fixed in time, and the staff cannot flexibly screen out possible active target user groups in the short, medium, and long term based on the prediction results.

[0085] In order to solve the above problems, the embodiments of the present application provide a user portrait indicator heat prediction method, device, equipment and storage medium, wherein the method first obtains the page click data of the user category to be predicted, without the need to perform data operations and statistical processing in the online database, which can reduce the impact on the online database operation efficiency and speed up the data statistics rate; at the same time, a custom interface is used to allow marketing personnel to customize the prediction time point and obtain prediction results for different time range requirements.

[0086] Optional, Figure 1 A schematic diagram of the user portrait index heat prediction system architecture provided in the embodiment of the present application. Figure 1 In the above architecture, the above architecture includes at least one of a receiving device 101, a processor 102 and a display device 103.

[0087] It is understandable that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the user portrait index heat prediction system architecture. In other feasible implementations of the present application, the above architecture may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently, which can be determined according to the actual application scenario and is not limited here. Figure 1The components shown may be implemented in hardware, software, or a combination of software and hardware.

[0088] In a specific implementation process, the receiving device 101 may be an input / output interface or a communication interface.

[0089] The processor 102 can obtain the user's query operation through the receiving device 101, and obtain the page click data of the user category to be predicted. There is no need to perform data operations and statistical processing in the online database, which can reduce the impact on the online database operation efficiency and speed up the data statistics rate. At the same time, a custom interface is used to allow marketing personnel to customize the prediction time point and obtain prediction results for different time range requirements.

[0090] The display device 103 can be used to display the above results, etc., and can also interact with the user through the display device.

[0091] The display device 103 may also be a touch display screen, which is used to receive user instructions while displaying the above content to achieve interaction with the user.

[0092] In some embodiments, the display device 103 may be a mobile terminal, a tablet computer, a computer, a laptop computer, a liquid crystal display, an OLED display, a projection display device, etc.

[0093] Optionally, the display device 103 can be a staff member's mobile terminal or a computer device of a bank branch. The staff can receive the user index heat sent by the processor 102 through the mobile terminal or computer device, so that the staff can provide targeted services to the user based on the index heat.

[0094] It should be understood that the above-mentioned processor can be implemented by the processor reading instructions in the memory and executing the instructions, or it can be implemented by a chip circuit.

[0095] In addition, the network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0096] The technical solution of the present application is described in detail below in conjunction with specific embodiments:

[0097] Optionally, Figure 2 A flowchart of a user portrait index heat prediction method provided in an embodiment of the present application. The execution subject of the embodiment of the present application can be Figure 1The specific execution subject of the processor 102 can be determined according to the actual application scenario. Figure 2 As shown, the method comprises the following steps:

[0098] S201: In response to a query operation of a user, determine a user category to be predicted and a time to be predicted according to the query operation.

[0099] In a possible implementation, the user may query by voice input, touch selection or input on the display interface, or by using an input / output device such as a keyboard.

[0100] Users can customize the input of the forecast time for a certain user category to be queried, so as to make accurate indicator forecasts for the forecast time.

[0101] S202: Obtain page click data of the user category to be predicted.

[0102] In the online database, obtain the page click data of the user category to be predicted.

[0103] Here, when predicting the heat of user portrait indicators, the embodiment of the present application can obtain real-time and accurate page click data through the online database, thereby improving the accuracy and real-time performance of the prediction results. In addition, there is no need to perform data processing in the online database, which reduces the resource usage of the online database and improves the data processing rate.

[0104] Optionally, public methods for data processing are defined in the AWK data processing function, including methods for pulling down data from an online database library, field splitting, and invalid data maintenance. Here, the AWK data processing function can be used to pull down data in the online database to obtain page click data.

[0105] Optionally, after obtaining the original data, the original data can be cleaned and converted into data that fully meets the needs, thereby improving the accuracy of the prediction.

[0106] S203: Process the page click data according to the preset time series dimension and the preset category dimension, and establish an interface for statistical data.

[0107] Optionally, data processing is performed on the page click data according to a preset time series dimension and a preset category dimension, including: data processing is performed on the page click data through an AWK text processing tool according to the preset time series dimension and the preset category dimension.

[0108] Here, compared with using complex logic to process large amounts of data in an online database, the embodiment of the present application uses AWK, a powerful text analysis tool, to speed up data processing efficiency, while reducing resource usage of the connected database, avoiding interference with the online transaction processing speed, and improving the prediction efficiency of user portrait indicator heat.

[0109] Optionally, the preset time series dimensions include current day, recent week, recent two weeks, and current quarter.

[0110] The preset category dimensions include the first-level category dimension, the second-level category dimension, and the third-level category dimension.

[0111] Optionally, the first-level category dimensions include indicators such as product holdings, transaction behavior, and credit and risk. Users can customize the category dimensions to determine the business preference classification that needs to be predicted.

[0112] Establish an interface for statistical data to be collected, including: establishing an interface for time dimension + category dimension + number of clicks on portrait indicators; or, establishing an interface for time dimension + number of clicks on portrait indicators; or, establishing an interface for category dimension + number of clicks on portrait indicators.

[0113] Here, the embodiment of the present application can obtain the click status of user portrait indicators within a future time range through a customized time range (for example, the next week, the next month, the next quarter), and enable users to flexibly grasp the type of popularity indicators through the category dimension. Different interfaces for data to be counted are established through the above two dimensions. The data to be counted can be obtained quickly, conveniently and accurately through the access interface, without downloading a large amount of data for training, thereby further improving the prediction efficiency and prediction accuracy.

[0114] S204: Obtain the pending statistical data through the pending statistical data interface according to the pending prediction time.

[0115] S205: Perform heat analysis on the statistical data to obtain the index heat of the user category to be predicted within the time to be predicted.

[0116] The embodiment of the present application provides a method for predicting the heat of user portrait indicators. The user can customize the prediction time range. For the user category that needs to be queried, the page click data of the user category to be predicted is first obtained. There is no need to perform data operations and statistical processing in the online database, which reduces the impact on the efficiency of online database operations and speeds up the data statistics rate. After obtaining the page click data, a public statistical method interface can be established on the time series and category dimensions. Through this interface, the page click data within the preset time and the business type, business indicators and the like can be accurately obtained, so as to dynamically obtain accurate indicator heat according to different prediction time ranges, thereby improving the accuracy of the user portrait indicator heat.

[0117] Optionally, the embodiment of the present application can dynamically build different prediction models according to different prediction time ranges, thereby achieving accurate prediction of user portrait indicators. Figure 3 A flowchart of another user portrait index prediction method provided in an embodiment of the present application is shown as follows: Figure 3 As shown, the method includes:

[0118] S301: In response to a query operation of a user, determine a user category to be predicted and a time to be predicted according to the query operation.

[0119] S302: Obtain page click data of the user category to be predicted.

[0120] S303: Process the page click data according to the preset time series dimension and the preset category dimension, and establish an interface for statistical data.

[0121] S304: Obtain the data to be counted through the data to be counted interface according to the time to be predicted.

[0122] Among them, the implementation method of steps S301-S304 is similar to that of steps S201-S204, and will not be repeated here.

[0123] S305: Establish a prediction model based on the data to be counted.

[0124] Optionally, linear regression is used to build a prediction model.

[0125] Among them, linear regression is a lightweight prediction model, especially for a large amount of data, its main advantage is high efficiency. The establishment process of the linear regression prediction model is four steps: feature extraction, model construction, model training and prediction.

[0126] S306: According to the prediction results of the prediction model, the probabilities of different user portrait indicators of the user category to be predicted within the prediction time are obtained.

[0127] S307: Sort the probabilities of different user portrait indicators to obtain the indicator heat of the user category to be predicted.

[0128] Here, when determining the heat of user portrait indicators, the embodiment of the present application can dynamically build different prediction models according to different prediction time ranges through the interface of customizing the prediction time range, so that the user portrait system is more flexible. There is no need to store every possible prediction situation. The prediction model can adapt to different application scenarios, which improves the flexibility of indicator heat prediction and saves system space. At the same time, through the prediction model method, the accuracy of user portrait indicator prediction is further improved.

[0129] Optionally, after performing heat analysis on the statistical data to obtain the index heat of the user category to be predicted within the time to be predicted, the method further includes:

[0130] Displays the indicator heat.

[0131] The index heat here can be displayed by the above-mentioned display device 103.

[0132] Optionally, the embodiment of the present application may respond to a query operation of a user (the user here may be a staff member), and after each query result is obtained, the indicator heat is displayed on a display device such as a mobile terminal of the staff member.

[0133] Optionally, a preset update time period may be set, and the indicator heat is regularly displayed to the staff according to the preset update time period. It is understandable that the preset update time period here can be determined according to actual conditions, and the embodiment of the present application does not make specific restrictions on this.

[0134] Among them, the user portrait indicator heat prediction method provided in the embodiment of the present application can display the indicator heat to the user, realize the visualization of the indicator heat, facilitate the user to understand the various business needs of the target user category, and improve the user experience.

[0135] Optionally, after performing heat analysis on the statistical data to obtain the index heat of the user category to be predicted within the time to be predicted, the method further includes:

[0136] Based on the indicator heat, service push information is generated for the user category to be predicted.

[0137] Optionally, the service push information here can be pushed to the display interface of the user terminal at a fixed time.

[0138] Here, the embodiment of the present application can intelligently and automatically generate service push information based on the indicator heat of the user portrait, further improving the user experience.

[0139] Figure 4 A schematic diagram of the structure of a user portrait index heat prediction device provided in an embodiment of the present application, such as Figure 4 As shown, the device of the embodiment of the present application includes: a determination module 401, a first acquisition module 402, a first processing module 403, a second acquisition module 404 and a second processing module 405. The user portrait indicator heat prediction device here can be the above-mentioned processor itself, or a chip or integrated circuit that implements the function of the processor. It should be noted here that the division of the determination module 401, the first acquisition module 402, the first processing module 403, the second acquisition module 404 and the second processing module 405 is only a division of logical functions. Physically, the two can be integrated or independent.

[0140] The determination module is used to respond to the user's query operation and determine the user category to be predicted and the time to be predicted according to the query operation;

[0141] The first acquisition module is used to acquire page click data of the user category to be predicted;

[0142] The first processing module is used to process the page click data according to the preset time series dimension and the preset category dimension, and establish an interface for the data to be counted;

[0143] The second acquisition module is used to obtain the to-be-predicted statistical data through the to-be-stated data interface according to the to-be-predicted time;

[0144] The second processing module is used to perform heat analysis on the statistical data to obtain the index heat of the user category to be predicted within the time to be predicted.

[0145] Optionally, the second processing module is specifically used for:

[0146] Establish a prediction model based on the data to be counted;

[0147] According to the prediction results of the prediction model, the probability of different user portrait indicators of the user category to be predicted within the prediction time is obtained;

[0148] The probabilities of different user portrait indicators are sorted to obtain the indicator heat of the user category to be predicted.

[0149] Optionally, the first acquisition module is specifically used for:

[0150] In the online database, obtain the page click data of the user category to be predicted.

[0151] Optionally, the preset time series dimensions include current day, recent week, recent two weeks, and current quarter;

[0152] The preset category dimensions include the primary category dimension, the secondary category dimension and the tertiary category dimension;

[0153] The first processing module is specifically used for:

[0154] Establish the time dimension + category dimension + portrait indicator click count interface;

[0155] or,

[0156] Establish the time dimension + portrait indicator click count interface;

[0157] or,

[0158] Establish category dimension + portrait indicator click count interface.

[0159] Optionally, after the second processing module performs heat analysis processing on the statistical data to obtain the index heat of the user category to be predicted within the time to be predicted, the device further includes:

[0160] Display module, used to display indicator heat.

[0161] Optionally, after the second processing module performs heat analysis processing on the statistical data to obtain the index heat of the user category to be predicted within the time to be predicted, the device further includes:

[0162] The generation module is used to generate service push information for the user category to be predicted based on the indicator heat.

[0163] Optionally, the first processing module is specifically used for:

[0164] According to the preset time series dimension and the preset category dimension, the page click data is processed through the AWK text processing tool.

[0165] like Figure 5 As shown, the user portrait index heat prediction device includes: a processor 501 and a memory 502, each component is connected to each other using different buses, and can be installed on a common motherboard or installed in other ways as needed. The processor 501 can process instructions executed in the user portrait index heat prediction device, including instructions for graphic information stored in or on the memory for display on an external input / output device (such as a display device coupled to an interface). In other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Figure 5 A processor 501 is taken as an example.

[0166] The memory 502 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as the program instructions / modules corresponding to the method of the user portrait index heat prediction device in the embodiment of the present application (for example, the attached Figure 4 As shown, the determination module 401, the first acquisition module 402, the first processing module 403, the second acquisition module 404 and the second processing module 405). The processor 501 executes various functional applications and the user portrait index heat prediction method by running the non-transient software programs, instructions and modules stored in the memory 502, that is, the method of implementing the user portrait index heat prediction device in the above method embodiment.

[0167] The user portrait index heat prediction device may further include: an input device 503 and an output device 504. The processor 501, the memory 502, the input device 503 and the output device 504 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0168] The input device 503 can receive input digital or character information, and generate key signal input related to user settings and function control of the user portrait index heat prediction device, such as a touch screen, a keypad, a mouse, or multiple mouse buttons, a trackball, a joystick and other input devices. The output device 504 can be an output device such as a display device of the user portrait index heat prediction device. The display device can include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device can be a touch screen.

[0169] The user portrait index heat prediction device of the embodiment of the present application can be used to execute the technical solutions in the above-mentioned method embodiments of the present application. Its implementation principles and technical effects are similar and will not be repeated here.

[0170] An embodiment of the present application also provides a computer-readable storage medium, which stores computer execution instructions. When the computer execution instructions are executed by a processor, they are used to implement any of the above-mentioned user portrait indicator heat prediction methods.

[0171] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, is used to implement any of the above-mentioned user portrait indicator heat prediction methods.

[0172] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0173] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0174] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0175] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A user portrait index heat prediction method, characterized in that: include: In response to a query operation of a user, determining a user category to be predicted and a time to be predicted according to the query operation; Obtaining page click data of the user category to be predicted; According to the preset time series dimension and the preset category dimension, the page click data is processed and an interface for the data to be counted is established; According to the time to be predicted, obtaining the statistical data to be counted through the statistical data interface; Performing heat analysis on the to-be-predicted data to obtain the index heat of the to-be-predicted user category within the to-be-predicted time period; The heat analysis processing of the to-be-stated data to obtain the index heat of the to-be-predicted user category within the to-be-predicted time period includes: Establishing a prediction model based on the data to be counted; According to the prediction results of the prediction model, the probability of different user portrait indicators of the user category to be predicted within the prediction time is obtained; The probabilities of the different user portrait indicators are sorted to obtain the indicator heat of the user category to be predicted.

2. The method according to claim 1, characterized in that The obtaining of page click data of the to-be-predicted user category includes: In the online database, the page click data of the user category to be predicted is obtained.

3. The method according to claim 1, characterized in that The preset time series dimensions include the current day, the past week, the past two weeks and the current quarter; The preset category dimensions include a primary category dimension, a secondary category dimension, and a tertiary category dimension; The establishing of the interface for statistical data includes: Establish the time dimension + category dimension + portrait indicator click count interface; or, Establish the time dimension + portrait indicator click count interface; or, Establish category dimension + portrait indicator click count interface.

4. The method according to any one of claims 1 to 3, characterized in that: After performing heat analysis on the to-be-stated data to obtain the index heat of the to-be-predicted user category within the to-be-predicted time, the method further includes: Displays the heat of the indicator.

5. The method according to any one of claims 1 to 3, characterized in that: After performing heat analysis on the to-be-stated data to obtain the index heat of the to-be-predicted user category within the to-be-predicted time, the method further includes: Generate service push information for the user category to be predicted according to the indicator heat.

6. The method according to any one of claims 1 to 3, characterized in that: The processing of the page click data according to the preset time series dimension and the preset category dimension includes: According to the preset time series dimension and the preset category dimension, the page click data is processed by using the AWK text processing tool.

7. A user portrait index heat prediction device, characterized in that: include: A determination module, configured to respond to a user's query operation and determine a user category to be predicted and a time to be predicted according to the query operation; A first acquisition module, used to acquire page click data of the user category to be predicted; A first processing module is used to process the page click data according to a preset time series dimension and a preset category dimension, and establish an interface for statistical data; A second acquisition module is used to acquire the to-be-predicted statistical data through the to-be-stated data interface according to the to-be-predicted time; The second processing module is used to perform heat analysis on the to-be-predicted data to obtain the index heat of the to-be-predicted user category within the to-be-predicted time period; The second processing module is specifically used to establish a prediction model based on the statistical data; obtain the probabilities of different user portrait indicators of the user category to be predicted within the prediction time based on the prediction results of the prediction model; and sort the probabilities of the different user portrait indicators to obtain the indicator heat of the user category to be predicted.

8. A user portrait index heat prediction device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the user portrait indicator heat prediction method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer execution instructions, which, when executed by a processor, are used to implement the user portrait indicator heat prediction method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images