Age range analysis method and device, terminal equipment and storage medium
By obtaining the information and metadata of smart terminal applications, performing feature extraction and using machine learning algorithms to train the age range analysis and prediction model, the problem of under-applied smart terminal data is solved and effective analysis of the customer's age range is achieved.
Patent Information
- Application Number
- CN202510128019.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-05
- Publication Date
- 2025-06-10
AI Technical Summary
How to analyze the age range of customers based on the data generated by the smart terminal, solving the problem of insufficient application of data in the prior art.
By obtaining the information and metadata of installed applications of smart terminals, performing feature extraction, and using machine learning algorithms to train to obtain the age range analysis prediction model.
The ability to analyze the age range of customers based on smart terminal data is realized, and the application value of data is improved.
Smart Images
Figure CN120123724A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of artificial intelligence, and in particular, to a method, device, terminal device, and storage medium for analyzing an age range. Background Art
[0002] With the popularization of intelligent terminals, various applications are installed on intelligent terminals, and these applications will generate a large amount of data. However, this data has not been fully utilized. How to analyze the age of customers based on this data is a technical problem that urgently needs to be solved. Summary of the Invention
[0003] In view of this, this application provides a method, device, terminal device, and storage medium for analyzing an age range, which can identify and analyze the age range of the customer corresponding to the intelligent terminal according to the information of the applications installed on the intelligent terminal.
[0004] A method for analyzing an age range includes:
[0005] Obtaining the information of the applications installed on the target device;
[0006] Obtaining the metadata corresponding to each piece of the application information, where the metadata includes the interaction mode, icon design, usage frequency, usage duration, application size, and update frequency of the application;
[0007] Performing feature extraction on the metadata corresponding to the installed application information respectively to obtain corresponding training feature vectors;
[0008] Using a machine learning algorithm to train the training feature vectors to obtain an age range analysis prediction model.
[0009] In one embodiment, the step of using a machine learning algorithm to train the set of feature vectors to obtain an age range analysis prediction model includes:
[0010] Obtaining a plurality of first training samples, each of the first training samples including a training feature vector and a corresponding target feature vector;
[0011] Inputting the training feature vector into a preset model to be trained to obtain a predicted feature vector;
[0012] Calculating a corresponding loss function according to the predicted feature vector and the target feature vector;
[0013] In the case that the first loss function does not meet the first preset training stop condition, determining the change range of the model parameters of the preset model to be trained according to a preset learning rate;
[0014] Update the model parameters of the preset model to be trained according to the variation range of the model parameters, so as to obtain an updated preset model to be trained;
[0015] Input the training feature vector into the updated preset model to be trained to obtain an updated predicted feature vector until an age range analysis prediction model is obtained.
[0016] In one embodiment, after the first loss function satisfies the first preset training stop condition, the analysis method further includes:
[0017] Obtain the output training feature vector;
[0018] Input the output training feature vector into a preset application classification model to obtain predicted application category information.
[0019] In one embodiment, before the step of inputting the output training feature vector into a preset application classification model to obtain predicted application category information, it further includes:
[0020] Obtain a plurality of second training samples, each of the second training samples including a plurality of output training feature vectors and corresponding application category labels;
[0021] Input the second training samples into an initial preset application classification model to obtain predicted application categories;
[0022] Train the initial preset application classification model according to the application category labels, the predicted application categories and a preset classification loss function until the convergence degree of the preset classification loss function meets a preset threshold to obtain the preset application classification model.
[0023] In one embodiment, the preset classification loss function adopts a softmax cross-entropy loss function.
[0024] In one embodiment, the machine learning algorithm adopts a deep learning algorithm.
[0025] In one embodiment, the machine learning algorithm adopts a decision tree algorithm.
[0026] In addition, an analysis device for an age range is further provided, including:
[0027] A program information acquisition unit, configured to acquire information of applications installed in a target device;
[0028] A metadata acquisition unit, configured to acquire metadata corresponding to each of the application information, where the metadata includes an interaction mode of the application, an icon design, a usage frequency, a usage duration, an application size, and an update frequency;
[0029] A feature vector extraction unit for separately performing feature extraction on the metadata corresponding to the installed application information to obtain corresponding training feature vectors;
[0030] A model generation unit for training the training feature vectors using a machine learning algorithm to obtain an age range analysis and prediction model.
[0031] In addition, a terminal device is provided. The terminal device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, the steps of the above analysis method are implemented.
[0032] In addition, a storage medium is provided. A computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the above analysis method are implemented.
[0033] The above analysis method for age range includes obtaining the installed application information of a target device, obtaining the metadata corresponding to each application information, where the metadata includes the interaction mode, icon design, usage frequency, usage duration, application size, and update frequency of the application, separately performing feature extraction on the metadata corresponding to the installed application information to obtain corresponding training feature vectors, and training the training feature vectors using a machine learning algorithm to obtain an age range analysis and prediction model, so as to be able to use the age range analysis and prediction model to analyze the age range of the user corresponding to any input terminal device. Description of the Drawings
[0034] Figure 1 It is a schematic flowchart of an analysis method for age range provided in an embodiment of the present application;
[0035] Figure 2 It is a schematic flowchart of a method for obtaining an age range analysis and prediction model provided in an embodiment of the present application;
[0036] Figure 3 It is a schematic flowchart of another analysis method for age range provided in an embodiment of the present application;
[0037] Figure 4 It is a schematic flowchart of yet another analysis method for age range provided in an embodiment of the present application;
[0038] Figure 5 It is a schematic block diagram of the structure of an analysis device for age range provided in an embodiment of the present application;
[0039] Figure 6 It is a schematic block diagram of the internal structure of a terminal device provided in an embodiment of the present application.
[0040] The realization, functional features, and advantages of the present application will be further described in conjunction with embodiments with reference to the accompanying drawings. Detailed implementation manners
[0041] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, and should not be construed as a limitation to the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present application.
[0042] In addition, if the description in the present application involves "first", "second", etc., it is only for descriptive purposes (such as for distinguishing the same or similar elements), and should not be construed as indicating or implying its relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments may be combined with each other, but it must be based on the fact that those of ordinary skill in the art can implement it. When the combination of technical solutions appears to be contradictory or unable to be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present application.
[0043] As Figure 1 shown, the present application provides an analysis method for age range, including:
[0044] Step S110, obtaining the information of the applications installed on the target device.
[0045] The target device is a smart terminal, and the smart terminal usually installs various application information.
[0046] Step S120, obtaining the metadata corresponding to each application information, where the metadata includes the interaction mode, icon design, usage frequency, usage duration, application size, and update frequency of the application.
[0047] In this example, when the smart terminal user uses the application, a large amount of metadata is usually generated, including the interaction mode, icon design, usage frequency, usage duration, application size, and update frequency of the application.
[0048] Step S130, respectively performing feature extraction on the metadata corresponding to the installed application information to obtain the corresponding training feature vectors.
[0049] Step S140, using a machine learning algorithm to train the training feature vectors to obtain an age range analysis prediction model.
[0050] The above age range analysis method includes obtaining information on installed applications of a target device, obtaining metadata corresponding to each piece of application information, where the metadata includes the interaction mode, icon design, usage frequency, usage duration, application size, and update frequency of the application, respectively extracting features from the metadata corresponding to the installed application information to obtain corresponding training feature vectors, and using a machine learning algorithm to train the training feature vectors to obtain an age range analysis prediction model, so that the age range of the user corresponding to any input terminal device can be analyzed using this age range analysis prediction model.
[0051] In one embodiment, as Figure 2 shown, step S140 includes:
[0052] Step S141, obtaining a plurality of first training samples, each first training sample including a training feature vector and a corresponding target feature vector.
[0053] Step S142, inputting the training feature vector into a preset model to be trained to obtain a predicted feature vector.
[0054] Step S143, calculating a corresponding loss function according to the predicted feature vector and the target feature vector.
[0055] Step S144, in the case where the first loss function does not satisfy the first preset training stop condition, determining the change amplitude of the model parameters of the preset model to be trained according to a preset learning rate.
[0056] Step S145, updating the model parameters of the preset model to be trained according to the change amplitude of the model parameters to obtain an updated preset model to be trained.
[0057] Step S146, inputting the training feature vector into the updated preset model to be trained to obtain an updated predicted feature vector until an age range analysis prediction model is obtained.
[0058] In this embodiment, by obtaining a plurality of first training samples, each first training sample including a training feature vector and a corresponding target feature vector, the preset model to be trained is trained to obtain an age range analysis prediction model.
[0059] In one embodiment, after the first loss function satisfies the first preset training stop condition, as Figure 3 shown, the above analysis method further includes:
[0060] Step S147, obtaining the output training feature vector.
[0061] Step S148: Input the output training feature vectors into a preset application classification model to obtain predicted application category information.
[0062] In this embodiment, the predicted application category information is obtained by further adding application category labels.
[0063] Such as Figure 4 shown, in one embodiment, before step S148, it further includes:
[0064] Step S149: Obtain a plurality of second training samples, each second training sample including a plurality of output training feature vectors and corresponding application category labels.
[0065] Step S150: Input the second training samples into an initial preset application classification model to obtain predicted application categories.
[0066] Step S151: Train the initial preset application classification model according to the application category labels, predicted application categories, and a preset classification loss function until the convergence degree of the preset classification loss function meets a preset threshold to obtain a preset application classification model.
[0067] In one embodiment, the preset classification loss function adopts a softmax cross-entropy loss function.
[0068] In one embodiment, the machine learning algorithm adopts a deep learning algorithm.
[0069] In one embodiment, the machine learning algorithm adopts a decision tree algorithm.
[0070] In addition, as Figure 5 shown, there is also provided an analysis device 200 for age range, including:
[0071] A program information acquisition unit 210, configured to acquire information of applications installed in a target device;
[0072] A metadata acquisition unit 220, configured to acquire metadata corresponding to each application information, where the metadata includes an interaction mode, icon design, usage frequency, usage duration, application size, and update frequency of the application;
[0073] A feature vector extraction unit 230, configured to respectively perform feature extraction on the metadata corresponding to the information of the installed applications to obtain corresponding training feature vectors;
[0074] A model generation unit 240, configured to use a machine learning algorithm to train the training feature vectors to obtain an age range analysis prediction model.
[0075] In addition, in an embodiment of the present application, there is also provided a terminal device, and the internal structure of the terminal device may be as Figure 6As shown. The terminal device includes a processor, a memory, a communication interface, and a database connected via a system bus. Among them, the processor is used to provide computing and control capabilities. The memory of the terminal device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the terminal device is used to store data called by the computer program. The communication interface of the terminal device is used to communicate with external terminals for data. The input device of the terminal device is used to receive signals input by external devices. When the computer program is executed by the processor, it implements an analysis method as in the above embodiments.
[0076] Those skilled in the art can understand that Figure 6 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the terminal device to which the solution of the present application is applied.
[0077] In addition, the present application also proposes a readable storage medium, the readable storage medium includes a computer program, and when the computer program is executed by a processor, it implements the steps of the analysis method as described in the above embodiments. It can be understood that the readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.
[0078] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to the memory, storage, database, or other media provided in the present application and used in the embodiments can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0079] It should be noted that in this text, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article or method comprising a series of elements not only includes those elements but also other elements not expressly listed, or further includes elements inherent to such process, apparatus, article or method. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, apparatus, article or method comprising such element.
[0080] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.
Claims
1. A method for analyzing age range, characterized in that: include: Get the information of installed applications on the target device; Obtaining metadata corresponding to each of the application information, the metadata including the application's interaction mode, icon design, usage frequency, usage duration, application size, and update frequency; Extracting features from metadata corresponding to the installed application information to obtain corresponding training feature vectors; The training feature vector is trained using a machine learning algorithm to obtain an age range analysis prediction model.
2. The analysis method according to claim 1, characterized in that The step of using a machine learning algorithm to train the feature vector set to obtain an age range analysis prediction model includes: Acquire a plurality of first training samples, each of which includes a training feature vector and a corresponding target feature vector; Inputting the training feature vector into a preset model to be trained to obtain a prediction feature vector; Calculating a corresponding loss function according to the predicted feature vector and the target feature vector; When the first loss function does not satisfy a first preset training stop condition, determining a change range of a model parameter of the preset model to be trained according to a preset learning rate; Updating the model parameters of the preset model to be trained according to the variation range of the model parameters to obtain an updated preset model to be trained; The training feature vector is input into the updated preset model to be trained to obtain an updated prediction feature vector, until an age range analysis prediction model is obtained.
3. The analysis method according to claim 2, characterized in that After the first loss function satisfies the first preset training stop condition, the analysis method further includes: Get the output training feature vector; The output training feature vector is input into a preset application classification model to obtain predicted application category information.
4. The analysis method according to claim 3, characterized in that Before the step of inputting the output training feature vector into a preset application classification model to obtain predicted application category information, the step further includes: Acquire a plurality of second training samples, each of which includes a plurality of output training feature vectors and corresponding application category labels; Inputting the second training sample into an initial preset application classification model to obtain a predicted application category; The initial preset application classification model is trained according to the application category label, the predicted application category and the preset classification loss function until the convergence degree of the preset classification loss function meets the preset threshold, thereby obtaining the preset application classification model.
5. The analysis method according to claim 4, characterized in that The preset classification loss function adopts the softmax cross entropy loss function.
6. The analysis method according to claim 2, characterized in that The machine learning algorithm adopts a deep learning algorithm.
7. The analysis method according to claim 2, characterized in that The machine learning algorithm adopts a decision tree algorithm.
8. An age range analysis device, characterized in that include: A program information acquisition unit, used to acquire information about application programs installed on the target device; A metadata acquisition unit, used to acquire metadata corresponding to each of the application information, wherein the metadata includes an application interaction mode, icon design, usage frequency, usage duration, application size, and update frequency; A feature vector extraction unit, used to extract features from metadata corresponding to the installed application information to obtain corresponding training feature vectors; A model generation unit is used to train the training feature vector using a machine learning algorithm to obtain an age range analysis prediction model.
9. A terminal device, characterized in that: The terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the analysis method according to any one of claims 1 to 7 when executed by the processor.
10. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the steps of the analysis method according to any one of claims 1 to 7.