A software uninstallation method, system, device and medium

Abstract

A software uninstallation method, system, device and medium provided by the present invention relate to the technical field of software uninstallation. The method includes obtaining multiple installed software information in a user device, time series data of usage records of each installed software, and an expected hard disk cleaning size input by the user; generating multiple software uninstallation plans and the similarity between different software uninstallation plans using a variational autoencoder based on the multiple installed software information in the user device, the time series data of usage records of each installed software, and the expected hard disk cleaning size input by the user; determining a target uninstallation plan based on the multiple software uninstallation plans and the similarity between different software uninstallation plans; and performing software uninstallation based on the target uninstallation plan. This method can improve the uninstallation efficiency of device software.

Description

Technical Field

[0001] The present invention relates to the technical field of software uninstallation, and particularly relates to a software uninstallation method, system, device and medium. Background Art

[0002] With the development of computer technology and the popularization of personal digital devices, users usually install a large number of software on their devices. Over time, these software may occupy a large amount of storage space, and due to frequent updates, they may cause the system to run slowly. Therefore, it is very important to regularly uninstall software and clean the hard disk in order to free up storage space and improve the performance of the system.

[0003] Traditional software uninstallation methods often rely on direct selection by users or make uninstallation decisions through simple rules (such as unused software). However, such software uninstallation methods often require users to waste a lot of time checking and choosing the software to be uninstalled, which is time-consuming and laborious.

[0004] Therefore, how to improve the uninstallation efficiency of device software is an urgent problem to be solved currently. Summary of the Invention

[0005] The main technical problem to be solved by the present invention is how to improve the uninstallation efficiency of device software, which is an urgent problem to be solved currently.

[0006] According to a first aspect, the present invention provides a software uninstallation method, including: obtaining multiple installed software information in a user device, time series data of the usage record of each installed software, and an expected hard disk cleaning size input by the user; generating multiple software uninstallation plans and the similarity between different software uninstallation plans by using a variational autoencoder based on the multiple installed software information in the user device, the time series data of the usage record of each installed software, and the expected hard disk cleaning size input by the user; determining a target uninstallation plan based on the multiple software uninstallation plans and the similarity between different software uninstallation plans; and performing software uninstallation based on the target uninstallation plan.

[0007] In a possible implementation, determining the target uninstallation plan based on the multiple software uninstallation plans and the similarity between different software uninstallation plans includes: determining the total hard disk cleaning amount, system function loss degree, and user experience loss degree of each software uninstallation plan using an evaluation model based on the multiple software uninstallation plans, the multiple installed software information in the user device, and the time series data of each installed software usage record; constructing a software uninstallation graph structure, where the software uninstallation graph structure includes multiple nodes and multiple edges between the nodes. Each node represents a software uninstallation plan, and the node features of each node include the total hard disk cleaning amount, system function loss degree, and user experience loss degree of each software uninstallation plan. The edge between two nodes represents the similarity between two software uninstallation plans; determining the target uninstallation plan by processing the software uninstallation graph structure based on a graph neural network model.

[0008] In a possible implementation, the input of the variational autoencoder is the multiple installed software information in the user device, the time series data of each installed software usage record, and the expected hard disk cleaning size input by the user. The output of the variational autoencoder is multiple software uninstallation plans and the similarity between different software uninstallation plans.

[0009] In a possible implementation, the evaluation model is a gated recurrent unit. The input of the evaluation model is the multiple software uninstallation plans, the multiple installed software information in the user device, and the time series data of each installed software usage record. The output of the evaluation model is the total hard disk cleaning amount, system function loss degree, and user experience loss degree of each software uninstallation plan.

[0010] According to a second aspect, the present invention provides a software uninstallation system, including:

[0011] An acquisition module, configured to acquire the multiple installed software information in the user device, the time series data of each installed software usage record, and the expected hard disk cleaning size input by the user;

[0012] A variational autoencoder module, configured to generate multiple software uninstallation plans and the similarity between different software uninstallation plans using a variational autoencoder based on the multiple installed software information in the user device, the time series data of each installed software usage record, and the expected hard disk cleaning size input by the user;

[0013] A target uninstallation plan determination module, configured to determine the target uninstallation plan based on the multiple software uninstallation plans and the similarity between different software uninstallation plans;

[0014] An uninstallation module, configured to perform software uninstallation based on the target uninstallation plan.

[0015] In a possible implementation, the target offloading scheme determination module is further configured to:

[0016] Use an evaluation model based on the multiple software offloading schemes, the multiple installed software information in the user equipment, and the time series data of each installed software usage record to determine the total hard disk cleaning amount, system function loss degree, and user experience loss degree of each software offloading scheme;

[0017] Construct a software offloading graph structure, where the software offloading graph structure includes multiple nodes and multiple edges between the nodes. Each node represents a software offloading scheme, and the node features of each node include the total hard disk cleaning amount, system function loss degree, and user experience loss degree of each software offloading scheme. The edge between two nodes represents the similarity between the two software offloading schemes;

[0018] Process the software offloading graph structure based on a graph neural network model to determine the target offloading scheme.

[0019] In a possible implementation, the input of the variational autoencoder is the multiple installed software information in the user equipment, the time series data of each installed software usage record, and the expected hard disk cleaning size input by the user. The output of the variational autoencoder is multiple software offloading schemes and the similarity between different software offloading schemes.

[0020] In a possible implementation, the evaluation model is a gated recurrent unit. The input of the evaluation model is the multiple software offloading schemes, the multiple installed software information in the user equipment, and the time series data of each installed software usage record. The output of the evaluation model is the total hard disk cleaning amount, system function loss degree, and user experience loss degree of each software offloading scheme.

[0021] According to a third aspect, an embodiment of the present invention provides an electronic device, including: a processor; a memory; and a computer program; wherein, the computer program is stored in the memory and configured to be executed by the processor to implement the method as described above. The method includes: obtaining the multiple installed software information in the user equipment, the time series data of each installed software usage record, and the expected hard disk cleaning size input by the user; using a variational autoencoder to generate multiple software offloading schemes and the similarity between different software offloading schemes based on the multiple installed software information in the user equipment, the time series data of each installed software usage record, and the expected hard disk cleaning size input by the user; determining a target offloading scheme based on the multiple software offloading schemes and the similarity between different software offloading schemes; and performing software offloading based on the target offloading scheme.

[0022] According to a fourth aspect, the present embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the foregoing provided software uninstallation method is implemented. The method includes: obtaining multiple installed software information in a user device, time series data of usage records of each installed software, and an expected hard disk cleaning size input by a user; generating multiple software uninstallation plans and similarities between different software uninstallation plans using a variational autoencoder based on the multiple installed software information in the user device, the time series data of usage records of each installed software, and the expected hard disk cleaning size input by the user; determining a target uninstallation plan based on the multiple software uninstallation plans and the similarities between different software uninstallation plans; and performing software uninstallation based on the target uninstallation plan.

[0023] A software uninstallation method and system provided by the present invention includes obtaining multiple installed software information in a user device, time series data of usage records of each installed software, and an expected hard disk cleaning size input by a user; generating multiple software uninstallation plans and similarities between different software uninstallation plans using a variational autoencoder based on the multiple installed software information in the user device, the time series data of usage records of each installed software, and the expected hard disk cleaning size input by the user; determining a target uninstallation plan based on the multiple software uninstallation plans and the similarities between different software uninstallation plans; and performing software uninstallation based on the target uninstallation plan. This method can improve the uninstallation efficiency of device software. Description of the Drawings

[0024] Figure 1 It is a schematic diagram of an application scenario of a software uninstallation method provided by an embodiment of the present invention;

[0025] Figure 2 It is a schematic flowchart of a software uninstallation method provided by an embodiment of the present invention;

[0026] Figure 3 It is a schematic flowchart of determining a target uninstallation plan provided by an embodiment of the present invention;

[0027] Figure 4 It is a schematic diagram of a software uninstallation system provided by an embodiment of the present invention;

[0028] Figure 5 It is a schematic diagram of an electronic device provided by an embodiment of the present invention;

[0029] Figure 6 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Detailed Embodiments

[0030] The present invention will be further described in detail below in conjunction with the specific embodiments and the accompanying drawings. Similar elements in different embodiments are denoted by related similar element numbers. In the following embodiments, many detailed descriptions are provided to enable a better understanding of the present invention. However, those skilled in the art can easily recognize that some of the features can be omitted in different situations, or can be replaced by other elements, materials, or methods. In some cases, some operations related to the present invention are not shown or described in the specification, which is to avoid the core part of the present invention being overwhelmed by excessive descriptions. For those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations based on the descriptions in the specification and the general technical knowledge in the art.

[0031] Figure 1 FIG. is a schematic diagram of an application scenario of a software uninstallation method provided by an embodiment of the present invention. Figure 1 The application scenario of the software uninstallation method in FIG. may include a server 11, a network 12, a terminal 13, and a storage device 14.

[0032] In some embodiments, the server 11 may be a single server or a server group. The server 11 may access information and / or data stored in the terminal 13 or the storage device 14 through the network 12. In some embodiments, the server 11 may be used to execute Figure 2 the software uninstallation method shown in FIG.

[0033] The network 12 can facilitate the exchange of information and / or data. In some embodiments, the network 12 may be any form of wired or wireless network, or any combination thereof.

[0034] The terminal 13 may refer to one or more terminal devices used by a user. In some embodiments, the terminal 13 may include one or more combinations of mobile devices, tablet computers, laptop computers, etc. For example, the terminal may include information about multiple installed software in the user equipment.

[0035] The storage device 14 can store data and / or instructions. For example, the storage device 14 can store data instructions of the software uninstallation method.

[0036] In an embodiment of the present invention, there is provided a software uninstallation method as shown in Figure 2 FIG., and the software uninstallation method includes steps S1 to S4:

[0037] Step S1, obtain multiple installed software information in the user equipment, time series data of the usage record of each installed software, and the expected hard disk cleaning size input by the user.

[0038] Installed software information refers to the relevant information of all installed software stored on the user's device.

[0039] Installed software information includes but is not limited to software name, version number, installation path, file size, installation date, the most recent startup date, etc. For example, for Software A: Name = "Microsoft Office", Version = "2019", File Size = "1.5 GB", Installation Date = "2023-01-15", the most recent startup date = "2024-07-27"

[0040] The time series data of each installed software usage record records the detailed history of the user's use of each software, including the usage time point, usage duration, etc. For example, the time series data of Software A usage records can be: 2024-07-27 (usage duration 2 hours), 2024-07-25 (usage duration 1 hour), 2024-07-20 (usage duration 30 minutes).

[0041] The specific amount of hard disk space that the user hopes to free up by uninstalling software. For example, the amount of hard disk space that the user hopes to free up is 5 GB. The expected hard disk cleaning size input by the user is helpful for understanding the user's specific needs, so that the system can generate an uninstallation plan that meets the user's expectations and ensure that the post-uninstallation effect meets the user's hard disk space requirements.

[0042] Step S2, based on the multiple installed software information in the user device, the time series data of each installed software usage record, and the expected hard disk cleaning size input by the user, use a variational autoencoder to generate multiple software uninstallation plans and the similarity between different software uninstallation plans.

[0043] A software uninstallation plan is a set of software uninstallation suggestions generated based on the software information and usage records on the user device, combined with the amount of hard disk space that the user expects to free up. For example, Uninstallation Plan A may include uninstalling Software X and Y to free up approximately 3 GB of space; Uninstallation Plan B may include uninstalling Software Z and W to free up approximately 2.5 GB of space.

[0044] The similarity between software uninstallation plans is an index to measure the similarity degree between two or more uninstallation plans. For example, if both Uninstallation Plan A and B include Software X, then these two plans will get a higher score in terms of similarity.

[0045] The Variational Autoencoder (VAE) is a generative model that can learn the latent representation of data and generate new samples from it. The input of the variational autoencoder is the information of multiple installed software in the user device, the time series data of the usage record of each installed software, and the expected hard disk cleaning size input by the user. The output of the variational autoencoder is multiple software uninstallation plans and the similarity between different software uninstallation plans. The input layer receives the above features as input. The encoder network maps the input to the latent space. The decoder network reconstructs the samples in the latent space into suggestions for software uninstallation plans.

[0046] The latent space learned by the variational autoencoder can capture the complex structure of software usage patterns, including the relationships between software and their usage frequencies and durations.

[0047] Since the variational autoencoder is trained based on the software information and usage records on the user device, the generated uninstallation plans will be more in line with the user's actual usage habits.

[0048] For example, if the user rarely uses certain software, the variational autoencoder will give these software lower weights in the latent space, making them more likely to appear in the uninstallation plan.

[0049] The expected hard disk cleaning size input by the user can be used as a constraint condition to adjust the sampling strategy in the latent space to ensure that the generated plan can approach this target value.

[0050] Step S3, determine the target uninstallation plan based on the multiple software uninstallation plans and the similarity between different software uninstallation plans.

[0051] In some embodiments, Figure 3 FIG. is a schematic flow chart of a method for determining a target uninstallation plan provided by an embodiment of the present invention. The determination of the target uninstallation plan includes steps S21 to S23:

[0052] Step S21, use an evaluation model to determine the total hard disk cleaning amount, system function loss degree, and user experience loss degree of each software uninstallation plan based on the multiple software uninstallation plans, the information of multiple installed software in the user device, and the time series data of the usage record of each installed software.

[0053] The evaluation model is a gated recurrent unit. The input of the evaluation model is the multiple software uninstallation plans, the information of multiple installed software in the user device, and the time series data of the usage record of each installed software. The output of the evaluation model is the total hard disk cleaning amount, system function loss degree, and user experience loss degree of each software uninstallation plan.

[0054] The Gated Recurrent Unit (GRU) is used to process sequential data and temporal information. The gated recurrent unit consists of three components: a memory unit, an update gate, and a reset gate.

[0055] The total hard disk cleaning amount of each software uninstallation plan refers to the total amount of hard disk space that can be freed on the user device after executing a certain software uninstallation plan. For example, if a plan recommends uninstalling three software programs and the total freed space is 5GB, then the total hard disk cleaning amount of this plan is 5GB.

[0056] The system function loss degree of each software uninstallation plan represents the degree of overall function loss on the system. For example, if a plan recommends uninstalling all instant messaging software, then the system lacks the instant messaging function, and the system function loss degree is relatively large. Conversely, if one of the software programs with duplicate functions is uninstalled, the system function loss degree is relatively small.

[0057] The user experience loss degree of each software uninstallation plan is an indicator that measures the impact of the software uninstallation plan on the user's daily usage experience. This may involve factors such as the frequency of software use, the user's dependence on the software, and the availability of software alternatives. For example, if the uninstalled software is used by the user every day, the user experience loss degree will be high; if it is a rarely used software, the loss degree will be low.

[0058] In some embodiments, the evaluation model includes a plan analysis layer and a user experience loss determination layer. Both the plan analysis layer and the user experience loss determination layer include a gated recurrent unit structure. The input of the plan analysis layer is the multiple software uninstallation plans and the multiple installed software information in the user device. The output of the plan analysis layer is the total hard disk cleaning amount and the system function loss degree of each software uninstallation plan. The input of the user experience loss determination layer is the total hard disk cleaning amount, the system function loss degree of each software uninstallation plan, and the time series data of each installed software usage record. The output of the user experience loss determination layer is the user experience loss degree of each software uninstallation plan. The hierarchical design enables each part of the model to focus on processing specific types of information. For example, the plan analysis layer focuses on evaluating the impact of the uninstallation plan on the system, while the user experience loss determination layer focuses on evaluating the potential loss of the user experience. This clearly divided design improves the interpretability of the model, making the results easier to understand and analyze. The step-by-step processing can avoid simultaneously processing all complex inputs in a single model, thereby reducing the computational burden. For example, the plan analysis layer first calculates the hard disk cleaning degree and the system function loss degree, and then the user experience loss determination layer further processes based on these results, avoiding the complexity and resource consumption of processing all inputs at once.

[0059] Step S22, construct a software uninstallation graph structure. The software uninstallation graph structure includes multiple nodes and multiple edges between the nodes. Each node represents a software uninstallation plan, and the node features of each node include the total amount of hard disk cleaning, the loss degree of system functions, and the loss degree of user experience for each software uninstallation plan. The edge between two nodes represents the similarity between two software uninstallation plans.

[0060] The software uninstallation graph structure is a graphical data structure composed of nodes and edges, used to represent different software uninstallation plans and their mutual relationships. In this graph, each node represents a specific software uninstallation plan, and the features of the node include the total amount of hard disk cleaning, the loss degree of system functions, and the loss degree of user experience of this plan.

[0061] Each node corresponds to a software uninstallation plan. For example, Plan A may involve uninstalling Software X and Y, with an expected 1GB of space freed, a medium loss degree of functions, and a low loss degree of user experience. The features of the node are these quantitative indicators.

[0062] The edge connects two nodes, representing the similarity between two software uninstallation plans. The calculation of similarity is based on the features of the plans, such as the similarity of the total amount of hard disk cleaning, the loss degree of system functions, and the loss degree of user experience.

[0063] Step S23, process the software uninstallation graph structure based on the graph neural network model to determine the target uninstallation plan.

[0064] The graph neural network model includes a graph neural network (Graph Neural Network, GNN) and a fully connected layer. The graph neural network is a neural network that directly acts on graph-structured data. The input of the graph neural network model is the software uninstallation graph structure, and the output of the graph neural network model is the target uninstallation plan.

[0065] The graph neural network model can capture and utilize the complex relationships in the software uninstallation graph structure. By learning the node features and the weights of the edges, the model can identify the plan with the lowest loss degree of system functions and user experience while meeting user requirements (such as the total amount of hard disk cleaning). This enables the model to screen out the optimal uninstallation plan from numerous possible plans, ensuring that sufficient hard disk space is freed while minimizing the negative impact on system functions and user experience.

[0066] By constructing a graph structure, three key factors, namely the total amount of hard disk cleaning, the loss degree of system functions, and the loss degree of user experience, can be considered simultaneously, ensuring that the uninstallation plan can not only effectively release hard disk space but also minimize the adverse effects on system functions and user experience. In the graph structure, nodes represent software uninstallation plans, and their characteristics reflect the attributes of the plans; edges represent the similarity between plans, which helps the model identify which plans are similar in function or effect. This structure facilitates the algorithm to capture the internal connections between plans, thereby making more reasonable decisions.

[0067] Step S4, perform software uninstallation based on the target uninstallation plan.

[0068] When the target uninstallation plan is determined, perform software uninstallation based on the target uninstallation plan.

[0069] Based on the same inventive concept, Figure 4 FIG. is a schematic diagram of a software uninstallation system provided by an embodiment of the present invention. The software uninstallation system includes:

[0070] An acquisition module 41, configured to acquire information of multiple installed software in a user device, time series data of usage records of each installed software, and an expected hard disk cleaning size input by the user;

[0071] A variational autoencoder module 42, configured to generate multiple software uninstallation plans and the similarity between different software uninstallation plans using a variational autoencoder based on the information of multiple installed software in the user device, the time series data of usage records of each installed software, and the expected hard disk cleaning size input by the user;

[0072] A target uninstallation plan determination module 43, configured to determine a target uninstallation plan based on the multiple software uninstallation plans and the similarity between different software uninstallation plans;

[0073] An uninstallation module 44, configured to perform software uninstallation based on the target uninstallation plan.

[0074] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, as Figure 5 shown, including:

[0075] Including: a processor 51; a memory 52; and a computer program; wherein, the computer program is stored in the memory 52 and configured to be executed by the processor 51 to implement the software uninstallation method provided as described above. The method includes: obtaining multiple installation software information in the user device, time series data of the usage records of each installation software, and the expected hard disk cleaning size input by the user; generating multiple software uninstallation plans and the similarity between different software uninstallation plans using a variational autoencoder based on the multiple installation software information in the user device, the time series data of the usage records of each installation software, and the expected hard disk cleaning size input by the user; determining a target uninstallation plan based on the multiple software uninstallation plans and the similarity between different software uninstallation plans; and performing software uninstallation based on the target uninstallation plan.

[0076] Based on the same inventive concept, this embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by the processor 51, it implements the software uninstallation method provided as described above. The method includes: obtaining multiple installation software information in the user device, time series data of the usage records of each installation software, and the expected hard disk cleaning size input by the user; generating multiple software uninstallation plans and the similarity between different software uninstallation plans using a variational autoencoder based on the multiple installation software information in the user device, the time series data of the usage records of each installation software, and the expected hard disk cleaning size input by the user; determining a target uninstallation plan based on the multiple software uninstallation plans and the similarity between different software uninstallation plans; and performing software uninstallation based on the target uninstallation plan.

[0077] The software uninstallation method provided by the embodiments of this application can be applied to electronic devices such as terminal devices (such as mobile phones), tablet computers, laptop computers, ultra-mobile personal computers (UMPCs), handheld computers, netbooks, personal digital assistants (PDAs), wearable devices (such as smart watches, smart glasses, or smart helmets, etc.), augmented reality (AR) / virtual reality (VR) devices, smart home devices, in-vehicle computers, etc. The embodiments of this application do not impose any restrictions on this.

[0078] Taking the mobile phone 100 as an example of the above-mentioned electronic device, Figure 6 shows a schematic structural diagram of the mobile phone 100.

[0079] As Figure 6As shown in the figure, the mobile phone 100 may include a processing module 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0080] The processing module 110 may include one or more processing units. For example, the processing module 110 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Among them, different processing units may be independent devices or integrated in one or more processors.

[0081] The processing module 110 may be used to: obtain information of multiple installed software in the user device, time series data of the usage record of each installed software, and the expected hard disk cleaning size input by the user; generate multiple software uninstallation plans and the similarity between different software uninstallation plans using a variational autoencoder based on the information of multiple installed software in the user device, the time series data of the usage record of each installed software, and the expected hard disk cleaning size input by the user; determine a target uninstallation plan based on the multiple software uninstallation plans and the similarity between different software uninstallation plans; and perform software uninstallation based on the target uninstallation plan.

[0082] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are proposed in this specification, so such modifications, improvements, and corrections still fall within the spirit and scope of the exemplary embodiments of this specification.

[0083] In the meantime, this specification uses specific terms to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that the "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0084] In addition, unless clearly stated in the claims, the order of the processing elements and sequences, the use of numerical letters, or the use of other names described in this specification are not used to limit the order of the processes and methods in this specification. Although some currently useful embodiments of the invention are discussed through various examples in the above disclosure, it should be understood that such details only serve the purpose of illustration. The appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through software solutions, such as installing the described system on existing servers or mobile devices.

[0085] Similarly, it should be noted that, in order to simplify the expression of the disclosure in this specification and thus help the understanding of one or more embodiments of the invention, in the previous description of the embodiments of this specification, sometimes multiple features are merged into one embodiment, drawing, or description thereof. However, this method of disclosure does not mean that the features required by the subject matter of this specification are more than those mentioned in the claims. In fact, the features of the embodiments are fewer than all the features of the individual embodiments disclosed above.

[0086] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification can be considered to be in accordance with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments clearly introduced and described in this specification.

Claims

1. A software uninstallation method, characterized in that: include: Obtain information about multiple installed software in the user's device, time series data of each installed software usage record, and the expected hard disk cleanup size entered by the user; Based on the multiple pieces of installed software information in the user device, the time series data of each installed software usage record, and the expected hard disk cleaning size input by the user, a variational autoencoder is used to generate multiple software uninstallation schemes and similarities between different software uninstallation schemes. The input of the variational autoencoder is the multiple pieces of installed software information in the user device, the time series data of each installed software usage record, and the expected hard disk cleaning size input by the user. The output of the variational autoencoder is the similarities between multiple software uninstallation schemes and different software uninstallation schemes. The encoder network maps the input to a latent space, and the decoder network reconstructs samples in the latent space into suggestions for software uninstallation schemes. Determining a target uninstallation solution based on the similarities between the multiple software uninstallation solutions and the different software uninstallation solutions, wherein determining the target uninstallation solution based on the similarities between the multiple software uninstallation solutions and the different software uninstallation solutions comprises: Determine the total amount of hard disk cleanup, system function loss, and user experience loss of each software uninstallation solution using an evaluation model based on the multiple software uninstallation solutions, the multiple installed software information in the user device, and the time series data of each installed software usage record; Constructing a software uninstallation graph structure, wherein the software uninstallation graph structure includes a plurality of nodes and a plurality of edges between the plurality of nodes, wherein each node represents a software uninstallation solution, and the node characteristics of each node include the total amount of hard disk cleanup, the system function loss degree, and the user experience loss degree of each software uninstallation solution, and the edge between two nodes represents the similarity between the two software uninstallation solutions; Processing the software uninstallation graph structure based on a graph neural network model to determine a target uninstallation solution; The software is uninstalled based on the target uninstallation solution.

2. The software uninstallation method according to claim 1, characterized in that: The evaluation model is a gated loop unit, and the input of the evaluation model is the multiple software uninstallation solutions, the multiple installed software information in the user device, and the time series data of the usage record of each installed software. The output of the evaluation model is the total hard disk cleanup amount, system function loss degree, and user experience loss degree of each software uninstallation solution.

3. A software uninstallation system, characterized in that: include: An acquisition module, used to acquire information of multiple installed software in a user device, time series data of each installed software usage record, and an expected hard disk cleanup size input by a user; A variational autoencoder module, used to generate multiple software uninstallation schemes and similarities between different software uninstallation schemes using a variational autoencoder based on multiple pieces of installed software information in the user device, time series data of each installed software usage record, and the expected hard disk cleanup size input by the user, wherein the input of the variational autoencoder is multiple pieces of installed software information in the user device, time series data of each installed software usage record, and the expected hard disk cleanup size input by the user, and the output of the variational autoencoder is multiple software uninstallation schemes and similarities between different software uninstallation schemes, the encoder network maps the input to a latent space, and the decoder network reconstructs samples in the latent space into suggestions for software uninstallation schemes; a target uninstallation solution determination module, configured to determine a target uninstallation solution based on the similarities between the multiple software uninstallation solutions and the different software uninstallation solutions, and the target uninstallation solution determination module is further configured to: Determine the total amount of hard disk cleanup, system function loss, and user experience loss of each software uninstallation solution using an evaluation model based on the multiple software uninstallation solutions, the multiple installed software information in the user device, and the time series data of each installed software usage record; Constructing a software uninstallation graph structure, wherein the software uninstallation graph structure includes a plurality of nodes and a plurality of edges between the plurality of nodes, wherein each node represents a software uninstallation solution, and the node characteristics of each node include the total amount of hard disk cleanup, the system function loss degree, and the user experience loss degree of each software uninstallation solution, and the edge between two nodes represents the similarity between the two software uninstallation solutions; Processing the software uninstallation graph structure based on a graph neural network model to determine a target uninstallation solution; The uninstallation module is used to uninstall the software based on the target uninstallation solution.

4. The software uninstallation system according to claim 3, characterized in that: The evaluation model is a gated loop unit, and the input of the evaluation model is the multiple software uninstallation solutions, the multiple installed software information in the user device, and the time series data of the usage record of each installed software. The output of the evaluation model is the total hard disk cleanup amount, system function loss degree, and user experience loss degree of each software uninstallation solution.

5. An electronic device, characterized in that: include: processor; Memory; and a computer program; wherein the computer program is stored in the memory and is configured to be executed by the processor to implement the software uninstallation method according to any one of claims 1 to 2.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the software uninstallation method according to any one of claims 1 to 2 is implemented.

Images