A method and system for determining software information based on artificial intelligence

Abstract

A method and system for determining software information based on artificial intelligence. The present invention relates to the technical field of software information determination. The method includes obtaining a screen recording video of a user during a chat on a social software; determining user social software usage information based on the screen recording video of the user during a chat on the social software using a screen recording processing model; determining multiple similar standard users, the social software usage information of each similar standard user, and the chat setting interface that has been set for each similar standard user based on the user social software usage information; clustering the social software usage information of each similar standard user using the K-means clustering algorithm to obtain K clusters; determining the target chat setting interface of the user based on the user social software usage information and the K clusters; and setting the target chat setting interface of the user as the chat interface of the user. This method can determine a chat interface suitable for the user and improve the user experience.

Description

Technical Field

[0001] The present invention relates to the field of software information technology, and particularly relates to a method and system for determining software information based on artificial intelligence. Background Art

[0002] With the rapid development of information technology, social software has become an indispensable part of people's daily lives. Users use social software for text, voice, and video chats, sharing life details and information exchanges. However, due to significant differences in the usage habits, preferences, and needs of different users, how to provide a personalized and intelligent user experience has become an important research direction. Traditional social software usually provides limited customization options, such as basic settings like changing the background color and font size, making it difficult to meet the personalized needs of all users. In addition, for new users, they often feel confused when faced with complex and diverse setting options and don't know how to adjust the chat interface according to their preferences.

[0003] Therefore, how to determine a suitable chat interface for users and improve the user experience is an urgent problem to be solved currently. Summary of the Invention

[0004] The main technical problem to be solved by the present invention is how to determine a suitable chat interface for users and improve the user experience.

[0005] According to a first aspect, the present invention provides a method for determining software information based on artificial intelligence, including: obtaining a screen recording video of a user during a chat on social software; determining user social software usage information based on the screen recording video of the user during a chat on social software using a screen recording processing model; determining multiple similar standard users, the social software usage information of each similar standard user, and the chat setup interface that has been set for each similar standard user based on the usage information of the user's social software; clustering the social software usage information of each similar standard user using the K-means clustering algorithm to obtain K clusters; determining the target chat setup interface of the user based on the usage information of the user's social software and the K clusters; and setting the target chat setup interface of the user as the user's chat interface.

[0006] In a possible implementation, the determining the target chat setup interface of the user based on the usage information of the user's social software and the K clusters includes:

[0007] Taking the cluster closest to the usage information of the user's social software as the target cluster;

[0008] Obtaining the chat setup interface that has been set for each similar standard user in the target cluster;

[0009] Based on the user's social software usage information and the chat setup interfaces of each similar standard user in the target cluster, use a generative adversarial network to generate multiple simulated chat setup interfaces for the user and the matching degree of each simulated chat setup interface;

[0010] Display the multiple simulated chat setup interfaces of the user and the matching degree of each simulated chat setup interface on the user interface and obtain the target simulated chat setup interface selected by the user;

[0011] Use the target simulated setup interface selected by the user as the target chat setup interface.

[0012] In a possible implementation, the screen recording processing model is a gated recurrent unit. The input of the screen recording processing model is the screen recording video of the user during social software chatting, and the output of the screen recording processing model is the user's social software usage information.

[0013] In a possible implementation, the input of the generative adversarial network is the chat setup interfaces of each similar standard user in the target cluster, and the output of the generative adversarial network is multiple simulated chat setup interfaces for the user and the matching degree of each simulated chat setup interface.

[0014] According to a second aspect, the present invention provides an artificial intelligence-based software information determination system, including:

[0015] An acquisition module for acquiring the screen recording video of the user during social software chatting;

[0016] A usage information determination module for determining the user's social software usage information based on the screen recording video of the user during social software chatting using a screen recording processing model;

[0017] A similar standard user determination module for determining multiple similar standard users, the social software usage information of each similar standard user, and the chat setup interfaces of each similar standard user based on the user's social software usage information;

[0018] A clustering module for clustering the social software usage information of each similar standard user based on the K-means clustering algorithm to obtain K clusters;

[0019] A target chat setup interface determination module for determining the user's target chat setup interface based on the user's social software usage information and the K clusters;

[0020] A setup module for setting the user's target chat setup interface as the user's chat interface.

[0021] In a possible implementation, the target chat setting interface determination module is further configured to:

[0022] Take the cluster closest to the user's social software usage information as the target cluster;

[0023] Obtain the chat setting interfaces of each similar standard user in the target cluster;

[0024] Based on the user's social software usage information and the chat setting interfaces of each similar standard user in the target cluster, use a generative adversarial network to generate multiple simulated chat setting interfaces for the user and the matching degree of each simulated chat setting interface;

[0025] Display the multiple simulated chat setting interfaces of the user and the matching degree of each simulated chat setting interface on the user interface and obtain the target simulated chat setting interface selected by the user;

[0026] Take the target simulated setting interface selected by the user as the target chat setting interface.

[0027] In a possible implementation, the screen recording processing model is a gated recurrent unit. The input of the screen recording processing model is the screen recording video of the user during social software chatting, and the output of the screen recording processing model is the user's social software usage information.

[0028] In a possible implementation, the input of the generative adversarial network is the chat setting interface of each similar standard user in the target cluster, and the output of the generative adversarial network is multiple simulated chat setting interfaces for the user and the matching degree of each simulated chat setting interface.

[0029] 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 is configured to be executed by the processor to implement the method as described above. The method includes: obtaining a screen recording video of the user during social software chatting; using a screen recording processing model to determine the user's social software usage information based on the screen recording video of the user during social software chatting; determining multiple similar standard users, the social software usage information of each similar standard user, and the chat setting interface of each similar standard user based on the user's social software usage information; performing clustering on the social software usage information of each similar standard user based on the K-means clustering algorithm to obtain K clusters; determining the target chat setting interface of the user based on the user's social software usage information and the K clusters; setting the target chat setting interface of the user as the user's chat interface.

[0030] 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, it implements the aforementioned method for determining software information based on artificial intelligence. The method includes: obtaining a screen recording video of a user during a chat on a social software; determining user social software usage information based on the screen recording video of the user during a chat on the social software using a screen recording processing model; determining a plurality of similar standard users, the social software usage information of each similar standard user, and the chat settings interface that has been set for each similar standard user based on the user social software usage information; clustering the social software usage information of each similar standard user using the K-means clustering algorithm to obtain K clusters; determining the target chat settings interface of the user based on the user social software usage information and the K clusters; and setting the target chat settings interface of the user as the user's chat interface.

[0031] A method and system for determining software information based on artificial intelligence provided by the present invention. The method includes obtaining a screen recording video of a user during a chat on a social software; determining user social software usage information based on the screen recording video of the user during a chat on the social software using a screen recording processing model; determining a plurality of similar standard users, the social software usage information of each similar standard user, and the chat settings interface that has been set for each similar standard user based on the user social software usage information; clustering the social software usage information of each similar standard user using the K-means clustering algorithm to obtain K clusters; determining the target chat settings interface of the user based on the user social software usage information and the K clusters; and setting the target chat settings interface of the user as the user's chat interface. This method can determine a chat interface suitable for the user and improve the user experience. Description of the Drawings

[0032] Figure 1 It is a flowchart of a method for determining software information based on artificial intelligence provided by an embodiment of the present invention;

[0033] Figure 2 It is a flowchart of a method for determining the target chat settings interface of a user provided by an embodiment of the present invention;

[0034] Figure 3 It is a schematic diagram of a system for determining software information based on artificial intelligence provided by an embodiment of the present invention. Detailed Embodiments

[0035] 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, in order to avoid overwhelming the core part of the present invention with 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.

[0036] In an embodiment of the present invention, there is provided a method for determining software information based on artificial intelligence as shown in Figure 1 The method for determining software information based on artificial intelligence includes steps S1 to S6:

[0037] Step S1, obtaining a screen recording video of the user during a chat on a social software.

[0038] The screen recording video of the user during a chat on a social software is a video that records and collects the screen activities of the user during the chat process using the social software.

[0039] Step S2, determining the user's social software usage information based on the screen recording video of the user during a chat on the social software using a screen recording processing model.

[0040] The screen recording processing model is a gated recurrent unit. The input of the screen recording processing model is the screen recording video of the user during a chat on the social software, and the output of the screen recording processing model is the user's social software usage information. The gated recurrent unit is an implementation manner of artificial intelligence.

[0041] The gated recurrent unit (GRU) controls the flow of information by introducing a gating mechanism to solve the problem of long-term dependence.

[0042] The gated recurrent unit is used to process sequence data and temporal information. The gated recurrent unit includes three components: a memory unit, an update gate, and a reset gate. Through the gated recurrent unit model, the screen recording video of the user during a chat on the social software for consecutive time periods can be processed, and the relationships in the time series of the screen recording video of the user during a chat on the social software can be better captured, making the output features more accurate and comprehensive.

[0043] The user's social software usage information includes the operation frequency of the social software, interface setting preferences, interface interaction mode information, and content preference information.

[0044] Interface setting preferences include whether one prefers the dark mode, font size, message notification settings, etc.

[0045] Interface interaction mode information includes whether one prefers to communicate through text, voice, or video calls, and whether one often uses emojis or stickers, etc.

[0046] The operations of the user's social software form a time - series process, including actions such as clicks, swipes, and text input. The gated recurrent unit can capture the sequential relationships between these operations and their changes over time. When analyzing the user's behavior patterns, for example, the user may return to previous operation habits or preference settings after a period of time. The gated recurrent unit can remember and associate these behaviors over a long time span, thus understanding the user's preferences more accurately.

[0047] Step S3: Determine multiple similar standard users, the social software usage information of each similar standard user, and the configured chat interface of each similar standard user based on the usage information of the user's social software.

[0048] Similar standard users are other users with behavior characteristics or preferences similar to those of the target user.

[0049] The configured chat interface of each similar standard user refers to the chat interface style that has been configured by the similar standard user in their social software. The configured chat interface of each similar standard user includes all visual elements such as color theme, font size, button layout, etc.

[0050] In some embodiments, a deep neural network model can be used to process the usage information of the user's social software to determine multiple similar standard users, the social software usage information of each similar standard user, and the configured chat interface of each similar standard user.

[0051] The deep neural network model includes Deep Neural Networks (DNN). A deep neural network can include multiple processing layers, each processing layer consists of multiple neurons, and each neuron performs a matrix transformation on the data.

[0052] Step S4: Cluster the social software usage information of each similar standard user based on the K - means clustering algorithm to obtain K clusters.

[0053] The K-means clustering algorithm is an unsupervised learning algorithm. The K-means clustering algorithm is used to divide a data set into K clusters, such that the objects within the same cluster are similar to some extent, while the objects between different clusters are as different as possible. Each cluster is represented by its center point (centroid).

[0054] In the K-means clustering algorithm, a cluster refers to a set of data points divided according to a distance metric (such as Euclidean distance).

[0055] K is a pre-set parameter that determines how many different clusters one hopes to divide the data into. By performing clustering analysis on the social software usage information of similar standard users, user groups with common characteristics can be identified. This helps to deeply understand the user behavior patterns and lay a foundation for providing a personalized chat setting interface subsequently.

[0056] Step S5, determine the target chat setting interface of the user based on the user social software usage information and the K clusters.

[0057] In some embodiments, Figure 2 is a schematic flowchart of a process for determining the target chat setting interface of a user provided by an embodiment of the present invention. The determination of the target chat setting interface of the user includes steps S21 to S25:

[0058] Step S21, take the cluster closest to the user social software usage information as the target cluster.

[0059] From all the clusters obtained by the K-means clustering algorithm, select the cluster closest to the social software usage information of the target user as the target cluster. The distance can be the Euclidean distance.

[0060] Step S22, obtain the chat setting interfaces that have been set for each similar standard user in the target cluster.

[0061] When the target cluster is determined, then obtain the chat setting interfaces that have been set for each similar standard user in the target cluster.

[0062] Step S23, based on the user social software usage information and the chat setting interfaces that have been set for each similar standard user in the target cluster, use a generative adversarial network to generate multiple simulated chat setting interfaces of the user and the matching degree of each simulated chat setting interface.

[0063] The input of the generative adversarial network is the chat setting interfaces that have been set for each similar standard user in the target cluster, and the output of the generative adversarial network is multiple simulated chat setting interfaces of the user and the matching degree of each simulated chat setting interface.

[0064] The simulated chat setting interface is multiple new interface design schemes generated by a generative adversarial network according to the chat settings of users in the target cluster.

[0065] The matching degree of each simulated chat setting interface is a score of the degree of fit between each simulated chat setting interface and the preferences of the target user.

[0066] The generative adversarial network (GANs) consists of two parts: a generator and a discriminator. The generator attempts to generate realistic samples, while the discriminator tries to distinguish between real samples and generated samples. Through the adversarial training between the two, the generator can gradually learn to generate high-quality samples.

[0067] User social software usage information includes users' operation habits, preference settings, etc. For example, a certain user may be more inclined to use the voice message function and prefers a dark mode background.

[0068] The chat setting interfaces of each similar standard user in the target cluster are the chat interface styles that have been configured by other users who are similar to the target user's behavior pattern or preferences. The chat setting interfaces of each similar standard user in the target cluster include color themes, font sizes, button layouts, etc.

[0069] Providing these two types of information as input to the generative adversarial network can provide rich training materials for the model. By analyzing this data, the generative adversarial network can learn the common characteristics and personalized preferences in different user interface designs.

[0070] After receiving the above input, the generator will attempt to generate new chat interface design schemes based on the learned features. It does not simply copy existing interface designs but can create novel design schemes while ensuring that these new designs conform to the preferences of the target user and determining the matching degree of each simulated chat setting interface at the same time.

[0071] Step S24: Display the multiple simulated chat setting interfaces of the user and the matching degree of each simulated chat setting interface on the user interface and obtain the target simulated chat setting interface selected by the user.

[0072] For example, the system provides the user with three simulated chat setting interfaces: one with a light background and large fonts, with a matching degree of 80%; another with a dark background and a custom background image, with a matching degree of 90%; and another with a strong sense of technology, with a matching degree of 75%. These interfaces and their matching degrees will be displayed on the user interface for the user to choose.

[0073] Step S25: Use the target simulated setting interface selected by the user as the target chat setting interface.

[0074] The target simulation setting interface is the final solution selected by the user from multiple simulation chat setting interfaces, and this solution is considered to best meet the user's personal preferences.

[0075] Step S6: Set the user's target chat setting interface as the user's chat interface.

[0076] After determining the user's target chat setting interface, set the user's target chat setting interface as the user's chat interface.

[0077] Based on the same inventive concept, Figure 3 The following is a schematic diagram of a software information determination system based on artificial intelligence provided by an embodiment of the present invention. The software information determination system based on artificial intelligence includes:

[0078] An acquisition module 31, configured to acquire a screen recording video of the user during a chat on a social software;

[0079] A usage information determination module 32, configured to determine user social software usage information based on the screen recording video of the user during a chat on the social software using a screen recording processing model;

[0080] A similar standard user determination module 33, configured to determine multiple similar standard users, the social software usage information of each similar standard user, and the chat setting interface that has been set for each similar standard user based on the usage information of the user's social software;

[0081] A clustering module 34, configured to perform clustering on the social software usage information of each similar standard user based on the K-means clustering algorithm to obtain K clusters;

[0082] A target chat setting interface determination module 35, configured to determine the user's target chat setting interface based on the user's social software usage information and the K clusters;

[0083] A setting module 36, configured to set the user's target chat setting interface as the user's chat interface.

[0084] Similarly, it should be noted that, in order to simplify the presentation disclosed in this specification and thus help understand one or more embodiments of the invention, in the foregoing description of the embodiments of this specification, sometimes multiple features are merged into one embodiment, drawing, or description thereof. However, this disclosure method does not mean that the features required by the object of this specification are more than those mentioned in the claims. In fact, the features of the embodiment are less than all the features of the single embodiment disclosed above.

[0085] 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 may be regarded as consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly presented and described in this specification.

Claims

1. A method for determining software information based on artificial intelligence, characterized in that, Including: Obtain a screen recording video of the user during a chat on a social software; Based on the screen recording video of the user during a chat on the social software, use a screen recording processing model to determine the user's social software usage information. The screen recording processing model is a gated recurrent unit. The input of the screen recording processing model is the screen recording video of the user during a chat on the social software, and the output of the screen recording processing model is the user's social software usage information. The user's social software usage information includes the operation frequency of the social software, interface setting preference information, interface interaction mode information, and content preference information. The interface setting preference information includes whether to prefer the dark mode, font size, and message notification settings. The interface interaction mode information includes whether to prefer text communication, voice or video calls, and whether to often use emojis or stickers; Based on the usage information of the user's social software, determine multiple similar standard users, the social software usage information of each similar standard user, and the chat set interface of each similar standard user; Cluster the social software usage information of each similar standard user based on the K-means clustering algorithm to obtain K clusters; Based on the user's social software usage information and the K clusters, determine the target chat setting interface of the user. The determining the target chat setting interface of the user based on the user's social software usage information and the K clusters includes: Take the cluster closest to the user's social software usage information as the target cluster; Obtain the chat set interface of each similar standard user in the target cluster; Based on the user's social software usage information and the chat set interface of each similar standard user in the target cluster, use a generative adversarial network to generate multiple simulated chat setting interfaces of the user and the matching degree of each simulated chat setting interface. The simulated chat setting interface is multiple new interface design schemes generated by the generative adversarial network according to the chat settings of the users in the target cluster; Display the multiple simulated chat setting interfaces of the user and the matching degree of each simulated chat setting interface on the user interface and obtain the target simulated chat setting interface selected by the user; Take the target simulated setting interface selected by the user as the target chat setting interface; Set the target chat setting interface of the user as the user's chat interface.

2. The method for determining software information based on artificial intelligence according to claim 1, wherein The input of the generative adversarial network is the chat set interface of each similar standard user in the target cluster, and the output of the generative adversarial network is multiple simulated chat setting interfaces of the user and the matching degree of each simulated chat setting interface.

3. An artificial intelligence-based software information determination system, characterized in that, Including: An obtaining module, configured to obtain a screen recording video of the user during a chat on a social software; A usage information determination module, configured to determine user social software usage information based on a screen recording video during the user's chat in social software using a screen recording processing model, where the screen recording processing model is a gated recurrent unit, the input of the screen recording processing model is the screen recording video during the user's chat in social software, the output of the screen recording processing model is user social software usage information, and the user social software usage information includes the operation frequency of the social software, interface setting preference information, interface interaction mode information, and content preference information. The interface setting preference information includes whether to prefer the dark mode, font size, and message notification settings. The interface interaction mode information includes whether to prefer text communication, voice or video calls, and whether to often use emojis or stickers; A similar standard user determination module, configured to determine multiple similar standard users, the social software usage information of each similar standard user, and the chat set interface of each similar standard user based on the usage information of the user's social software; A clustering module, configured to cluster the social software usage information of each similar standard user based on the K-means clustering algorithm to obtain K clusters; A target chat set interface determination module, configured to determine the target chat set interface of the user based on the user's social software usage information and the K clusters. The target chat set interface determination module is further configured to: Use the cluster closest to the user's social software usage information as the target cluster; Obtain the chat set interfaces of each similar standard user in the target cluster; Based on the user's social software usage information and the chat set interfaces of each similar standard user in the target cluster, use a generative adversarial network to generate multiple simulated chat set interfaces of the user and the matching degree of each simulated chat set interface. The simulated chat set interface is multiple new interface design schemes generated by the generative adversarial network according to the chat settings of the users in the target cluster; Display the multiple simulated chat set interfaces of the user and the matching degree of each simulated chat set interface on the user interface and obtain the target simulated chat set interface selected by the user; Use the target simulated set interface selected by the user as the target chat set interface; A setting module, configured to set the target chat set interface of the user as the user's chat interface.

4. The software information determination system based on artificial intelligence according to claim 3, wherein, The input of the generative adversarial network is the chat set interface of each similar standard user in the target cluster, and the output of the generative adversarial network is multiple simulated chat set interfaces of the user and the matching degree of each simulated chat set interface.

5. An electronic device, characterized in that, It includes: A processor; A memory; And a computer program. Among them, the computer program is stored in the memory and is configured to be executed by the processor to implement the artificial intelligence-based software information determination 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 the processor, it implements the artificial intelligence-based software information determination method according to any one of claims 1 to 2.

Images