Software cockpit self-adaption method and device and medium
Patent Information
- Application Number
- CN202411402442.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-09
- Publication Date
- 2025-02-28
Smart Images
Figure CN119537683A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure at least relates to the field of software technology, and in particular to a software cockpit self-adaptation method, a software cockpit self-adaptation device, and a computer-readable storage medium. Background Art
[0002] The "Cockpit" in industrial software / commercial software refers to an operating interface that integrates enterprise or production line key performance indicators (KPIs, Key Performance Indicator), real-time data monitoring, alarm reminders, decision support and other functions.
[0003] Different users or the same user using the software at different times have different requirements for the use of each functional module (display content) in the software cockpit, so it is necessary to make personalized adaptive adjustments to the cockpit for users. There is currently no good solution for how to make such adjustments. Summary of the invention
[0004] The technical problem to be solved by the present disclosure is to provide a software cockpit self-adaptation method, a software cockpit self-adaptation device and a computer-readable storage medium in view of the above-mentioned deficiencies, so as to solve the problem of how to make the software cockpit adapt to the user's usage needs.
[0005] In a first aspect, the present disclosure provides a software cockpit self-adaptation method, the method
[0006] The law includes:
[0007] Acquire a solution feature vector of the software cockpit self-adaptation solution, where the solution feature vector represents the display layout of the software in the software cockpit self-adaptation solution, and the display layout includes a display interface, a display mode, a display level, a display position, and a display size of the display content;
[0008] Obtaining a user preference vector of the first user using the software, where the user preference vector is obtained based on usage data of each display content used by the first user in a historical process of using the software, where the usage data represents the usage operation, usage frequency, and usage duration of each display content by the first user;
[0009] A first software cockpit self-adaptation scheme having the highest similarity between a scheme feature vector and a user preference vector is obtained, and a software cockpit is displayed to a first user according to the first software cockpit self-adaptation scheme.
[0010] Furthermore, the solution feature vector of the software cockpit self-adaptation solution is obtained, specifically including:
[0011] Obtaining first display weights defined for each display interface, display mode, display level, display position, and display size;
[0012] Obtain the display layout of each display content in the software cockpit self-adaptation solution;
[0013] According to the first display weight and the display layout, obtaining a second display weight for each display content in the software cockpit self-adaptation solution;
[0014] The second display weights of all display contents in the software cockpit self-adaptation solution are combined to obtain a solution feature vector of the software cockpit self-adaptation solution.
[0015] Further, obtaining a user preference vector of the first user using the software specifically includes:
[0016] Obtaining first usage weights defined for each usage operation, usage frequency, and usage duration;
[0017] Obtaining usage data of each displayed content used by the first user during a certain historical period of time when the first user used the software;
[0018] According to the first usage weight and the usage data, obtaining a second usage weight of each display content used by the first user during the process of using the software in a certain historical period;
[0019] The second usage weights of all displayed contents used by the first user in a process of using the software in a certain historical period are combined to obtain a user preference vector of the first user using the software in the certain historical period.
[0020] Furthermore, the method further includes obtaining a certain historical period, specifically including:
[0021] Obtain a certain historical period according to the time period characteristics set by the first user; or,
[0022] A plurality of user preference vectors of the first user using the software in a plurality of historical time periods are obtained, and in response to a plurality of user preference vectors having the same plurality of display contents and similar corresponding second usage weights, the corresponding plurality of historical time periods are merged into one historical time period.
[0023] Furthermore, the method further includes obtaining a software cockpit self-adaptation solution, specifically including:
[0024] Obtain the software cockpit display solution developed by the developer as a software cockpit self-adaptation solution; and / or,
[0025] Obtaining a software cockpit display solution customized by a second user as a software cockpit self-adaptation solution; and / or,
[0026] Obtain all existing display contents of the software and randomly arrange and display them to obtain a software cockpit self-adaptation solution, or obtain corresponding display contents in the user preference vector and randomly arrange and display them to obtain a software cockpit self-adaptation solution.
[0027] Further, obtaining a first software cockpit self-adaptation solution with the highest similarity between the solution feature vector and the user preference vector specifically includes:
[0028] Based on the cosine similarity, Pearson correlation coefficient, and Jaccard similarity of the feature vectors, the similarity between the solution feature vector and the user preference vector is calculated, and the first software cockpit self-adaptive solution corresponding to the solution feature vector with the highest similarity is obtained; or,
[0029] Based on the matching of statistical information, a first software cockpit self-adaptation solution is obtained, which has the highest similarity between the solution feature vector and the user preference vector; or,
[0030] Based on the machine learning model, the first software cockpit self-adaptation solution is obtained, whose solution feature vector has the highest similarity with the user preference vector.
[0031] In a second aspect, the present disclosure provides a software cockpit self-adaptation device, the device comprising:
[0032] A solution module is used to obtain a solution feature vector of the software cockpit self-adaptation solution. The solution feature vector represents the display layout of the software in the software cockpit self-adaptation solution. The display layout includes a display interface, a display mode, a display level, a display position, and a display size of the display content.
[0033] A preference module, used to obtain a user preference vector of the first user using the software, where the user preference vector is obtained based on usage data of each display content used by the first user in the process of using the software historically, where the usage data represents the usage operation, usage frequency, and usage duration of each display content by the first user;
[0034] The adaptation module is connected to the solution module and the preference module, and is used to obtain the first software cockpit self-adaptation solution with the highest similarity between the solution feature vector and the user preference vector, and display the software cockpit to the first user according to the first software cockpit self-adaptation solution.
[0035] Furthermore, the solution module specifically includes:
[0036] A display weight definition unit, used to obtain first display weights defined for each display interface, display mode, display level, display position, and display size;
[0037] A display layout acquisition unit, used to acquire the display layout of each display content in the software cockpit self-adaptation solution;
[0038] A display weight matching unit, connected to the display weight definition unit and the display layout acquisition unit, for acquiring a second display weight for each display content in the software cockpit self-adaptation solution according to the first display weight and the display layout;
[0039] The scheme feature vector is connected to the display weight matching unit and is used to combine the second display weights of all display contents in the software cockpit self-adaptation scheme to obtain the scheme feature vector of the software cockpit self-adaptation scheme.
[0040] Furthermore, the preference module specifically includes:
[0041] A usage weight definition unit, used to obtain first usage weights defined for each usage operation, usage frequency, and usage duration;
[0042] A usage data acquisition unit, used to acquire usage data of each displayed content used by the first user during a certain historical period of time when the first user uses the software;
[0043] A usage weight matching unit, connected to the usage weight definition unit and the usage data acquisition unit, for acquiring a second usage weight of each display content used by the first user in a certain historical period of time during the use of the software according to the first usage weight and the usage data;
[0044] The user preference vector unit is connected to the usage weight matching unit and is used to combine the second usage weights of all displayed contents used by the first user in a certain historical period of time to obtain the user preference vector of the first user in using the software in a certain historical period of time.
[0045] In a third aspect, the present disclosure provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the software cockpit self-adaptation method or the software cockpit self-adaptation device as described above is implemented.
[0046] The present disclosure provides a software cockpit self-adaptation method, a software cockpit self-adaptation device and a computer-readable storage medium. The method obtains a solution feature vector of the software cockpit self-adaptation solution, obtains a user preference vector of a first user using the software, and uses a content recommendation algorithm to obtain a first software cockpit self-adaptation solution with the highest similarity between the solution feature vector and the user preference vector. Finally, the software cockpit is displayed to the first user based on the first software cockpit self-adaptation solution, so that the software cockpit effectively adapts to the user's usage needs. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] Figure 1 is a flow chart of a software cockpit self-adaptation method according to an embodiment of the present disclosure;
[0048] Figure 2 is a structural schematic diagram of a software cockpit self-adaptation device according to an embodiment of the present disclosure;
[0049] Figure 3 is a flow chart of another software cockpit self-adaptation method according to an embodiment of the present disclosure;
[0050] Figure 4 It is a system architecture diagram of a software cockpit self-adaptation device according to an embodiment of the present disclosure. DETAILED DESCRIPTION
[0051] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.
[0052] It should be understood that the specific embodiments and drawings described herein are only used to explain the present disclosure rather than to limit the present disclosure.
[0053] It can be understood that, in the absence of conflict, the various embodiments of the present disclosure and the various features in the embodiments can be combined with each other.
[0054] It can be understood that, for the convenience of description, the drawings of the present disclosure only show parts related to the present disclosure, while parts irrelevant to the present disclosure are not shown in the drawings.
[0055] It can be understood that each unit and module involved in the embodiments of the present disclosure may correspond to only one physical structure, or may be composed of multiple physical structures, or multiple units and modules may be integrated into one physical structure.
[0056] It will be understood that, in the absence of conflict, the functions and steps marked in the flowcharts and block diagrams of the present disclosure may occur in an order different from that marked in the drawings.
[0057] It is understood that the flowcharts and block diagrams of the present disclosure illustrate the possible architectures, functions, and operations of the systems, devices, equipment, and methods according to the various embodiments of the present disclosure. Each box in the flowchart or block diagram may represent a unit, module, program segment, or code, which contains executable instructions for implementing the specified functions. Moreover, each box or combination of boxes in the block diagram and flowchart may be implemented by a hardware-based system that implements the specified functions, or may be implemented by a combination of hardware and computer instructions.
[0058] It can be understood that the units and modules involved in the embodiments of the present disclosure can be implemented by software or hardware, for example, the units and modules can be located in a processor.
[0059] In order to facilitate understanding of the present disclosure, the main inventive concept of the present disclosure is first introduced.
[0060] The main inventive idea of the present disclosure is to provide a cockpit self-adaptation method based on a content recommendation system algorithm. The starting point of the present disclosure is to enable the display content of the cockpit of industrial platforms, Internet of Things platforms, BI (Business Intelligence) software, etc. to keep up with the continuous development of the business.
[0061] In industrial software, the cockpit is usually designed for senior managers in the fields of factory operations, production management, supply chain management, energy management, etc. It displays the core data of enterprise operations in a graphical and intuitive way, helping enterprise leaders to quickly understand the overall status and make efficient decisions. Specifically, the cockpit of industrial software may include the following features: data visualization, key indicator monitoring, abnormal warning, decision support, and user customization.
[0062] The adaptation of the cockpit generally refers to the user's requirements based on their own business characteristics, and the developer transforms the cockpit into a form suitable for the business based on the requirements so that users can quickly understand and make decisions. However, this adaptation generally goes through a complete process from requirement proposal to R&D, which takes some time and may not be able to effectively keep up with business changes. Alternatively, users can customize the cockpit, but for many users, they may not know what kind of cockpit they need.
[0063] Moreover, the content that the business focuses on will change at different stages, but the software cockpit often needs to be manually redeveloped or adapted (adaptation also needs to go through R&D discussions). In this case, the module content of the cockpit often lags behind the business.
[0064] The goal of the present disclosure is to achieve cockpit adaptability. "Adaptability" means that this cockpit-style interface can dynamically adjust the layout, content, and interaction methods according to factors such as the user's personalized needs, screen size, device type, data input, or scenario changes to achieve the best visualization effect and user experience.
[0065] Therefore, the present invention discloses a cockpit adaptive solution based on a content recommendation system algorithm. After collecting and storing data such as the software composition and the user's operating behavior, the data is imported into the content recommendation system algorithm, and then the business module that needs to be displayed is generated. On this basis, the display content of the cockpit will be adjusted. The imported content recommendation algorithm can fix a time frequency according to the business situation, such as calculating once a month, so as to achieve the purpose of rapid and automatic adjustment according to user habits and save time for customized research and development.
[0066] The present disclosure collects modules / contents frequently used by users and determines whether users prefer this module / content, such as the number of clicks on this module / content, collection behavior, and whether there is a write operation. Write operations are more important than read operations, and the presence of write operations can be considered that users attach more importance to this module / content.
[0067] The present disclosure solves the problem of how to provide business modules that need to be viewed in a timely manner in the cockpit of an industrial platform, an Internet of Things platform, and BI software. These modules may be a map (such as the map location of equipment points), a production output line graph, a pie chart of equipment type distribution, a link, or even just a floating alarm text message. There are various types of modules, and these contents are arranged on an entire interface.
[0068] The content-based recommendation system algorithm (Content-Based Filtering) adopted in this disclosure is a personalized recommendation technology. Its core principle is to use the user's past behavior and interests and the display content characteristics of the software interface to perform similarity matching, so as to recommend items that are similar to their preferences or have the same attribute characteristics to users. The specific algorithm process includes the following steps:
[0069] 1) Feature Extraction:
[0070] Perform content analysis on each recommended solution and extract key feature information. These features are relevant information of the display layout, which can be the display interface, display mode, display level, display position, display size, etc. of the display content, and various data that can reflect the display characteristics of the cockpit.
[0071] 2) User Preference Calculation (User Profile Construction):
[0072] Based on the user's historical behavior records, the user's personal interest model or preference profile is constructed. For each user, the system will assign corresponding weights or scores to each feature dimension to quantify the user's preference for different features.
[0073] 3) Similarity Computation:
[0074] Use a specific similarity measurement method (such as cosine similarity, Euclidean distance, Pearson correlation coefficient, etc.) to calculate the similarity between the user's personal profile and all candidate solutions. The commonly used cosine similarity calculation formula is as follows:
[0075]
[0076] 4) Recommendation Generation:
[0077] Based on the results of the similarity calculation above, find the solution that best matches the user's interests and has the highest similarity as the recommendation result. Generally speaking, the recommendation list will be sorted from high to low according to the similarity, and the most relevant content will be displayed to the user first.
[0078] Content-based recommendation systems focus on the personalized needs of individual users, so they can provide relatively accurate recommendations in some scenarios, especially for new users or sparse data. At the same time, the algorithm has a certain effect on alleviating the cold start problem.
[0079] Based on the above inventive concept, specific embodiments are provided below.
[0080] Embodiment 1:
[0081] like Figure 1 As shown, the present disclosure provides a software cockpit self-adaptation method, the method comprising:
[0082] S1. Obtaining a solution feature vector of a software cockpit self-adaptation solution, where the solution feature vector represents a display layout of the software in the software cockpit self-adaptation solution, where the display layout includes a display interface, a display mode, a display level, a display position, and a display size of the display content;
[0083] S2. Obtaining a user preference vector of the first user using the software, where the user preference vector is obtained based on usage data of each display content used by the first user in the process of historically using the software, where the usage data represents the usage operation, usage frequency, and usage duration of each display content by the first user;
[0084] S3. Obtain a first software cockpit self-adaptation scheme having the highest similarity between the scheme feature vector and the user preference vector, and display the software cockpit to the first user according to the first software cockpit self-adaptation scheme.
[0085] In this embodiment, the method obtains the solution feature vector of the software cockpit self-adaptation solution, obtains the user preference vector of the first user using the software, uses the content recommendation algorithm to obtain the first software cockpit self-adaptation solution with the highest similarity between the solution feature vector and the user preference vector, and finally displays the software cockpit to the first user according to the first software cockpit self-adaptation solution, so that the software cockpit effectively adapts to the user's usage needs. The method can be applied to Figure 2 In the device shown, the device comprises a solution module 1 for executing step S1, a preference module 2 for executing step S2 and an adaptation module 3 for executing step S3.
[0086] Specifically, this embodiment provides a cockpit adaptive solution based on the content recommendation system algorithm. After collecting and storing data such as the software composition and user operation behavior, it is imported into the content recommendation system algorithm, and then the arrangement and display mode of the business modules to be displayed are obtained. On this basis, the display content of the cockpit will be adjusted. Its overall logic is as follows: Figure 3 As shown, the system itself has a default homepage or cockpit interface, which is mainly composed of elements such as data indicator boards, line graphs, bar graphs, pie charts, and tables. After the user starts the software, the software first enters the default homepage / cockpit. In the cockpit, the user uses each module to collect various behavioral operations of the software users (multiple people under the same software under privatization, or multiple users of the same account under publicization) using the software, record these usage data, and input them and system elements into the content recommendation algorithm to obtain a recommended cockpit display solution, which is adjusted in the software to adapt to the user's cockpit. According to the output results of the content recommendation algorithm, the cockpit is adjusted to the recommended content.
[0087] In one implementation, obtaining a solution feature vector of a software cockpit self-adaptation solution specifically includes:
[0088] Obtaining first display weights respectively defined for each display interface, display mode, display level, display position, and display size;
[0089] Obtain the display layout of each display content in the software cockpit self-adaptation solution;
[0090] According to the first display weight and the display layout, obtaining a second display weight for each display content in the software cockpit self-adaptation solution;
[0091] The second display weights of all display contents in the software cockpit self-adaptation solution are combined to obtain a solution feature vector of the software cockpit self-adaptation solution.
[0092] In this embodiment, the first display weight is first defined, such as, the display interface is defined as the first page, the first display weight is defined as a1=1, the second page a1=0.9, etc.; the display mode is defined as the icon, the first display weight is defined as a2=1, the menu a2=0.9, etc.; the display level is level 0 (such as the menu or icon is directly displayed in the interface), the first display weight is defined as a3=1, the first level (such as the menu or icon needs to click the upper level menu or icon to display) a3=0.9, etc.; the display position is defined according to the front and back, and the display size is defined according to the size or ratio, etc.; if there is one of the contents defined above that is not specifically defined, it can be understood that its weight is 1, such as the display size of all display contents (such as icons or menus) in the interface is the same, and there is no special definition of the display size weight a5, which is still within the inventive concept of the present disclosure. Then calculate the second display weight. For a display content, its corresponding first display weight can be multiplied or added, etc. (the weight of the present disclosure does not need to be equal to 1 or less than 1, as long as it can represent the relative importance). Finally, the second display weights can be combined and arranged according to the arrangement order of all display contents in the software cockpit self-adaptation solution to obtain the solution feature vector of the software cockpit self-adaptation solution.
[0093] In one embodiment, obtaining a user preference vector of a first user using software specifically includes:
[0094] Obtaining first usage weights defined for each usage operation, usage frequency, and usage duration;
[0095] Obtaining usage data of each displayed content used by the first user during a certain historical period of time when the first user used the software;
[0096] According to the first usage weight and the usage data, obtaining a second usage weight of each display content used by the first user during the process of using the software in a certain historical period;
[0097] The second usage weights of all displayed contents used by the first user in a process of using the software in a certain historical period are combined to obtain a user preference vector of the first user using the software in the certain historical period.
[0098] In this embodiment, the idea of obtaining the user preference vector is similar to the idea of obtaining the solution feature vector. For example, different first usage weights b1 are defined for different user operation behavior data such as browsing, collecting, downloading data, modifying data, etc., and the ranges or proportions corresponding to different weights are divided according to statistical data for usage frequency and usage time.
[0099] For example, software user A (may be multiple people, but the same account) focuses on today's output and this month's production completion rate indicators, especially the factory overview and production scheduling modules. The system collects user A's historical behavior data and extracts user preference characteristics as follows: production indicator weight 0.8, equipment management module preference weight 0.6, warehousing and logistics module preference weight 0.7. Each candidate solution is to be displayed in the cockpit. For candidate solution D, its content characteristics are: production weight 0.6, equipment management weight 0.8, warehousing and logistics weight 0.6. Calculate the similarity between user A and solution D:
[0100]
[0101] After calculating the highest similarity value, the candidate indicator content in solution D is recommended to user A.
[0102] In one embodiment, the method further includes obtaining a certain historical period, specifically including:
[0103] Obtain a certain historical period according to the time period characteristics set by the first user; or,
[0104] A plurality of user preference vectors of the first user using the software in a plurality of historical time periods are obtained, and in response to a plurality of user preference vectors having the same plurality of display contents and similar corresponding second usage weights, the corresponding plurality of historical time periods are merged into one historical time period.
[0105] In this embodiment, different users have different concerns, and the same user has different concerns at different time points. For example, user A may focus on output in the first half of the year, and may focus on quality in the second half of the year. Users can set time period characteristics according to their needs, so that when collecting data for the content recommendation algorithm, historical operation data corresponding to the time period characteristics of the current period is collected to recommend content for the current user's usage needs. Software can also automatically identify such time period characteristics. For example, the software starts to collect user usage data every day. After statistics, it is found that the modules and frequencies used by users at the beginning and end of the month are very different, so the beginning and end of the month are divided into two time periods, etc.
[0106] In one embodiment, the method further includes obtaining a software cockpit self-adaptation solution, specifically including:
[0107] Obtain the software cockpit display solution developed by the developer as a software cockpit self-adaptation solution; and / or,
[0108] Obtaining a software cockpit display solution customized by a second user as a software cockpit self-adaptation solution; and / or,
[0109] Obtain all existing display contents of the software and randomly arrange and display them to obtain a software cockpit self-adaptation solution, or obtain corresponding display contents in the user preference vector and randomly arrange and display them to obtain a software cockpit self-adaptation solution.
[0110] In this embodiment, the software cockpit solution may include several solutions developed by software developers, and may refer to display solutions obtained by self-adjustment of other users, or may be automatically arranged by a machine to obtain possible display solutions. The automatic arrangement may refer to the usage habits of user A to generate an arrangement solution to save computing time.
[0111] In one embodiment, obtaining a first software cockpit self-adaptation solution having the highest similarity between a solution feature vector and a user preference vector specifically includes:
[0112] Based on the cosine similarity, Pearson correlation coefficient, and Jaccard similarity of the feature vectors, the similarity between the solution feature vector and the user preference vector is calculated, and the first software cockpit self-adaptive solution corresponding to the solution feature vector with the highest similarity is obtained; or,
[0113] Based on the matching of statistical information, a first software cockpit self-adaptation solution is obtained, which has the highest similarity between the solution feature vector and the user preference vector; or,
[0114] Based on the machine learning model, the first software cockpit self-adaptation solution is obtained, whose solution feature vector has the highest similarity with the user preference vector.
[0115] In this embodiment, the content-based recommendation system algorithm includes the following methods in addition to similarity methods such as cosine similarity, Pearson correlation coefficient, and Jaccard similarity based on feature vectors:
[0116] Matching based on statistical information: Bag of Words and TF-IDF (Term Frequency-Inverse Document Frequency): In scenarios with rich text content (such as news articles, movie introductions, etc.), you can use the Bag of Words and TF-IDF to quantify the similarity of text content. The Bag of Words model ignores the order of words and only focuses on the frequency of word occurrence; TF-IDF further considers the importance of words in the entire document, reduces the influence of common words, and highlights unique words related to the topic.
[0117] Machine learning based models:
[0118] Naive Bayes classifier: Based on the user’s preference history for the feature labels of items (such as the type of movie, actors, directors, etc.), a Naive Bayes model is constructed to predict the probability of the user’s preference for new items.
[0119] Logistic regression or support vector machine (SVM): can be used for binary classification problems to determine whether a user likes an item. The training data comes from the user's preference labels or ratings for the item.
[0120] Decision tree or random forest: By building a decision tree or integrating multiple decision trees (such as random forest), recursive division is performed based on the characteristic attributes of users and items to predict users' preferences for items.
[0121] In this embodiment, the above various methods can be used, and it is only necessary to obtain the first software cockpit self-adaptation solution with the highest similarity between the solution feature vector and the user preference vector.
[0122] A more specific example is as follows:
[0123] Table 1 An example of the display content of an industrial software
[0124]
[0125] Industrial software including the functions (display interface) and specific functional points (display content) shown in Table 1, using Figure 4 The system architecture shown realizes cockpit adaptation, which can be implemented on different mobile phones and other terminals, different systems such as Apple or Android, different APPs (Applications) such as WeChat, and can also be implemented on PC (Personal Computer). The basic technical architecture for implementing this solution includes: 1) Client, including PC, mobile, etc. Users log in to their accounts to browse, collect, download data, modify data, etc. on the client. 2) The server stores data, including user usage behavior data, module content data, module weight data, etc. Here, the module can be understood as a solution.
[0126] The implementation process includes: Step 1, on the client Client, the user logs in to the account and performs various operations on the client, such as browsing the cockpit, the contents of each module, etc. Step 2, the client obtains the user behavior and configuration information module get_user_mode to record the user's usage operations on the client (including browsing, collection, etc.). Step 3, the server get_user_data obtains the behavior operation data, detailed information on the contents of each module of the software (such as the module's classification, location, name of the included data indicators, content, etc.), and the weight data of each module (including manually set weight parameters). The module here should be understood as display content. Step 4, the content-based recommendation system algorithm module analysis_mode inputs the parameters of step 3 into the recommendation system algorithm model to obtain the similarity, and then outputs a list of recommended content. Step 5, the decision support display module Decision_support adjusts the display of the homepage / cockpit according to the list of recommended content.
[0127] This embodiment uses a content-based recommendation system algorithm module to adjust the display content module, comprehensively referring to the user's software operation behavior and the module content details, and the content is based on the user's behavioral operation, which can increase the weight of the user's core content. Therefore, it can flexibly adjust the display content according to the user's usage habits, and thus better adapt to business needs.
[0128] Embodiment 2:
[0129] like Figure 2 As shown, the present disclosure provides a software cockpit self-adaptation device, the device comprising:
[0130] Solution module 1 is used to obtain a solution feature vector of the software cockpit self-adaptation solution, where the solution feature vector represents the display layout of the software in the software cockpit self-adaptation solution, and the display layout includes a display interface, a display mode, a display level, a display position, and a display size of the display content;
[0131] Preference module 2, used to obtain a user preference vector of the first user using the software, the user preference vector is obtained based on the usage data of each display content used by the first user in the process of using the software historically, the usage data represents the usage operation, usage frequency and usage duration of each display content by the first user;
[0132] The adaptation module 3 is connected to the solution module 1 and the preference module 2, and is used to obtain the first software cockpit self-adaptation solution with the highest similarity between the solution feature vector and the user preference vector, and display the software cockpit to the first user according to the first software cockpit self-adaptation solution.
[0133] In one embodiment, the solution module 1 specifically includes:
[0134] A display weight definition unit, used to obtain first display weights defined for each display interface, display mode, display level, display position, and display size;
[0135] A display layout acquisition unit, used to acquire the display layout of each display content in the software cockpit self-adaptation solution;
[0136] A display weight matching unit, connected to the display weight definition unit and the display layout acquisition unit, for acquiring a second display weight for each display content in the software cockpit self-adaptation solution according to the first display weight and the display layout;
[0137] The scheme feature vector is connected to the display weight matching unit and is used to combine the second display weights of all display contents in the software cockpit self-adaptation scheme to obtain the scheme feature vector of the software cockpit self-adaptation scheme.
[0138] In one embodiment, the preference module 2 specifically includes:
[0139] A usage weight definition unit, used to obtain first usage weights defined for each usage operation, usage frequency, and usage duration;
[0140] A usage data acquisition unit, used to acquire usage data of each displayed content used by the first user during a certain historical period of time when the first user uses the software;
[0141] A usage weight matching unit, connected to the usage weight definition unit and the usage data acquisition unit, for acquiring a second usage weight of each display content used by the first user in a certain historical period of time during the use of the software according to the first usage weight and the usage data;
[0142] The user preference vector unit is connected to the usage weight matching unit and is used to combine the second usage weights of all displayed contents used by the first user in a certain historical period of time to obtain the user preference vector of the first user in using the software in a certain historical period of time.
[0143] In one embodiment, the preference module 2 further includes a historical period unit, which is specifically used to:
[0144] Obtain a certain historical period according to the time period characteristics set by the first user; or,
[0145] A plurality of user preference vectors of the first user using the software in a plurality of historical time periods are obtained, and in response to a plurality of user preference vectors having the same plurality of display contents and similar corresponding second usage weights, the corresponding plurality of historical time periods are merged into one historical time period.
[0146] In one embodiment, the solution module 1 further includes an adaptive solution unit, which is specifically used to:
[0147] Obtain the software cockpit display solution developed by the developer as a software cockpit self-adaptation solution; and / or,
[0148] Obtaining a software cockpit display solution customized by a second user as a software cockpit self-adaptation solution; and / or,
[0149] Obtain all existing display contents of the software and randomly arrange and display them to obtain a software cockpit self-adaptation solution, or obtain corresponding display contents in the user preference vector and randomly arrange and display them to obtain a software cockpit self-adaptation solution.
[0150] In one embodiment, the adaptation module 3 includes a similarity matching unit, which is specifically used to:
[0151] Based on the cosine similarity, Pearson correlation coefficient, and Jaccard similarity of the feature vectors, the similarity between the solution feature vector and the user preference vector is calculated, and the first software cockpit self-adaptive solution corresponding to the solution feature vector with the highest similarity is obtained; or,
[0152] Based on the matching of statistical information, a first software cockpit self-adaptation solution is obtained, which has the highest similarity between the solution feature vector and the user preference vector; or,
[0153] Based on the machine learning model, the first software cockpit self-adaptation solution is obtained, whose solution feature vector has the highest similarity with the user preference vector.
[0154] Embodiment 3:
[0155] Embodiment 3 of the present disclosure provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the software cockpit self-adaptation method as described in Embodiment 1 is implemented, or the software cockpit self-adaptation device as described in Embodiment 2 is implemented.
[0156] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, computer program modules or other data). Computer-readable storage media include, but are not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable read only memory), flash memory or other memory technology, CD-ROM (Compact Disc Read-Only Memory), digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer.
[0157] In addition, the present disclosure may also provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the software cockpit self-adaptation method as described in Example 1. The computer device may be a software cockpit self-adaptation device as described in Example 2.
[0158] The memory is connected to the processor, the memory may be a flash memory or a read-only memory or other memory, and the processor may be a central processing unit or a single-chip microcomputer.
[0159] Embodiments 1-3 of the present disclosure provide a software cockpit self-adaptation method, a software cockpit self-adaptation device, and a computer-readable storage medium. The method obtains a solution feature vector of the software cockpit self-adaptation solution, obtains a user preference vector of a first user using the software, and uses a content recommendation algorithm to obtain a first software cockpit self-adaptation solution with the highest similarity between the solution feature vector and the user preference vector. Finally, the software cockpit is displayed to the first user based on the first software cockpit self-adaptation solution, so that the software cockpit effectively adapts to the user's usage needs.
[0160] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present disclosure, but the present disclosure is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and substance of the present disclosure, and these modifications and improvements are also considered to be within the scope of protection of the present disclosure.
Claims
1. A software cockpit self-adaptation method, characterized in that: The method comprises: Acquire a solution feature vector of the software cockpit self-adaptation solution, where the solution feature vector represents the display layout of the software in the software cockpit self-adaptation solution, and the display layout includes a display interface, a display mode, a display level, a display position, and a display size of the display content; Obtaining a user preference vector of the first user using the software, where the user preference vector is obtained based on usage data of each display content used by the first user in a historical process of using the software, where the usage data represents the usage operation, usage frequency, and usage duration of each display content by the first user; A first software cockpit self-adaptation scheme having the highest similarity between a scheme feature vector and a user preference vector is obtained, and a software cockpit is displayed to a first user according to the first software cockpit self-adaptation scheme.
2. The method according to claim 1, characterized in that Obtain the solution feature vector of the software cockpit self-adaptation solution, including: Obtaining first display weights defined for each display interface, display mode, display level, display position, and display size; Obtain the display layout of each display content in the software cockpit self-adaptation solution; According to the first display weight and the display layout, obtaining a second display weight for each display content in the software cockpit self-adaptation solution; The second display weights of all display contents in the software cockpit self-adaptation solution are combined to obtain a solution feature vector of the software cockpit self-adaptation solution.
3. The method according to claim 1 or 2, characterized in that: Obtaining a user preference vector of the first user using the software, specifically including: Obtaining first usage weights defined for each usage operation, usage frequency, and usage duration; Obtaining usage data of each displayed content used by the first user during a certain historical period of time when the first user used the software; According to the first usage weight and the usage data, obtaining a second usage weight of each display content used by the first user during the process of using the software in a certain historical period; The second usage weights of all displayed contents used by the first user in a process of using the software in a certain historical period are combined to obtain a user preference vector of the first user using the software in the certain historical period.
4. The method according to claim 3, characterized in that The method further includes obtaining a certain historical period, specifically including: Obtain a certain historical period according to the time period characteristics set by the first user; or, A plurality of user preference vectors of the first user using the software in a plurality of historical time periods are obtained, and in response to a plurality of user preference vectors having the same plurality of display contents and similar corresponding second usage weights, the corresponding plurality of historical time periods are merged into one historical time period.
5. The method according to claim 3, characterized in that: The method also includes obtaining a software cockpit self-adaptation solution, specifically including: Obtain the software cockpit display solution developed by the developer as a software cockpit self-adaptation solution; and / or, Obtaining a software cockpit display solution customized by a second user as a software cockpit self-adaptation solution; and / or, Obtain all existing display contents of the software and randomly arrange and display them to obtain a software cockpit self-adaptation solution, or obtain corresponding display contents in the user preference vector and randomly arrange and display them to obtain a software cockpit self-adaptation solution.
6. The method according to claim 1, characterized in that Obtaining the first software cockpit self-adaptive solution with the highest similarity between the solution feature vector and the user preference vector, specifically including: Based on the cosine similarity, Pearson correlation coefficient, and Jaccard similarity of the feature vectors, the similarity between the solution feature vector and the user preference vector is calculated, and the first software cockpit self-adaptive solution corresponding to the solution feature vector with the highest similarity is obtained; or, Based on the matching of statistical information, a first software cockpit self-adaptation solution is obtained, which has the highest similarity between the solution feature vector and the user preference vector; or, Based on the machine learning model, the first software cockpit self-adaptation solution is obtained, whose solution feature vector has the highest similarity with the user preference vector.
7. A software cockpit self-adaptation device, characterized in that: The device comprises: A solution module is used to obtain a solution feature vector of the software cockpit self-adaptation solution. The solution feature vector represents the display layout of the software in the software cockpit self-adaptation solution. The display layout includes a display interface, a display mode, a display level, a display position, and a display size of the display content. A preference module, used to obtain a user preference vector of the first user using the software, the user preference vector is obtained based on usage data of each display content used by the first user in the process of using the software historically, the usage data represents the usage operation, usage frequency, and usage duration of each display content by the first user; The adaptation module is connected to the solution module and the preference module, and is used to obtain the first software cockpit self-adaptation solution with the highest similarity between the solution feature vector and the user preference vector, and display the software cockpit to the first user according to the first software cockpit self-adaptation solution.
8. The device according to claim 7, characterized in that The solution modules include: A display weight definition unit, used to obtain first display weights defined for each display interface, display mode, display level, display position, and display size; A display layout acquisition unit, used to acquire the display layout of each display content in the software cockpit self-adaptation solution; A display weight matching unit, connected to the display weight definition unit and the display layout acquisition unit, for acquiring a second display weight for each display content in the software cockpit self-adaptation solution according to the first display weight and the display layout; The scheme feature vector is connected to the display weight matching unit and is used to combine the second display weights of all display contents in the software cockpit self-adaptation scheme to obtain the scheme feature vector of the software cockpit self-adaptation scheme.
9. The device according to claim 7 or 8, characterized in that The preference modules include: A usage weight definition unit, used to obtain first usage weights defined for each usage operation, usage frequency, and usage duration; A usage data acquisition unit, used to acquire usage data of each displayed content used by the first user during a certain historical period of time when the first user uses the software; A usage weight matching unit, connected to the usage weight definition unit and the usage data acquisition unit, for acquiring a second usage weight of each display content used by the first user in a certain historical period of time during the use of the software according to the first usage weight and the usage data; The user preference vector unit is connected to the usage weight matching unit and is used to combine the second usage weights of all displayed contents used by the first user in a certain historical period of time to obtain the user preference vector of the first user in using the software in a certain historical period of time.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the software cockpit self-adaptation method as described in any one of claims 1 to 6 or the software cockpit self-adaptation device as described in any one of claims 7 to 9 is implemented.