A data visualization recommendation method, electronic device and storage medium

Abstract

The application discloses a data visualization recommendation method, an electronic device and a storage medium, and relates to the technical field of data visualization. The data visualization recommendation method comprises the following steps: obtaining interaction behavior information and historical behavior data of a target user with respect to a visualization system; determining a regional preference degree according to the interaction behavior information, and determining a preferred display rule according to the regional preference degree; determining a user preference according to the interaction behavior information and the historical behavior data; and dynamically adjusting a display recommendation strategy according to the user preference and the preferred display rule. According to the embodiment of the application, the user preference information is determined according to the interaction behavior information and the historical behavior data, the display recommendation strategy is customized according to the user preference information, the flexibility of the display recommendation strategy is improved, and the user experience is improved.

Description

Technical Field

[0001] This invention relates to the field of data visualization technology, and in particular to a data visualization recommendation method, electronic device, and storage medium. Background Technology

[0002] In the field of data visualization and intelligent analytics, while traditional data visualization tools have made some progress in presenting data, they often have limitations. These tools often require users to have a certain level of data analysis knowledge in order to manually select and adjust the dimensions and perspectives of the data presentation. However, for non-professional users, this can become quite complex and time-consuming. Furthermore, when faced with large-scale and multidimensional datasets, users find it difficult to quickly identify and understand key information and potential patterns within the data.

[0003] Existing visualization systems typically lack a deep understanding and analysis of user interactions, failing to automatically adjust the displayed content and methods based on specific user needs and preferences. Furthermore, they rarely offer context-based intelligent recommendations to help users explore data more effectively. The lack of advanced analytics capabilities is also a problem, often requiring users to use additional software or tools for in-depth data analysis. Therefore, how to automatically adapt visualization systems to user interactions and provide personalized displays and recommendations has become a pressing issue. Summary of the Invention

[0004] This invention provides a data visualization recommendation method, electronic device, and storage medium to solve the problem that existing visualization systems cannot deeply understand and analyze user interaction behavior, and automatically adjust the display content and method according to the user's specific needs and preferences.

[0005] According to one aspect of the present invention, a recommendation method for data visualization is provided, wherein the method includes:

[0006] Acquire information on the target user's interactive behavior and historical behavior data with respect to the visualization system;

[0007] The degree of regional preference is determined based on the interactive behavior information, and the preference display rules are determined based on the degree of regional preference.

[0008] User preferences are determined based on the interaction behavior information and the historical behavior data;

[0009] The display recommendation strategy is dynamically adjusted based on the user preferences and the preference display rules.

[0010] According to another aspect of the present invention, a data visualization recommendation apparatus is provided, wherein the apparatus comprises:

[0011] The data determination module is used to acquire information on the target user's interactive behavior and historical behavior data in relation to the visualization system.

[0012] The rule determination module is used to determine the degree of regional preference based on the interaction behavior information, and to determine the preference display rules based on the degree of regional preference.

[0013] The preference recommendation module is used to determine user preferences based on the interaction behavior information and the historical behavior data;

[0014] The strategy recommendation module is used to dynamically adjust the display recommendation strategy based on the user preferences and the preference display rules.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the recommended method for data visualization as described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the recommended method for data visualization as described in any embodiment of the present invention.

[0020] The technical solution of this invention obtains the target user's interaction behavior information and historical behavior data with the visualization system, determines the degree of regional preference based on the interaction behavior information, determines the preference display rules based on the degree of regional preference, determines user preferences based on the interaction behavior information and historical behavior data, and dynamically adjusts the display recommendation strategy based on user preferences and preference display rules. This achieves the determination of user preferences based on interaction behavior information and historical behavior data, and the customization of the display recommendation strategy according to user preferences, thereby improving the flexibility of the display recommendation strategy and enhancing the user experience.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a data visualization recommendation method provided according to Embodiment 1 of the present invention;

[0024] Figure 2 This is a flowchart of a data visualization recommendation method provided according to Embodiment 2 of the present invention;

[0025] Figure 3 This is a schematic diagram of the structure of a data visualization recommendation device provided according to Embodiment 3 of the present invention;

[0026] Figure 4 This is a schematic diagram of the structure of an electronic device that implements a data visualization recommendation method according to an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1This is a flowchart of a data visualization recommendation method according to Embodiment 1 of the present invention. This embodiment is applicable to situations where the visualization system adjusts the display recommendation strategy according to user preferences. This method can be executed by a data visualization recommendation device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0031] S110. Obtain information on the target user's interactive behavior and historical behavior data regarding the visualization system.

[0032] A visualization system refers to a system that uses graphics, text, charts, and other visualization methods to present data. The visualization system interface can be divided into different display areas, such as a main display area, a secondary display area, and a control panel area. The visualization system can recommend data filtering conditions, color schemes, and chart types based on user needs, allowing users to easily customize their display strategies. Interactive behavior information refers to information generated by user interactions with the visualization system. Generally, interactive behavior information may include, but is not limited to, the number of interactions in each area, the operation time, the duration of the operation, the gaze duration, and the current operation area. Historical behavior data refers to the user's historical interaction data with the visualization system. For example, historical behavior data may include, but is not limited to, the chart selection frequency for each chart type, the color selection frequency for each color scheme, and the condition selection frequency for each data filtering condition at historical moments, determining the chart weight coefficient for each chart type, the color weight coefficient for each color scheme, the condition weight coefficient for each data filtering condition, and historical interactive behavior information.

[0033] In this embodiment, based on the target user's operational behavior towards the visualization system, the number of regional interactions, regional operation time, regional operation duration, regional gaze duration, and current operation area of ​​the target user in each area of ​​the visualization system can be determined. These parameters are then used as interaction behavior information. Furthermore, the chart selection frequency for each chart type, the color selection frequency for each color scheme, and the condition selection frequency for each data filtering condition are extracted from the user's historical data. This determines the chart weight coefficient for each chart type, the color weight coefficient for each color scheme, the condition weight coefficient for each data filtering condition, and historical interaction behavior information. The chart selection frequency, color selection frequency, condition selection frequency, chart weight coefficient, color weight coefficient, and condition weight coefficient are then used as historical behavior data.

[0034] In actual operation, a user interaction monitor can be pre-set to record mouse clicks, scrolling, and other information in real time. This determines the number of interactions, operation time, duration, and current operation area of ​​the target user in each region of the visualization system. A pre-set eye-tracking device (e.g., an eye tracker) collects the target user's gaze point position and gaze time, determining the user's dwell time in each region as the region gaze duration. Simultaneously, the chart selection frequency for each chart type, color selection frequency for each color scheme, and condition selection frequency for each data filter condition are extracted from pre-recorded historical user data. This determines the chart weight coefficient for each chart type, color weight coefficient for each color scheme, condition weight coefficient for each data filter condition, and historical interaction behavior information. These chart selection frequencies, color selection frequencies, condition selection frequencies, chart weight coefficients, color weight coefficients, condition weight coefficients, and historical interaction behavior information are then used as historical behavior data.

[0035] S120. Determine the degree of regional preference based on the interaction behavior information, and determine the preference display rules based on the degree of regional preference.

[0036] In this context, "regional preference level" refers to the degree of interest in each display area. Regional preference levels can be categorized as high-preference or low-preference areas. Generally, areas with higher frequency of interaction or longer attention duration are identified as high-preference areas, while the remaining areas are considered low-preference areas. Regional preference levels can also be quantified numerically; higher values ​​indicate higher regional preference. Preference display rules can be understood as display rules adjusted based on regional preference levels. In practice, preference display rules can include the size of the data display area and the content of the displayed data.

[0037] In this embodiment, the region operation time, region interaction count, and region gaze duration can be extracted from the interaction behavior information. Regions with a region operation time greater than or equal to a preset threshold can be designated as high-preference regions; alternatively, regions with a region interaction count greater than or equal to a preset threshold can be designated as high-preference regions; alternatively, regions with a gaze duration greater than or equal to a preset gaze duration can be identified as high-preference regions; or, the region operation frequency can be determined based on the region operation time and region interaction count belonging to the same region, and regions with a region operation frequency greater than or equal to a preset frequency threshold can be identified as high-preference regions. The size of the data display area and the content of the data display can then be adjusted according to the region preference level.

[0038] In practical operation, the following parameters can be determined for high-preference areas: preset basic data display size, preset gaze size weight coefficient, preset gaze information weight coefficient, data volume, preset area display volume, and preset operation frequency weight coefficient. The product of the preset operation frequency weight coefficient and the area operation frequency is used as the first product, and the product of the preset gaze size weight coefficient and the area gaze duration is used as the second product. The sum of the first product, the second product, and the preset basic data display size is used as the data display area size for the high-preference area. Simultaneously, the product of the data volume and the area operation frequency is used as the third product, and the product of the preset gaze information weight coefficient and the area gaze duration is used as the fourth product. The sum of the third product, the fourth product, and the preset area display volume is used as the data display content content for the high-preference area. In practical applications, the preset gaze size weight coefficient, preset gaze information weight coefficient, and preset operation frequency weight coefficient can be updated according to the degree of regional preference. For example, when the degree of regional preference is high, the preset gaze size weight coefficient, preset gaze information weight coefficient, and preset operation frequency weight coefficient can be increased. In one embodiment, after determining the data display area size and data content content of the high-preference area, the data display area size and data content content of other areas can also be adaptively adjusted according to the corresponding area gaze duration and area operation frequency.

[0039] S130. Determine user preferences based on interaction behavior information and historical behavior data.

[0040] User preferences can be understood as recommendation information tailored to user preferences; it is the act of providing personalized content and functions to users based on their specific preferences and behavioral patterns. For example, user preferences may include, but are not limited to, chart recommendations, color scheme recommendations, and filter-based recommendations.

[0041] In this embodiment, historical behavior data can be extracted, and user preferences can be determined based on this data. In actual operation, if the chart preference level is determined to be greater than a preset preference level threshold, the target user is determined to prefer using the chart, and the chart recommendation is taken as the user preference; if the color preference level is determined to be greater than a preset color level threshold, the target user is determined to prefer changing the color scheme, and the color scheme recommendation is taken as the user preference; if the filter condition preference level is determined to be greater than a preset filter condition preference threshold, the target user is determined to prefer using the data filter condition, and the filter condition recommendation is taken as the user preference. Alternatively, a preset gaze weight coefficient and the area gaze time in the interaction behavior information can be determined, and the product of the area gaze time and the preset gaze weight coefficient can be combined to determine the user preference.

[0042] In one embodiment, when user preferences include chart preferences, the chart with the highest chart selection frequency for each chart can be determined as the recommended chart; when user preferences include color scheme preferences, the color scheme with the highest color selection frequency for each color scheme can be determined as the recommended color scheme; when user preferences include filter condition preferences, the data filter condition with the highest filter condition selection frequency for each data filter condition can be determined as the recommended data filter condition.

[0043] S140. Dynamically adjust the display recommendation strategy based on user preferences and preference display rules.

[0044] Among them, the display recommendation strategy refers to the recommendation display rules generated by the visualization system for users.

[0045] In this embodiment, once user preferences and preference display rules are determined, the display recommendation strategy can be dynamically adjusted according to these preferences. In actual operation, the size of the data display area and the content of the displayed data can be adjusted according to user preferences, and charts, color schemes, and filtering conditions can be recommended to the user according to the preference display rules. In an exemplary implementation, if a user prefers to use bar charts to analyze time series data, the visualization system can proactively recommend using bar charts according to the preference display rules, and automatically adjust the chart's color and style based on the user's operating habits, enabling the user to understand the data more intuitively and deeply.

[0046] This invention, through obtaining target user interaction behavior information and historical behavior data of a visualization system, determines the degree of regional preference based on the interaction behavior information, determines the preference display rules based on the degree of regional preference, determines user preferences based on the interaction behavior information and historical behavior data, and dynamically adjusts the display recommendation strategy based on user preferences and preference display rules. This achieves the goal of determining user preferences based on interaction behavior information and historical behavior data, and customizing the display recommendation strategy according to user preferences, thereby improving the flexibility of the display recommendation strategy and enhancing the user experience.

[0047] In one embodiment, the data visualization recommendation method further includes:

[0048] The recommended operation area is determined based on the current operation area in the interaction behavior information and the historical interaction behavior information in the historical behavior data.

[0049] Historical interaction behavior data refers to interaction behavior data at historical moments. In actual operation, historical interaction behavior information can include the number of regional interactions at a historical moment, the time of regional operation, the duration of regional operation, the duration of regional gaze, the current operation area, and the operation process. The recommended operation area can be understood as the predicted future operation area for the user.

[0050] In this embodiment, the user's current operating area can be determined, and historical interaction behavior information from historical behavior data can be identified. Based on the current operating area and rational interaction behavior information, the user's future actions can be inferred, and data views or analysis tools that the user may be interested in can be provided in advance. During actual operation, a neural network model can be pre-trained, and based on this model, future user actions can be determined, and a recommended operating area can be identified for these future actions. In one embodiment, the recommended operating area can be enlarged or highlighted to facilitate further user operations and improve user convenience.

[0051] Example 2

[0052] Figure 2 This is a flowchart of a data visualization recommendation method according to Embodiment 2 of the present invention. This embodiment is a further explanation of a data visualization recommendation method based on the above embodiments. Figure 2 As shown, the method includes:

[0053] S201. In response to the target user's operation behavior, determine the target user's number of regional interactions, regional operation time, regional operation duration, regional gaze duration, preset gaze weight coefficient, and current operation area in each area of ​​the visualization system as interaction behavior information.

[0054] Here, "operational behavior" refers to the target user's actions on the visualization system. For example, operational behavior may include, but is not limited to, mouse clicks, drags, and eye movements. "Number of interactions per region" refers to the number of interactions with each display region, such as the number of mouse clicks. "Region operation time" refers to the operation time for each display region; "region gaze duration" refers to the duration the eyes remain in each region. For example, this can be achieved by using a pre-set eye-tracking device (e.g., an eye tracker) to collect the target user's gaze point position and gaze duration, using the user's dwell time in each region as the region gaze duration; "current operation region" refers to the display region currently being operated on. "Preset gaze weight coefficient" refers to a pre-set weight coefficient for the region gaze duration, used to characterize the impact of region gaze duration on data interaction.

[0055] In this embodiment, the number of regional interactions, regional operation time, regional operation duration, regional gaze duration, and current operation area of ​​each region can be collected from preset sensors. The number of regional interactions, regional operation time, regional operation duration, regional gaze duration, preset gaze weight coefficient, and current operation area of ​​each region are used as interactive behavior information.

[0056] S202. Extract the chart selection frequency of each chart type, the color selection frequency of each color scheme, and the condition selection frequency of each data filtering condition from the user's historical data. Determine the chart weight coefficient of each chart type, the color weight coefficient of each color scheme, the condition weight coefficient of each data filtering condition, and historical interaction behavior information.

[0057] Here, chart selection frequency refers to the selection frequency of each chart type within a historical timeframe. Color selection frequency refers to the selection frequency of each color scheme within a historical timeframe. Filter selection frequency refers to the selection frequency of each data filter condition within a historical timeframe. In one embodiment, chart selection frequency, color selection frequency, and condition selection frequency can be statistically analyzed over a period of time. Chart weight coefficient refers to the weight coefficient of each chart type; color weight coefficient refers to the weight coefficient of each color scheme; condition weight coefficient refers to the weight coefficient of each data filter condition; and historical interaction behavior information refers to interaction behavior information at historical timeframes.

[0058] The chart weight coefficient, color weight coefficient, and conditional weight coefficient are dynamically adjusted based on the chart selection frequency, color selection frequency, conditional selection frequency, and area gaze duration. The higher the chart selection frequency and area gaze duration for a given chart type, the higher the chart weight coefficient for that chart type.

[0059] In this embodiment, the visualization system can record the frequency of chart selection for each chart type, the frequency of color selection for each color scheme, and the frequency of condition selection for each data filtering condition at any given time in the user's historical data. It can also determine the chart weight coefficient for each chart type, the color weight coefficient for each color scheme, the condition weight coefficient for each data filtering condition, and historical interaction behavior information.

[0060] S203. Take the chart selection frequency, color selection frequency, condition selection frequency, chart weight coefficient, color weight coefficient, condition weight coefficient, and historical interaction behavior information as historical behavior data.

[0061] S204. Determine the regional operation time and number of regional interactions belonging to the same area in the interactive behavior information, and determine the ratio of the regional operation time to the number of regional interactions belonging to the same area as the regional operation frequency.

[0062] In this embodiment, the regional operation time and the number of regional interactions belonging to the same region can be determined, and the ratio of the regional operation time to the number of regional interactions belonging to the same region can be used as the regional operation frequency.

[0063] S205. Regions whose regional operation frequency is greater than or equal to a preset frequency threshold, or regions whose regional gaze duration in the interaction behavior information is greater than or equal to a preset regional gaze duration, are identified as high-preference regions.

[0064] Here, the high-preference area can be understood as the display area with a higher degree of preference. The preset frequency threshold refers to the frequency threshold set in advance to determine the high-preference area; the preset area gaze duration refers to the duration threshold set in advance to determine the high-preference area.

[0065] In this embodiment, the regional operation frequency of each display area can be determined, and areas with a regional operation frequency greater than or equal to a preset frequency threshold are designated as high-preference areas. The regional gaze duration of each display area can also be determined, and areas with a gaze duration greater than or equal to a preset gaze duration are designated as high-preference areas. In one embodiment, display areas other than high-preference areas can be designated as low-preference areas.

[0066] S206. Determine the preset data base display size, preset gaze size weight coefficient, data volume, preset gaze information weight coefficient, preset area display volume, and preset operation frequency weight coefficient for high preference areas.

[0067] Among them, the preset data base display size refers to the base display size of each display area that is set in advance; the preset gaze size weight coefficient refers to the gaze duration weight coefficient related to the display size; the preset gaze information weight coefficient refers to the gaze duration weight coefficient related to the display quantity of the preset area; the preset area display quantity refers to the data display content content of each area that is set in advance; and the preset operation frequency weight coefficient refers to the weight coefficient of the operation frequency of the area that is set in advance.

[0068] In the embodiments, preset data base display size, preset gaze size weight coefficient, preset gaze information weight coefficient, preset area display volume, and preset operation frequency weight coefficient of the pre-set high preference area can be extracted.

[0069] S207. Update the preset gaze size weight coefficient, preset gaze information weight coefficient, and preset operation frequency weight coefficient according to the degree of regional preference.

[0070] In the embodiment, when the degree of regional preference changes, the preset gaze size weight coefficient, preset gaze information weight coefficient, and preset operation frequency weight coefficient for each display area can be changed, and the preset gaze size weight coefficient, preset gaze information weight coefficient, and preset operation frequency weight coefficient can be updated based on the degree of regional preference.

[0071] In one embodiment, updating the preset gaze size weight coefficient, the preset gaze information weight coefficient, and the preset operation frequency weight coefficient according to the degree of regional preference includes:

[0072] Determine the fixation duration for regions with a high degree of regional preference.

[0073] The product of the learning rate and the region fixation duration of the preset update model is determined as the weight coefficient update amount;

[0074] The sum of the preset gaze size weight coefficient and the updated weight coefficient is used as the updated preset gaze size weight coefficient;

[0075] The sum of the preset gaze information weight coefficient and the weight coefficient update amount is used as the updated preset gaze information weight coefficient;

[0076] The sum of the preset operation frequency weight coefficient and the weight coefficient update amount is used as the updated preset operation frequency weight coefficient.

[0077] Here, the preset learning rate refers to a parameter that is set in advance to control the learning speed of the model in the visualization system. The preset update model refers to a model that is set in advance to update the preset gaze size weight coefficient, the preset gaze information weight coefficient, and the preset operation frequency weight coefficient. For example, the preset update model can be a neural network model or a machine learning model.

[0078] In this embodiment, the region fixation duration corresponding to the high-preference region can be extracted, and the product of the learning rate of the preset update model and the region fixation duration can be determined. This product is then used as the weight coefficient update amount. The preset fixation size weight coefficient, preset fixation information weight coefficient, and preset operation frequency weight coefficient are respectively increased by the weight coefficient update amount to obtain the updated preset fixation size weight coefficient, updated preset fixation information weight coefficient, and updated preset operation frequency weight coefficient.

[0079] S208. Determine the data display area size and data display content of the high-preference area according to the preset data base display size, preset area display volume, updated preset gaze size weight coefficient, preset gaze information weight coefficient, and preset operation frequency weight coefficient.

[0080] In this embodiment, the size change can be determined according to the updated preset gaze size weight coefficient, the region operation frequency, and the preset operation frequency weight coefficient. The sum of the size change and the preset basic data display size is used as the data display area size for the high-preference region. The data volume change is determined according to the preset region display volume, the region operation frequency, and the preset gaze information weight coefficient. The sum of the data volume change and the preset region display volume is used as the data display content content.

[0081] In one embodiment, the data display area size and data display content of the high-preference area are determined according to the preset basic data display size of the high-preference area, the preset area display volume, and the updated preset gaze size weight coefficient, preset gaze information weight coefficient, and preset operation frequency weight coefficient, including:

[0082] The product of the preset operation frequency weighting coefficient and the regional operation frequency is determined as the first product, and the product of the preset gaze size weighting coefficient and the regional gaze duration is determined as the second product;

[0083] The sum of the first product, the second product, and the preset basic data display size is used as the data display area size for the high-preference region;

[0084] The product of the data volume and the frequency of regional operations is determined as the third product, and the product of the preset gaze information weight coefficient and the regional gaze duration is determined as the fourth product.

[0085] The sum of the third product, the fourth product, and the preset area display quantity is used as the data display content content of the high-preference area.

[0086] In this embodiment, the product of a preset operation frequency weighting coefficient and the regional operation frequency can be used as the first product, and the product of a preset gaze size weighting coefficient and the regional gaze duration can be used as the second product. The sum of the first product, the second product, and the preset basic data display size is determined as the data display area size of the high-preference region. Then, the product of the data volume and the regional operation frequency is used as the third product, and the product of a preset gaze information weighting coefficient and the regional gaze duration is used as the fourth product. The sum of the third product, the fourth product, and the preset regional display volume is determined as the data display content content of the high-preference region.

[0087] S209. Use the size of the data display area and the content of the data display as the preferred display rules.

[0088] S210. Extract the area gaze time and preset gaze weight coefficient from the interaction behavior information, as well as the chart selection frequency of each chart type, the color selection frequency of each color scheme, the condition selection frequency of each data filtering condition, the chart weight coefficient of each chart type, the color weight coefficient of each color, and the condition weight coefficient of each data filtering condition from the historical behavior data.

[0089] In the embodiments, the region gaze time and preset gaze weight coefficient in the pre-stored interaction behavior information can be extracted, as well as the chart selection frequency of each chart type, the color selection frequency of each color scheme, the condition selection frequency of each data filtering condition, the chart weight coefficient of each chart type, the color weight coefficient of each color, and the condition weight coefficient of each data filtering condition in the historical behavior data.

[0090] S211. Determine the degree of chart preference, color preference, and filter condition preference based on chart selection frequency, color selection frequency, condition selection frequency, chart weight coefficient, color weight coefficient, condition weight coefficient, area gaze time, and preset gaze weight coefficient.

[0091] Among them, chart preference refers to the degree to which users like to use charts; color preference refers to the degree to which users like to use color schemes; and filter preference refers to the degree to which users like to use data filtering conditions.

[0092] In one embodiment, determining the degree of chart preference, color preference, and filtering condition preference based on chart selection frequency, color selection frequency, condition selection frequency, chart weight coefficient, color weight coefficient, condition weight coefficient, region fixation time, and preset fixation weight coefficient includes:

[0093] The product of the determined region fixation time and the preset fixation weight coefficient is used as fixation information;

[0094] The sum of gaze information and chart selection frequency is used as chart selection information, and the sum of gaze information and color selection frequency is used as color selection information.

[0095] The sum of the products of each chart selection information and the corresponding chart weight coefficient is used as the chart preference level.

[0096] The sum of the products of each color selection information and the corresponding color weight coefficient is determined as the degree of color preference.

[0097] The sum of the products of the selection frequency of each filter condition and the weight coefficient of the filter condition corresponding to the selection frequency is determined as the degree of preference of the filter condition.

[0098] In this embodiment, the product of the region fixation time and a preset fixation weight coefficient can be determined as fixation information. The sum of the fixation information and the chart selection frequency can be determined as chart selection information, and the sum of the fixation information and the color selection frequency can be determined as color selection information. Furthermore, the sum of the products of each chart selection information and its corresponding chart weight coefficient can be determined as the chart preference level, the sum of the products of each color selection information and its corresponding color weight coefficient can be determined as the color preference level, and the sum of the products of each filter condition selection frequency and its corresponding filter condition weight coefficient can be determined as the filter condition preference level.

[0099] S212. When the chart preference level is greater than the preset chart preference threshold, the chart recommendation will be taken as the user preference.

[0100] The preset chart preference threshold can be understood as a pre-set threshold used to determine whether a user prefers the recommended charts. The preset chart preference threshold can be set according to user needs.

[0101] In this embodiment, the relationship between the degree of chart preference and the preset chart preference threshold can be compared. When it is determined that the degree of chart preference is greater than the preset chart preference threshold, the chart recommendation can be taken as the user preference.

[0102] S213. When the degree of color preference is greater than the preset color preference threshold, the color recommendation will be taken as the user preference.

[0103] The preset color preference threshold can be understood as a pre-set threshold used to determine whether a user prefers color recommendations. The preset color preference threshold can be set according to user needs.

[0104] In this embodiment, the degree of color preference can be compared with a preset color preference threshold. When it is determined that the degree of color preference is greater than the preset color preference threshold, the color recommendation can be taken as the user preference.

[0105] S214. When the degree of preference for filtering conditions is greater than the preset threshold for filtering conditions, the filtering condition recommendation will be taken as the user preference.

[0106] The preset filter preference threshold can be understood as a pre-set threshold used to determine whether a user prefers the recommended filter conditions. The preset filter preference threshold can be set according to user needs.

[0107] In this embodiment, the degree of preference for filtering conditions can be compared with the preset threshold for filtering conditions. When it is determined that the degree of preference for filtering conditions is greater than the preset threshold for filtering conditions, the filtering condition recommendation can be taken as the user preference.

[0108] S215. Dynamically adjust the display recommendation strategy based on user preferences and preference display rules.

[0109] In this embodiment of the invention, by responding to the target user's operational behavior, the number of regional interactions, regional operation time, regional operation duration, regional gaze duration, and the current operation area of ​​each region in the visualization system are determined as interactive behavior information. Chart selection frequency, color selection frequency, conditional selection frequency, chart weight coefficient, color weight coefficient, conditional weight coefficient, and historical interactive behavior information are used as historical behavior data. High-preference regions are identified based on the interactive behavior information and historical behavior data, and the data display area size and data content content of these high-preference regions are determined to adaptively determine user preferences based on preferences. By extracting the chart selection frequency of each chart type, the color selection frequency of each color scheme, the conditional selection frequency of each data filtering condition, the chart weight coefficient of each chart type, the color weight coefficient of each color, and the conditional weight coefficient of each data filtering condition from the historical behavior data, the degree of chart preference, color preference, and filtering condition preference are determined according to the chart selection frequency, color selection frequency, conditional selection frequency, chart weight coefficient, color weight coefficient, and conditional weight coefficient. This determines user preferences, enabling the visualization system to automatically adapt to the user's interactive behavior, providing personalized displays and recommendations, and improving the user experience.

[0110] Example 3

[0111] In one embodiment, this embodiment takes an intelligent multidimensional data interactive visualization analysis system as an example of a visualization system. The intelligent multidimensional data interactive visualization analysis system includes: a user interaction module, a behavior analysis engine, an adaptive display logic module, an intelligent recommendation system, a context-aware module, a prediction model integration module, a custom recommendation algorithm interface, a real-time collaboration framework, and an advanced analysis plugin library as an example to further illustrate a data visualization recommendation method.

[0112] The user interaction module monitors user actions such as clicks and drags in real time and transmits the data to the behavior analysis engine. The behavior analysis engine uses machine learning algorithms to analyze user behavior and intelligently infer users' interests (high-preference areas). Based on the analysis results, the adaptive display logic module dynamically adjusts the dimensions and level of detail of the data display to adapt to user needs. The intelligent recommendation system further provides customized display perspectives and methods based on user behavior (interaction behavior information) and interests (high-preference areas). The context-aware module deeply analyzes the original context of the data, providing analytical suggestions and enhancing user insights. The predictive model integration module allows users to adjust prediction parameters through interactive operations and displays prediction results in real time. The customizable recommendation algorithm interface allows users to customize personalized recommendation strategies according to their analytical needs. The real-time collaboration framework supports multi-user collaboration, enabling data sharing and communication. The advanced analysis plugin library provides a variety of tools to meet users' needs for in-depth analysis.

[0113] In one embodiment, the user interaction monitor in the user interaction module can track and record various operations performed by the user on the data visualization interface in real time. Operation information may include basic clicks and drags, as well as more complex behaviors such as zooming and data selection. By accurately capturing each user's action, the user interaction monitor ensures that it accurately reflects the user's interaction intent. For example, the user interaction monitor can also determine the contextual information of the operation, such as the time of the operation, the duration of the operation, and the frequency of the operation, thereby providing rich data for understanding the user's behavioral patterns and preferences. In one embodiment, the interaction behavior information collected by the user interaction monitor can be stored as historical behavior data.

[0114] The behavior analysis engine performs in-depth analysis of data collected by the user interaction monitor. This processor utilizes advanced machine learning techniques, including Hidden Markov Models (HMMs) and Deep Neural Networks (DNNs), to process and parse user interaction behavior information. In one embodiment, by modeling and analyzing user interaction behavior information on an intelligent multidimensional data interactive visualization analysis system, the behavior analysis engine can identify user behavior patterns. These patterns may include user preferences for specific datasets, operational habits, and specific behavioral trends exhibited during analysis. For example, if a user frequently performs in-depth analysis of a certain data area within a certain time period, the processor can identify this behavioral pattern. The behavior analysis engine can not only identify existing behavioral patterns but also predict future user actions by learning from historical interaction data. This predictive capability allows the system to more proactively adapt to user needs, providing users with data views or analytical tools they might be interested in advance. For example, if the system predicts that a user might want to view a detailed view of a specific dataset next, the intelligent multidimensional data interactive visualization analysis system can automatically adjust the display parameters. The advanced analytical capabilities of the behavior analysis engine greatly enhance the system's personalized service level. By accurately capturing and predicting user behavior, the system can provide a data analysis experience that is more tailored to user needs, making the user experience more convenient and intuitive.

[0115] The adaptive display logic module is an intelligent component in the intelligent multi-dimensional data interactive visualization analysis system. Its core task is to determine the degree of regional preference based on user interaction behavior information and to determine the preference display rules based on the degree of regional preference. In actual operation, the adaptive display logic module first receives interaction behavior information from the user interaction monitor. This data records in detail all user operations on the data visualization interface, including clicking, dragging, zooming, selection, and eye gaze. Using the output of the behavior analysis processor, the engine identifies user behavior patterns and points of interest (high-preference areas). If the user's operation frequency f for a certain area is significantly higher than that for a specific area, it may indicate that the user is particularly interested in that area. Based on user behavior analysis, the engine uses a mathematical model to dynamically adjust display parameters. The display size S can be calculated using the following formula: S = α·f + β + θ·g, where α is a weighting coefficient related to the user interaction frequency (region operation frequency), f is the region operation frequency, β is the preset basic display size, θ is a weighting coefficient related to the region gaze duration (preset gaze size weighting coefficient), and g is the region gaze duration. This ensures that even display areas with low interaction frequency can receive basic display. For data points that users are particularly interested in (high-preference areas), the engine may need to display more detailed information. The content content D displayed can be calculated using the following formula: D = γ·I + δ + κ·g, where γ is the weight coefficient related to the user's point of interest (region operation frequency), I is the amount of data, δ is the preset display volume for the region, κ is the weight coefficient related to the region's gaze duration (preset gaze information weight coefficient), and g is the region's gaze duration, ensuring the display of basic information. The adaptive display logic module also includes a feedback mechanism that continuously adjusts α, β, γ, δ, θ, κ, η, and μ based on the user's subsequent behavior and feedback. The feedback mechanism is not only based on the user's actions on the recommendation results but also on the user's region gaze duration, adjusting the recommendation algorithm's decision-making process to optimize the display effect.

[0116] In one embodiment, g recommend This will directly affect the system's learning process; for example, weights can be dynamically updated in the following ways: Where λ is the preset learning rate, g recommend This refers to the user's regional gaze in the recommended results market. In this way, the system will prioritize recommending content that users gaze at for longer periods, further improving user satisfaction.

[0117] By introducing a gaze mechanism, the system can more accurately capture users' interests and focus, thus making the dynamic adjustment of display and recommendation more intelligent and personalized.

[0118] In one embodiment, the intelligent recommendation system provides customized data displays and analytical suggestions by analyzing user behavior patterns and preferences: the intelligent recommendation generator first needs to collect information on user interactions with the system. This interaction information includes, but is not limited to, the frequency f of user selection of a desired chart type. chart Preferred color scheme c pref and commonly used data filtering conditions f filter User preference models can be built using the collected behavioral data. For example, user preferences for different chart types can be calculated using the following weighted summation formula: Among them, P chart This indicates the user's overall preference for chart types, w i f is the chart weight coefficient for the i-th chart type. chart,i η is the frequency with which users select the i-th chart type, η is the weighting coefficient related to gaze duration (preset gaze weighting coefficient), and g is the region gaze duration. Similarly, user preference for color schemes can be calculated as follows: Among them, P color Indicates the user's preference for a color scheme, v j c is the color weight coefficient for the j-th color scheme. pref,j This represents the probability of a user selecting the j-th color. User preferences for data filtering conditions can also be determined using a similar method: Among them, P fiiiter s represents the degree of user preference for data filtering conditions. k f is the condition weight coefficient of the k filtering conditions. filter,k This represents the frequency of the user's application of the k-th filter condition. Based on the user preference model, the intelligent recommendation generator applies recommendation algorithms to generate display and analysis suggestions. Ultimately, the intelligent recommendation generator recommends the most suitable chart type, color scheme, and data filtering conditions to the user based on the calculated preference level. The recommended chart type can be based on the chart selection frequency f of the chart type. chart Determine: Chart recommend =argmax(f chart Among them, Chart recommend This refers to the type of chart recommended to users. The intelligent recommendation generator also includes a feedback loop that adjusts the weighting coefficients based on user feedback regarding the actual use and satisfaction with the recommendations. i ,v j ,s k To optimize the performance of the recommendation algorithm.

[0119] The implemented context-aware module provides detailed information related to the current operating area, such as data sources, influencing factors, and historical trends, helping users understand the data in a broader context. The design goal of the context-aware module is to provide a richer and more comprehensive perspective on data analysis.

[0120] The predictive model integration module provides an interactive predictive model, allowing users to directly interact with the built-in predictive model. This module offers intuitive control over model parameters through a user-friendly interface, such as adjusting the window size for time series analysis or feature weights in classification models. The interface features easy-to-use controls, such as sliders and drop-down menus, allowing users to fine-tune model parameters without specialized knowledge. This design simplifies the user experience and makes model adjustments quick and direct. Users can see the real-time impact of parameter changes on prediction results through simple sliding or selection operations. When users adjust parameters, the predictive model recalculates and updates the results instantly. This immediacy ensures users can quickly assess the impact of different parameter settings on the model's predictive accuracy and stability. For example, by adjusting the time series window size, users can observe the impact of different time ranges on trend prediction. The interactive predictive model also includes a results display that uses charts, curves, and animations to visually present the prediction results. This not only helps users better understand the model's output but also makes complex predictive data easier to digest and analyze. The design of the interactive predictive model also reflects educational and exploratory purposes. It encourages users to learn how the model behaves through practice, gaining a deeper understanding of how different parameters affect the final prediction. This interactive learning experience not only enhances users' data analysis skills but also increases their understanding and trust in the predictive modeling process.

[0121] The real-time collaboration framework, or real-time multi-user collaboration platform, is an advanced feature in intelligent multi-dimensional data interactive visualization and analysis systems. It allows multiple users to work simultaneously on the same dataset, enabling close collaboration. By providing a shared view of data and a space for analysis results, the real-time collaboration framework allows users to participate in the data analysis process regardless of their location. To facilitate effective communication among team members, the platform integrates various real-time communication tools, including convenient chat functionality and efficient video conferencing options. These tools not only enhance information exchange among team members but also support rapid decision-making and problem-solving, thereby improving the overall team's collaboration efficiency and the synergy of analytical work. Through this innovative collaboration method, teams can pool their expertise and perspectives to collectively drive data analysis projects forward.

[0122] The customizable recommendation algorithm interface supports an advanced analytics plugin system, equipped with a suite of sophisticated data analysis tools and algorithms. These plugins include, but are not limited to, advanced algorithms such as clustering, classification, and regression, providing users with a rich algorithm library to address diverse data analysis needs. In other words, users can flexibly select and apply these plugins based on their specific analytical objectives, enabling deeper data mining and insights. Whether exploring the intrinsic structure of data, performing pattern recognition, or predicting future trends, the advanced analytics plugin system provides the necessary support, making the data analysis process more efficient and accurate. Through this system, users can easily expand their analytical capabilities, delve deeper into the potential of their data, and gain valuable business insights.

[0123] In one embodiment, the visualization system can be applied to a custom algorithm development environment. This custom algorithm development environment is a highly flexible feature of the intelligent multidimensional data interactive visualization analysis system, designed specifically for users with special or advanced analytical needs. Within this environment, users can develop personalized data analysis algorithms using various tools and application programming interfaces (APIs) provided by the system, tailored to their specific requirements. The user-friendly system environment allows users to build and implement their own algorithm logic without needing to delve into complex underlying technical details. This means that even users without a strong programming or data science background can transform their ideas into practical data analysis solutions through this environment. Furthermore, this development environment supports algorithm testing and verification, ensuring that the algorithms developed by users are both effective and reliable in practical applications. In this way, the system not only enhances the personalization and flexibility of data analysis but also greatly expands its application scope and depth.

[0124] In one embodiment, the visualization system also includes a results export tool that allows users to easily export analysis results to various formats, such as Portable Document Format (PDF), Portable Network Graphics (PNG), and Comma-Separated Values ​​(CSV). Whether the results need to be saved as static image files, further data processing and analysis are desired in spreadsheet format, or interactive web pages are created to dynamically display data insights, the results export tool can meet these needs. This tool is designed with convenience and versatility in mind, ensuring that users can choose the most suitable format based on their reporting or sharing requirements.

[0125] In this embodiment of the invention, the visualization system, through an integrated intelligent recommendation system, can perform in-depth analysis based on users' historical interaction data and real-time interaction behavior, intelligently recommending the most suitable data display perspective and analysis methods. Simultaneously, when a user shows strong interest in a specific data area, the system can automatically recognize this behavior and adjust display parameters in real time, such as zooming in on the data area or providing more detailed information. Furthermore, users not only receive intelligent recommendations based on personal preferences and behavior, but can also see in real time how these recommendations are transformed into customized data views through an adaptive display engine. This seamless personalized experience allows users to focus more on data analysis itself, rather than data adjustment and configuration, greatly improving the efficiency and depth of data analysis.

[0126] Example 4

[0127] Figure 3 This is a schematic diagram of the structure of a data visualization recommendation device provided according to Embodiment 3 of the present invention. Figure 3 As shown, the device includes: a data determination module 31, a rule determination module 32, a preference recommendation module 33, and a strategy recommendation module 34.

[0128] Among them, the data determination module 31 is used to obtain the target user's interactive behavior information and historical behavior data regarding the visualization system;

[0129] The rule determination module 32 is used to determine the degree of regional preference based on the interaction behavior information, and to determine the preference display rules based on the degree of regional preference.

[0130] The preference recommendation module 33 is used to determine user preferences based on interaction behavior information and historical behavior data.

[0131] The strategy recommendation module 34 is used to dynamically adjust the display recommendation strategy based on user preferences and preference display rules.

[0132] In this embodiment of the invention, a data determination module acquires the target user's interaction behavior information and historical behavior data with respect to the visualization system. A rule determination module determines the degree of regional preference based on the interaction behavior information and determines the preference display rules based on the degree of regional preference. A preference recommendation module determines user preferences based on the interaction behavior information and historical behavior data. A strategy recommendation module dynamically adjusts the display recommendation strategy based on user preferences and preference display rules. This enables the determination of user preferences based on interaction behavior information and historical behavior data, and the customization of the display recommendation strategy according to user preferences, thereby improving the flexibility of the display recommendation strategy and enhancing the user experience.

[0133] In one embodiment, the data determination module 31 includes:

[0134] The interactive information determination unit is used to respond to the target user's operation behavior and determine the target user's regional interaction count, regional operation time, regional operation duration, regional gaze duration, preset gaze weight coefficient, and current operation area as interactive behavior information for each area of ​​the visualization system.

[0135] The information extraction unit is used to extract the chart selection frequency of each chart type, the color selection frequency of each color scheme, and the condition selection frequency of each data filtering condition at each user's historical time, and to determine the chart weight coefficient of each chart type, the color weight coefficient of each color scheme, the condition weight coefficient of each data filtering condition, and historical interaction behavior information.

[0136] Among them, the chart weight coefficient, color weight coefficient, and condition weight coefficient are dynamically adjusted based on the chart selection frequency, color selection frequency, condition selection frequency, and area gaze duration.

[0137] The historical data determination unit is used to take chart selection frequency, color selection frequency, condition selection frequency, chart weight coefficient, color weight coefficient, condition weight coefficient, and historical interaction behavior information as historical behavior data.

[0138] In one embodiment, the rule determination module 32 includes:

[0139] The operation frequency determination unit is used to determine the regional operation time and the number of regional interactions belonging to the same area in the interactive behavior information, and to determine the ratio of the regional operation time to the number of regional interactions belonging to the same area as the regional operation frequency.

[0140] The preference region determination unit is used to identify regions whose region operation frequency is greater than or equal to a preset frequency threshold, or regions whose region gaze duration in the interaction behavior information is greater than or equal to a preset region gaze duration, as high preference regions.

[0141] The coefficient extraction unit is used to determine the preset data base display size, preset gaze size weight coefficient, data volume, preset gaze information weight coefficient, preset area display volume, and preset operation frequency weight coefficient for high-preference areas.

[0142] The coefficient update unit is used to update the preset gaze size weight coefficient, the preset gaze information weight coefficient, and the preset operation frequency weight coefficient according to the degree of regional preference.

[0143] The display determination unit is used to determine the data display area size and data display content of the high-preference area according to the preset data base display size of the high-preference area, the preset area display volume, the updated preset gaze size weight coefficient, the preset gaze information weight coefficient, and the preset operation frequency weight coefficient.

[0144] The display rule determination unit is used to determine the size of the data display area and the content of the data display content as the preferred display rules.

[0145] In one embodiment, the coefficient update unit is specifically used for:

[0146] Determine the fixation duration for regions with a high degree of regional preference.

[0147] The product of the learning rate and the region fixation duration of the preset update model is determined as the weight coefficient update amount;

[0148] The sum of the preset gaze size weight coefficient and the updated weight coefficient is used as the updated preset gaze size weight coefficient;

[0149] The sum of the preset gaze information weight coefficient and the weight coefficient update amount is used as the updated preset gaze information weight coefficient;

[0150] The sum of the preset operation frequency weight coefficient and the weight coefficient update amount is used as the updated preset operation frequency weight coefficient.

[0151] In one embodiment, a determining unit is shown, specifically used for:

[0152] The product of the preset operation frequency weighting coefficient and the regional operation frequency is determined as the first product, and the product of the preset gaze size weighting coefficient and the regional gaze duration is determined as the second product;

[0153] The sum of the first product, the second product, and the preset basic data display size is used as the data display area size for the high-preference region;

[0154] The product of the data volume and the frequency of regional operations is determined as the third product, and the product of the preset gaze information weight coefficient and the regional gaze duration is determined as the fourth product.

[0155] The sum of the third product, the fourth product, and the preset area display quantity is used as the data display content content of the high-preference area.

[0156] In one embodiment, the preference recommendation module 33 includes:

[0157] The weight coefficient extraction unit is used to extract the area gaze time and preset gaze weight coefficient from the interaction behavior information, as well as the chart selection frequency of each chart type, the color selection frequency of each color scheme, the condition selection frequency of each data filtering condition, the chart weight coefficient of each chart type, the color weight coefficient of each color, and the condition weight coefficient of each data filtering condition from the historical behavior data.

[0158] The preference determination unit is used to determine the preference degree of charts, colors, and filtering conditions based on chart selection frequency, color selection frequency, condition selection frequency, chart weight coefficient, color weight coefficient, condition weight coefficient, area gaze time, and preset gaze weight coefficient.

[0159] The first preference determination unit is used to determine the chart recommendation as the user preference when the chart preference degree is greater than the preset chart preference threshold.

[0160] The second preference determination unit is used to determine the color recommendation as the user preference when the color preference level is greater than the preset color preference threshold.

[0161] The third preference determination unit is used to determine the filter condition recommendation as the user preference when the preference level of the filter condition is greater than the preset filter condition preference threshold.

[0162] In one embodiment, the preference degree determination unit is specifically used for:

[0163] The product of the determined region fixation time and the preset fixation weight coefficient is used as fixation information;

[0164] The sum of gaze information and chart selection frequency is used as chart selection information, and the sum of gaze information and color selection frequency is used as color selection information.

[0165] The sum of the products of each chart selection information and the corresponding chart weight coefficient is used as the chart preference level.

[0166] The sum of the products of each color selection information and the corresponding color weight coefficient is determined as the degree of color preference.

[0167] The sum of the products of the selection frequency of each filter condition and the weight coefficient of the filter condition corresponding to the selection frequency is determined as the degree of preference of the filter condition.

[0168] In one embodiment, the data visualization recommendation device further includes:

[0169] The operation recommendation module is used to determine the recommended operation area based on the current operation area in the interaction behavior information and the historical interaction behavior information in the historical behavior data.

[0170] The data visualization recommendation device provided in this embodiment of the invention can execute the data visualization recommendation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0171] Example 5

[0172] Figure 4This is a schematic diagram of the structure of an electronic device that implements a recommended method for data visualization according to an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0173] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0174] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0175] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as recommendation methods for data visualization.

[0176] In some embodiments, the data visualization recommendation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the data visualization recommendation method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the data visualization recommendation method by any other suitable means (e.g., by means of firmware).

[0177] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0178] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0179] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0180] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0181] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0182] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0183] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0184] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A data visualization recommendation method, characterized in that, include: Acquire information on target users' interactive behavior and historical behavior data with respect to the visualization system; The degree of regional preference is determined based on the interactive behavior information, and the preference display rules are determined based on the degree of regional preference. User preferences are determined based on the interaction behavior information and the historical behavior data; wherein, the user preferences include at least chart recommendations, color scheme recommendations, and filter condition recommendations; The display recommendation strategy is dynamically adjusted based on the user preferences and the preference display rules. The step of determining the degree of regional preference based on the interaction behavior information and determining the preference display rules based on the degree of regional preference includes: Determine the regional operation time and number of regional interactions belonging to the same area in the interactive behavior information, and determine the ratio of the regional operation time to the number of regional interactions belonging to the same area as the regional operation frequency; The regions whose regional operation frequency is greater than or equal to a preset frequency threshold, or whose regional gaze duration in the interaction behavior information is greater than or equal to a preset regional gaze duration, are identified as high-preference regions. Determine the preset data base display size, preset gaze size weight coefficient, data volume, preset gaze information weight coefficient, preset area display volume, and preset operation frequency weight coefficient for the high-preference area; Update the preset gaze size weight coefficient, the preset gaze information weight coefficient, and the preset operation frequency weight coefficient according to the region preference degree; The data display area size and data display content of the high-preference area are determined according to the preset data base display size of the high-preference area, the preset area display volume, the updated preset gaze size weight coefficient, the preset gaze information weight coefficient, and the preset operation frequency weight coefficient. The size of the data display area and the content of the data display are used as preference display rules; The step of determining the data display area size and data display content of the high-preference area according to the preset basic data display size, preset area display volume, updated preset gaze size weight coefficient, preset gaze information weight coefficient, and preset operation frequency weight coefficient includes: The product of the preset operation frequency weighting coefficient and the region operation frequency is determined as the first product, and the product of the preset gaze size weighting coefficient and the region gaze duration is determined as the second product; The sum of the first product, the second product, and the preset basic data display size is used as the data display area size of the high-preference area; The product of the data volume and the region operation frequency is determined as the third product, and the product of the preset gaze information weight coefficient and the region gaze duration is determined as the fourth product; The sum of the third product, the fourth product, and the preset area display quantity is taken as the data display content content of the high preference area.

2. The method according to claim 1, characterized in that, The acquisition of target user interaction behavior information and historical behavior data with respect to the visualization system includes: In response to the target user's operation behavior, the number of regional interactions, regional operation time, regional operation duration, regional gaze duration, preset gaze weight coefficient, and current operation area of ​​the target user in each area of ​​the visualization system are determined as interaction behavior information. Extract the chart selection frequency of each chart type, the color selection frequency of each color scheme, and the condition selection frequency of each data filtering condition from the user's historical data. Determine the chart weight coefficient for each chart type, the color weight coefficient for each color scheme, the condition weight coefficient for each data filtering condition, and historical interaction behavior information. The chart weight coefficient, the color weight coefficient, and the condition weight coefficient are dynamically adjusted based on the chart selection frequency, the color selection frequency, the condition selection frequency, and the region gaze duration. The chart selection frequency, color selection frequency, condition selection frequency, chart weight coefficient, color weight coefficient, condition weight coefficient, and historical interaction behavior information are used as historical behavior data.

3. The method according to claim 1, characterized in that, The step of updating the preset gaze size weight coefficient, the preset gaze information weight coefficient, and the preset operation frequency weight coefficient according to the region preference degree includes: The fixation duration of regions with a high degree of regional preference was determined. The product of the learning rate of the preset update model and the gaze duration of the region is determined as the weight coefficient update amount; The sum of the preset gaze size weight coefficient and the updated weight coefficient is used as the updated preset gaze size weight coefficient; The sum of the preset gaze information weight coefficient and the weight coefficient update amount is used as the updated preset gaze information weight coefficient; The sum of the preset operation frequency weight coefficient and the weight coefficient update amount is used as the updated preset operation frequency weight coefficient.

4. The method according to claim 1, characterized in that, Determining user preferences based on the interaction behavior information and the historical behavior data includes: Extract the region gaze time and preset gaze weight coefficient from the interaction behavior information, as well as the chart selection frequency of each chart type, the color selection frequency of each color scheme, the filter condition selection frequency of each data filter condition, the chart weight coefficient of each chart type, the color weight coefficient of each color scheme, and the condition weight coefficient of each data filter condition from the historical behavior data. The degree of preference for charts, colors, and filtering conditions is determined based on the chart selection frequency, color selection frequency, filter condition selection frequency, chart weight coefficient, color weight coefficient, condition weight coefficient, area gaze time, and preset gaze weight coefficient. When the degree of chart preference is greater than the preset chart preference threshold, the chart recommendation will be taken as the user preference; When the degree of color preference is greater than the preset color preference threshold, the color recommendation will be taken as the user preference; When the degree of preference for the filtering condition is greater than the preset threshold for filtering condition preference, the filtering condition recommendation will be taken as the user preference.

5. The method according to claim 4, characterized in that, The process of determining the degree of chart preference, color preference, and filter condition preference according to the chart selection frequency, color selection frequency, filter condition selection frequency, chart weight coefficient, color weight coefficient, condition weight coefficient, region gaze time, and preset gaze weight coefficient includes: The product of the determined region fixation time and the preset fixation weight coefficient is used as fixation information; The sum of the gaze information and the chart selection frequency is determined as the chart selection information, and the sum of the gaze information and the color selection frequency is determined as the color selection information. The sum of the products of each chart selection information and the corresponding chart weight coefficient is determined as the degree of chart preference. The sum of the products of each color selection information and the corresponding color weight coefficient is determined as the degree of color preference. The sum of the products of the selection frequency of each filter condition and the weight coefficient of the filter condition corresponding to the selection frequency is determined as the degree of preference of the filter condition.

6. The method according to claim 1, characterized in that, The method further includes: The recommended operation area is determined based on the current operation area in the interaction behavior information and the historical interaction behavior information in the historical behavior data.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the recommended method for data visualization according to any one of claims 1-6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the recommended method for data visualization according to any one of claims 1-6.

Images