Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the following detailed description of specific embodiments thereof is given with reference to the accompanying drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the application and not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the matters related to the present application are shown in the accompanying drawings. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart depicts operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently, or at the same time. Furthermore, the order of the operations may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figures. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application are within the scope of the protection of the present application.
The terms first, second and the like in the description and in the claims, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type and not limited to the number of objects, e.g., the first object may be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/", generally means that the associated object is an "or" relationship.
The data visualization method, device, equipment and medium based on the AI model provided in the embodiments of the present application are described in detail below with reference to the accompanying drawings by means of specific embodiments and application scenarios thereof.
Example 1
Fig. 1 is a flowchart of an AI model-based data visualization method according to an embodiment of the present application. As shown in fig. 1, the method specifically comprises the following steps:
s101, acquiring historical behavior information of a user;
first, the method and the device are suitable for a scene of data after data visualization is performed on user display. Based on the above usage scenario, it can be appreciated that the execution subject of the present application may be a server. Specifically, the acquisition of the historical behavior information, the determination of the concerned data and the visualization strategy, the dynamic visualization display and the like can be executed by a server, and the user views the data displayed in the dynamic visualization to acquire the information required by the user.
The server is a hardware device or computer program specially used for providing computing, storage and website services, the client is a hardware device or computer program which is communicated and interacted with the server, the server transmits data to the client, and the client displays the data to a user. Users are the crowd looking up the data through the client.
The historical behavior information refers to information for recording and storing behaviors, activities or interactions performed by the user on the client before the current time point, and may include historical browsing information and operation behavior information.
The logging function on the server may capture various activities and events of the client and store them as log files. The log file may include an access log, an error log, a security log, a performance log, and the like. By acquiring and reading the log file, the historical behavior information of the user can be acquired.
S102, inputting the historical behavior information into a pre-trained AI model, and determining the attention data of a user according to the output result of the AI model;
AI models refer to mathematical models constructed and trained using artificial intelligence techniques for solving specific problems or performing specific tasks. Pre-training refers to the process of initial training of an AI model using a large-scale dataset prior to a particular task. Pre-training typically employs a deep learning model and a supervised training method. The deep learning model is a machine learning model based on a neural network, consists of a plurality of neural network layers, has a deep structure, and comprises a feedforward neural network, a circulating neural network, a long-term and short-term memory network, a converter, a generation countermeasure network and the like; in supervised training, the training data of the model includes input samples and corresponding labels or target outputs, and the goal of the supervised training is to let the model learn the mapping between the input samples and the labels so that the corresponding labels can be predicted given a new input sample.
The output of the AI model may include at least one user interest data, and a probability value for each user interest data. The historical behavior information is input into an AI model, and the computer calculates and feeds back the user interest data and probability values of the user interest data.
The focus data may refer to data that a user focuses on and needs to be preferentially presented to the user. The manner of determining the attention data of the user may determine the attention data in the candidate data using at least one of the user interest data according to the output of the AI model, the probability value of each of the user interest data, and the domain information of the candidate data to be presented to the user.
S103, determining a visualization strategy of the data of interest according to the data of interest and the evolution time of the data of interest;
visualization policies may refer to policies and methods that effectively convey and present data, and may specify visualization styles and dynamic presentation parameters.
The amount of data of the data of interest determines the visualization style in the visualization strategy.
The evolution time of the data of interest may refer to the duration of the entire course of the data of interest, i.e. the time span of the evolution time of the data of interest. The time span of the evolution time of the data of interest determines the dynamic presentation parameters in the visualization strategy.
The method for determining the visualization strategy of the data of interest can adopt a method for determining the visualization style in the visualization strategy according to the data quantity of the data of interest and determining the dynamic display parameters in the visualization strategy according to the time span of the evolution time.
S104, based on the visualization strategy, carrying out dynamic visualization display on the data of interest.
The dynamic visual display mode can be adopted by using a proper dynamic visual tool or library, the dynamic visual display is created according to a visual strategy, and the client receives the concerned data and the dynamic visual display data and displays the dynamic visual display.
Among other things, dynamic visualizations tools or libraries may include D3.js, plotly, matplotlib, tableau, etc.
In the embodiment of the application, historical behavior information of a user is obtained; inputting the historical behavior information into a pre-trained AI model, and determining the attention data of a user according to the output result of the AI model; determining a visualization strategy of the data of interest according to the data of interest and the evolution time of the data of interest; and dynamically and visually displaying the data of interest based on the visual strategy. According to the technical scheme, the data of interest of the user can be determined by inputting the historical behavior information into the pre-trained AI model, and the user can be helped to quickly acquire key information and analyze the key information by determining the visual strategy and carrying out dynamic visual display, so that the browsing experience of the user is optimized.
Example two
Fig. 2 is a flow chart of a data visualization method based on an AI model according to a second embodiment of the present application. The scheme makes better improvement on the embodiment, and the specific improvement is as follows: acquiring historical behavior information of a user, including: acquiring historical browsing information and operation behavior information of a user; the method further comprises the steps of: acquiring personal image information and operation equipment information of a user; accordingly, inputting the historical behavior information into a pre-trained AI model includes: and inputting the history browsing information, the operation behavior information, the personal portrait information and the operation equipment information into a pre-trained AI model.
As shown in fig. 2, the method specifically comprises the following steps:
s201, acquiring historical browsing information and operation behavior information of a user;
the history browsing information refers to recorded information for data accessed by the user in past browsing activities. By detecting the location, size, and rollability of the data element to determine whether the data element is visible in the current window, intersection Observer API (cross viewer) may be used to snoop for data elements entering or exiting the window, for example. If the data element is visible in the current window, the data element is recorded in the log file.
The operation behavior information may refer to record information of interaction behavior and operation of a user, and may include click event, hover time, scroll line, form submission, keyboard event, page navigation, pop-up window and modal frame, etc., by using an event monitor to monitor events occurring on a current page, the operation behavior information may be obtained, and the operation behavior information may be recorded in a log file to form an operation behavior record. Among them, an event listener is a mechanism for capturing and processing specific events.
By acquiring and reading the log file, the history browsing information and the operation behavior information can be acquired.
S202, acquiring personal image information and operation equipment information of a user;
personal portrayal information refers to data describing characteristics, attributes and behaviors of a user's individual for describing and analyzing the individual's characteristics and interests. The method for obtaining the personal portrait information of the user can adopt the method that the user inputs the personal portrait information when registering an account number of the user, the server receives the personal portrait information and records and stores the personal portrait information, and the method can also adopt the method that the personal portrait information is extracted and deduced from mass data by utilizing big data analysis and mining technology.
The operation device information may be information capable of uniquely identifying the current operation device, and in particular, may refer to an IP address of the operation device. The IP address (Internet Protocol Address) is a set of digits in the internet that are used to identify and locate devices, consisting of 32-bit or 128-bit binary digits, that are used to uniquely identify each device in the network. In most home and office networks, IP addresses are typically dynamically assigned to an operating device by a router via DHCP protocol (Dynamic Host Configuration Protocol ), the operating device sends a request to the router when connecting to the network, the router assigns an available IP address to the operating device, and the current IP address of the current operating device can be viewed at the network setup interface of the computer.
S203, inputting the history browsing information, the operation behavior information, the personal portrait information and the operation equipment information into a pre-trained AI model;
the history browsing information, the operation behavior information, the personal portrait information and the operation equipment information are input into an AI model, and the computer calculates and feeds back the user interest data and probability values of the user interest data.
S204, according to the output result of the AI model, determining the attention data of the user;
s205, determining a visualization strategy of the data of interest according to the data of interest and the evolution time of the data of interest;
s206, based on the visualization strategy, carrying out dynamic visualization display on the data of interest.
The method has the advantages that more basis can be provided for calculation and analysis of the AI model by acquiring the historical browsing information, the operation behavior information, the personal portrait information and the operation equipment information, so that the accuracy of the output result of the AI model is improved.
Example III
Fig. 3 is a flow chart of a data visualization method based on an AI model according to a third embodiment of the present application. The scheme makes better improvement on the first embodiment, and the specific improvement is as follows: determining a visualization strategy of the data of interest according to the data of interest and the evolution time of the data of interest, wherein the visualization strategy comprises the following steps: and determining a visualization strategy of the data of interest according to the data quantity of the data of interest and the time span of the evolution time of the data of interest.
As shown in fig. 3, the method specifically comprises the following steps:
s301, acquiring historical behavior information of a user;
s302, inputting the historical behavior information into a pre-trained AI model, and determining the attention data of a user according to the output result of the AI model;
s303, determining a visualization strategy of the data of interest according to the data quantity of the data of interest and the time span of the evolution time of the data of interest.
The data amount may refer to a size or capacity of data of interest, and may be in bytes (bytes). The byte number acquisition method is used for acquiring the byte number of each data element in the data of interest, and the byte numbers of each data element are summed to obtain the total byte number as the data amount of the data of interest. The BYTE number obtaining method may be sys.getsizeof () function in Python, sizeof () function in C/c++, or BYTE constant of java.long. Intelger class in Java, etc.
A time span refers to a distance or range in time that describes the duration of an event, process or period of time, and in particular, the duration of the entire course of change of data of interest. The time length obtained by recording the beginning change time and the ending change time of the data of interest and subtracting the beginning change time from the ending change time is the time span of the evolution time of the data of interest.
The method for determining the visualization strategy of the data of interest can adopt a method for determining the visualization style in the visualization strategy according to the data quantity of the data of interest and determining the dynamic display parameters in the visualization strategy according to the time span of the evolution time.
In this technical solution, optionally, determining a visualization policy of the data of interest according to the data amount of the data of interest and a time span of an evolution time of the data of interest includes:
determining a visualization style in the visualization strategy according to the data volume of the concerned data; wherein the visualization style comprises: at least one of dynamic chart, geographic dimension visualization, 3D visualization, interactive visualization, text visualization, and big data visualization;
determining dynamic display parameters in the visualization strategy according to the time span of the evolution time; wherein the dynamic presentation parameters include a dynamic frame number and a dynamic frame rate.
Visualization styles refer to the appearance and style used in data visualization to present data, and may include dynamic charts, geographic dimension visualization, 3D visualization, interactive visualization, text visualization, and big data visualization, among others. Specifically, the dynamic chart shows the change trend and the evolution process of the data in an animation or time sequence mode, so that a user can be helped to better understand the dynamic property and trend change of the data; the geographic dimension visualization associates data with geographic space, displays the data by a map or other geographic information system tools, and can present information such as geographic positions, regional differences, spatial distribution and the like; the 3D visualization displays data by utilizing a three-dimensional graphic technology, so that a user can observe the structure and the relation of the data in a three-dimensional space, and the method is suitable for displaying a data set with depth and complex association; interactive visualizations allow users to actively interact and explore with the data visualizations, and users can select, filter, zoom, pan or hover over the chart to obtain detailed information to explore different perspectives and associations of the data; the text visualization presents the structure and the content of text data in a graphical mode, and can comprise word cloud, text network, text matrix and other forms, and is used for analyzing text semantic, emotion and other information; big data visualization involves processing and exposing large-scale data sets, using specific techniques and algorithms to process and present large amounts of data to help users find patterns, trends, and insights.
It will be appreciated that different visualization styles differ for the summarization abstraction capability of the data, the larger the amount of data of interest data, the better the summarization abstraction capability should be selected.
The dynamic display parameters refer to parameters for controlling the visual change effect, including the number of dynamic frames and the dynamic frame rate. The number of dynamic frames refers to the number of static images used in dynamic visualization, which determines the duration and smoothness of the animation; the dynamic frame rate refers to the number of frames played per second in dynamic visualization, and determines the smoothness of the animation and the continuity in visual perception.
It will be appreciated that the longer the time span of the evolution time, the greater the number of dynamic frames and the greater the dynamic frame rate.
The visual style and dynamic display parameters are determined, so that the accurate control of the dynamic visual display effect can be realized, and the requirements of users are met.
S304, based on the visualization strategy, dynamic visualization display is carried out on the data of interest.
The method has the advantages that the visualization strategy of the concerned data is determined according to the data quantity of the concerned data and the time span of the evolution time of the concerned data, so that the display result of dynamic visualization can be more helpful for a user to acquire and analyze the data concerned by the user.
Example IV
Fig. 4 is a flowchart of a data visualization method based on an AI model according to a fourth embodiment of the present application. The scheme makes better improvement on the first embodiment, and the specific improvement is as follows: inputting the historical behavior information into a pre-trained AI model, and determining the attention data of the user according to the output result of the AI model, wherein the method comprises the following steps: and inputting the historical behavior information into a pre-trained AI model, and determining the attention data of the user according to at least one user interest data output by the AI model and the probability value of each user interest data.
As shown in fig. 4, the method specifically comprises the following steps:
s401, acquiring historical browsing information and operation behavior information of a user;
s402, inputting the historical behavior information into a pre-trained AI model, and determining the attention data of the user according to at least one user interest data output by the AI model and the probability value of each user interest data.
User interest data may refer to data that may be of interest to a user. The probability value is a value indicating the degree of likelihood of occurrence of an event, and specifically, a value indicating the degree of interest of the user in the data.
The manner of determining the attention data of the user may determine the attention data in the candidate data using at least one of the user interest data according to the output of the AI model, the probability value of each of the user interest data, and the domain information of the candidate data to be presented to the user.
In this technical solution, optionally, determining the data of interest of the user according to at least one user interest data output by the AI model and the probability value of each user interest data includes:
and determining the concerned data in the candidate data according to the at least one user interest data outputted by the AI model, the probability value of each user interest data and the domain information of the candidate data to be displayed to the user.
Candidate data refers to all data related to each user interest data. The domain information may refer to a specific domain or subject related to the candidate data, and may be largely classified into finance, medical health, education, and the like.
The method for determining the concerned data in the candidate data can adopt the mode of sorting the user interest data from large to small according to the probability value, and selecting the candidate data with preset data quantity as the concerned data according to the sorting result. The preset data amount can be set according to the data capacity of dynamic visualization, the data content of candidate data and the like.
The method has the advantages that the concerned data in the candidate data is determined according to at least one user interest data outputted by the AI model, the probability value of each user interest data and the field information of the candidate data to be displayed to the user, so that the output result of the AI model can be checked, the correlation of the concerned data is improved, and the browsing experience of the user is optimized.
In this technical solution, optionally, before determining the data of interest in the candidate data, the method further includes:
the field to which the historical behavior information pertains is obtained;
determining the confidence level of the output result of the AI model of the concerned data according to the domain correlation degree of the domain of the historical behavior information and the domain information of the candidate data to be displayed to the user;
determining a data amount adjustment range of the data of interest according to the confidence;
determining the data quantity of the data of interest screened from the candidate data according to the data quantity adjustment range;
the domain is the domain information of the historical behavior information, namely the domain information of each data related to the historical behavior information. The manner of acquiring the domain of the historical behavior information may be to determine domain information of each data according to terms, tags or features contained in each data related to the historical behavior information.
And calculating the total data quantity of all the data related to the historical behavior information, calculating the data quantity of the data, of which the domain information is consistent with the domain information of the candidate data, in all the data, dividing the obtained data quantity by the total data quantity, and obtaining the ratio, namely the domain correlation degree of the domain of the historical behavior information and the domain information of the candidate data to be displayed to the user.
Confidence refers to the assessment of the degree of trust or reliability of a point of view, information or conclusion. And acquiring the domain correlation degree of the domain of the historical behavior information and the domain information of each group of candidate data, and calculating the average value of all acquired domain correlation degrees as the confidence degree of the output result of the AI model.
It will be appreciated that the higher the confidence, the higher the degree of attention to the candidate data, and the greater the amount of data that may be presented to the user for the data of interest. The data volume adjustment range is the preset data volume, the total data volume of the candidate data is obtained, the confidence coefficient and the obtained total data volume are multiplied, and the obtained result is the data volume adjustment range of the concerned data.
And summarizing and compressing the candidate data according to the data quantity adjustment range and the ordering sequence of the user interest data, so that the data quantity of the concerned data is smaller than the data quantity adjustment range.
The method has the advantages that the confidence coefficient of the output result of the AI model is determined, the data size adjustment range of the concerned data is determined according to the confidence coefficient, the accurate control of the data size of the concerned data can be realized, and the requirements of users can be fully met.
S403, determining a visualization strategy of the data of interest according to the data of interest and the evolution time of the data of interest;
s404, based on the visualization strategy, dynamic visualization display is carried out on the data of interest.
The method has the advantages that the attention data of the user is determined according to at least one user interest data output by the AI model and the probability value of each user interest data, so that the refining property and the correlation of the attention data can be improved, the output result of the AI model can be verified and adjusted, and the accuracy of the AI model is improved.
Example five
Fig. 5 is a schematic structural diagram of an AI model-based data visualization device provided in a fifth embodiment of the present application. As shown in fig. 5, the apparatus includes:
a historical behavior acquisition module 510, configured to acquire historical behavior information of a user;
the attention data determining module 520 is configured to input the historical behavior information into a pre-trained AI model, and determine attention data of a user according to an output result of the AI model;
a visualization policy determining module 530, configured to determine a visualization policy of the data of interest according to the data of interest and the evolution time of the data of interest;
and the visual display module 540 is configured to dynamically and visually display the data of interest based on the visual policy.
In the embodiment of the application, a historical behavior acquisition module is used for acquiring historical behavior information of a user; the attention data determining module is used for inputting the historical behavior information into a pre-trained AI model and determining attention data of a user according to an output result of the AI model; the visualization strategy determining module is used for determining a visualization strategy of the concerned data according to the concerned data and the evolution time of the concerned data; and the visual display module is used for dynamically and visually displaying the data of interest based on the visual strategy. According to the data visualization device based on the AI model, through inputting the historical behavior information into the pre-trained AI model, the data of interest of the user can be determined, and through determining the visualization strategy and carrying out dynamic visualization display, the user can be helped to quickly acquire key information, analyze the key information and optimize the browsing experience of the user.
The data visualization device based on the AI model in the embodiment of the application may be a device, or may be a component, an integrated circuit, or a chip in a terminal. The device may be a mobile electronic device or a non-mobile electronic device. By way of example, the mobile electronic device may be a cell phone, tablet computer, notebook computer, palm computer, vehicle-mounted electronic device, wearable device, ultra-mobile personal computer (ultra-mobile personal computer, UMPC), netbook or personal digital assistant (personal digital assistant, PDA), etc., and the non-mobile electronic device may be a server, network attached storage (Network Attached Storage, NAS), personal computer (personal computer, PC), television (TV), teller machine or self-service machine, etc., and the embodiments of the present application are not limited in particular.
The AI model-based data visualization device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems, which is not specifically limited in the embodiments of the present application.
The data visualization device based on the AI model provided in this embodiment of the present application can implement each process implemented in the first to fourth embodiments, and in order to avoid repetition, a description thereof is omitted here.
Example six
As shown in fig. 6, the embodiment of the present application further provides an electronic device 600, including a processor 601, a memory 602, and a program or an instruction stored in the memory 602 and capable of being executed on the processor 601, where the program or the instruction implements each process of the embodiment of the data visualization device based on the AI model when executed by the processor 601, and the process can achieve the same technical effects, and for avoiding repetition, a detailed description is omitted herein.
The electronic device in the embodiment of the application includes the mobile electronic device and the non-mobile electronic device described above.
Example seven
The embodiment of the present application further provides a readable storage medium, where a program or an instruction is stored, and when the program or the instruction is executed by a processor, the processes of the embodiment of the data visualization device based on the AI model are implemented, and the same technical effects can be achieved, so that repetition is avoided, and no redundant description is provided herein.
Wherein the processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium such as a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and the like.
Example eight
The embodiment of the application further provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled with the processor, the processor is configured to run a program or an instruction, implement each process of the embodiment of the data visualization device based on the AI model, and achieve the same technical effect, so that repetition is avoided, and no further description is provided here.
It should be understood that the chips referred to in the embodiments of the present application may also be referred to as system-on-chip chips, chip systems, or system-on-chip chips, etc.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solutions of the present application may be embodied essentially or in a part contributing to the prior art in the form of a computer software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), comprising several instructions for causing a terminal (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the methods described in the embodiments of the present application.
The embodiments of the present application have been described above with reference to the accompanying drawings, but the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those of ordinary skill in the art without departing from the spirit of the present application and the scope of the claims, which are also within the protection of the present application.
The foregoing description is only of the preferred embodiments of the present application and the technical principles employed. The present application is not limited to the specific embodiments described herein, but is capable of numerous obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the present application. Therefore, while the present application has been described in connection with the above embodiments, the present application is not limited to the above embodiments, but may include many other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the claims.