Disclosure of Invention
The embodiment of the application provides a visualization method, visualization equipment and visualization media based on data comprehensive analysis, and the visualization method, the visualization equipment and the visualization media are used for solving the technical problems that the conventional manual treatment of daily business data and the information study and judgment need to depend on professional personnel, the labor cost is high, the time consumption is long, and the continuous and efficient operation is difficult to maintain.
In a first aspect, an embodiment of the present application provides a visualization method based on data comprehensive analysis, where the method includes: collecting first data; performing data preprocessing on the first data to obtain second data; acquiring a first data key value contained in second data; determining a data model corresponding to the second data according to the first data key value; and importing the second data into the data model to generate a data research and judgment report.
According to the implementation method provided by the embodiment of the application, the data format arrangement, the data diagram selection and the acquisition of the daily service data for providing study and judgment information are realized by collecting the first data, and the time loss caused by manually selecting the data is avoided; the second data is obtained by preprocessing the first data, so that meaningless or repeated data in the first data are cleaned, statistics of the meaningless data is avoided, and optimized data are provided for subsequent research on daily service data; the second data are imported into the data model to obtain the data study and judgment report, so that the automatic selection of a proper chart and the visual display of the data are realized, a basis is provided for scientific decision-making, the labor cost is reduced, and the working efficiency is improved.
In one implementation of the present application, before acquiring the first data, the method further includes: acquiring a task instruction, wherein the task instruction comprises a second data key value; and acquiring the first data according to the second data key value.
According to the implementation method provided by the embodiment of the application, the second data key value in the task instruction is obtained, and the daily business data which needs to be subjected to data format arrangement, data diagram selection and judgment information providing are accurately acquired. The collection of unnecessary data is avoided, and the working efficiency is improved.
In one implementation of the present application, before acquiring the first data, the method further includes: acquiring a task instruction, wherein the task instruction comprises a second data key value and an uploading acquisition instruction; acquiring third data uploaded by a user according to the uploading acquisition instruction; and acquiring first data according to the second data key value and the third data.
According to the implementation method provided by the embodiment of the application, the collection of daily business data is achieved by acquiring the third data uploaded by the user. By acquiring the second data key value in the task instruction, the method and the device realize accurate acquisition of daily business data (first data) which needs data format arrangement, data chart selection and research and judgment information provision from the third data, and realize accurate acquisition of data uploaded by a user.
In an implementation manner of the present application, performing data preprocessing on first data to obtain second data specifically includes: normalizing the first data to normalize the data value of the first data to be in the range of 0 mean value and 1 variance; performing data cleaning on the first data after normalization processing; after data cleaning, screening first data meeting preset constraint conditions to obtain second data.
According to the implementation method provided by the embodiment of the application, the repeated and meaningless data in the first data are cleaned by preprocessing the first data, and invalid statistics of the flaw data is avoided. By normalizing the first data, the processing process of the first data is optimized, and the contribution of each feature in the first data to the processing result is the same. The first data meeting the preset constraint conditions are screened, so that personalized data sorting and analysis of the user are met.
In one implementation of the present application, after performing data preprocessing on the first data to obtain the second data, the method further includes: performing word segmentation processing on the second data to obtain a plurality of words; determining a first keyword corresponding to the second data according to a preset keyword algorithm and a plurality of word segments; and determining a first data key value corresponding to the second data according to the first keyword and a preset key dictionary, wherein the preset key dictionary comprises the first keyword and the first data key value.
According to the implementation method provided by the embodiment of the application, the second data is subjected to word segmentation processing, so that the first keywords corresponding to the second data are effectively acquired; through the first key words and the preset key words, the first data key values corresponding to the second data are quickly acquired.
In an implementation manner of the present application, importing the second data into the data model, and generating a data studying and judging report specifically includes: acquiring a second keyword of second data; determining a study and judgment conclusion according to a preset study and judgment strategy, a second keyword and a study and judgment conclusion database; and importing the research and judgment conclusion into a data model to generate a data research and judgment report.
According to the implementation method provided by the embodiment of the application, the study and judgment conclusion is determined according to the preset study and judgment strategy, the second keyword and the study and judgment conclusion database, the automatic analysis and processing of the daily business data are realized, and the intelligent study and judgment of the daily business data are further realized; the research and judgment conclusion is automatically generated by the computer, so that intelligent and automatic scientific decision is realized, and the labor cost is reduced.
In an implementation manner of the present application, determining a study and judgment conclusion according to a preset study and judgment policy, a second keyword, and a study and judgment conclusion database specifically includes: determining the attribution area of the second data in the research and judgment conclusion database according to the second keyword; determining the attribution type of the second data corresponding to the attribution area according to the second data and the attribution area; and determining a study conclusion corresponding to the second data from the study conclusion database according to the attribution type.
According to the implementation method provided by the embodiment of the application, the attribution area of the second data in the research and judgment conclusion database is obtained by determining the second keyword of the second data, so that the regional search of data resources is realized, and the time loss caused by searching all the research and judgment conclusion databases is avoided; by determining the data attribution type of the second data, the research and judgment conclusion corresponding to the second data is accurately and quickly searched in the research and judgment conclusion database, and resource loss caused by the fact that the attribution type is screened from all the attribution types is avoided.
In one implementation of the present application, the method further comprises: when a downloading instruction is acquired, a downloading report is generated; when the first data is detected to be changed, triggering an acquisition instruction; and acquiring the first data again according to the acquisition instruction so as to update the data studying and judging report.
According to the implementation method provided by the embodiment of the application, the downloading report is generated, the offline reading of the user is realized, and convenience is provided for the user to read the data study and judgment report. By updating the data studying and judging report again, the real-time updating of the data is realized, and the accuracy of the data studying and judging report is ensured.
In a second aspect, an embodiment of the present application further provides a visualization device based on data analysis-by-synthesis, including: a processor; and a memory having executable code stored thereon, the executable code, when executed, causing the processor to perform a visualization method based on data analysis-by-synthesis as described above.
In a third aspect, an embodiment of the present application further provides a non-volatile computer storage medium, where computer instructions are stored, and when the computer instructions are executed, the computer instructions implement the above visualization method based on data analysis-by-synthesis.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The embodiment of the application provides a visualization method, visualization equipment and visualization media based on data comprehensive analysis, wherein first data are collected through a server, and the first data can be data of the server or data uploaded by an external user; after the first data is acquired, by performing data preprocessing on the first data, for example, performing normalization processing on the first data, smoothing processing on the data is realized, so that the server can more easily process the first data. Determining a data model corresponding to the second data by acquiring a first data key value in the second data; and then the second data is imported into the data model, so that the automatic generation of the data studying and judging report is realized. After the data studying and judging report is generated, a downloading interface is provided for the required personnel to download. In addition, when the server detects that the first data changes, a collection instruction can be automatically generated so as to update the data research and judgment report.
It should be noted that, in the visualization method based on data analysis-by-synthesis proposed in the embodiment of the present application, the execution subject is a server.
The technical solutions proposed in the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a visualization method based on data comprehensive analysis according to an embodiment of the present application. As shown in fig. 1, the visualization method provided in the embodiment of the present application mainly includes the following steps:
step 101, collecting first data.
Specifically, a task instruction is generated in the server based on an operation of the user. After the server acquires the task instruction, the server collects data corresponding to a second data key value in the server memory according to the second data key value in the task instruction, and sets the collected data as first data. It should be noted that the second data key is a preset collection condition (for example, when the milk tea is the second data key, the server will collect data related to the milk tea). In addition, the first data collected in the server memory is working event data, wherein the working event data at least comprises: and dispatching the work tasks, reporting problems, reporting hidden dangers and other relevant data generated in the event. Further specifically, the server collects the work event data from the server memory through the preset interface, and the setting method of the preset interface may be implemented by an existing method or technology, which is not limited in the embodiment of the present application. The number of preset interfaces may be any feasible number, and a person skilled in the art may determine a specific value of the number of preset interfaces through multiple experiments.
In addition, the data in the memory of the server can be collected into the first data, the user uploading service is further provided, and the server can collect the data uploaded by the user into the first data. Specifically, a task instruction is generated based on the operation of a user, wherein the task instruction comprises a second data key value and an uploading acquisition instruction. And the server acquires third data uploaded by the user according to the uploading acquisition instruction, and acquires the third data according to the second data key value to acquire the first data. It should be noted that the second data key value is a preset collection condition (for example, when milk tea is the second data key value, the server collects data related to milk tea in third data), and the third data is data uploaded by the user.
And finishing the acquisition of the first data.
And 102, performing data preprocessing on the first data to obtain second data.
It should be noted that the data preprocessing includes data normalization, data cleaning, and data constraint, and the second data is data obtained by preprocessing the first data.
Specifically, the server, according to a normalization formula:
and performing data normalization processing on the first data, and normalizing the data value of the first data to be in a range with a mean value of 0 and a variance of 1. Wherein mean is the mean, σ is the standard deviation, X is the value before normalization, and X' is the value after normalization.
After normalization processing is completed, the data is cleaned, specifically, repeated and redundant data is screened and removed, missing data is supplemented completely, and error data is corrected or deleted and finally sorted into second data. It should be noted that the method for cleaning data may be implemented by an existing method or technology, and this is not limited in the embodiment of the present application.
After the data cleaning is finished, the server restricts the first data subjected to the data cleaning according to preset restriction conditions to obtain second data. It should be noted that the preset constraint condition is used for constraining the first data for completing data cleansing, for example, when the preset constraint condition is greater than 80, the server screens the data greater than 80 from the first data for completing data cleansing. In addition, the content of the preset constraint condition may be any feasible content, and a person skilled in the art may determine the specific content of the preset constraint condition through multiple experiments.
It should be noted that, the present application is used for automatically processing and analyzing a plurality of daily service data, so that the first data (whether the work event data acquired through the server memory or the data uploaded by the user) is composed of a plurality of daily service data, and the second data acquired according to the first data is also composed of a plurality of daily service data.
At this point, the preprocessing of the first data is completed, and the second data is obtained from the first data.
And 103, acquiring a first data key value contained in the second data.
Specifically, the server performs word segmentation processing on the second data through the final word segmentation to obtain a plurality of word segmentations, and it should be noted that the application uses the disabled word bank in the process of performing word segmentation processing on the second data, wherein the disabled word bank is used for deleting meaningless word segmentations, the content of the disabled word bank may be any feasible content, and a person skilled in the art may determine the specific content of the disabled word bank through multiple experiments.
After completing word segmentation processing, the server calculates the weights of a plurality of segmented words according to a preset keyword algorithm (such as a TextRank algorithm, an LDA algorithm and a TPR-TextRank algorithm), and selects the segmented word with the largest weight as a first keyword. The server brings the first keyword into a preset key dictionary, and searches a first data key value related to the first keyword from the preset key dictionary. It should be noted that the content of the first data key value may be any feasible content, and those skilled in the art may determine the specific content of the first data key value through multiple experiments.
It should be noted that the server presets different first data key values according to the content types of the second data, that is, the first data key values are used to indicate different content types of the second data.
And obtaining the first data key value from the second data.
And step 104, determining a data model corresponding to the second data according to the first data key value.
It should be noted that, the present application is used for automatically processing and analyzing a plurality of daily service data, so that the first data (whether the work event data acquired through the server memory or the data uploaded by the user) is composed of a plurality of daily service data, and the second data acquired according to the first data is also composed of a plurality of daily service data.
It should be noted that the data model is a template for displaying the second data, and the data model includes a basic component, a visualization component, and a conclusion studying component. The basic component is used for counting the quantity of each item of daily business data in the second data; the visualization component is used for displaying various daily business data (for example, the proportion condition of a certain item of daily business data) in the second data; and the studying and judging conclusion component is used for analyzing each daily service data and generating a studying and judging conclusion. In addition, the styles of the visualization component include bar charts, line charts, pie charts, area charts, water wave charts, and the like. The study conclusion component selects a study conclusion from the study conclusion database. The content in the data model and the content in the study conclusion database may be any feasible content, and those skilled in the art may determine the specific content of the data model and the study conclusion database through multiple experiments.
Specifically, the server presets a corresponding relationship between a preset data model and a first data key value, for example, when the first data key value of the second data is a pension, the data model of the second data is a pension data model. And after the server obtains the first data key value of the second data model, importing the second data into the corresponding data model according to the corresponding relation between the preset data model and the first data key value.
And the server finds the data model corresponding to the second data and imports the second data into the data model.
And 105, importing the second data into the data model to generate a data study and judgment report.
It should be noted that the data study and judgment report is composed of three parts: basic data, visual charts and studying and judging conclusions. The basic data is a statistic value of each daily business data in the second data, and the visual chart is a display chart of each daily business data in the second data; the research and judgment conclusion is the analysis result of each daily service data.
Specifically, after the second data is imported into the data model, the server obtains a second keyword of the second data, where it should be noted that the second keyword is used to represent a type name of the daily business data. The server can determine the specific type of each daily business data contained in the second data according to the second keyword. Then, the server determines a study and judgment conclusion corresponding to the second keyword (that is, determines a study and judgment conclusion of the daily business data corresponding to the second keyword) according to a preset study and judgment policy, the second keyword and a study and judgment conclusion database.
Further specifically, the server searches an attribution area corresponding to the second keyword in a research and judgment conclusion database according to the second keyword; after the attribution area is determined, the server acquires each attribution type of the attribution area, simultaneously acquires the proportion condition of each attribution type in the second data, and determines the attribution type with the highest proportion as the attribution type corresponding to the second data in the attribution area; and after determining the attribution type corresponding to the second data, the server extracts the judging conclusion corresponding to the attribution type from the judging conclusion database. And importing the research and judgment conclusion into the data model to generate a data research and judgment report.
It should be noted that the position of the basic data, the visual chart and the study and judgment conclusion in the data study and judgment report may be any feasible position, and those skilled in the art may determine the specific position of the basic data, the visual chart and the study and judgment conclusion in the data study and judgment report through many experiments.
Thus, the data study and judgment report is automatically acquired.
In addition, the server provides a downloading service, and when the server acquires a downloading instruction, the server generates a downloading report by the data studying and judging report; in addition, when the server detects that the first data is changed, the server automatically generates a collection instruction; and according to the acquisition instruction, the server acquires the first data again so as to update the data studying and judging report.
The above is a method embodiment in the present application, and based on the same inventive concept, the present application embodiment further provides an online learning device based on data ambiguity. As shown in fig. 2, the apparatus includes: a processor; and a memory having executable code stored thereon, the executable code, when executed, causing the processor to perform a visualization method based on data analysis-by-synthesis as in the above embodiments.
Specifically, the server sends an execution instruction to the memory through the bus, and when the memory receives the execution instruction, sends an execution signal to the processor through the bus so as to activate the processor. It should be noted that, the acquisition module in the processor is used for acquiring the first data; the acquisition module is used for carrying out data preprocessing on the first data to acquire second data; an obtaining module, configured to obtain a first data key included in the second data; the determining module is used for determining a data model corresponding to the second data according to the first data key value; and the generating module is used for importing the second data into the data model and generating a data studying and judging report.
In addition, the embodiment of the present application also provides a non-volatile computer storage medium, on which executable instructions are stored, and when the executable instructions are executed, the visualization method based on the data comprehensive analysis is implemented. After the user can analyze the data through the medium, the visual data chart and the study and judgment conclusion are obtained, and the study and judgment report is generated, so that the problems that time is wasted due to repeated work in work summary, the chart is inaccurate to use, the study and judgment conclusion is not standard and the like are solved, a basis is provided for scientific decision making, the labor cost is reduced, and the working efficiency is improved.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
It should also be noted that 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 an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of the present application shall be included in the scope of the claims of the present application.