CN117874315B - User demand analysis display method, system, computer equipment and storage medium - Google Patents
User demand analysis display method, system, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117874315B CN117874315B CN202410281762.7A CN202410281762A CN117874315B CN 117874315 B CN117874315 B CN 117874315B CN 202410281762 A CN202410281762 A CN 202410281762A CN 117874315 B CN117874315 B CN 117874315B
- Authority
- CN
- China
- Prior art keywords
- data
- demand analysis
- time
- mark
- time sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 213
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000010586 diagram Methods 0.000 claims abstract description 46
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000004140 cleaning Methods 0.000 claims description 23
- 238000003491 array Methods 0.000 claims description 19
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 6
- 230000006835 compression Effects 0.000 claims description 6
- 238000007906 compression Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 230000000875 corresponding effect Effects 0.000 description 49
- 230000000007 visual effect Effects 0.000 description 10
- 230000008859 change Effects 0.000 description 7
- 238000013461 design Methods 0.000 description 6
- 239000003550 marker Substances 0.000 description 6
- 238000007405 data analysis Methods 0.000 description 5
- 238000013079 data visualisation Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000012098 association analyses Methods 0.000 description 3
- 238000013480 data collection Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/904—Browsing; Visualisation therefor
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of data and image processing, and discloses a user demand analysis and display method, a system, computer equipment and a storage medium. Wherein the method comprises the following steps: establishing a demand analysis index set; collecting a plurality of time sequence data corresponding to each demand analysis index in a target period; dividing a target period into a plurality of periods; dividing each data sample according to the period length; determining a current demand analysis index from the demand analysis index set; in each period, acquiring global association support between the current demand analysis index and each of the other demand analysis indexes by utilizing a plurality of data subsamples; for each remaining demand analysis index, PAM modulation is carried out by utilizing a plurality of global association supporters obtained in a plurality of periods to output a PAM waveform diagram; and superposing the plurality of PAM wave patterns to obtain a display diagram for user demand analysis. The invention can display the multidimensional user demand analysis index.
Description
Technical Field
The invention relates to the technical field of data and image processing, in particular to a user demand analysis display method, a system, computer equipment and a storage medium.
Background
Data visualization is a scientific and technological study on the visual manifestations of data. The enterprise is in order to improve the matching degree of the product and market demand and provide the product which is more fit with the actual demand for users, the enterprise generally adopts a user demand analysis mode to provide guidance for the subsequent establishment of product strategies, namely, the enterprise obtains the association degree between user demand analysis indexes through data acquisition, index extraction, data analysis and other modes and carries out visual display on the association degree, so that the internal relation between the user demand analysis indexes can be more intuitively obtained. At present, common data visualization display means mainly comprise: tables, histograms, scatter plots, topology, two-dimensional/three-dimensional models, and the like. The various data visual display means can intuitively reflect the data state, but the following disadvantages also exist: on one hand, the single data visualization display means is difficult to embody the association relation between multi-dimensional data, and the association relation between the data can be realized only by carrying out multiple times of graphic switching and graphic comparison; on the other hand, the multidimensional data is displayed through a unified visual interface by combining various data visual display means, and the association relation between the data can be embodied, but the interface is complex easily and difficult to distinguish.
Disclosure of Invention
The invention aims to provide a user demand analysis display method, a system, computer equipment and a storage medium, which solve the problems that an image interface is complex and association relations among data indexes are difficult to intuitively embody when a multi-dimensional user demand analysis index is displayed by using the existing data visualization display method.
The invention is realized by the following technical scheme:
In one aspect, a method for analyzing and displaying user requirements is provided, including the following steps: establishing a demand analysis index set; the demand analysis index set comprises a plurality of demand analysis indexes to be analyzed; collecting a plurality of time sequence data corresponding to each demand analysis index in a target period to obtain a data sample corresponding to each demand analysis index; dividing a target period into a plurality of periods; dividing each data sample according to the period length to obtain a plurality of data sub-samples corresponding to each data sample; determining a current demand analysis index from the demand analysis index set; in each period, acquiring global association support between the current demand analysis index and each other demand analysis index by utilizing a plurality of data subsamples to acquire a plurality of global association support in each period; performing PAM modulation by utilizing a plurality of global associated supporters obtained in a plurality of periods aiming at each remaining demand analysis index to obtain a PAM waveform diagram corresponding to each remaining demand analysis index; and superposing the plurality of PAM wave patterns to obtain a display diagram for user demand analysis.
Further, the target period includes a plurality of continuous data acquisition time points.
Further, before the target period is divided into a plurality of periods, the method includes the following steps: carrying out data cleaning on each data sample to obtain a plurality of cleaned data samples; and compressing the target time period according to the plurality of cleaned data samples to obtain a new target time period.
Further, the data cleaning comprises the following steps: adding a time tag to each time sequence data; the time tag is a data acquisition time point corresponding to time sequence data; detecting whether each time sequence data is empty, and adding a first mark for each detected empty data; associating each first mark with a corresponding data acquisition time point; detecting whether the time sequence data without the first mark is noise data or not, and adding a second mark for each detected noise data; associating each second mark with a corresponding data acquisition time point; collecting all first marks and all second marks of each remaining data sample; adding a third mark for each time sequence data according to the data acquisition time point associated with each first mark; the added third mark and the acquired first mark have the same data acquisition time point; adding a fourth mark for each time sequence data according to the data acquisition time point associated with each acquired second mark; the added fourth mark and the acquired second mark have the same data acquisition time point; deleting all time sequence data with the first mark, the second mark, the third mark and the fourth mark to obtain a cleaned data sample;
further, compressing the target period includes the steps of: adding a new time tag for each time sequence data in each data sample after cleaning; a new time tag corresponds to a new data acquisition time point; the added multiple new data acquisition time points are continuous; the time unit of each new data acquisition time point is set to seconds.
Further, before obtaining the global association support degree, the method comprises the following steps: acquiring a data source of each time sequence data in each data subsamples; dividing a plurality of time sequence data belonging to the same data source into the same array from a plurality of data subsamples to obtain a plurality of arrays; and sequencing the plurality of time sequence data in each array according to the sequence of the data acquisition time points to obtain a plurality of time sequence arrays.
Further, the obtaining the global association support degree includes the following steps: executing the step A on each time sequence array to obtain the local support degree of each type of data pair in each time sequence array; counting the sum of the local supporters of each type of data pair in a plurality of time sequence arrays to obtain the global associated supporters of each type of data pair; screening out the global association support degree between the current demand analysis index and each other demand analysis index from the obtained multiple global association support degrees; the step A comprises the following steps: establishing a time window; the time window is used for acquiring the association degree of the data pairs in the time sequence array; each data pair comprises two adjacent time sequence data; moving the time window from the head of the time sequence array to the tail of the time sequence array; obtaining corresponding association degree data every time the time window is moved, and obtaining a plurality of association degree data; the step length of the time window is 1; sorting the plurality of associated data in order of magnitude from large to small; weighting each data pair according to the sequencing result; counting the local support degree of each type of data pair; each class of data pair comprises one or more data pairs of the same type, and the local support degree is the sum of weights of the one or more data pairs of the same type.
In a second aspect, there is provided a user demand analysis display system comprising: the set establishing module is used for establishing a demand analysis index set; the demand analysis index set comprises a plurality of demand analysis indexes to be analyzed; the data acquisition module is used for acquiring a plurality of time sequence data corresponding to each demand analysis index in a target period to obtain a data sample corresponding to each demand analysis index; a period dividing module for dividing the target period into a plurality of periods; the sample dividing module is used for dividing each data sample according to the period length to obtain a plurality of data sub-samples corresponding to each data sample; the index determining module is used for determining a current demand analysis index from the demand analysis index set; the global association support degree acquisition module is used for acquiring global association support degrees between the current demand analysis index and each other demand analysis index by utilizing a plurality of data subsamples in each period to acquire a plurality of global association support degrees in each period; the PAM waveform diagram generating module is used for carrying out PAM modulation on each remaining demand analysis index by utilizing a plurality of global association supporters obtained in a plurality of periods to obtain a PAM waveform diagram corresponding to each remaining demand analysis index; and the PAM waveform diagram processing module is used for superposing a plurality of PAM waveform diagrams to obtain an exhibition diagram for user demand analysis.
Further, the target period comprises a plurality of continuous data acquisition time points; the user demand analysis display system further includes: the data cleaning module is used for cleaning the data of each data sample to obtain a plurality of cleaned data samples; and the target period compression module is used for compressing the target period according to the plurality of cleaned data samples to obtain a new target period.
Further, the data cleaning module includes: a first tag adding unit for adding a time tag for each time series data; the time tag is a data acquisition time point corresponding to time sequence data; a first data marking unit for detecting whether each time sequence data is empty, and adding a first mark for each empty data detected; the first data association unit is used for associating each first mark with a corresponding data acquisition time point; a second data marking unit for detecting whether each of the remaining time series data to which the first mark is not added is noise data, and adding the second mark for each of the detected noise data; the second data association unit is used for associating each second mark with a corresponding data acquisition time point; the data acquisition unit is used for acquiring all first marks and all second marks of each other data sample; the third data marking unit is used for adding a third mark for each time sequence data according to the data acquisition time point associated with each acquired first mark; the added third mark and the acquired first mark have the same data acquisition time point; a fourth data marking unit, configured to add a fourth mark to each time sequence data according to the data acquisition time point associated with each acquired second mark; the added fourth mark and the acquired second mark have the same data acquisition time point; and the data deleting unit is used for deleting all time sequence data with the first mark, the second mark, the third mark and the fourth mark to obtain a cleaned data sample.
Further, the target period compression module includes: a second tag adding unit, configured to add a new time tag to each time sequence data in each data sample after cleaning; a new time tag corresponds to a new data acquisition time point; the added multiple new data acquisition time points are continuous; a time unit setting unit for setting a time unit of each new data acquisition time point as seconds.
Further, the user demand analysis display system further includes: the data source acquisition module is used for acquiring a data source of each time sequence data in each data subsamples; the first array building module is used for dividing a plurality of time sequence data belonging to the same data source into the same array from a plurality of data subsamples to obtain a plurality of arrays; the second array building module is used for sequencing the plurality of time sequence data in each array according to the sequence of the data acquisition time points to obtain a plurality of time sequence arrays.
Further, the global association support obtaining module includes: the local support degree acquisition unit is used for acquiring the local support degree of each type of data pair in each time sequence array; the global association support degree acquisition unit is used for counting the sum of the local support degrees of each type of data pair in a plurality of time sequence arrays to obtain the global association support degree of each type of data pair; and screening the global association support degree between the current demand analysis index and each other demand analysis index from the obtained plurality of global association support degrees.
Further, the local support degree obtaining unit includes: a time window establishing subunit, configured to establish a time window; the time window is used for acquiring the association degree of the data pairs in the time sequence array; each data pair comprises two adjacent time sequence data; a correlation obtaining subunit, configured to move the time window from the head of the timing array to the tail of the timing array; obtaining corresponding association degree data every time the time window is moved, and obtaining a plurality of association degree data; the step length of the time window is 1; the association degree ordering subunit is used for ordering the plurality of association data according to the order of the numerical values from the big to the small; a data pair assignment subunit, configured to assign a weight to each data pair according to the sorting result; the local support degree statistics subunit is used for counting the local support degree of each type of data pair; each class of data pair comprises one or more data pairs of the same type, and the local support degree is the sum of weights of the one or more data pairs of the same type.
In a third aspect, there is provided a computer device comprising: a memory, a processor, a transceiver, and a display; the memory, the processor and the transceiver are sequentially in communication connection, and the display is in communication connection with the processor; the memory is for storing a computer program, the transceiver is for receiving and transmitting messages, and the processor is for reading the computer program and executing the user demand analysis presentation according to the first aspect.
In a fourth aspect, a computer readable storage medium is provided, wherein the computer readable storage medium has instructions stored thereon, which when executed on a computer, perform the user demand analysis presentation method according to the first aspect.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. On the one hand, the advantage of simple structure of the pulse waveform diagram is utilized, the visual display of the demand analysis indexes is carried out in a pulse waveform diagram form, namely, in order to concisely and intuitively embody the association relation and association degree among the demand analysis indexes of multiple dimensions, the global association support degree between the current demand analysis indexes and each other demand analysis index is obtained, the current demand analysis indexes correspond to baseband signals, the global association support degree is used as a parameter of PAM modulation (pulse amplitude modulation), the baseband signals are subjected to PAM modulation, the association relation and association degree between the current demand analysis indexes and each other demand analysis indexes are reflected by the PAM waveform after the modulation, namely, the amplitude of the PAM wave is positive correlation between regular demand analysis indexes, the amplitude of the PAM wave is uncorrelated between the demand analysis indexes, the amplitude of the PAM wave is negative, the demand analysis indexes are negatively correlated, and the correlation degree between the demand analysis indexes is higher as the absolute value of the amplitude is larger; and further, overlapping each PAM waveform diagram to realize unified display of the association relation and association degree of the current demand analysis index and the other multiple demand analysis indexes in one PAM waveform diagram. Because the PAM waveform diagram has a simple structure, even if the change trend of a plurality of requirement analysis index data is uniformly displayed in one PAM waveform diagram, the association relation and the association degree among the requirement analysis indexes can be clearly and intuitively reflected. On the other hand, the advantages of the time sequence characteristics can be reflected by utilizing the pulse waveform diagram, namely the target period is divided into a plurality of periods, the periods of the target period correspond to the periods of the PAM wave, and the association relation and the association degree of the demand analysis indexes in each period are displayed by using one period of the PAM waveform, so that the time sequence characteristics of the demand analysis indexes are reflected by utilizing the PAM wave, namely the association relation and the association degree change trend along with time among the demand analysis indexes are reflected by using the change trend of the PAM wave. 2. And (3) data cleaning is performed on the data samples, namely on one hand, the null data and the noise data in each data sample are deleted, so that the accurate global association support degree is ensured to be acquired. On the other hand, in order to ensure the consistency of each time sequence data in each data sample in the time dimension and further maintain the authenticity of the association relationship between the time sequence data corresponding to each requirement analysis index at the same time point, the invention deletes the data with the same time label in the data sample and the time sequence data with the same time label in a mode of adding the time label and the label to the time sequence data in the data sample in addition to deleting the empty data and the noise data in the data sample, so that the time sequence data in each data sample can be kept uniform in the data acquisition time, and the deviation of the association relationship caused by different data acquisition time is avoided. 3. The target time period is compressed according to the processed data samples, and the time unit of the data acquisition time point is adjusted, so that good PAM waveforms can be output. 4. The time sequence data of different types of requirement analysis indexes of the same data source are analyzed to obtain local association support degrees, and the global association support degrees are obtained by integrating the local association support degrees, so that the internal rules of multidimensional data are reflected.
Drawings
In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings that are needed in the examples will be briefly described below, it being understood that the following drawings only illustrate some examples of the present invention and therefore should not be considered as limiting the scope, and that other related drawings may be obtained from these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a user demand analysis display method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a data sample format according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of adding a first mark and all second marks to a data sample according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of the result of adding a first mark and all second marks to a data sample according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a data sample after deleting time-series data corresponding to all marks according to an embodiment of the present invention;
fig. 6 is a display diagram of user demand analysis in one period according to an embodiment of the present invention.
Detailed Description
For the purpose of making apparent the objects, technical solutions and advantages of the present invention, the present invention will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present invention and the descriptions thereof are for illustrating the present invention only and are not to be construed as limiting the present invention.
Examples: the graph and the table are data visual display modes which are frequently used at present, and the data can be intuitively displayed through the graph and the table. For example, the histogram can intuitively show the magnitude of the value, and the combination of a plurality of histograms can reflect the change trend of the value, but the histogram or the combination of a plurality of histograms cannot well reflect the relationship between the data corresponding to each histogram; the topological graph can uniformly display the association relation among the data in one graph, and establishes the relation among the data in an arrow or connecting line mode, but when the data dimension is more, the relation structure among the data is complex, and the specific data relation is difficult to identify on one graph; the scatter diagram can reflect the distribution condition of a large amount of data, but the scatter diagram cannot reflect the internal relation among the data; the table can count a large amount of data and calculate the relation among the data through a corresponding algorithm, but the data display mode of the table is not visual, the statistical analysis result is displayed in a digital mode, although the statistical analysis result of the table can be graphically displayed in the prior art, the adopted image display is only a single graph, and the defects of the visual display of the data through the means of a histogram, a topological graph, a scatter graph and the like are also overcome.
In addition, most enterprises and public institutions at present, such as banks, asset management institutions and the like, acquire a large amount of user data for improving the matching degree of products and market demands and providing the users with products more fitting actual demands, analyze the acquired user data to obtain the internal relation between the user data, and analyze the user demands according to the internal relation of the data. The acquired user data has large volume, multiple data dimensions, complex data characteristics and obvious time sequence, and is influenced by various factors such as living environment, social environment, user growth, user character and the like, so that the internal relationship among the acquired user data is very complex, the internal relationship among the acquired user data changes continuously along with the time, and the internal relationship among the data also changes. Therefore, the existing data visualization display mode is difficult to intuitively reflect the association relation among a large number of multidimensional data, and is unfavorable for user demand analysis.
In this regard, the first aspect of the present embodiment provides a method for analyzing and displaying a user demand, which displays, by means of a pulse waveform diagram, analysis indexes of each user demand and a variation trend thereof; the global association support degree is used for reflecting the association relation and the association degree between the indexes of the user demand analysis, and is used as a waveform amplitude modulation parameter to output a PAM waveform diagram corresponding to the index of the user demand analysis through PAM modulation; uniformly displaying each PAM waveform diagram in one diagram, reflecting the association relation among the user demand analysis indexes, and reflecting the association degree among the user demand analysis indexes by using the amplitude of the PAM wave; the time sequence change characteristics of the user demand analysis indexes are reflected by the waveform change of the PAM wave along with time, so that the association relation and the association degree of the multi-dimensional user demand analysis indexes are uniformly displayed in one graph, and the PAM waveform graph has a simple structure and visual display effect.
The following describes the specific implementation steps and effects of a user demand analysis display method according to the present embodiment in detail. As shown in fig. 1, the method comprises the following steps:
Step1: and establishing a demand analysis index set.
The established demand analysis index set contains a plurality of demand analysis indexes to be analyzed. It should be noted that, the set requirement analysis index set is different in type according to different actual services, and the number of requirement analysis indexes is also changed according to different actual services; therefore, the type and the number of the demand analysis indexes are required to be determined according to the actual service. The set of established demand analysis metrics may be represented by the following format:
X set of demand analysis indices= { demand analysis index X1, demand analysis index X2, demand analysis index X3, … …, demand analysis index xn }.
Step 2: and in the target period, collecting a plurality of time sequence data corresponding to each demand analysis index to obtain a data sample corresponding to each demand analysis index.
The target period of time in this step means: the data acquisition period is specified according to the actual traffic situation. For example, it may be to collect historical data over the past 5 years. It is worth mentioning that:
First, the determined time length of the target period may be determined according to the storage amount of the historical data, if the storage amount of the historical data is large and the generation time interval corresponding to the data is small, in order to reduce the cost of subsequent data analysis processing, the time length of the target period may be reduced, for example, the target period is determined to be the past 1 year or 3 years; if the storage amount of the historical data is small or the corresponding generation time interval of the data is large, in order to ensure the reliability of the analysis result of the subsequent data and fully embody the association relation between the data, the time length of the target period is required to be prolonged, for example, the target period is determined to be 5 years or even 10 years, but it should be noted that, in order to ensure the practicability of the acquired data, the time length of the target period should not be set too long, so that the too long historical data is prevented from lacking in referent value to become noise data, and further the analysis processing result of the subsequent data is influenced.
Second, the target period should be a continuous period. For example, if the determined target period is the last 5 years, assuming the current year is the y year, then the last 5 years should be the y-1 year (including consecutive 365 or 366 days), the y-2 year (including consecutive 365 or 366 days), the y-3 year, the y-4 year, and the y-5 year, rather than the last 5 years consisting of the y-1, y-2, y-4, y-6, and y-7 years; and, each year in the past should contain 365 or 366 consecutive days. The purpose of determining the target period in the above manner is to: the time sequence characteristics of the data are considered, the historical data of the continuous time period are collected, the consistency of the collected data in time can be improved, and the incidence relation deviation caused by different data collection time is avoided.
In addition, the collected data is time sequence data of each demand analysis index in the target period. The historical data of the demand analysis index in the target period has a corresponding generation date, and the embodiment refers to the historical data of the demand analysis index in the target period as time sequence data so as to illustrate that the time sequence characteristics are provided among the historical data.
In addition, the historical data of each requirement analysis index collected in the target period forms a corresponding data sample, as shown in fig. 2.
Step 3: and carrying out data cleaning on each data sample to obtain a plurality of cleaned data samples. Specifically, the data cleaning includes the following steps:
step 3.1: a time stamp is added to each time series data. The time tag is a data acquisition time point corresponding to time sequence data.
Taking the time unit of the data acquisition time point as "day" as an example, for a certain time series data, the time tag added to the data acquisition time point may be "xx year xx month xx day".
Step 3.2: detecting whether each time sequence data is empty, and adding a first mark for each detected empty data; each first marker is associated with a corresponding data acquisition time point.
In consideration of practical situations, since there may be no corresponding time series data for one or more days in the target period, one or more null data exists in the plurality of time series data in the acquired target period. And because the empty data is meaningless for the subsequent data analysis processing, in the step, whether each time sequence data acquired is empty or not is detected, so that the meaningless data is eliminated.
Step 3.3: detecting whether the time sequence data without the first mark is noise data or not, and adding a second mark for each detected noise data; each second marker is associated with a corresponding data acquisition time point.
In the same way, considering the actual situation, because one or more time sequence data anomalies may exist in the time sequence data acquired in the target period, the anomalies will affect the result of the subsequent data analysis processing, so the step performs noise detection on the rest data except the marked first mark in the data sample on the basis of step 3.2, so as to eliminate the influence of the noise data on the subsequent data analysis result.
Step 3.4: collecting all first marks and all second marks of each remaining data sample; and adding a third mark for each time sequence data according to the data acquisition time point associated with each first mark. The added third mark and the acquired first mark have the same data acquisition time point; adding a fourth mark for each time sequence data according to the data acquisition time point associated with each acquired second mark; the fourth marker added has the same data acquisition time point as the second marker acquired.
In one aspect, as can be seen from the foregoing, the plurality of time series data in the data samples have time series; on the other hand, the association relationship between the requirement analysis indexes is obtained according to the time sequence data in each data sample. Because of the processing in step 3.2 and step 3.3, there may be a difference in the data acquisition time points corresponding to the remaining time series data in each data sample. Therefore, in order to ensure the accuracy of the association relationship between the analysis indexes of each requirement obtained by analysis, the consistency of the time sequence data used in time is ensured, and the deviation of the association analysis result is avoided.
As shown in fig. 3, a data sample A1 and a data sample A2 are taken as examples. Assuming that the time sequence data a 21 in the data sample A1 is null data and the time sequence data a m1 is noise data, processing in the step 3.2 and the step 3.3 to obtain a data sample A1'; assuming that the time sequence data a 32 in the data sample A2 is null data and the time sequence data a (m-1)2 is noise data, the data sample A2' is obtained after the processing in step 3.2 and step 3.3. As can be seen from fig. 3, the time series data a 21 in the data sample A1' has a first flag, and the time series data a m1 has a second flag; the timing data a 32 in the data sample A2' has a first flag, and the timing data a (m-1)2 has a second flag. Wherein the first tag of timing data a 21 is associated with data acquisition time point t 2, the second tag of timing data a m1 is associated with data acquisition time point t m, the first tag of timing data a 32 is associated with data acquisition time point t 3, and the second tag of timing data a (m-1)2 is associated with data acquisition time point t m-1.
In order to ensure the accuracy of the association relationship between the analysis indexes of each requirement obtained by analysis, for the data sample A1', a first mark and a second mark of the data sample A2' are required to be acquired, a third mark is added for the time series data a 31 according to a data acquisition time point t 3 associated with the acquired first mark, the third mark of the time series data a 31 is associated with a data acquisition time point t 3, a fourth mark is added for the time series data a (m-1)1 according to a data acquisition time point t m-1 associated with the acquired second mark, and the fourth mark of the time series data a (m-1)1 is associated with a data acquisition time point t m-1. Similar operations are employed for data sample A2', and are not described in detail herein. The data sample A1 'and the data sample A2' processed in step 3.4 are shown in figure 4,
Step 3.5: and deleting all time sequence data with the first mark, the second mark, the third mark and the fourth mark to obtain a cleaned data sample.
Also taking the data sample A1 'and the data sample A2' as an example, the data sample a1″ and the data sample a2″ after the processing in step 3.5 are shown in fig. 5. After the processing in step 3.5, the data sampling time point corresponding to each time sequence data in the data sample A1 'is consistent with the data sampling time point of each time sequence data in the data sample A2'.
Step 4: and compressing the target time period according to the cleaned data sample to obtain a new target time period.
As can be seen from fig. 5, in the data sample after data cleaning, the data acquisition time points corresponding to each time series data are not continuous time points, and in this step, compressing the target time refers to transforming a plurality of discontinuous data acquisition time points into continuous data acquisition time points, so as to facilitate PAM modulation and output of good PAM waveforms. Specifically, the method comprises the following steps:
Step 4.1: adding a new time tag to each time sequence data in each data sample after cleaning, so that one new time tag corresponds to one new data acquisition time point, and a plurality of added new data acquisition time points are continuous.
The specific treatment mode is as follows: subtracting the number of time sequence data deleted before from the data acquisition time point corresponding to the current time tag. Taking the data sample A1 'as an example, if the deleted time series data in the data sample A1' is only a 21、a31、a3(m-1)1 and a m1,, after the processing in step 4.1, the new data collection time point corresponding to the time stamp of the remaining time series number a 3(m-1)1 in the data sample should be t m-3.
Step 4.2: the time unit of each new data acquisition time point is set to seconds. In most cases, the time unit of user data acquisition is "day", and in order to make the graph output after PAM modulation more conform to PAM waveform, the time unit of the data acquisition time point is set to be second, i.e. the "day" is compressed to be "second", and of course, the time units such as "nanosecond" and "millisecond" can also be selected.
Step 5: the target period is divided into a plurality of periods.
Because the collected time series data is affected by various factors such as living environment, social environment, growth of users, character of users and the like, and changes continuously with the lapse of time, the internal relations among the time series data in each time stage may also be different. If all time series data in the target period are uniformly subjected to association analysis, the final association relationship may be distorted. Therefore, the target period is divided into a plurality of periods, and each time sequence data in each period is independently subjected to association analysis, so that association relation of each time sequence data in the period is ensured to be more practical.
It should be noted that, when dividing the target period, the time length of each period needs to be determined according to the amount of the time sequence data remaining in each data sample after the processing in step3, if the amount of the time sequence data remaining in each data sample is large, the period duration can be reduced, and correspondingly the period number is increased, and if the amount of the time sequence remaining in each data sample is small, the period duration can be enlarged, and correspondingly the period number is reduced. The specific period duration and period number are determined according to the length of the target period and the residual time sequence data quantity, and of course, the social environment and other factors can also be referred to at the time point of data acquisition.
Step 6: dividing each data sample according to the period length to obtain a plurality of data subsamples corresponding to each data sample, wherein one period corresponds to one data subsamples.
Step 7: and determining the current demand analysis index from the demand analysis index set. And setting the determined demand analysis index as x1.
Step 8: acquiring a data source of each time sequence data in each data subsamples; from a plurality of data subsamples, dividing a plurality of time sequence data belonging to the same data source into the same array to obtain a plurality of arrays.
Often, the time series data streams are not simply linear correlation, in many system data streams, the variation condition of a plurality of streams can present a certain periodicity, which represents that a certain specific correlation exists between modes of the data streams, but the respective modes may have great differences. The data source in this step may be understood as a user, and the plurality of different types of time series data from the same data source are divided into the same array, that is, the plurality of different types of time series data collected from the same user are unified and summarized. Since a plurality of time series data from the same user can characterize the behavior characteristics and the demand characteristics of the user, the time series data of different types of demand analysis indexes of the same data source are analyzed as a whole, so that the interpretation of the (transverse) internal rules among the data is facilitated.
Step 9: and sequencing the plurality of time sequence data in each array according to the sequence of the data acquisition time points to obtain a plurality of time sequence arrays.
Step 10: and in each period, acquiring the global association support degree between the current demand analysis index and each other demand analysis index by utilizing a plurality of data subsamples, and obtaining a plurality of global association support degrees in each period.
One of the basic principles of this embodiment is: and using the global association support degree between the current demand analysis index and the other demand analysis indexes to represent the association strength between the current demand analysis index and the other demand analysis indexes, and taking the association strength as a parameter of PAM amplitude modulation. If the demand analysis index x1 is taken as the current demand analysis index, in each period, the demand analysis index x1 corresponds to one global association support degree with the demand analysis index x2, the demand analysis indexes x3, … … and the demand analysis index xn respectively, that is, each period includes n-1 global association support degrees.
Specifically, before the global association support degree is obtained, the method comprises the following steps:
Step 10.1: and C, executing the step A on each time sequence array to obtain the local support degree of each type of data pair in each time sequence array. Wherein, step A includes:
Step A1: and establishing a time window for acquiring the association degree of the data pairs in the time sequence array. Each data pair contains two adjacent time series data.
Step A2: and starting from the head of the time sequence array, moving a time window to the tail of the time sequence array by taking 1 step length, and obtaining corresponding association degree data every time the time window is moved, so as to obtain a plurality of association degree data. It should be noted that the association degree data may select an existing association degree function. The association data comprises a positive number, a negative number and zero, wherein the association degree is positive number and represents positive correlation between two data, the association degree is negative number and represents negative correlation between two data, and the association degree is zero and represents uncorrelation between two data.
Step A3: the plurality of association data are ordered in order of magnitude from greater to lesser.
Step A4: and weighting each data pair according to the sequencing result. The assignment principle is as follows: the weight given by the association degree data positioned at the front of the sequence is larger than the weight given by the association degree data positioned at the rear of the sequence; if the plurality of association degree data have the same size, the same weight is given.
Step A5: and (5) counting the local support degree of each type of data pair. Each class of data pair comprises one or more data pairs of the same type, and the local support degree is the sum of weights of the one or more data pairs of the same type. It should be noted that, two adjacent time series data in the time window represent a data pair, and because the association relationship between two time series data framed by each time the time window moves is different, one association relationship corresponds to one type of data pair in this embodiment.
Step 10.2: and counting the sum of the local supporters of each type of data pair in a plurality of time sequence arrays to obtain the global associated supporters of each type of data pair. The purpose of this step is to (longitudinally) calculate the global associative support of each class of data pair in multiple timing arrays.
Step 10.3: and screening the global association support degree between the current demand analysis index and each other demand analysis index from the obtained plurality of global association support degrees.
Because the plurality of global association supporters obtained in step 10.2 not only includes the global association supporters between the current demand analysis index and each of the other demand analysis indexes, but also includes the global association supporters between the other plurality of demand analysis indexes, the global association supporters between the current demand analysis index and each of the other demand analysis indexes need to be selected from all the global association supporters obtained in step 10.2.
Step 11: and (3) performing PAM modulation on each remaining demand analysis index by utilizing a plurality of global associated supporters obtained in a plurality of periods to obtain a PAM waveform diagram corresponding to each remaining demand analysis index.
According to the method, global association support degree between the current demand analysis index and each of the other demand analysis indexes is obtained, the current demand analysis index corresponds to a baseband signal, the global association support degree is used as a parameter of PAM (pulse amplitude modulation) modulation, the baseband signal is subjected to PAM modulation, and the association relation and the association degree between the current demand analysis index and each of the other demand analysis indexes are reflected by using the PAM waveform after the modulation.
Step 12: and superposing the plurality of PAM wave patterns to obtain a display diagram for user demand analysis.
And overlapping each PAM waveform diagram to realize unified display of the association relation and association degree of the current demand analysis index and the other multiple demand analysis indexes in one PAM waveform diagram. Because the PAM waveform diagram has a simple structure, even if the change trend of a plurality of requirement analysis index data is uniformly displayed in one PAM waveform diagram, the association relation and the association degree among the requirement analysis indexes can be clearly and intuitively reflected. Finally, a display of user demand analysis may refer to fig. 6.
Fig. 6 shows, by taking one cycle as an example, the association relationship and the association degree between the current demand analysis index and each of the other demand analysis indexes in one cycle by using a plurality of PAM waveform curves. The horizontal axis of coordinates represents the current demand analysis index, each PAM waveform is used for representing the association relation and association degree between the rest of the demand analysis indexes and the current demand analysis index, in each period, each PAM waveform curve represents the demand analysis index related to the current demand analysis index, the height and the association degree of each PAM waveform curve can be checked corresponding to the vertical axis. It should be noted that, in order to further distinguish the correspondence between each PAM waveform curve and the requirement analysis index, the PAM waveform curve may be colored, or any other marking means capable of distinguishing different PAM waveform curves.
It should be noted that, fig. 6 is only used to show an example of a manner and an effect of representing a correlation between a current demand analysis index and the demand analysis index x1, a correlation between a demand analysis index x2 and the demand analysis index xn after overlapping a plurality of PAM modulation maps, and does not represent a true correlation between a current demand analysis index and the rest of analysis indexes.
The second aspect of the present embodiment provides a user demand analysis display system corresponding to the above first aspect of the present invention. The system comprises: a set establishing module, a data acquisition module, a data cleaning module, a target period compressing module, a period dividing module, a sample dividing module, an index determining module, a data source obtaining module, a first array establishing module, a second array establishing module, a global association support obtaining module, a PAM waveform diagram generating module and a PAM waveform diagram processing module,
Wherein,
The set establishing module is used for establishing a demand analysis index set. The demand analysis index set comprises a plurality of demand analysis indexes to be analyzed.
The data acquisition module is used for acquiring a plurality of time sequence data corresponding to each demand analysis index in a target period to obtain a data sample corresponding to each demand analysis index.
The data cleaning module is used for cleaning data of each data sample to obtain a plurality of cleaned data samples.
The target period compression module is used for compressing the target period according to the plurality of cleaned data samples to obtain a new target period.
The period dividing module is used for dividing the target period into a plurality of periods.
The sample dividing module is used for dividing each data sample according to the period length to obtain a plurality of data sub-samples corresponding to each data sample.
The index determining module is used for determining a current demand analysis index from the demand analysis index set.
The data source acquisition module is used for acquiring a data source of each time sequence data in each data subsamples.
The first array building module is used for dividing a plurality of time sequence data belonging to the same data source into the same array from a plurality of data subsamples to obtain a plurality of arrays.
The second array building module is used for sequencing the plurality of time sequence data in each array according to the sequence of the data acquisition time points to obtain a plurality of time sequence arrays.
The global association support degree acquisition module is used for acquiring global association support degrees between the current demand analysis index and each other demand analysis index by utilizing a plurality of data subsamples in each period to obtain a plurality of global association support degrees in each period.
The PAM waveform diagram generating module is used for carrying out PAM modulation on each remaining demand analysis index by utilizing a plurality of global association supporters obtained in a plurality of periods to obtain a PAM waveform diagram corresponding to each remaining demand analysis index.
And the PAM waveform diagram processing module is used for superposing a plurality of PAM waveform diagrams to obtain an exhibition diagram for user demand analysis.
Further, the data cleaning module includes: the system comprises a first label adding unit, a first data marking unit, a first data association unit, a second data marking unit, a second data association unit, a data acquisition unit, a third data marking unit, a fourth data marking unit and a data deleting unit.
The first tag adding unit is used for adding a time tag for each time sequence data; the time tag is a data acquisition time point corresponding to time sequence data.
The first data marking unit is used for detecting whether each time sequence data is empty, and adding a first mark for each detected empty data.
The first data association unit is used for associating each first mark with a corresponding data acquisition time point.
The second data marking unit is used for detecting whether each of the rest time sequence data without the first mark is noise data, and adding the second mark for each detected noise data.
The second data association unit is used for associating each second mark with a corresponding data acquisition time point.
The data acquisition unit is used for acquiring all first marks and all second marks of each of the remaining data samples.
The third data marking unit is used for adding a third mark for each time sequence data according to the data acquisition time point associated with each acquired first mark; the third marker added has the same data acquisition time point as the first marker acquired.
And the fourth data marking unit is used for adding a fourth mark added by the fourth mark for each time sequence data according to the data acquisition time point associated with each acquired second mark, and the fourth mark added by the fourth mark and the acquired second mark have the same data acquisition time point.
The data deleting unit is used for deleting all time sequence data with the first mark, the second mark, the third mark and the fourth mark to obtain cleaned data samples.
Further, the target period compression module includes: a second tag adding unit and a time unit setting unit.
The second tag adding unit is used for adding a new time tag for each time sequence data in each cleaned data sample; a new time tag corresponds to a new data acquisition time point; the added plurality of new data acquisition time points are consecutive.
The time unit setting unit is configured to set a time unit of each new data acquisition time point to seconds.
Further, the global association support obtaining module includes: and the local support degree acquisition unit and the global association support degree acquisition unit.
The local support degree acquisition unit is used for acquiring the local support degree of each type of data pair in each time sequence array.
The global association support degree acquisition unit is used for counting the sum of the local support degrees of each type of data pair in a plurality of time sequence arrays to obtain the global association support degree of each type of data pair; and screening the global association support degree between the current demand analysis index and each other demand analysis index from the obtained plurality of global association support degrees.
Further, the local support degree acquisition unit includes: the system comprises a time window establishment subunit, a relevance acquisition subunit, a relevance sorting subunit, a data pair assignment subunit and a local support statistics subunit.
The time window establishing subunit is used for establishing a time window; the time window is used for acquiring the association degree of the data pairs in the time sequence array; each data pair contains two adjacent time series data.
The association degree obtaining subunit is used for moving the time window from the head part of the time sequence array to the tail part of the time sequence array; obtaining corresponding association degree data every time the time window is moved, and obtaining a plurality of association degree data; the step size of the time window is 1.
The association degree ordering subunit is used for ordering the plurality of association data in order of magnitude from big to small.
The data pair assignment subunit is used for assigning a weight to each data pair according to the sorting result.
The local support degree statistics subunit is used for counting the local support degree of each type of data pair; each class of data pair comprises one or more data pairs of the same type, and the local support degree is the sum of weights of the one or more data pairs of the same type.
A third aspect of the present embodiment provides a computer device for performing a user demand analysis display method according to the first aspect or any possible design of the first aspect, including: a memory, a processor, a transceiver, and a display; the memory, the processor and the transceiver are sequentially in communication connection, and the display is in communication connection with the processor; the memory is for storing a computer program, the transceiver is for receiving and transmitting messages, and the processor is for reading the computer program and executing the user demand analysis presentation according to the first aspect. In particular, the memory may include, but is not limited to, random access memory (Random-AccessMemory, RAM), read-only memory (ROM), flash memory (flash memory), first-in first-out memory (FirstInputFirstOutput, FIFO), and/or first-in last-out memory (FirstInputLastOutput, FILO), among others; the processor may be, but is not limited to, a microprocessor of the type STM32F105 family. In addition, the computer device may include, but is not limited to, a power module, a display screen, and other necessary components.
The working process, working details and technical effects of the foregoing computer device provided in the third aspect of the present embodiment may be referred to a user demand analysis and display method described in the first aspect or any possible design schemes in the first aspect, which are not described herein again.
A fourth aspect of the present embodiment provides a computer-readable storage medium storing instructions comprising a user requirement analysis presentation method according to the first aspect or any of the possible designs of the first aspect, i.e. the computer-readable storage medium has instructions stored thereon that, when executed on a computer, perform a user requirement analysis presentation method according to the first aspect or any of the possible designs of the first aspect. The computer readable storage medium refers to a carrier for storing data, and may include, but is not limited to, a floppy disk, an optical disk, a hard disk, a flash memory, and/or a memory stick (memory stick), where the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable devices.
The working process, working details and technical effects of the foregoing computer readable storage medium provided in the fourth aspect of the present embodiment may refer to a user requirement analysis and display method as described in the first aspect or any possible design schemes in the first aspect, which are not repeated herein.
A fifth aspect of the present embodiment provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform a user requirement analysis presentation method as described in the first aspect or any of the possible designs of the first aspect. Wherein the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (4)
1. The user demand analysis and display method is characterized by comprising the following steps of:
Establishing a demand analysis index set; the demand analysis index set comprises a plurality of demand analysis indexes to be analyzed;
Collecting a plurality of time sequence data corresponding to each demand analysis index in a target period to obtain a data sample corresponding to each demand analysis index;
Dividing a target period into a plurality of periods;
dividing each data sample according to the period length to obtain a plurality of data sub-samples corresponding to each data sample;
Determining a current demand analysis index from the demand analysis index set;
In each period, acquiring global association support between the current demand analysis index and each other demand analysis index by utilizing a plurality of data subsamples to acquire a plurality of global association support in each period;
performing PAM modulation by utilizing a plurality of global associated supporters obtained in a plurality of periods aiming at each remaining demand analysis index to obtain a PAM waveform diagram corresponding to each remaining demand analysis index;
superposing a plurality of PAM wave patterns to obtain a display chart for user demand analysis;
The target period comprises a plurality of continuous data acquisition time points;
before dividing the target period into a plurality of periods, the method comprises the following steps: carrying out data cleaning on each data sample to obtain a plurality of cleaned data samples; compressing the target time period according to the plurality of cleaned data samples to obtain a new target time period;
The data cleaning comprises the following steps: adding a time tag to each time sequence data; the time tag is a data acquisition time point corresponding to time sequence data; detecting whether each time sequence data is empty, and adding a first mark for each detected empty data; associating each first mark with a corresponding data acquisition time point; detecting whether the time sequence data without the first mark is noise data or not, and adding a second mark for each detected noise data; associating each second mark with a corresponding data acquisition time point; collecting all first marks and all second marks of each remaining data sample; adding a third mark for each time sequence data according to the data acquisition time point associated with each first mark; the added third mark and the acquired first mark have the same data acquisition time point; adding a fourth mark for each time sequence data according to the data acquisition time point associated with each acquired second mark; the added fourth mark and the acquired second mark have the same data acquisition time point; deleting all time sequence data with the first mark, the second mark, the third mark and the fourth mark to obtain a cleaned data sample;
Compressing the target period of time, comprising the steps of: adding a new time tag for each time sequence data in each data sample after cleaning; a new time tag corresponds to a new data acquisition time point; the added multiple new data acquisition time points are continuous; setting the time unit of each new data acquisition time point as seconds;
Before the global association support degree is obtained, the method comprises the following steps: acquiring a data source of each time sequence data in each data subsamples; dividing a plurality of time sequence data belonging to the same data source into the same array from a plurality of data subsamples to obtain a plurality of arrays; sequencing a plurality of time sequence data in each array according to the sequence of the data acquisition time points to obtain a plurality of time sequence arrays;
The obtaining of the global association support degree comprises the following steps: executing the step A on each time sequence array to obtain the local support degree of each type of data pair in each time sequence array; counting the sum of the local supporters of each type of data pair in a plurality of time sequence arrays to obtain the global associated supporters of each type of data pair; screening out the global association support degree between the current demand analysis index and each other demand analysis index from the obtained multiple global association support degrees;
The step A comprises the following steps: establishing a time window; the time window is used for acquiring the association degree of the data pairs in the time sequence array; each data pair comprises two adjacent time sequence data; moving the time window from the head of the time sequence array to the tail of the time sequence array; obtaining corresponding association degree data every time the time window is moved, and obtaining a plurality of association degree data; the step length of the time window is 1; sorting the plurality of associated data in order of magnitude from large to small; weighting each data pair according to the sequencing result; counting the local support degree of each type of data pair; each class of data pair comprises one or more data pairs of the same type, and the local support degree is the sum of weights of the one or more data pairs of the same type.
2. A user demand analysis display system, comprising:
The set establishing module is used for establishing a demand analysis index set; the demand analysis index set comprises a plurality of demand analysis indexes to be analyzed;
the data acquisition module is used for acquiring a plurality of time sequence data corresponding to each demand analysis index in a target period to obtain a data sample corresponding to each demand analysis index;
a period dividing module for dividing the target period into a plurality of periods;
The sample dividing module is used for dividing each data sample according to the period length to obtain a plurality of data sub-samples corresponding to each data sample;
the index determining module is used for determining a current demand analysis index from the demand analysis index set;
The global association support degree acquisition module is used for acquiring global association support degrees between the current demand analysis index and each other demand analysis index by utilizing a plurality of data subsamples in each period to acquire a plurality of global association support degrees in each period;
The PAM waveform diagram generating module is used for carrying out PAM modulation on each remaining demand analysis index by utilizing a plurality of global association supporters obtained in a plurality of periods to obtain a PAM waveform diagram corresponding to each remaining demand analysis index;
the PAM waveform diagram processing module is used for superposing a plurality of PAM waveform diagrams to obtain an exhibition diagram for user demand analysis;
The target period comprises a plurality of continuous data acquisition time points;
the user demand analysis display system further includes:
The data cleaning module is used for cleaning the data of each data sample to obtain a plurality of cleaned data samples;
The target period compression module is used for compressing the target period according to the plurality of cleaned data samples to obtain a new target period;
The data cleaning module comprises:
A first tag adding unit for adding a time tag for each time series data; the time tag is a data acquisition time point corresponding to time sequence data;
a first data marking unit for detecting whether each time sequence data is empty, and adding a first mark for each empty data detected;
the first data association unit is used for associating each first mark with a corresponding data acquisition time point;
a second data marking unit for detecting whether each of the remaining time series data to which the first mark is not added is noise data, and adding the second mark for each of the detected noise data;
The second data association unit is used for associating each second mark with a corresponding data acquisition time point;
the data acquisition unit is used for acquiring all first marks and all second marks of each other data sample;
the third data marking unit is used for adding a third mark for each time sequence data according to the data acquisition time point associated with each acquired first mark; the added third mark and the acquired first mark have the same data acquisition time point;
A fourth data marking unit, configured to add a fourth mark to each time sequence data according to the data acquisition time point associated with each acquired second mark; the added fourth mark and the acquired second mark have the same data acquisition time point;
The data deleting unit is used for deleting all time sequence data with the first mark, the second mark, the third mark and the fourth mark to obtain a cleaned data sample;
The target period compression module includes:
A second tag adding unit, configured to add a new time tag to each time sequence data in each data sample after cleaning; a new time tag corresponds to a new data acquisition time point; the added multiple new data acquisition time points are continuous;
a time unit setting unit configured to set a time unit of each new data acquisition time point as seconds;
the user demand analysis display system further includes:
The data source acquisition module is used for acquiring a data source of each time sequence data in each data subsamples;
the first array building module is used for dividing a plurality of time sequence data belonging to the same data source into the same array from a plurality of data subsamples to obtain a plurality of arrays;
The second array building module is used for sequencing the plurality of time sequence data in each array according to the sequence of the data acquisition time points to obtain a plurality of time sequence arrays;
the global association support acquisition module comprises:
The local support degree acquisition unit is used for acquiring the local support degree of each type of data pair in each time sequence array;
The global association support degree acquisition unit is used for counting the sum of the local support degrees of each type of data pair in a plurality of time sequence arrays to obtain the global association support degree of each type of data pair; screening out the global association support degree between the current demand analysis index and each other demand analysis index from the obtained multiple global association support degrees;
the local support degree acquisition unit includes:
A time window establishing subunit, configured to establish a time window; the time window is used for acquiring the association degree of the data pairs in the time sequence array; each data pair comprises two adjacent time sequence data;
A correlation obtaining subunit, configured to move the time window from the head of the timing array to the tail of the timing array; obtaining corresponding association degree data every time the time window is moved, and obtaining a plurality of association degree data; the step length of the time window is 1;
The association degree ordering subunit is used for ordering the plurality of association data according to the order of the numerical values from the big to the small;
a data pair assignment subunit, configured to assign a weight to each data pair according to the sorting result;
The local support degree statistics subunit is used for counting the local support degree of each type of data pair; each class of data pair comprises one or more data pairs of the same type, and the local support degree is the sum of weights of the one or more data pairs of the same type.
3. A computer device, comprising: a memory, a processor, a transceiver, and a display; the memory, the processor and the transceiver are sequentially in communication connection, and the display is in communication connection with the processor; the memory is used for storing a computer program, the transceiver is used for receiving and transmitting messages, and the processor is used for reading the computer program and executing the user demand analysis display method as claimed in claim 1.
4. A computer readable storage medium having instructions stored thereon which, when executed on a computer, perform the user demand analysis presentation method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410281762.7A CN117874315B (en) | 2024-03-13 | 2024-03-13 | User demand analysis display method, system, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410281762.7A CN117874315B (en) | 2024-03-13 | 2024-03-13 | User demand analysis display method, system, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117874315A CN117874315A (en) | 2024-04-12 |
| CN117874315B true CN117874315B (en) | 2024-05-14 |
Family
ID=90590475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410281762.7A Active CN117874315B (en) | 2024-03-13 | 2024-03-13 | User demand analysis display method, system, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117874315B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104036360A (en) * | 2014-06-19 | 2014-09-10 | 中国科学院软件研究所 | User data processing system and processing method based on magcard attendance behaviors |
| CN105205112A (en) * | 2015-09-01 | 2015-12-30 | 西安交通大学 | System and method for excavating abnormal features of time series data |
| CN112214533A (en) * | 2020-10-20 | 2021-01-12 | 上海船舶研究设计院（中国船舶工业集团公司第六0四研究院） | Time sequence data aggregation method and device |
| CN113313170A (en) * | 2021-05-28 | 2021-08-27 | 中国人民解放军战略支援部队航天工程大学 | Full-time global training big data platform based on artificial intelligence |
| CN116680325A (en) * | 2023-06-25 | 2023-09-01 | 杭州电子科技大学 | Time sequence record link data matching method and device based on attribute relevance |
| CN117350775A (en) * | 2023-10-13 | 2024-01-05 | 山东卓业医疗科技有限公司 | Medical surgical robot market current situation demand analysis method and system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10223327B2 (en) * | 2013-03-14 | 2019-03-05 | Fisher-Rosemount Systems, Inc. | Collecting and delivering data to a big data machine in a process control system |
| US10896421B2 (en) * | 2014-04-02 | 2021-01-19 | Brighterion, Inc. | Smart retail analytics and commercial messaging |
| US20210064224A1 (en) * | 2019-08-30 | 2021-03-04 | GE Precision Healthcare LLC | Systems and methods for graphical user interfaces for medical device trends |
-
2024
- 2024-03-13 CN CN202410281762.7A patent/CN117874315B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104036360A (en) * | 2014-06-19 | 2014-09-10 | 中国科学院软件研究所 | User data processing system and processing method based on magcard attendance behaviors |
| CN105205112A (en) * | 2015-09-01 | 2015-12-30 | 西安交通大学 | System and method for excavating abnormal features of time series data |
| CN112214533A (en) * | 2020-10-20 | 2021-01-12 | 上海船舶研究设计院（中国船舶工业集团公司第六0四研究院） | Time sequence data aggregation method and device |
| CN113313170A (en) * | 2021-05-28 | 2021-08-27 | 中国人民解放军战略支援部队航天工程大学 | Full-time global training big data platform based on artificial intelligence |
| CN116680325A (en) * | 2023-06-25 | 2023-09-01 | 杭州电子科技大学 | Time sequence record link data matching method and device based on attribute relevance |
| CN117350775A (en) * | 2023-10-13 | 2024-01-05 | 山东卓业医疗科技有限公司 | Medical surgical robot market current situation demand analysis method and system |
Non-Patent Citations (4)
| Title |
|---|
| Classification, Clustering and Association Rule Mining in Educational Datasets Using Data Mining Tools: A Case Study;Sadiq Hussain 等;《Cybernetics and Algorithms in Intelligent Systems》;20180517;196–211 * |
| Moushumi Sharmin 等.Visualization of time-series sensor data to inform the design of just-in-time adaptive stress interventions.《UbiComp '15: Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing》.2015,505–516. * |
| 蓄水池算法研究与时间序列预测应用;王唯佳;《中国优秀硕士学位论文全文数据库 基础科学辑》;20210115(第01期);A002-1017 * |
| 面向空气污染的时空多变量数据可视分析;任珂;《中国博士学位论文全文数据库 工程科技Ⅰ辑》;20210915(第09期);B027-27 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117874315A (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hermosilla et al. | Regional detection, characterization, and attribution of annual forest change from 1984 to 2012 using Landsat-derived time-series metrics | |
| CN106598988B (en) | Data processing method and equipment | |
| TWI598839B (en) | Method and apparatus for determining a target location | |
| Alvarez et al. | Improvement of plankton biovolume estimates derived from image-based automatic sampling devices: application to FlowCAM | |
| CN102629271B (en) | Complex data visualization method and equipment based on stacked tree graph | |
| CN110418161A (en) | Video reviewing method and device, electronic equipment and readable storage medium storing program for executing | |
| Stern et al. | On reconciling disparate studies of the sea-ice floe size distribution | |
| Guan et al. | DEM generation from lidar data in wooded mountain areas by cross-section-plane analysis | |
| CN109034036A (en) | A kind of video analysis method, Method of Teaching Quality Evaluation and system, computer readable storage medium | |
| JP2011523706A (en) | Signal search with 3D bitmap | |
| Huettmann et al. | Large-scale effects on the spatial distribution of seabirds in the Northwest Atlantic | |
| CN112053756A (en) | Inspection result quality evaluation method and system based on clinical specimen inspection data | |
| CN112153320B (en) | Method and device for measuring size of article, electronic equipment and storage medium | |
| CN114741612B (en) | Consumption habit classification method, system and storage medium based on big data | |
| CN108230016A (en) | A kind of market for farm products Price pass-through analysis method and analytical equipment | |
| CN113325443A (en) | Dynamic visual analysis method for GNSS space signal quality | |
| US20210004639A1 (en) | Apparatus and method for interactively viewing and clustering data segments from long data recordings | |
| CN117874315B (en) | User demand analysis display method, system, computer equipment and storage medium | |
| CN114297516A (en) | Event discovery and display method and system based on knowledge graph | |
| CN111027599B (en) | Clustering visualization method and device based on random sampling | |
| CN113076730A (en) | Test report intelligent management method, device, system and storage medium | |
| Hatami | Carbon estimation of individual trees using high laser density data of airborne lidar: A case study in Bois Noir, France | |
| CN114490624B (en) | Big data-based intelligent statistical method and system for people, house, enterprise and readable storage medium | |
| KR20200005853A (en) | Method and System for People Count based on Deep Learning | |
| JP7560044B2 (en) | Server for managing plankton distribution information, user terminal, and system equipped with server and user terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |