Internet information propagation effect analysis method based on multi-dimensional data

Abstract

The invention provides an Internet information propagation effect analysis method based on multi-dimensional data, and belongs to the technical field of information. The problem that the information spreading effect and influence cannot be comprehensively evaluated is solved; the method specifically comprises the following steps: S1, collecting Internet propagation information, S2, classifying propagation files according to a propagation region and propagation time, calculating regional propagation force, and constructing a regional propagation force diagram; analyzing the type of the propagation node; constructing a propagation node type graph; s3, analyzing the content of the propagation file, and judging the expression tendency of the propagation file to obtain an expression tendency graph; s4, calculating an influence value of the propagation file, and constructing an influence figure graph; s5, constructing a multi-dimensional analysis graph according to the regional propagation force graph, the propagation node type graph, the expression tendency graph and the influence character graph; according to the method, a plurality of propagation dimensions are displayed, so that a user can intuitively understand and analyze the propagation effect of information.

Description

Technical Field

[0001] The present invention discloses an Internet information dissemination effect analysis method based on multi-dimensional data, and relates to the field of information technology. Background Art

[0002] The existing analysis methods of Internet information dissemination effects have the following shortcomings: Few analysis dimensions: Existing information dissemination analysis tools cannot comprehensively evaluate the effectiveness and impact of information dissemination.

[0003] Poor readability: Traditional information dissemination analysis tools typically only display a single or a few information dimensions through charts, resulting in an incomplete presentation of information. When attempting to display multiple information dimensions simultaneously, although intended to provide a more comprehensive analytical perspective, the actual presentation is poor due to the complex layout of the charts, crowded visual elements, or lack of effective integration, making it difficult to quickly understand the information, seriously affecting practicality and user interpretation efficiency.

[0004] User limitations: Traditional information dissemination analysis tools (such as Gephi, UCINET, and the Python-NLP library) are complex in user interfaces, require complex parameter configuration, require programming skills (such as Python scripting), and are highly code-dependent. Furthermore, they have a steep learning curve and require long-term training to master. As a result, non-professional users are often deterred by the high time investment and technical barriers to entry when faced with these tools, hindering their widespread application in daily analysis tasks. Summary of the Invention

[0005] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide an Internet information dissemination effect analysis method based on multi-dimensional data, aiming to solve the problem of difficulty in finding talent information.

[0006] In order to achieve the above-mentioned purpose, the present invention is implemented through the following technical solutions: The Internet information dissemination effect analysis method based on multi-dimensional data includes: Step S1: Collect Internet dissemination information, including dissemination files, dissemination time, and dissemination area, where dissemination files include disseminator information, dissemination file content, dissemination file forwarding volume, and dissemination file comment volume; Step S2: Classify the propagation files according to the propagation regions to obtain regional propagation files, calculate the regional propagation power according to the regional propagation files, and construct a regional propagation power map based on the regional propagation power; Classify the propagation files according to the propagation time to obtain the propagation files in the time period, count the number of files propagated in the time period, analyze the propagation node type; and construct a propagation node type graph; Step S3: Analyze the content of the disseminated files, determine the expression tendency of the disseminated files, count the number of files with different expression tendencies, and visualize the statistical results to obtain an expression tendency graph; Step S4: Calculate the influence value of the dissemination file based on the number of forwarding and commenting on the dissemination file, display the corresponding disseminator information according to the influence value, and construct an influencer map; Step S5: Integrate the regional communication power map, communication node type map, expression tendency map and influential person map to construct a multi-dimensional analysis map.

[0007] Furthermore, the specific steps of step S2 are as follows: Step S21: Count the spread files to obtain the number a of spread files, count the spread regions to obtain the type b of spread regions; classify the spread files according to the type of spread regions to obtain regional spread files, record the number of regional spread files, normalize the number of regional spread files to obtain the regional spread power of each type of spread region, and construct a regional spread power map based on the regional spread power; Step S22: Obtain the propagation time of the Internet propagation information, divide the propagation time into stages, obtain the divided time periods, analyze the divided time periods, obtain the change in the number of propagated files in the divided time periods, obtain the propagation node type based on the change in the number of propagated files, count the propagation node types, and construct a propagation node graph.

[0008] Furthermore, the specific steps of step S21 are as follows: Step S211: Classify the dissemination files according to the number of dissemination files a and the type of dissemination area b; loop through the dissemination files, obtain the dissemination area of each dissemination file, count the number of files in the same dissemination area, and obtain the number of dissemination files in each area, which is recorded as cb(1), cb(2), ..., cb(b); Step S212: Obtain the maximum number of regionally spread files to obtain the maximum number of regionally spread files, recorded as zdc; obtain the minimum number of regionally spread files to obtain the minimum number of regionally spread files, recorded as zxc; normalize the number of regionally spread files based on the maximum number of regionally spread files zbc and the minimum number of regionally spread files zxc to obtain the regional spread power cbl(i); ; Where: cb(i) refers to the number of regional dissemination files, 1≤i≤b; Step S213: Construct a semicircular sector area, obtain the maximum arc Π of the semicircular sector area, set the arc hd for the region according to the maximum arc of the semicircular sector area and the regional communication power, sort the arcs in descending order, obtain a descending arc list, fill the semicircular sector area according to the descending arc list, and mark the type of communication area at the corresponding arc position; obtain pictures of each communication area, and display the pictures of each communication area in the order of the descending arc list on the outside of the semicircular sector area; obtain a regional communication power map.

[0009] Furthermore, the specific steps of step S22 are as follows: Step S221: Obtain the start propagation time, recorded as qsj; obtain the end propagation time, recorded as zsj; calculate based on the start propagation time and the end propagation time to obtain the propagation time interval qj, qj = zsj - qsj, divide the propagation time interval into three equal parts to obtain the early information propagation period, the middle information propagation period, and the late information propagation period; The early stage of information dissemination is recorded as xcq, and the value range of xcq is [qsj, qsj+qj / 3]; The middle period of information dissemination is denoted as xcz, and the value range of xcz is [qsj+qj / 3,zsj-qj / 3]; The late stage of information dissemination is denoted as xch, and the value range of xch is [zsj-qj / 3, zsj]; Analyze the early, middle and late stages of information dissemination respectively to obtain information nodes in different dissemination periods; Step S222: Obtain the node type, highlight different node types using different colors, sort the nodes in the order of early information dissemination, mid-term information dissemination, and late information dissemination, and construct a dissemination node graph.

[0010] Furthermore, the specific steps of step S221 are as follows: Analyze the early stage of information dissemination, extract the dissemination files with the dissemination time at xcq, and obtain the dissemination files in the early stage of information dissemination. According to the dissemination files in the early stage of information dissemination, obtain the number of files at different times, which is recorded as qws(qt), where: qws(qt) means that the number of files at time qt is qws; qt∈[qsj,qsj+qj / 3]; Through qws (qt) image drawing, a curve showing the change of the number of propagated files and time is obtained; qs nodes are selected by user and evenly distributed on the change curve; Calculate the front-end change rate of the node according to the change curve to obtain the first judgment value ypd(j) of the early node: ; Where: Δqt represents the small change of qt; qsj and qj are the value parameters of qt, qt∈[qsj,qsj+qj / 3]; Calculate the change rate of the node backend according to the change curve to obtain the second judgment value epd(j) of the early node: ; The node type is judged based on the first judgment value ypd(j) of the previous node and the second judgment value epd(j) of the previous node: If ypd(j) = 0, the node is the starting point; If epd(j) = 0, the node is the end point; If epd(j)>ypd(j)>0, the node is an ascending point; If ypd(j)≥epd(j)>0, the node is a bottleneck; If ypd(j)>0>epd(j), the node is a burst point; If ypd(j) < 0 and epd(j) < 0, the node is a drop point.

[0011] Furthermore, the specific steps of step S221 also include: Analyze the mid-term of information dissemination, extract the dissemination files with the dissemination time at xcz, and obtain the dissemination files in the mid-term of information dissemination. According to the dissemination files in the mid-term of information dissemination, obtain the number of files at different times, which is recorded as zws(zt), where: zws(zt) means that the number of files at time zt is zws; zt∈[qsj+qj / 3,zsj-qj / 3]; Through zws (zt) to draw the image, we can get the curve of the number of spread files and time; we can select zs nodes by ourselves and evenly distribute them on the curve. Calculate the front-end change rate of the node according to the change curve to obtain the first judgment value yzd (k) of the mid-term node: ; Where: Δzt represents a small change in zt; qsj and qj are the value parameters of zt, zt∈[qsj+qj / 3,zsj-qj / 3]; Calculate the node backend change rate according to the change curve to obtain the second judgment value ezd(k) of the mid-term node: ; The mid-term node type is judged according to the first judgment value yzd(k) and the second judgment value ezd(k) of the mid-term node to obtain the mid-term node type.

[0012] Furthermore, the specific steps of step S221 also include: Analyze the late stage of information dissemination, extract the dissemination files with the dissemination time at xch, and obtain the dissemination files in the late stage of information dissemination. According to the dissemination files in the late stage of information dissemination, obtain the number of files at different times, which is recorded as hws(ht), where: hws(ht) means that the number of files at time ht is hws; ht∈[zsj-qj / 3,zsj]; By drawing an image using hws (ht), we can get a curve showing the change in the number of files transmitted and the change in time. We can also select hs nodes by ourselves and evenly distribute them on the curve. Calculate the front-end change rate of the node according to the change curve to obtain the first judgment value yhd (h) of the later node: ; Where: Δht represents the small change of ht; zsj and qj are the value parameters of ht, ht∈[zsj-qj / 3,zsj]; Calculate the change rate of the node backend according to the change curve to obtain the second judgment value ehd (h) of the later node: ; The type of the later node is judged according to the first judgment value yhd(h) of the later node and the second judgment value ehd(h) of the later node to obtain the type of the later node.

[0013] Furthermore, the specific steps of step S3 are as follows: Step S31: Obtain the content of the communication file, analyze the expression tendency of the communication file content, and obtain the emotional polarity of the communication file content; based on the emotional polarity of the communication file content, define the communication file as a positive communication file, a negative communication file, or a neutral communication file; Step S32: Extract the propagation files with the same propagation time and propagation area, record them as local propagation files, obtain the number of local propagation files jsl; obtain the number of positive propagation files in the local propagation files, record them as zsl; obtain the number of negative propagation files in the local propagation files, record them as fsl; obtain the number of neutral propagation files in the local propagation files, record them as xsl; zsl+fsl+xsl=jsl; Define three nodes to store propagation files with different expression tendencies: Get the maximum value among zsl, fsl, and xsl, record it as mx1, and record the remaining two values as mx2 and mx3; Set the first node to the expression tendency corresponding to mx1 and set a unique color to highlight it; reduce mx1 to obtain the updated number of mx1; ; Where: jsl is the number of local propagation files; Compare the updated mx1 with mx2 and mx3, obtain the expression tendency corresponding to the maximum value, set it as the second node, and set a unique color for it to highlight; Similarly, set up the third node; Step S33: Set nodes for the expression tendency of the propagation files at different propagation times, arrange the nodes in chronological order, count the number of nodes of each type, and record the number of nodes of each type after the node to obtain an expression tendency graph.

[0014] Furthermore, the specific steps of step S4 are as follows: Step S41: According to the number of disseminated files a, the forwarding amount of the disseminated files and the comment amount of the disseminated files are obtained, and the forwarding amount of the disseminated files is recorded as zf(1), zf(2), ..., zf(a), and the comment amount of the disseminated files is recorded as pl(1), pl(2), ..., pl(a); Set weights qz1 and qz2 for the forwarding volume and comment volume of the disseminated file; calculate the impact value yxz (v) based on the forwarding volume and comment volume of the disseminated file and their corresponding weights: ; Where: zf(v) represents the forwarding volume of the v-th dissemination file, pl(v) represents the comment volume of the v-th dissemination file; Step S42: Combined with the dissemination area, the influence values of the dissemination files in the same dissemination area are counted, the maximum influence value is extracted, the regional influence extreme value is obtained, the dissemination file corresponding to the regional influence extreme value is obtained, the communicator information is obtained according to the dissemination file, the communicator's avatar and nickname are displayed, and a display diagram of regional representatives is obtained; the display diagrams of regional representatives are integrated to obtain a diagram of influential people.

[0015] Furthermore, the specific steps of step S5 are as follows: Step S51: Integrate the regional communication power map, the communication node type map, the expression tendency map, and the influential person map to display the regional communication power, different time nodes, the information dissemination status, the information expression tendency, and the most influential person in the information dissemination process through images; Step S52: Set the regional communication force map in the center of the image, obtain the communication region type b, set b equal-dividing lines for the regional communication force map according to the communication region type, fill the communication node type map along the equal-dividing lines, fill the expression tendency map on the side of the communication node type map, and add the influential person map at the end of the node type map according to the equal-dividing lines; obtain a multi-dimensional analysis map.

[0016] Compared with the prior art, the present invention has the following beneficial effects: Multi-dimensional analysis: This invention provides a comprehensive perspective on information dissemination by integrating multiple dimensions; it enables users to not only observe the dissemination effect of a single event or media, but also analyze the overall dissemination trend of information from multiple angles, thereby making more accurate strategic adjustments.

[0017] Improve readability: The present invention adopts a fan-shaped matrix display method, in which each sector represents a communication dimension, and the size and color depth of the sector are adjusted according to the communication strength of the dimension; this intuitive visual presentation is not only beautiful, but also improves the readability of information and the user's information analysis efficiency; users can see at a glance which dimensions are the most communicative and which need to be strengthened, so that they can respond quickly.

[0018] Expanded application scope: By optimizing the layout and visual presentation of information, users will not feel overloaded even when there is a large amount of information. This design is not only suitable for professional data analysts but also for non-professional users, making the application scope of this tool wider. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments with reference to the following drawings: Figure 1 Schematic diagram of the method of the present invention; Figure 2 This is a schematic diagram of the node types of the present invention; Figure 3 This is a multi-dimensional analysis display diagram of the present invention. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] Example 1 See also Figure 1 ,The analysis methods of Internet information dissemination effects based on multi-dimensional data include: Step S1: Collect Internet dissemination information, including dissemination files, dissemination time, and dissemination area, where dissemination files include disseminator information, dissemination file content, dissemination file forwarding volume, and dissemination file comment volume; It should be noted that collecting information disseminated on the Internet refers to obtaining public information published by users of various platforms through program application interfaces.

[0022] Step S2: Classify the propagation files according to the propagation regions to obtain regional propagation files, calculate the regional propagation power according to the regional propagation files, and construct a regional propagation power map based on the regional propagation power; Classify the propagation files according to the propagation time to obtain the propagation files in the time period, count the number of files propagated in the time period, analyze the propagation node type; and construct a propagation node type graph; Step S21: Count the spread files to obtain the number a of spread files, count the spread regions to obtain the type b of spread regions; classify the spread files according to the type of spread regions to obtain regional spread files, record the number of regional spread files, normalize the number of regional spread files to obtain the regional spread power of each type of spread region, and construct a regional spread power map based on the regional spread power; Step S211: Based on the number of disseminated files a and the type of dissemination area b; classify the dissemination files, loop through the dissemination files, obtain the dissemination area of each dissemination file, count the number of files in the same dissemination area, and obtain the number of dissemination files in each area, which is recorded as cb(1), cb(2), ..., cb(b); where cb(1) + cb(2) + ... + cb(b) = a; Step S212: Obtain the maximum number of regionally spread files to obtain the maximum number of regionally spread files, recorded as zdc; obtain the minimum number of regionally spread files to obtain the minimum number of regionally spread files, recorded as zxc; normalize the number of regionally spread files based on the maximum number of regionally spread files zbc and the minimum number of regionally spread files zxc to obtain the regional spread power cbl(i); ; Where: cb(i) refers to the number of regional dissemination files, 1≤i≤b; Step S213: Construct a semicircular sector area, obtain the maximum arc Π of the semicircular sector area, set the arc hd for the region according to the maximum arc of the semicircular sector area and the regional communication power, sort the arcs in descending order, obtain a descending arc list, fill the semicircular sector area according to the descending arc list, and mark the type of communication area at the corresponding arc position; obtain pictures of each communication area, and display the pictures of each communication area in the order of the descending arc list on the outside of the semicircular sector area; obtain a regional communication power map.

[0023] Step S22: Obtain the propagation time of the Internet propagation information, divide the propagation time into stages to obtain divided time periods, analyze the divided time periods, obtain the change in the number of propagated files in the divided time periods, obtain the propagation node type based on the change in the number of propagated files, collect statistics on the propagation node types, and construct a propagation node graph; Step S221: Obtain the start propagation time, recorded as qsj; obtain the end propagation time, recorded as zsj; calculate based on the start propagation time and the end propagation time to obtain the propagation time interval qj, qj = zsj - qsj, divide the propagation time interval into three equal parts to obtain the early information propagation period, the middle information propagation period, and the late information propagation period; The early stage of information dissemination is recorded as xcq, and the value range of xcq is [qsj, qsj + qj / 3]; The middle period of information dissemination is recorded as xcz, and the value range of xcz is [qsj+qj / 3,zsj-qj / 3]; The later stage of information dissemination is denoted as xch, and the value range of xch is [zsj-qj / 3, zsj]; Analyze the early, middle and late stages of information dissemination respectively to obtain information nodes in different dissemination periods; Step S2211: Analyze the early stage of information dissemination, extract the dissemination files with a dissemination time of xcq, and obtain the dissemination files in the early stage of information dissemination. According to the dissemination files in the early stage of information dissemination, obtain the number of files at different times, which is recorded as qws(qt), where: qws(qt) means that the number of files at time qt is qws; qt∈[qsj,qsj+qj / 3]; See also Figure 2 ; Use qws (qt) to draw an image and obtain the change curve of the number of propagated files and time; custom select qs nodes and evenly distribute qs nodes on the change curve; Calculate the front-end change rate of the node according to the change curve to obtain the first judgment value ypd(j) of the early node: ; Where: Δqt represents the small change of qt; qsj and qj are the value parameters of qt, qt∈[qsj,qsj+qj / 3]; Calculate the change rate of the node backend according to the change curve to obtain the second judgment value epd(j) of the early node: ; The node type is judged based on the first judgment value ypd(j) of the previous node and the second judgment value epd(j) of the previous node: If ypd(j) = 0, the node is the starting point; If epd(j) = 0, the node is the end point; If epd(j)>ypd(j)>0, the node is an ascending point; If ypd(j)≥epd(j)>0, the node is a bottleneck; If ypd(j)>0>epd(j), the node is a burst point; If ypd(j) < 0 and epd(j) < 0, the node is a drop point; It should be noted that: the starting point indicates the initial moment when the curve begins to rise, marking the entry of the quantity from a static or low level into the growth stage; the rising point indicates the node where the growth rate begins to accelerate, and the slope of the curve becomes steeper; the explosion point indicates that the quantity reaches a peak or critical threshold, which is the highest point in the growth stage; the blocking point indicates the node where growth is hindered, and the growth rate of the quantity drops significantly or stagnates; the falling point indicates the node where the quantity begins to decline continuously, marking the entry into the recession stage; the end point indicates the end point where the quantity tends to stabilize or return to zero, and the process is completely over.

[0024] Step S2212: Analyze the mid-term of information dissemination, extract the dissemination files with the dissemination time at xcz, and obtain the dissemination files in the mid-term of information dissemination. According to the dissemination files in the mid-term of information dissemination, obtain the number of files at different times, which is recorded as zws(zt), where: zws(zt) means that the number of files at time zt is zws; zt∈[qsj+qj / 3,zsj-qj / 3]; Through zws (zt) to draw the image, we can get the curve of the number of spread files and time; we can select zs nodes by ourselves and evenly distribute them on the curve. Calculate the front-end change rate of the node according to the change curve to obtain the first judgment value yzd (k) of the mid-term node: ; Where: Δzt represents a small change in zt; qsj and qj are the value parameters of zt, zt∈[qsj+qj / 3,zsj-qj / 3]; Calculate the node backend change rate according to the change curve to obtain the second judgment value ezd(k) of the mid-term node: ; The mid-term node type is determined based on the first determination value yzd(k) and the second determination value ezd(k) of the mid-term node in combination with the determination process of step S2211 to obtain the mid-term node type.

[0025] Step S2213: Analyze the late stage of information dissemination, extract the dissemination files with the dissemination time at xch, and obtain the dissemination files of the late stage of information dissemination. According to the dissemination files of the late stage of information dissemination, obtain the number of files at different times, which is recorded as hws(ht), where: hws(ht) means that the number of files at time ht is hws; ht∈[zsj-qj / 3,zsj]; By drawing an image using hws (ht), we can get a curve showing the change in the number of files transmitted and the change in time. We can also select hs nodes by ourselves and evenly distribute them on the curve. Calculate the front-end change rate of the node according to the change curve to obtain the first judgment value yhd (h) of the later node: ; Where: Δht represents the small change of ht; zsj and qj are the value parameters of ht, ht∈[zsj-qj / 3,zsj]; Calculate the change rate of the node backend according to the change curve to obtain the second judgment value ehd (h) of the later node: ; The type of the late node is determined based on the first determination value yhd(h) of the late node and the second determination value ehd(h) of the late node in combination with the determination process of step S2211 to obtain the type of the late node.

[0026] Step S222: Obtain node types, highlight different node types using different colors, sort the nodes in the order of early information dissemination, mid-information dissemination, and late information dissemination, and construct a dissemination node graph; Step S3: Analyze the content of the disseminated files, determine the expression tendency of the disseminated files, count the number of files with different expression tendencies, and visualize the statistical results to obtain an expression tendency graph; Step S31: Obtain the content of the dissemination file txt, analyze the expression tendency of the dissemination file content through TextBlob, and obtain the emotional polarity of the dissemination file content; the details are as follows: from textblob import TextBlob text = txt blob = TextBlob(text) print(blob.sentiment) # Output: polarity=-0.3 It should be noted that polarity=-0.3 represents the sentiment polarity of the disseminated file content txt, and the sentiment polarity ranges from -1 (negative) to 1 (positive).

[0027] According to the emotional polarity of the content of the communication document, the communication document is defined as positive communication document, negative communication document or neutral communication document; Among them: the sentiment polarity of positive communication files is [0.33, 1], the sentiment polarity of negative communication files is [-1, -0.33], and the sentiment polarity of neutral communication files is [-0.33, 0.33].

[0028] Step S32: Extract the propagation files with the same propagation time and propagation area, record them as local propagation files, obtain the number of local propagation files jsl; obtain the number of positive propagation files in the local propagation files, record them as zsl; obtain the number of negative propagation files in the local propagation files, record them as fsl; obtain the number of neutral propagation files in the local propagation files, record them as xsl; zsl+fsl+xsl=jsl; Define three nodes to store propagation files with different expression tendencies: Get the maximum value among zsl, fsl, and xsl, record it as mx1, and record the remaining two values as mx2 and mx3; Set the first node to the expression tendency corresponding to mx1 and set a unique color to highlight it; reduce mx1 to obtain the updated number of mx1; ; Where: jsl is the number of local propagation files; Compare the updated mx1 with mx2 and mx3, obtain the expression tendency corresponding to the maximum value, set it as the second node, and set a unique color for it to highlight; Set up the third node in the same way.

[0029] For example, if zsl = 60, fsl = 50, and xsl = 10, the maximum value is the number of positively propagated files. The first node is set to a positive trend and represented by blue. Then, the value of zal is reduced to zsl = 60 - (60 + 50 + 10) / 3 = 20. The values for the second comparison are zsl = 20, fsl = 50, and xsl = 10. The maximum value is the number of negatively propagated files. The second node is set to negative and colored red. The value of fsl is then reduced to fal = 50 - (60 + 50 + 10) / 3 = 10. The values for the third comparison are zsl=20, fsl=10, and xsl=10, where the maximum value is the number corresponding to the positively propagated files. The third node is set to a positive tendency and is represented by blue.

[0030] Step S33: Set nodes for the expression tendency of the propagation files at different propagation times, arrange the nodes in chronological order, count the number of nodes of each type, and record the number of nodes of each type after the node to obtain an expression tendency graph.

[0031] Step S4: Calculate the influence value of the dissemination file based on the number of forwarding and commenting on the dissemination file, display the corresponding disseminator information according to the influence value, and construct an influencer map; Step S41: According to the number of disseminated files a, the forwarding amount of the disseminated files and the comment amount of the disseminated files are obtained, and the forwarding amount of the disseminated files is recorded as zf(1), zf(2), ..., zf(a), and the comment amount of the disseminated files is recorded as pl(1), pl(2), ..., pl(a); According to the forwarding amount of the propagated files zf(1), zf(2), ..., zf(a), the forwarding amount of the propagated files is averaged to obtain the forwarding mean zfp; Set the weight qz1 based on the forwarding mean and the forwarding volume of the spread file; ; Where: zf(z) represents the forwarding amount of the zth dissemination file; According to the number of comments on the disseminated documents pl(1), pl(2), ..., pl(a), the mean of the number of comments on the disseminated documents is calculated to obtain the mean value of comments plp; Set the weight qz2 based on the mean value of comments and the number of comments on the disseminated document; ; Where: pl(z) represents the number of comments on the z-th propagated document; The influence value yxz(v) is calculated based on the forwarding volume and comment volume of the disseminated file and their corresponding weights: ; Where: zf(v) represents the forwarding volume of the v-th dissemination file, pl(v) represents the comment volume of the v-th dissemination file; Step S42: Combined with the dissemination area, the influence values of the dissemination files in the same dissemination area are counted, the maximum influence value is extracted, the regional influence extreme value is obtained, the dissemination file corresponding to the regional influence extreme value is obtained, the communicator information is obtained according to the dissemination file, the communicator's avatar and nickname are displayed, and a display diagram of regional representatives is obtained; the display diagrams of regional representatives are integrated to obtain a diagram of influential people.

[0032] Step S5: Integrate the regional communication force map, communication node type map, expression tendency map, and influential person map to construct a multi-dimensional analysis map; See also Figure 3 Step S51: Integrate the regional communication power map, the communication node type map, the expression tendency map, and the influential person map to display the regional communication power, different time nodes, the information dissemination status, the information expression tendency, and the most influential person in the information dissemination process through images; Step S52: Set the regional communication force map in the center of the image, obtain the communication region type b, set b equal-dividing lines for the regional communication force map according to the communication region type, fill the communication node type map along the equal-dividing lines, fill the expression tendency map on the side of the communication node type map, and add the influential person map at the end of the node type map according to the equal-dividing lines; obtain a multi-dimensional analysis map.

[0033] The above formulas are all dimensionless and calculated by taking their numerical values. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions. For example, if there are weight coefficients and proportional coefficients, the size of the settings is to quantify each parameter to obtain a specific value, which is convenient for subsequent comparison. Regarding the size of the weight coefficient and the proportional coefficient, as long as it does not affect the proportional relationship between the parameter and the quantized value, it is fine.

[0034] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. The Internet information dissemination effect analysis method based on multi-dimensional data is characterized by: The analysis method comprises: Step S1: Collect Internet dissemination information, including dissemination files, dissemination time, and dissemination area, where dissemination files include disseminator information, dissemination file content, dissemination file forwarding volume, and dissemination file comment volume; Step S2: Classify the propagation files according to the propagation regions to obtain regional propagation files, calculate the regional propagation power according to the regional propagation files, and construct a regional propagation power map based on the regional propagation power; Classify the propagation files according to the propagation time to obtain the propagation files in the time period, count the number of files propagated in the time period, analyze the propagation node type; and construct a propagation node type graph; Step S3: Analyze the content of the disseminated files, determine the expression tendency of the disseminated files, count the number of files with different expression tendencies, and visualize the statistical results to obtain an expression tendency graph; Step S4: Calculate the influence value of the dissemination file based on the number of forwarding and commenting on the dissemination file, display the corresponding disseminator information according to the influence value, and construct an influencer map; Step S5: Integrate the regional communication power map, communication node type map, expression tendency map and influential person map to construct a multi-dimensional analysis map.

2. The method for analyzing the effect of Internet information dissemination based on multi-dimensional data according to claim 1, characterized in that: The specific steps of step S2 are as follows: Step S21: Count the spread files to obtain the number a of spread files, count the spread regions to obtain the type b of spread regions; classify the spread files according to the type of spread regions to obtain regional spread files, record the number of regional spread files, normalize the number of regional spread files to obtain the regional spread power of each type of spread region, and construct a regional spread power map based on the regional spread power; Step S22: Obtain the propagation time of the Internet propagation information, divide the propagation time into stages, obtain the divided time periods, analyze the divided time periods, obtain the change in the number of propagated files in the divided time periods, obtain the propagation node type based on the change in the number of propagated files, count the propagation node types, and construct a propagation node graph.

3. The method for analyzing the effect of Internet information dissemination based on multi-dimensional data according to claim 2, characterized in that: The specific steps of step S21 are as follows: Step S211: Classify the dissemination files according to the number of dissemination files a and the type of dissemination area b; loop through the dissemination files, obtain the dissemination area of each dissemination file, count the number of files in the same dissemination area, and obtain the number of dissemination files in each area, which is recorded as cb(1), cb(2), ..., cb(b); Step S212: obtaining the maximum value of the number of regionally disseminated files, and obtaining the maximum number of regionally disseminated files, which is recorded as zdc; Obtain the minimum value of the number of regional propagation files to obtain the minimum number of regional propagation files, which is recorded as zxc; According to the maximum number of regional dissemination files zbc and the minimum number of regional dissemination files zxc, the number of regional dissemination files is normalized to obtain the regional dissemination power cbl(i); ； Where: cb(i) refers to the number of regional dissemination files, 1≤i≤b; Step S213: Construct a semicircular sector area, obtain the maximum arc Π of the semicircular sector area, set the arc hd for the region according to the maximum arc of the semicircular sector area and the regional communication power, sort the arcs in descending order, obtain a descending arc list, fill the semicircular sector area according to the descending arc list, and mark the type of communication area at the corresponding arc position; obtain pictures of each communication area, and display the pictures of each communication area in the order of the descending arc list on the outside of the semicircular sector area; obtain a regional communication power map.

4. The method for analyzing the effect of Internet information dissemination based on multi-dimensional data according to claim 2, characterized in that: The specific steps of step S22 are as follows: Step S221: Obtain the start propagation time, recorded as qsj; obtain the end propagation time, recorded as zsj; calculate based on the start propagation time and the end propagation time to obtain the propagation time interval qj, qj = zsj - qsj, divide the propagation time interval into three equal parts to obtain the early information propagation period, the middle information propagation period, and the late information propagation period; The early stage of information dissemination is recorded as xcq, and the value range of xcq is [qsj, qsj+qj / 3]; The middle period of information dissemination is denoted as xcz, and the value range of xcz is [qsj+qj / 3,zsj-qj / 3]; The late stage of information dissemination is denoted as xch, and the value range of xch is [zsj-qj / 3, zsj]; Analyze the early, middle and late stages of information dissemination respectively to obtain information nodes in different dissemination periods; Step S222: Obtain the node type, highlight different node types using different colors, sort the nodes in the order of early information dissemination, mid-term information dissemination, and late information dissemination, and construct a dissemination node graph.

5. The method for analyzing the effect of Internet information dissemination based on multi-dimensional data according to claim 4 is characterized in that: The specific steps of step S221 are as follows: Analyze the early stage of information dissemination, extract the dissemination files with the dissemination time at xcq, and obtain the dissemination files in the early stage of information dissemination. According to the dissemination files in the early stage of information dissemination, obtain the number of files at different times, which is recorded as qws(qt), where: qws(qt) means that the number of files at time qt is qws; qt∈[qsj,qsj+qj / 3]; Through qws (qt) image drawing, a curve showing the change of the number of propagated files and time is obtained; qs nodes are selected by user and evenly distributed on the change curve; Calculate the front-end change rate of the node according to the change curve to obtain the first judgment value ypd(j) of the early node: ； Where: Δqt represents the small change of qt; qsj and qj are the value parameters of qt, qt∈[qsj,qsj+qj / 3]; Calculate the change rate of the node backend according to the change curve to obtain the second judgment value epd(j) of the early node: ； The node type is judged based on the first judgment value ypd(j) of the previous node and the second judgment value epd(j) of the previous node: If ypd(j) = 0, the node is the starting point; If epd(j) = 0, the node is the end point; If epd(j)>ypd(j)>0, the node is an ascending point; If ypd(j)≥epd(j)>0, the node is a congestion point; If ypd(j)>0>epd(j), the node is a burst point; If ypd(j) < 0 and epd(j) < 0, the node is a drop point.

6. The method for analyzing the effect of Internet information dissemination based on multi-dimensional data according to claim 4 is characterized in that: The specific steps of step S221 also include: Analyze the mid-term of information dissemination, extract the dissemination files with the dissemination time at xcz, and obtain the dissemination files in the mid-term of information dissemination. According to the dissemination files in the mid-term of information dissemination, obtain the number of files at different times, which is recorded as zws(zt), where: zws(zt) means that the number of files at time zt is zws; zt∈[qsj+qj / 3,zsj-qj / 3]; Through zws (zt) to draw the image, we can get the curve of the number of spread files and time; we can select zs nodes by ourselves and evenly distribute them on the curve. Calculate the front-end change rate of the node according to the change curve to obtain the first judgment value yzd (k) of the mid-term node: ； Where: Δzt represents a small change in zt; qsj and qj are the value parameters of zt, zt∈[qsj+qj / 3,zsj-qj / 3]; Calculate the node backend change rate according to the change curve to obtain the second judgment value ezd(k) of the mid-term node: ； The mid-term node type is judged according to the first judgment value yzd(k) and the second judgment value ezd(k) of the mid-term node to obtain the mid-term node type.

7. The method for analyzing the effect of Internet information dissemination based on multi-dimensional data according to claim 4 is characterized in that: The specific steps of step S221 also include: Analyze the late stage of information dissemination, extract the dissemination files with the dissemination time at xch, and obtain the dissemination files in the late stage of information dissemination. According to the dissemination files in the late stage of information dissemination, obtain the number of files at different times, which is recorded as hws(ht), where: hws(ht) means that the number of files at time ht is hws; ht∈[zsj-qj / 3,zsj]; By drawing an image using hws (ht), we can get a curve showing the change in the number of files transmitted and the change in time. We can also select hs nodes by ourselves and evenly distribute them on the curve. Calculate the front-end change rate of the node according to the change curve to obtain the first judgment value yhd (h) of the later node: ； Where: Δht represents the small change of ht; zsj and qj are the value parameters of ht, ht∈[zsj-qj / 3,zsj]; Calculate the change rate of the node backend according to the change curve to obtain the second judgment value ehd (h) of the later node: ； The type of the later node is judged according to the first judgment value yhd(h) of the later node and the second judgment value ehd(h) of the later node to obtain the type of the later node.

8. The method for analyzing the effect of Internet information dissemination based on multi-dimensional data according to claim 1, characterized in that: The specific steps of step S3 are as follows: Step S31: Obtain the content of the communication file, analyze the expression tendency of the communication file content, and obtain the emotional polarity of the communication file content; based on the emotional polarity of the communication file content, define the communication file as a positive communication file, a negative communication file, or a neutral communication file; Step S32: Extract the propagation files with the same propagation time and propagation area, record them as local propagation files, obtain the number of local propagation files jsl; obtain the number of positive propagation files in the local propagation files, record them as zsl; obtain the number of negative propagation files in the local propagation files, record them as fsl; obtain the number of neutral propagation files in the local propagation files, record them as xsl; zsl+fsl+xsl=jsl; Define three nodes to store propagation files with different expression tendencies: Get the maximum value among zsl, fsl, and xsl, record it as mx1, and record the remaining two values as mx2 and mx3; Set the first node to the expression tendency corresponding to mx1 and set a unique color to highlight it; reduce mx1 to obtain the updated number of mx1; ； Where: jsl is the number of local propagation files; Compare the updated mx1 with mx2 and mx3, obtain the expression tendency corresponding to the maximum value, set it as the second node, and set a unique color for it to highlight; Similarly, set up the third node; Step S33: Set nodes for the expression tendency of the propagation files at different propagation times, arrange the nodes in chronological order, count the number of nodes of each type, and record the number of nodes of each type after the node to obtain an expression tendency graph.

9. The method for analyzing the effect of Internet information dissemination based on multi-dimensional data according to claim 1, characterized in that: The specific steps of step S4 are as follows: Step S41: According to the number of disseminated files a, the forwarding amount of the disseminated files and the comment amount of the disseminated files are obtained, and the forwarding amount of the disseminated files is recorded as zf(1), zf(2), ..., zf(a), and the comment amount of the disseminated files is recorded as pl(1), pl(2), ..., pl(a); Set weights qz1 and qz2 for the forwarding volume and comment volume of the disseminated file; calculate the impact value yxz (v) based on the forwarding volume and comment volume of the disseminated file and their corresponding weights: ； Where: zf(v) represents the forwarding volume of the v-th dissemination file, pl(v) represents the comment volume of the v-th dissemination file; Step S42: Combined with the dissemination area, the influence values of the dissemination files in the same dissemination area are counted, the maximum influence value is extracted, the regional influence extreme value is obtained, the dissemination file corresponding to the regional influence extreme value is obtained, the communicator information is obtained according to the dissemination file, the communicator's avatar and nickname are displayed, and a display diagram of regional representatives is obtained; the display diagrams of regional representatives are integrated to obtain a diagram of influential people.

10. The method for analyzing the effect of Internet information dissemination based on multi-dimensional data according to claim 1, characterized in that: The specific steps of step S5 are as follows: Step S51: Integrate the regional communication power map, the communication node type map, the expression tendency map, and the influential person map to display the regional communication power, different time nodes, the information dissemination status, the information expression tendency, and the most influential person in the information dissemination process through images; Step S52: Set the regional communication force map in the center of the image, obtain the communication region type b, set b equal-dividing lines for the regional communication force map according to the communication region type, fill the communication node type map along the equal-dividing lines, fill the expression tendency map on the side of the communication node type map, and add the influential person map at the end of the node type map according to the equal-dividing lines; obtain a multi-dimensional analysis map.

Images