Marketing effect analysis method and system based on digital marketing

Abstract

The present invention relates to the technical field of e-commerce, and discloses a marketing effect analysis method and system based on digital marketing, the method comprising: constructing a communication network between each of the delivery users, and calculating the propagation speed of digital products using the communication network; clustering the delivery users to obtain clustered users, calculating the activity level of the clustered users, identifying the active users among the clustered users, analyzing the centrality of the active users in the communication network, and identifying the trust of the communicators in the communicators; respectively calculating the click-through rate, discussion rate and dissemination rate of the digital products by the communicators, determining the product popularity of the digital products, calculating the purchase rate of the digital products by the delivery users, and identifying the audience positioning ability of digital marketing; analyzing the satisfaction of the delivery users with the digital products; and using the short-term benefits and long-term benefits as the marketing effect analysis results of the digital products under digital marketing. The present invention can improve the efficiency of marketing effect analysis under digital marketing.

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce, and in particular to a marketing effect analysis method and system based on digital marketing. Background Art

[0002] Digital marketing mainly refers to the refined operation of Internet traffic under the strategic planning of the enterprise, which includes paid advertising investment in various media channels within the budget of the enterprise and free traffic management, including but not limited to SEO optimization, encyclopedia Q&A, self-media operation, private domain traffic and other full media penetration, ultimately achieving the marketing goals of the enterprise, realizing a better marketing input-output ratio model, and adjusting subsequent marketing ideas based on feedback from the results.

[0003] At present, the marketing effect analysis methods under digital marketing include ROI (return on investment) evaluation method, visit traffic and conversion rate evaluation method, brand reputation and image evaluation method, user satisfaction evaluation method, etc. The ROI (return on investment) evaluation method mainly evaluates through the ratio of input and output, analyzes the relationship between input capital and output results, and thus considers the highest input score of digital marketing. The visit traffic and conversion rate evaluation method evaluates digital marketing from multiple perspectives through statistical analysis of visit volume and conversion rate. The brand reputation and image evaluation method evaluates the brand marketing effect by analyzing the brand's popularity and image. The user satisfaction evaluation method evaluates the effect of digital marketing from the user's perspective through the evaluation of user experience. Due to the complex network environment and large population base, it is not a simple matter to analyze the marketing effect of digital marketing in the network environment. This involves a large amount of data processing, and the marketing effect evaluated by only analyzing the brand image, or analyzing user satisfaction, or analyzing the traffic and conversion rate is not comprehensive. Therefore, the efficiency of marketing effect analysis under digital marketing is insufficient. Summary of the invention

[0004] In order to solve the above problems, the present invention provides a marketing effect analysis method and system based on digital marketing, which can improve the efficiency of marketing effect analysis under digital marketing.

[0005] In a first aspect, the present invention provides a marketing effect analysis method based on digital marketing, comprising:

[0006] Acquire digital products under digital marketing, query the delivery method of the digital products, analyze the delivery users of the digital products under the delivery method, construct a communication network between each of the delivery users, and calculate the communication speed of the digital products using the communication network;

[0007] Perform user clustering on the delivery users to obtain clustered users, calculate the activity level of the clustered users, identify active users among the clustered users by using the activity level, analyze the centrality of the active users in the communication network, and identify the trust of the communicators among the active users by the communicators by using the centrality;

[0008] Calculate the click rate, discussion rate and dissemination rate of the digital product by the recipients respectively, determine the product popularity of the digital product based on the trust, and calculate the purchase rate of the digital product by the users who placed the product, and identify the audience targeting capability of the digital marketing based on the purchase rate and the product popularity;

[0009] Collecting backend data of the digital product, querying the backend data for product feedback from the user on the digital product, extracting emotional information and evaluation information from the product feedback, obtaining the appearance occasion and appearance time of the digital product, and analyzing the satisfaction of the user on the digital product based on the appearance occasion and appearance time by using the emotional information and the evaluation information;

[0010] The short-term benefits of the digital products under the digital marketing are analyzed using the propagation speed, the audience positioning capability and the satisfaction level, and the long-term benefits of the digital products under the digital marketing are analyzed using the propagation speed, the audience positioning capability and the satisfaction level, and the short-term benefits and the long-term benefits are used as the marketing effect analysis results of the digital products under the digital marketing.

[0011] In a possible implementation manner of the first aspect, the constructing a propagation network between each of the delivery users includes:

[0012] Determine whether there is a communication relationship between each of the delivery users;

[0013] When the communication relationship exists between each of the delivery users, identifying the direct communication relationship and the indirect communication relationship between each of the delivery users;

[0014] According to the direct propagation relationship, a first series network is constructed between each of the delivery users;

[0015] According to the indirect communication relationship, combining the communication group of the communicator and the dissemination group of the disseminator among the delivery users;

[0016] Establishing a second series network between the transmitting group and the transmitted group;

[0017] When the propagation relationship does not exist between each of the delivery users, constructing a parallel network between each of the delivery users;

[0018] The propagation network is obtained by combining the first series network, the second series network and the parallel network.

[0019] In a possible implementation manner of the first aspect, calculating the propagation speed of the digital product by using the propagation network includes:

[0020] Query the dissemination time of the digital product by the disseminator in the dissemination network and the reception time of the digital product by the disseminator in the dissemination network;

[0021] According to the propagation time and the reception time, the average shortest duration in the propagation network is calculated using the following formula:

[0022]

[0023] in, represents the average minimum duration, Represents the total number of users in the distribution network. Indicates the transmission network The communication moment of the first communicator and the The shortest time between the receiving moments of the communicators;

[0024] The reciprocal of the average shortest duration is taken as the propagation speed.

[0025] In a possible implementation manner of the first aspect, clustering the delivery users to obtain clustered users includes:

[0026] Query the predecessor users of the delivery user in the communication network;

[0027] When there are duplications among the predecessor users, the delivery users are clustered in the propagation network to obtain clustered users.

[0028] In a possible implementation manner of the first aspect, calculating the activity level of the clustered users includes:

[0029] Identifying the out-degree and in-degree of the clustered users in the propagation network;

[0030] According to the out-degree and the in-degree, the activity level of the clustered users is calculated using the following formula:

[0031]

[0032] in, represents the activity level of the clustered users, represents the in-degree of cluster user k, represents the out-degree of cluster user k, and m represents the total number of cluster users.

[0033] In a possible implementation manner of the first aspect, analyzing the centrality of the active user in the communication network includes:

[0034] The closeness centrality of the active user in the communication network is calculated using the following formula:

[0035]

[0036] in, represents closeness to centrality, Represents the total number of active users, Indicates the serial number of the active user. Indicates active users With active users The shortest time between Indicates that among active users, The serial number of the active user outside;

[0037] The betweenness centrality of the active user in the communication network is calculated using the following formula:

[0038]

[0039] in, represents betweenness centrality, Represents the total number of active users, Indicates the serial number of the active user. Indicates that among active users, The serial number of the active user outside Indicates active users With active users The minimum duration between Indicates active users With active users There are nodes on the path between The number of the shortest durations of

[0040] The following formula is used to calculate the eigenvector centrality of the active user in the communication network:

[0041]

[0042] in, represents the eigenvector centrality, Representation Node The eigenvector centrality of represents a constant, Representative Node The set of active users in the neighborhood of Indicates the serial number of the active user. Representation Node Spread digital products to active users The volume of communication at that time;

[0043] The closeness centrality, the betweenness centrality, and the eigenvector centrality are used as the centrality of the active user in the communication network.

[0044] In a possible implementation of the first aspect, respectively calculating the click rate, discussion rate, and dissemination rate of the digital product by the recipients includes:

[0045] The ratio of the number of clicks of the digital product by the recipient to the number of displays is taken as the click rate;

[0046] The ratio of the number of discussions about the digital product by the disseminators to the total number of discussions is taken as the discussion rate;

[0047] The ratio of the number of times the digital product is disseminated by the disseminator to the total number of times the digital product is disseminated is taken as the dissemination rate.

[0048] In a possible implementation of the first aspect, determining the product popularity of the digital product according to the trust level by using the click rate, the discussion rate, and the dissemination rate includes:

[0049] According to the trust, the click rate, the discussion rate and the dissemination rate, the product popularity of the digital product is determined using the following formula:

[0050]

[0051] in, Indicates product awareness. Indicates trust, Indicates click rate, Indicates the discussion rate, Represents the transmission rate.

[0052] In a possible implementation of the first aspect, analyzing the satisfaction of the delivery user with the digital product by using the emotion information and the evaluation information according to the appearance occasion and the appearance time includes:

[0053] Based on the emotion information, identifying satisfaction information in the evaluation information;

[0054] Based on the appearance time, matching the evaluation information with the appearance occasion to obtain an evaluation-occasion pair;

[0055] identifying the target information in the occurrence occasion from the satisfaction information according to the evaluation-occasion pairing;

[0056] According to the target information, the satisfaction of the delivery user with the digital product is calculated using the following formula:

[0057]

[0058] in, Express satisfaction, a represents the very satisfied proportion in the target information, b represents the satisfied proportion in the target information, c represents the basically satisfied proportion in the target information, d represents the not very satisfied proportion in the target information, and e represents the dissatisfied proportion in the target information. Indicates the sequence number of the occurrence.

[0059] In a second aspect, the present invention provides a marketing effect analysis system based on digital marketing, the system comprising:

[0060] A speed calculation module is used to obtain digital products under digital marketing, query the delivery method of the digital products, analyze the delivery users of the digital products under the delivery method, build a propagation network between each of the delivery users, and calculate the propagation speed of the digital products using the propagation network;

[0061] A trust identification module is used to cluster the delivery users to obtain clustered users, calculate the activity level of the clustered users, identify active users in the clustered users by using the activity level, analyze the centrality of the active users in the communication network, and identify the trust of the communicators among the active users by the communicators by using the centrality;

[0062] A positioning identification module is used to respectively calculate the click rate, discussion rate and dissemination rate of the digital product by the disseminator, determine the product popularity of the digital product based on the trust, and calculate the purchase rate of the digital product by the user who placed the product, and identify the audience positioning capability of the digital marketing based on the purchase rate and the product popularity;

[0063] A satisfaction analysis module is used to collect backend data of the digital product, query the backend data for product feedback from the user who placed the product on the digital product, extract the emotional information and evaluation information of the user who placed the product from the product feedback, obtain the appearance occasion and appearance time of the digital product, and analyze the satisfaction of the user who placed the product on the digital product based on the appearance occasion and the appearance time using the emotional information and the evaluation information;

[0064] The effect analysis module is used to analyze the short-term benefits of the digital product under the digital marketing by using the propagation speed, the audience positioning ability and the satisfaction, and to analyze the long-term benefits of the digital product under the digital marketing by using the propagation speed, the audience positioning ability and the satisfaction, and to use the short-term benefits and the long-term benefits as the marketing effect analysis results of the digital product under the digital marketing.

[0065] Compared with the prior art, the technical principle and beneficial effects of this solution are:

[0066] The embodiment of the present invention constructs a propagation network between each of the delivery users to clarify the relationship of the digital product propagation between the delivery users. Furthermore, the embodiment of the present invention calculates the propagation speed of the digital product by using the propagation network to quickly calculate the propagation speed of the digital product on the Internet using a simple formula based on the propagation network, thereby improving the efficiency of propagation speed calculation. The embodiment of the present invention clusters the delivery users to reduce the number of nodes in the propagation network, and converts the original single delivery user as a single network node into multiple delivery users as single network nodes. Furthermore, the embodiment of the present invention calculates the activity level of the clustered users to characterize the activity level of the clustered users by point degree centrality, and simplifies the original complicated analysis process into an analysis of the out-degree and in-degree in the propagation network, thereby improving the efficiency of marketing effect analysis. Furthermore, the embodiment of the present invention analyzes the centrality of the active users in the propagation network to characterize the activity level of the active users in the propagation network by using the centrality. The importance of the active user in the communication network is greater, indicating that the active user has a stronger influence on other users in the communication network, and the trust of other users in the active user is higher. The embodiment of the present invention calculates the click rate, discussion rate and communication rate of the digital product by the disseminator respectively, so as to detect the user's access data to the digital product. Further, the embodiment of the present invention determines the product popularity of the digital product by using the click rate, discussion rate and communication rate according to the trust, so as to add the trust to the access data on the basis of detecting the user's access data to the digital product. This is because the higher the trust of the disseminator in the disseminator, the deeper the impression of the disseminator on the digital product, and the deeper the marketing effect brought by the disseminator's click rate, discussion rate and communication rate. Further, the embodiment of the present invention analyzes the satisfaction of the user with the digital product according to the appearance occasion and the appearance time, using the emotional information and the evaluation information, so as to observe whether the user is satisfied with the product push occasion. Therefore, the marketing effect analysis method and system based on digital marketing proposed in the embodiment of the present invention can improve the efficiency of marketing effect analysis under digital marketing. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0068] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0069] Figure 1 A flowchart of a marketing effect analysis method based on digital marketing provided by an embodiment of the present invention;

[0070] Figure 2 A module diagram of a marketing effect analysis system based on digital marketing provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0071] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0072] The embodiment of the present invention provides a marketing effect analysis method based on digital marketing, and the execution subject of the marketing effect analysis method based on digital marketing includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present invention. In other words, the marketing effect analysis method based on digital marketing can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0073] See also Figure 1 FIG. 1 is a flow chart of a marketing effect analysis method based on digital marketing provided by an embodiment of the present invention. Figure 1 The marketing effectiveness analysis methods based on digital marketing described in the article include:

[0074] S1. Acquire digital products under digital marketing, query the delivery method of the digital products, analyze the delivery users of the digital products under the delivery method, construct a communication network between each of the delivery users, and calculate the communication speed of the digital products using the communication network.

[0075] In an embodiment of the present invention, the digital marketing refers to the refined operation of Internet traffic under the strategic planning of the enterprise, including paid advertising investment in various media channels within the enterprise budget and free traffic management, including but not limited to SEO optimization, encyclopedia Q&A, self-media operation, private domain traffic and other full media penetration, ultimately achieving the marketing goals of the enterprise, realizing a better marketing input-output ratio model, and adjusting subsequent marketing ideas according to effect feedback. The digital product refers to the electronic product that the digital marketer needs to market in the Internet environment.

[0076] Furthermore, in an embodiment of the present invention, the delivery method includes manual delivery and machine delivery. The manual delivery refers to the method of manually spreading digital products by using IP images and anchors in the Internet environment. The machine delivery refers to delivering digital products to a certain software platform, and through the software platform recognizing the tags attached to the digital product, the digital product is personalized and pushed to some users.

[0077] Furthermore, in the embodiment of the present invention, the delivery user refers to a user who can view the digital product on the user terminal.

[0078] Furthermore, the embodiment of the present invention constructs a communication network between each of the delivery users to clarify the relationship of the digital product's dissemination among the delivery users.

[0079] Among them, the communication network refers to a directed graph structure that represents the relationship between the communicator and the disseminator among the delivery users, the communicator refers to the delivery user who receives the digital product and pushes the digital product to the communicator, and the disseminator refers to the delivery user who receives the digital product pushed by the communicator.

[0080] In one embodiment of the present invention, the construction of a communication network between each of the delivery users includes: determining whether there is a communication relationship between each of the delivery users; when the communication relationship exists between each of the delivery users, identifying the direct communication relationship and the indirect communication relationship between each of the delivery users; constructing a first series network between each of the delivery users based on the direct communication relationship; combining the communication group of the communicators and the communicated group of the communicated among the delivery users based on the indirect communication relationship; establishing a second series network between the communication group and the communicated group; when the communication relationship does not exist between each of the delivery users, constructing a parallel network between each of the delivery users; and obtaining the communication network by combining the first series network, the second series network and the parallel network.

[0081] Among them, the direct communication relationship refers to the relationship in which the communicator directly forwards the digital product to the communicator, and the indirect communication relationship refers to the relationship in which the digital product is pushed to the disseminator after accumulating enough user traffic. For example, a short video about the digital product cannot attract a large number of people to browse when it is less popular in the early stage, but after accumulating a certain number of likes, collections and reposts, the short video becomes a popular video. At this time, the popular video will attract a large number of people to browse. Therefore, it can be seen that the direct communication relationship refers to a one-to-one relationship, and the indirect communication relationship refers to a many-to-one relationship. Furthermore, the first series network refers to a directed graph structure from the communicator to the disseminator, and the second series network is a directed graph structure pointing to multiple communicators and a single disseminator. The parallel network refers to a network relationship in which there is no directed graph structure between the delivery users.

[0082] Furthermore, the embodiment of the present invention calculates the propagation speed of the digital product by utilizing the propagation network, so as to quickly calculate the propagation speed of the digital product on the Internet using a simple formula based on the propagation network, thereby improving the efficiency of propagation speed calculation.

[0083] The transmission speed refers to the speed at which a digital product is transmitted to a certain number of users per unit time.

[0084] In one embodiment of the present invention, the use of the communication network to calculate the propagation speed of the digital product includes: querying the propagation time of the digital product propagated by the propagator in the communication network and the reception time of the digital product received by the propagator in the communication network; and calculating the average shortest duration in the communication network according to the propagation time and the reception time using the following formula:

[0085]

[0086] in, represents the average minimum duration, Represents the total number of users in the distribution network. Indicates the transmission network The communication moment of the first communicator and the The shortest time between the receiving moments of the communicators;

[0087] The reciprocal of the average shortest duration is taken as the propagation speed.

[0088] The average shortest duration is measured by the average value of the shortest propagation duration between all nodes in the network. The smaller the value is, the faster the information propagation speed in the network is.

[0089] S2. Cluster the delivery users to obtain clustered users, calculate the activity level of the clustered users, identify active users among the clustered users using the activity level, analyze the centrality of the active users in the communication network, and identify the trust of the communicators among the active users by the communicators using the centrality.

[0090] The embodiment of the present invention clusters the delivery users to reduce the number of nodes in the propagation network, and converts the original single delivery user as a single network node into multiple delivery users as single network nodes.

[0091] The clustered users refer to a user group, including multiple delivery users.

[0092] In one embodiment of the present invention, clustering the delivery users to obtain clustered users includes: querying predecessor users of the delivery users in the propagation network; and when there are duplicate predecessor users, clustering the delivery users in the propagation network to obtain clustered users.

[0093] Exemplarily, when there are duplications among the predecessor users, the process of clustering the delivery users in the propagation network refers to: in the network structure from A to B, A to C, and A to D, B, C, and D are used as clustered users, and the original A with three successor nodes B, C, and D is converted into one successor node of the clustered user.

[0094] Furthermore, the embodiment of the present invention calculates the activity level of the clustered users to characterize the activity level of the clustered users through point degree centrality, thereby simplifying the original complicated analysis process into an analysis of the out-degree and in-degree in the communication network, thereby improving the efficiency of marketing effect analysis.

[0095] In one embodiment of the present invention, the calculating the activity level of the clustered users includes: identifying the out-degree and in-degree of the clustered users in the communication network; and calculating the activity level of the clustered users according to the out-degree and the in-degree using the following formula:

[0096]

[0097] in, represents the activity level of the clustered users, represents the in-degree of cluster user k, represents the out-degree of cluster user k, and m represents the total number of cluster users.

[0098] Optionally, the process of using the activity level to identify active users among the clustered users is: setting an activity threshold of the activity level, and when the activity level is greater than the activity threshold, treating the clustered users as the active users. The activity threshold is set according to actual conditions and is not further elaborated here.

[0099] Furthermore, an embodiment of the present invention analyzes the centrality of the active user in the communication network to use the centrality to characterize the importance of the active user in the communication network. The more important the active user is in the communication network, the stronger the influence of the active user on other users in the communication network, and the higher the trust of other users in the active user.

[0100] In one embodiment of the present invention, the analyzing the centrality of the active user in the communication network includes: calculating the closeness centrality of the active user in the communication network using the following formula:

[0101]

[0102] in, represents closeness to centrality, Represents the total number of active users, Indicates the serial number of the active user. Indicates active users With active users The shortest time between Indicates that among active users, The serial number of the active user outside;

[0103] The betweenness centrality of the active user in the communication network is calculated using the following formula:

[0104]

[0105] in, represents betweenness centrality, Represents the total number of active users, Indicates the serial number of the active user. Indicates that among active users, The serial number of the active user outside Indicates active users With active users The minimum duration between Indicates active users With active users There are nodes on the path between The number of the shortest durations of

[0106] The following formula is used to calculate the eigenvector centrality of the active user in the communication network:

[0107]

[0108] in, represents the eigenvector centrality, Representation Node The eigenvector centrality of represents a constant, Representative Node The set of active users in the neighborhood of Indicates the serial number of the active user. Representation Node Spread digital products to active users The volume of communication at that time;

[0109] The closeness centrality, the betweenness centrality, and the eigenvector centrality are used as the centrality of the active user in the communication network.

[0110] The neighborhood active users refer to the users in the communication network who are connected to the node Directly connected nodes, it should be noted that the node is also an active user. Further, the node Spread digital products to active users For example, when anchor A forwards a short video to fan B, the number of visits, likes, forwardings, and collections of the short video that fan B sees when he opens the short video is the volume of the short video.

[0111] In one embodiment of the present invention, the use of the centrality to identify the degree of trust of the communicator among the active users includes: obtaining the closeness centrality, the betweenness centrality and the eigenvector centrality in the centrality; and taking the sum of the closeness centrality, the betweenness centrality and the eigenvector centrality as the degree of trust of the communicator among the active users.

[0112] S3. Calculate the click rate, discussion rate and dissemination rate of the digital product by the recipients respectively; determine the product popularity of the digital product based on the trust level by using the click rate, discussion rate and dissemination rate; calculate the purchase rate of the digital product by the users; and identify the audience targeting capability of the digital marketing based on the purchase rate and the product popularity.

[0113] The embodiment of the present invention detects the user's access data to the digital product by respectively calculating the click rate, discussion rate and dissemination rate of the digital product by the disseminator.

[0114] In one embodiment of the present invention, respectively calculating the click rate, discussion rate and dissemination rate of the digital product by the disseminator includes: taking the ratio of the number of clicks on the digital product by the disseminator to the number of displays as the click rate; taking the ratio of the number of discussions on the digital product by the disseminator to the total number of discussions as the discussion rate; taking the ratio of the number of disseminations of the digital product by the disseminator to the total number of disseminations as the dissemination rate.

[0115] Furthermore, the embodiment of the present invention determines the product popularity of the digital product based on the trust, using the click-through rate, the discussion rate and the dissemination rate, so as to add the trust to the access data based on the detection of the user's access data to the digital product. This is because the higher the trust of the communicator in the communicator, the deeper the impression of the communicator on the digital product, and the more profound the marketing effect brought by the click-through rate, discussion rate and dissemination rate of the communicator.

[0116] The product awareness refers to the ability of a digital product to leave a deep impression on users.

[0117] In one embodiment of the present invention, determining the product popularity of the digital product based on the trust, using the click rate, the discussion rate, and the dissemination rate includes: determining the product popularity of the digital product based on the trust, the click rate, the discussion rate, and the dissemination rate using the following formula:

[0118]

[0119] in, Indicates product awareness. Indicates trust, Indicates click rate, Indicates the discussion rate, Represents the transmission rate.

[0120] Furthermore, in an embodiment of the present invention, the purchase rate refers to the ratio of the number of user purchases to the total number of times the product is displayed to the user, and the audience positioning capability refers to the ability of digital marketing to accurately locate the user's location and push it to the target user.

[0121] Optionally, the process of identifying the audience positioning capability of the digital marketing based on the purchase rate and the product awareness refers to: when a user purchases a digital product or the digital product leaves a deep impression on the user, it means that the digital marketing accurately locates the user's position and pushes it to the target user; when the user does not purchase the digital product or the digital product does not leave a deep impression on the user, it means that the digital marketing does not accurately locate the user's position and does not push it to the target user.

[0122] S4, collecting backend data of the digital product, querying the backend data for product feedback from the user on the digital product, extracting the emotional information and evaluation information of the user from the product feedback, obtaining the appearance occasion and appearance time of the digital product, and analyzing the satisfaction of the user on the digital product based on the appearance occasion and the appearance time by using the emotional information and the evaluation information.

[0123] In the embodiment of the present invention, the backend data refers to the backend data of the digital product, including the sales volume of the digital product, the communication between the user and the customer service when purchasing the digital product, the evaluation made by the user when purchasing the digital product, and other data.

[0124] Furthermore, the product feedback includes data such as the communication between the user and the customer service when purchasing the digital product, and the evaluation made by the user when purchasing the digital product.

[0125] Furthermore, the emotional information refers to the user's emotions, and the evaluation information refers to the user's positive or negative evaluation of the digital product. The emotional information is identified through the user's modal particles, emotional words, and emoticons, and the evaluation information is identified through the user's positive words and negative words.

[0126] Furthermore, the appearance occasion refers to other content attached to the marketing of digital products. For example, when the digital product is pushed in the anchor's short video, the content broadcast by the anchor is the appearance occasion. If the appearance occasion conflicts with the digital product, the marketing effect of the digital product will be greatly reduced. For example, the appearance occasion is a teaching occasion, and pushing a toy product in a teaching occasion is obviously a conflict.

[0127] Furthermore, the embodiment of the present invention analyzes the satisfaction of the delivery user with the digital product according to the appearance occasion and the appearance time by using the emotion information and the evaluation information, so as to observe whether the user is satisfied with the product push occasion.

[0128] In one embodiment of the present invention, the analyzing the satisfaction of the delivery user with respect to the digital product based on the appearance occasion and the appearance time using the emotion information and the evaluation information includes: identifying satisfaction information in the evaluation information based on the emotion information; matching the evaluation information with the appearance occasion based on the appearance time to obtain evaluation-occasion pairing; identifying target information in the appearance occasion from the satisfaction information based on the evaluation-occasion pairing; and calculating the satisfaction of the delivery user with respect to the digital product based on the target information using the following formula:

[0129]

[0130] in, Express satisfaction, a represents the very satisfied proportion in the target information, b represents the satisfied proportion in the target information, c represents the basically satisfied proportion in the target information, d represents the not very satisfied proportion in the target information, and e represents the dissatisfied proportion in the target information. Indicates the sequence number of the occurrence.

[0131] Among them, the satisfaction information includes very satisfied ratio, satisfied ratio, basically satisfied ratio, not quite satisfied ratio, dissatisfied ratio, etc. The very satisfied ratio, satisfied ratio, basically satisfied ratio, not quite satisfied ratio, and dissatisfied ratio are calculated by the very satisfied number, the satisfied number, the basically satisfied number, the not quite satisfied number, and the dissatisfied number. The very satisfied number, the satisfied number, the basically satisfied number, the not quite satisfied number, and the dissatisfied number are determined by collecting emotional data in emotional information and evaluation information. The specific method is to determine whether the user is satisfied through the evaluation information, and to determine the strength of the user's satisfaction through the strength of the emotional information. The strength of the emotional information can be determined by consulting the emotional dictionary.

[0132] S5. Analyze the short-term benefits of the digital products under the digital marketing by using the propagation speed, the audience positioning capability and the satisfaction level, and analyze the long-term benefits of the digital products under the digital marketing by using the propagation speed, the audience positioning capability and the satisfaction level, and use the short-term benefits and the long-term benefits as the marketing effect analysis results of the digital products under the digital marketing.

[0133] Optionally, the process of analyzing the short-term benefits of the digital product under the digital marketing by using the propagation speed, the audience positioning capability and the satisfaction level is to count the numerical changes of the propagation speed, the audience positioning capability and the satisfaction level in the short term. Further, the process of analyzing the long-term benefits of the digital product under the digital marketing by using the propagation speed, the audience positioning capability and the satisfaction level is to count the numerical changes of the propagation speed, the audience positioning capability and the satisfaction level in the long term.

[0134] It can be seen that the embodiment of the present invention constructs a propagation network between each of the delivery users to clarify the relationship of the digital product propagation between the delivery users. Furthermore, the embodiment of the present invention calculates the propagation speed of the digital product by using the propagation network, so as to quickly calculate the propagation speed of the digital product on the Internet by using a simple formula based on the propagation network, thereby improving the efficiency of propagation speed calculation. The embodiment of the present invention clusters the delivery users to reduce the number of nodes in the propagation network, and converts the original single delivery user as a single network node into multiple delivery users as single network nodes. Furthermore, the embodiment of the present invention calculates the activity level of the clustered users to characterize the activity level of the clustered users by point degree centrality, and simplifies the original complicated analysis process into an analysis of the out-degree and in-degree in the propagation network, thereby improving the efficiency of marketing effect analysis. Furthermore, the embodiment of the present invention analyzes the centrality of the active users in the propagation network to characterize the activity level of the active users in the propagation network by using the centrality. The importance of the active user in the communication network, the more important the active user is in the communication network, the stronger the influence of the active user on other users in the communication network, and the higher the trust of other users in the active user. The embodiment of the present invention calculates the click rate, discussion rate and communication rate of the digital product by the disseminator respectively, so as to detect the user's access data to the digital product. Further, the embodiment of the present invention determines the product popularity of the digital product by using the click rate, discussion rate and communication rate according to the trust, so as to add the trust to the access data on the basis of detecting the user's access data to the digital product. This is because the higher the trust of the disseminator in the disseminator, the deeper the impression of the disseminator on the digital product, and the deeper the marketing effect brought by the disseminator's click rate, discussion rate and communication rate. Further, the embodiment of the present invention analyzes the satisfaction of the user with the digital product according to the appearance occasion and the appearance time, using the emotional information and the evaluation information, so as to observe whether the user is satisfied with the product push occasion. Therefore, the marketing effect analysis method based on digital marketing proposed in the embodiment of the present invention can improve the efficiency of marketing effect analysis under digital marketing.

[0135] like Figure 2 Shown is a functional module diagram of the marketing effect analysis system based on digital marketing of the present invention.

[0136] The marketing effect analysis system 200 based on digital marketing of the present invention can be installed in an electronic device. According to the functions implemented, the marketing effect analysis system based on digital marketing can include a speed calculation module 201, a trust identification module 202, a positioning identification module 203, a satisfaction analysis module 204 and an effect analysis module 205. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0137] In the embodiment of the present invention, the functions of each module / unit are as follows:

[0138] The speed calculation module 201 is used to obtain digital products under digital marketing, query the delivery method of the digital products, analyze the delivery users of the digital products under the delivery method, build a communication network between each of the delivery users, and calculate the communication speed of the digital products using the communication network;

[0139] The trust identification module 202 is used to cluster the delivery users to obtain clustered users, calculate the activity level of the clustered users, identify active users in the clustered users by using the activity level, analyze the centrality of the active users in the communication network, and identify the trust level of the communicator in the active users by using the centrality;

[0140] The positioning identification module 203 is used to respectively calculate the click rate, discussion rate and dissemination rate of the digital product by the recipients, determine the product popularity of the digital product based on the trust, and calculate the purchase rate of the digital product by the users who placed the advertisement, and identify the audience positioning capability of the digital marketing based on the purchase rate and the product popularity;

[0141] The satisfaction analysis module 204 is used to collect the backend data of the digital product, query the product feedback of the user on the digital product in the backend data, extract the emotional information and evaluation information of the user from the product feedback, obtain the appearance occasion and appearance time of the digital product, and analyze the satisfaction of the user on the digital product according to the appearance occasion and appearance time by using the emotional information and the evaluation information;

[0142] The effect analysis module 205 is used to analyze the short-term benefits of the digital product under the digital marketing by using the propagation speed, the audience positioning capability and the satisfaction, and to analyze the long-term benefits of the digital product under the digital marketing by using the propagation speed, the audience positioning capability and the satisfaction, and to use the short-term benefits and the long-term benefits as the marketing effect analysis results of the digital product under the digital marketing.

[0143] In detail, each module in the marketing effect analysis system 200 based on digital marketing in the embodiment of the present invention is used in the same manner as described above. Figure 1 The marketing effectiveness analysis method based on digital marketing described in the above is similar to the technical means and can produce the same technical effects, so I will not go into details here.

[0144] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0145] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0146] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0147] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A marketing effect analysis method based on digital marketing, characterized in that: The method comprises: Acquire digital products under digital marketing, query the delivery method of the digital products, analyze the delivery users of the digital products under the delivery method, construct a communication network between each of the delivery users, and calculate the communication speed of the digital products using the communication network; Perform user clustering on the delivery users to obtain clustered users, calculate the activity level of the clustered users, identify active users among the clustered users by using the activity level, analyze the centrality of the active users in the communication network, and identify the trust of the communicators among the active users by the communicators by using the centrality; The using of the centrality to identify the degree of trust of the communicator among the active users includes: obtaining the closeness centrality, the betweenness centrality and the eigenvector centrality among the centrality; taking the sum of the closeness centrality, the betweenness centrality and the eigenvector centrality as the degree of trust of the communicator among the active users; Calculate the click rate, discussion rate and dissemination rate of the digital product by the recipients respectively, determine the product popularity of the digital product based on the trust, and calculate the purchase rate of the digital product by the users who placed the product, and identify the audience targeting capability of the digital marketing based on the purchase rate and the product popularity; The process of identifying the audience positioning capability of the digital marketing based on the purchase rate and the product popularity means that when a user purchases a digital product or the digital product has a deep impression on the user, it means that the digital marketing has accurately positioned the user and pushed it to the target user; when the user has not purchased the digital product or the digital product has not a deep impression on the user, it means that the digital marketing has not accurately positioned the user and has not pushed it to the target user; The audience targeting capability refers to the ability of digital marketing to accurately locate user locations and push them to target users; Collecting backend data of the digital product, querying the backend data for product feedback from the user on the digital product, extracting emotional information and evaluation information from the product feedback, obtaining the appearance occasion and appearance time of the digital product, and analyzing the satisfaction of the user on the digital product based on the appearance occasion and appearance time by using the emotional information and the evaluation information; The propagation speed, the audience positioning capability and the satisfaction are used to analyze the short-term benefits and long-term benefits of the digital product under the digital marketing, and the short-term benefits and the long-term benefits are used as the marketing effect analysis results of the digital product under the digital marketing.

2. The method according to claim 1, characterized in that The constructing of a communication network between each of the delivery users includes: Determine whether there is a communication relationship between each of the delivery users; When the communication relationship exists between each of the delivery users, identifying the direct communication relationship and the indirect communication relationship between each of the delivery users; According to the direct propagation relationship, a first series network is constructed between each of the delivery users; According to the indirect communication relationship, combining the communication group of the communicator and the dissemination group of the disseminator among the delivery users; Establishing a second series network between the transmitting group and the transmitted group; When the propagation relationship does not exist between each of the delivery users, constructing a parallel network between each of the delivery users; The propagation network is obtained by combining the first series network, the second series network and the parallel network.

3. The method according to claim 1, characterized in that The calculating the propagation speed of the digital product by using the propagation network includes: Query the dissemination time of the digital product by the disseminator in the dissemination network and the reception time of the digital product by the disseminator in the dissemination network; According to the propagation time and the reception time, the average shortest duration in the propagation network is calculated using the following formula: in, represents the average minimum duration, Represents the total number of users in the distribution network. Indicates the transmission network The communication moment of the first communicator and the The shortest time between the receiving moments of the communicators; The reciprocal of the average shortest duration is taken as the propagation speed.

4. The method according to claim 1, characterized in that: The step of clustering the delivery users to obtain clustered users includes: Query the predecessor users of the delivery user in the communication network; When there are duplications among the predecessor users, the delivery users are clustered in the propagation network to obtain clustered users.

5. The method according to claim 1, characterized in that: The calculating the activity level of the clustered users includes: Identifying the out-degree and in-degree of the clustered users in the propagation network; According to the out-degree and the in-degree, the activity level of the clustered users is calculated using the following formula: in, represents the activity level of the clustered users, represents the in-degree of cluster user k, represents the out-degree of cluster user k, and m represents the total number of cluster users.

6. The method according to claim 1, characterized in that The analyzing the centrality of the active user in the communication network includes: The closeness centrality of the active user in the communication network is calculated using the following formula: in, represents closeness to centrality, Represents the total number of active users, Indicates the serial number of the active user. Indicates active users With active users The shortest time between Indicates that among active users, The serial number of the active user outside; The betweenness centrality of the active user in the communication network is calculated using the following formula: in, represents betweenness centrality, Represents the total number of active users, Indicates the serial number of the active user. Indicates that among active users, The serial number of the active user outside Indicates active users With active users The minimum duration between Indicates active users With active users The number of the shortest durations when there is a node K on the path between them; The following formula is used to calculate the eigenvector centrality of the active user in the communication network: in, represents the eigenvector centrality, represents the eigenvector centrality of node K, represents a constant, F represents the set of active users in the neighborhood of node K, Indicates the serial number of the active user. Indicates that node K spreads digital products to active users The volume of communication at that time; The closeness centrality, the betweenness centrality, and the eigenvector centrality are used as the centrality of the active user in the communication network.

7. The method according to claim 1, characterized in that The respectively calculating the click rate, discussion rate and dissemination rate of the digital product by the disseminators includes: The ratio of the number of clicks of the digital product by the recipient to the number of displays is taken as the click rate; The ratio of the number of discussions about the digital product by the disseminators to the total number of discussions is taken as the discussion rate; The ratio of the number of times the digital product is disseminated by the disseminator to the total number of times the digital product is disseminated is taken as the dissemination rate.

8. The method according to claim 1, characterized in that Determining the product popularity of the digital product based on the trust by using the click rate, the discussion rate, and the dissemination rate includes: According to the trust, the click rate, the discussion rate and the dissemination rate, the product popularity of the digital product is determined using the following formula: in, Indicates product popularity. Indicates trust, Indicates the click rate, Indicates the discussion rate, Represents the transmission rate.

9. The method according to claim 1, characterized in that: The analyzing the satisfaction of the user with respect to the digital product by using the emotion information and the evaluation information according to the appearance occasion and the appearance time includes: Based on the emotion information, identifying satisfaction information in the evaluation information; Based on the appearance time, matching the evaluation information with the appearance occasion to obtain an evaluation-occasion pair; identifying the target information in the occurrence occasion from the satisfaction information according to the evaluation-occasion pairing; According to the target information, the satisfaction of the delivery user with the digital product is calculated using the following formula: in, Express satisfaction, a represents the very satisfied proportion in the target information, b represents the satisfied proportion in the target information, c represents the basically satisfied proportion in the target information, d represents the not very satisfied proportion in the target information, e represents the dissatisfied proportion in the target information, and x represents the serial number of the occurrence occasion.

10. A marketing effect analysis system based on digital marketing for implementing the marketing effect analysis method based on digital marketing according to claim 1, characterized in that: The system comprises: A speed calculation module is used to obtain digital products under digital marketing, query the delivery method of the digital products, analyze the delivery users of the digital products under the delivery method, build a propagation network between each of the delivery users, and calculate the propagation speed of the digital products using the propagation network; A trust identification module is used to cluster the delivery users to obtain clustered users, calculate the activity level of the clustered users, identify active users in the clustered users using the activity level, analyze the centrality of the active users in the communication network, and use the centrality to identify the trust of the communicator in the active users; using the centrality to identify the trust of the communicator in the active users includes: obtaining the closeness centrality, the betweenness centrality and the eigenvector centrality in the centrality; taking the sum of the closeness centrality, the betweenness centrality and the eigenvector centrality as the trust of the communicator in the active users; A positioning identification module is used to respectively calculate the click rate, discussion rate and dissemination rate of the digital product by the disseminator, determine the product popularity of the digital product based on the trust, and calculate the purchase rate of the digital product by the user who placed the product, and identify the audience positioning capability of the digital marketing based on the purchase rate and the product popularity; A satisfaction analysis module is used to collect backend data of the digital product, query the backend data for product feedback from the user who placed the product on the digital product, extract the emotional information and evaluation information of the user who placed the product from the product feedback, obtain the appearance occasion and appearance time of the digital product, and analyze the satisfaction of the user who placed the product on the digital product based on the appearance occasion and the appearance time using the emotional information and the evaluation information; The effect analysis module is used to analyze the short-term benefits and long-term benefits of the digital product under the digital marketing by using the propagation speed, the audience positioning ability and the satisfaction, and use the short-term benefits and the long-term benefits as the marketing effect analysis results of the digital product under the digital marketing.

Images