Customer Mining Method and System Based on Short Videos

Abstract

The present invention discloses a customer mining method and system based on short videos, which relates to the technical field of customer mining. The present invention includes: Step 1. Short video data acquisition, Step 2. User viewing behavior analysis, Step 3. User homepage analysis, Step 4. User address analysis, and Step 5. Platform recommendation processing. When short video users watch other videos related to the customer's products, the present invention analyzes the attention degree of short video users to these videos, so as to accurately grasp potential customers, prevent the loss of potential customers, and perform video push. By judging which regions' short video users pay enough attention to the customer's products and comprehensively analyzing the actual offline situations of these regions, taking the purchasing power and the competitiveness of the commodity discount strength of other relevant merchants as a reference for the customer's development plan, thus reducing the customer's operation cost.

Description

Technical Field

[0001] The present invention relates to the technical field of customer mining, and particularly to a customer mining method and system based on short videos. Background Art

[0002] Traditional customer discovery methods generally adopt offline surveys. It is often difficult for customers to conduct accurate customer discovery and analysis. Moreover, for customers who want to increase the product placement of offline merchants, it is also difficult to make development plans through a large amount of data. Due to its simplicity, short videos are loved by the public, and using short videos to increase exposure has become the choice of more and more merchants. Therefore, it is very necessary for customers to conduct customer discovery and development planning through short video data.

[0003] The prior art, such as the potential customer mining method based on short video data disclosed in the invention patent application with the publication number of CN116976958A, includes: retrieving the account information corresponding to each short video browsed in the previous time period from the database; obtaining the customer personal information corresponding to each account information; generating browsing record information; matching the content type with a browsing duration ranking before a preset ranking corresponding to the customer, and identifying the customer as a primary potential customer; obtaining the personal basic information of the customer; identifying the content type corresponding to the customer as an ultimate potential customer, and generating corresponding ultimate potential data.

[0004] The prior art, such as an instant recommendation method and system based on short videos disclosed in the invention patent application with the publication number of CN111737517A, includes: receiving a matching degree judgment request from a preset client in a terminal device; calculating the matching degree between the user and the short video, and judging whether the matching degree is greater than a preset threshold; obtaining at least one recommended short video related to the content of the short video; and displaying it by the preset client on the same playback interface as the short video. Based on the method provided by this invention, it can timely reflect the potential preferences of users to improve the user experience while alleviating the information cocoon.

[0005] It can be seen from the above scheme that the current customer mining method lacks certain attention to the analysis of short video users' preferences for customers based on their operating behaviors when watching other videos related to merchants. Customers will advertise their products in the form of short videos. If some short video users are interested in the customer's products, they will often watch other videos related to the customer's products. The more videos they watch, the more likely these short video users are to become potential customers. If these users are not accurately grasped, it is easy to cause potential customer loss, thereby reducing customer sales. At the same time, there is a lack of attention to the development planning based on short video users' preferences for products and the actual offline conditions in the region. When customers make development plans for offline merchant product placement, in addition to considering the degree of preference of users in the region for the products, they also need to consider the purchasing power of users in the region. If a large number of products are not placed in a large number of offline merchants based on actual conditions, it is easy to have a situation of oversupply, thereby increasing the customer's operating costs. Summary of the invention

[0006] The purpose of the present invention is to provide a customer mining method and system based on short videos, which solves the problems existing in the background technology.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solutions: The first aspect of the present invention provides a customer mining method based on short videos, including: Step 1. Short video data acquisition: Obtain the IP address consent sharing status of each viewing user of each promotional video of the customer, so as to screen each allowed user of each promotional video of the customer, obtain the like status, collection status, number of views and viewing time of each user of each promotional video of the customer, and obtain each viewing video of each user of each promotional video of the customer within the target time period.

[0008] Step 2. User viewing behavior analysis: Analyze the video attention coefficient of each user allowed by each promotional video of the client.

[0009] Step 3. User homepage analysis: Analyze the image correlation coefficients of each promotional video of the client that allows users to watch each video within the target time period, and evaluate the short video attention coefficients of each promotional video of the client that allows users to watch related products.

[0010] Step 4. User address analysis: Obtain the regions to which each permitted user of each promotional video of the customer belongs, analyze each permitted user in each region of each promotional video of the customer, evaluate the adaptation coefficients of each region of each promotional video of the customer, analyze each video streaming region of the customer, determine whether the customer has a plan to increase offline merchants. If so, obtain the per capita GDP value of each video streaming region of the customer and the ratio of the online average price to the offline average price of each other relevant customer, analyze each recommended development region of the customer, and evaluate the estimated number of increased offline merchants in each recommended development region of the customer;

[0011] Step 5. Platform recommendation processing: The short video platform sends each video streaming region of the customer, each recommended development region, and the corresponding estimated number of increased offline merchants to the customer's email.

[0012] Preferably, for the specific analysis method of the video attention coefficient of each permitted user of each promotional video of the customer: Obtain the like attention tuning parameter value corresponding to each like status and the favorite attention tuning parameter value corresponding to each favorite status from the local database. According to the like status and favorite status of each permitted user of each promotional video of the customer, map to obtain the like attention tuning parameter value a xn and the favorite attention tuning parameter value b xn , where x represents the number of each promotional video, x = 1, 2,..., y, y is a positive integer greater than 2, n represents the number of each permitted user, n = 1, 2,..., m, and m is a positive integer greater than 2.

[0013] Obtain the playing duration c of each promotional video of the customer from the local database x and the total number of views d x . According to the number of views f xn and the viewing duration g xn of each permitted user of each promotional video of the customer, analyze the video attention coefficient of each permitted user of each promotional video of the customer

[0014] Preferably, for the specific analysis method of the image correlation coefficient of each video viewed by each permitted user of each promotional video of the customer within the target time period: According to each video viewed by each permitted user of each promotional video of the customer within the target time period, extract each image of each video viewed by each permitted user of each promotional video of the customer within the target time period.

[0015] Obtain the image features of the relevant products of the customer from the local database, and determine whether the images of each video that allows users to watch within the target time period in each promotional video of the customer show the image features of the relevant products. If the image of a certain video that allows a user to watch within the target time period in a certain promotional video of the customer shows the image features of a certain relevant product, then mark this image as the target image, so as to screen the target images of each video that allows users to watch within the target time period in each promotional video of the customer, and count the number of images h of each video that allows users to watch within the target time period in each promotional video of the customer xni and the number of target images k xni , where i represents the number of each video that allows users to watch, i = 1, 2,..., j, and j is a positive integer greater than 2

[0016] Analyze the image correlation coefficient of each video that allows users to watch within the target time period in each promotional video of the customer

[0017] Preferably, the specific evaluation method for evaluating the short video attention coefficient of each relevant product by each user allowed to watch each promotional video of the customer is: obtain the like status and favorite status of each video that allows users to watch within the target time period in each promotional video of the customer from the local database, and map the like attention tuning parameter value corresponding to each like status and the favorite attention tuning parameter value corresponding to each favorite status to obtain the like attention tuning parameter value l of each video that allows users to watch within the target time period in each promotional video of the customer xni and the favorite attention tuning parameter value r xni .

[0018] Obtain the tags of each video that allows users to watch within the target time period in each promotional video of the customer and the target tags of the customer from the local database. If a certain tag of a certain video that allows a user to watch within the target time period in a certain promotional video of the customer is the same as a certain target tag, then mark this tag as a relevant tag, so as to screen the relevant tags of each video that allows users to watch within the target time period in each promotional video of the customer, and count the number of tags s of each video that allows users to watch within the target time period in each promotional video of the customer xni and the number of relevant tags t xni .

[0019] According to the image correlation coefficient δ of each video that allows users to watch within the target time period in each promotional video of the customer xni , calculate the short video attention coefficient of each relevant product by each user allowed to watch each promotional video of the customer

[0020] Preferably, the adaptation coefficient of each region for evaluating the customer's various promotional videos is specifically evaluated as follows: Based on the short video attention coefficient ε of each permitted user for the relevant products in each of the customer's promotional videos xn , and according to the video attention coefficient β of each permitted user for each of the customer's promotional videos xn , calculate the personal adaptation coefficient φ of each permitted user for each of the customer's promotional videos xn =ε xn +β xn .

[0021] Based on each permitted user in each region of each of the customer's promotional videos, map to obtain the personal adaptation coefficient of each permitted user in each region of each of the customer's promotional videos, count the personal adaptation coefficients of all permitted users in each region of each of the customer's promotional videos, and use it as the adaptation coefficient of each region of each of the customer's promotional videos.

[0022] Preferably, the specific analysis method for analyzing each video push region of the customer is as follows: Based on the adaptation coefficient u of each region of each of the customer's promotional videos xp , where p represents the number of each region, p = 1, 2,..., q, and q is a positive integer greater than 2, calculate the average value of the adaptation coefficients of each region of the customer where y represents the number of promotional videos.

[0023] Obtain the average value threshold of the adaptation coefficient from the local database, compare the average value of the adaptation coefficients of each region of the customer with the average value threshold of the adaptation coefficient. If the average value of the adaptation coefficient of a certain region of the customer is greater than the average value threshold of the adaptation coefficient, mark this region as a video push region, so as to screen each video push region of the customer.

[0024] Preferably, the specific analysis method for analyzing each recommended development region of the customer is as follows: Based on the average value of the adaptation coefficients of each region of the customer, extract the average value T of the adaptation coefficients of each video push region of the customer N , and based on this, analyze the offline merchant recommendation reference coefficient D of the customer in each video push region N , where N represents the number of each video push region, N = 1, 2,..., M, and M is a positive integer greater than 2.

[0025] Obtain the average per capita GDP value A and the ratio value B of the customer's online average price to the offline average price from the local database. Based on the per capita GDP value P of each video push region of the customer N , the ratio value Q of the online average price to the offline average price of each other relevant customer NR , where R represents the number of each other relevant customer, R = 1, 2,..., S, and S is a positive integer greater than 2, calculate the recommended development coefficient of each video push region of the customer where S is the number of other relevant customers.

[0026] Obtain the recommended development coefficient threshold from the local database, compare the recommended development coefficients of each video streaming area of the customer with the recommended development coefficient threshold. If the recommended development coefficient of a certain video streaming area of the customer is greater than the recommended development coefficient threshold, mark this video streaming area as a recommended development area, so as to screen each recommended development area of the customer.

[0027] Preferably, for analyzing the offline merchant recommendation reference coefficient of the customer in each video streaming area, the specific analysis method is: obtain the ideal number of offline merchants corresponding to each adaptation coefficient interval from the local database, and map to obtain the ideal number of offline merchants E in each video streaming area of the customer N 。

[0028] Obtain the number of offline merchants F of the customer in each video streaming area from the local database N , the average sales amount G per unit time N and the average passenger flow H N , the average sales amount J of the offline merchants of the customer in all regions N and the average passenger flow K N , and analyze the offline merchant recommendation reference coefficient of the customer in each video streaming area

[0029]

[0030] Preferably, for evaluating the estimated increase in the number of offline merchants in each recommended development area of the customer, the specific evaluation method is: according to the recommended development coefficients of each video streaming area of the customer, extract the recommended development coefficients of each recommended development area of the customer.

[0031] Obtain the estimated increase in the number of offline merchants in each recommended development coefficient interval from the local database, and map to obtain the estimated increase in the number of offline merchants in each recommended development area of the customer.

[0032] The second aspect of the present invention provides a customer mining system for executing the above-mentioned customer mining method based on short videos, including: a short video data acquisition module, which is used to obtain the ip address consent sharing status of each viewing user of each promotional video of the customer, so as to screen each permitted user of each promotional video of the customer, obtain the like status, favorite status, number of views and viewing duration of each permitted user of each promotional video of the customer, and obtain each viewing video of each permitted user of each promotional video of the customer within the target time period.

[0033] A user viewing behavior analysis module, which is used to analyze the video attention coefficient of each permitted user of each promotional video of the customer.

[0034] The user home page analysis module is used to analyze the image correlation coefficients of each video watched by users allowed for each promotional video of the customer within the target time period, and evaluate the short video attention coefficients of each user allowed for each promotional video of the customer for the relevant products.

[0035] The user address analysis module is used to obtain the regions to which each user allowed for each promotional video of the customer belongs, analyze each user allowed for each region of each promotional video of the customer, evaluate the adaptation coefficients of each region of each promotional video of the customer, analyze the video push regions of each customer's video, determine whether the customer has a plan to increase offline merchants. If so, obtain the per capita GDP value of each video push region of the customer and the ratio value of the online average price to the offline average price of each other relevant customer, analyze each recommended development region of the customer, and evaluate the estimated number of increased offline merchants in each recommended development region of the customer;

[0036] The platform recommendation processing module is used for the short video platform to send the video push regions of the customer, each recommended development region and the corresponding estimated number of increased offline merchants to the customer's email.

[0037] The beneficial effects of the present invention are as follows: (1) In step 1. Short video data acquisition of the present invention, by acquiring various data of each promotional video of the customer, it is convenient for subsequent analysis.

[0038] (2) In step 2. User viewing behavior analysis and step 3. User home page analysis of the present invention, while paying attention to the video attention coefficients of short video users for each promotional video of the customer, it also analyzes other videos watched by these short video users within the target time period, and analyzes the attention degree of these short video users to other videos related to the customer's products, so as to accurately grasp potential customers, prevent the loss of potential customers, and thus increase the customer's sales.

[0039] (3) In step 4. User address analysis of the present invention, by analyzing the ip addresses of short video users, the regions where the short video users are located are judged, so as to judge which regions of short video users pay enough attention to the customer's products, and comprehensively analyze the actual offline situations of these regions, taking the competitiveness of the purchasing power and the discount strength of other relevant merchants' products as a reference for the customer's development plan. If the customer already has stores in these regions, the actual situations of these stores will be analyzed, so as to reduce the incidence of the situation of oversupply due to too many offline stores and reduce the customer's operating costs.

[0040] (4) In step 5. Platform recommendation processing of the present invention, by sending the analyzed data to the customer, it is convenient for the customer to make a development plan. Brief Description of the Drawings

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0042] Figure 1 It is a schematic flowchart of the method of the present invention.

[0043] Figure 2 It is a schematic diagram of the system modules of the present invention. Detailed implementation manners

[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0045] Refer to Figure 1 As shown, the first aspect of the present invention provides a customer mining method based on short videos, including: Step 1. Short video data acquisition: Obtain the IP address consent sharing status of each viewing user of each promotion video of the customer, so as to screen each permitted user of each promotion video of the customer, obtain the like status, favorite status, number of views and viewing duration of each permitted user of each promotion video of the customer, and obtain each viewing video of each permitted user of each promotion video of the customer within the target time period.

[0046] In a specific embodiment, the specific acquisition method of the IP address consent sharing status of each viewing user of each promotion video of the customer is: Obtain the IP address consent sharing status of each viewing user of each promotion video of the customer from the short video platform terminal.

[0047] In a specific embodiment, the specific screening method of each permitted user of each promotion video of the customer is: If the IP address consent sharing status of a certain viewing user of a certain promotion video of the customer is the consent sharing status, then mark this viewing user as a permitted user, so as to screen each permitted user of each promotion video of the customer.

[0048] In a specific embodiment, obtaining the like status, collection status, number of views, and viewing duration of each permitted user for each promotional video of the customer, and obtaining each video viewed by each permitted user for each promotional video of the customer within a target time period. The specific obtaining method is as follows: obtaining the like status, collection status, number of views, and viewing duration of each permitted user for each promotional video of the customer from the local database, and obtaining each video viewed by each permitted user for each promotional video of the customer within a target time period from the short video platform terminal.

[0049] It should be noted that the local database is used to store the like status, collection status, number of views, and viewing duration of each permitted user for each promotional video of the customer, the like attention tuning parameter value corresponding to each like status, the collection attention tuning parameter value corresponding to each collection status, the playing duration of each promotional video of the customer, the total number of views, the image features of each related product of the customer, the like status and collection status of each video viewed by each permitted user for each promotional video of the customer within a target time period, the tags of each video viewed by each permitted user for each promotional video of the customer within a target time period, the target tags of the customer, the IP address range included in each region, the average adaptation coefficient threshold, the appropriate average per capita GDP value of the customer's products, the ratio of the online average price to the offline average price of the customer, the recommended development coefficient threshold, the ideal number of offline merchants corresponding to each adaptation coefficient interval, the number of offline merchants of the customer in each video promotion region, the average sales amount and average customer flow per unit time, the average sales amount and average customer flow of the offline merchants of the customer in all regions, and the estimated increase in the number of offline merchants in each recommended development coefficient interval.

[0050] It should be noted that the IP address consent sharing status includes: consent to share, do not consent to share.

[0051] It should be noted that the like status includes: liked and not liked.

[0052] It should be noted that the collection status includes: collected and not collected.

[0053] Step 1. Short video data acquisition of the present invention: By acquiring various data of each promotional video of the customer, it is convenient for subsequent analysis.

[0054] Step 2. User viewing behavior analysis: Analyzing the video attention coefficient of each permitted user for each promotional video of the customer.

[0055] In a specific embodiment of the present invention, the method for specifically analyzing the video attention coefficients of each permitted user for each promotion video of the customer is as follows: Obtain the like attention tuning values corresponding to each like status and the collection attention tuning values corresponding to each collection status from the local database, and map them according to the like status and collection status of each permitted user for each promotion video of the customer to obtain the like attention tuning value a xn and the collection attention tuning value b xn of each permitted user for each promotion video of the customer, where x represents the number of each promotion video, x = 1, 2,..., y, y is a positive integer greater than 2, and n represents the number of each permitted user, n = 1, 2,..., m, m is a positive integer greater than 2.

[0056] Obtain the playing duration c x and the total number of views d x of each promotion video of the customer from the local database, and analyze the video attention coefficients of each permitted user for each promotion video of the customer based on the number of views f xn and the viewing duration g xn of each permitted user for each promotion video of the customer.

[0057] Step 3. User homepage analysis: Analyze the image correlation coefficients of each video viewed by each permitted user for each promotion video of the customer within the target time period, and evaluate the short video attention coefficients of each permitted user for each promotion video of the customer for the related products.

[0058] In a specific embodiment of the present invention, the method for specifically analyzing the image correlation coefficients of each video viewed by each permitted user for each promotion video of the customer within the target time period is as follows: Extract each image of each video viewed by each permitted user for each promotion video of the customer within the target time period based on each video viewed by each permitted user for each promotion video of the customer within the target time period.

[0059] Obtain each image feature of the related products of the customer from the local database, and determine whether each image of each video viewed by each permitted user for each promotion video of the customer within the target time period shows each image feature of the related products. If a certain image of a certain video viewed by a certain permitted user for a certain promotion video of the customer within the target time period shows a certain image feature of the related products, then mark this image as the target image, so as to screen each target image of each video viewed by each permitted user for each promotion video of the customer within the target time period, and count the number of images h xni and the number of target images k xni of each video viewed by each permitted user for each promotion video of the customer within the target time period, where i represents the number of each video viewed, i = 1, 2,..., j, j is a positive integer greater than 2.

[0060] Analyze the image correlation coefficients of each video watched by users allowed in each promotional video of the customer within the target time period

[0061] In a specific embodiment, to determine whether the images of each video watched by users allowed in each promotional video of the customer within the target time period show the image features of relevant products, the specific determination method is as follows: By using the existing method for determining whether image features appear in an image, it can be determined whether the images of each video watched by users allowed in each promotional video of the customer within the target time period show the image features of relevant products.

[0062] It should be noted that if the customer's product is processed meat food, the image features include: the image features of the outer packaging of the customer's processed meat, the image features of the outer packaging of processed meat of other customers, the image features of meat-related foods, and other image features.

[0063] In a specific embodiment of the present invention, to evaluate the short video attention coefficients of relevant products for users allowed in each promotional video of the customer, the specific evaluation method is as follows: Obtain the like status and favorite status of each video watched by users allowed in each promotional video of the customer within the target time period from the local database, and map them according to the like attention adjustment parameter values corresponding to each like status and the favorite attention adjustment parameter values corresponding to each favorite status to obtain the like attention adjustment parameter value l xni and the favorite attention adjustment parameter value r xni .

[0064] Obtain the tags of each video watched by users allowed in each promotional video of the customer within the target time period and the target tags of the customer from the local database. If a tag of a certain video watched by a certain user allowed in a certain promotional video of the customer within the target time period is the same as a target tag, then mark this tag as a relevant tag, so as to screen the relevant tags of each video watched by users allowed in each promotional video of the customer within the target time period, and count the number of tags s xni and the number of relevant tags t xni .

[0065] Based on the image correlation coefficient δ xni of each video watched by users allowed in each promotional video of the customer, calculate the short video attention coefficients of relevant products for users allowed in each promotional video of the customer

[0066] In step 2. user viewing behavior analysis and step 3. user homepage analysis of the present invention, while paying attention to the video attention coefficients of short video users for each promotional video of the customer, other videos watched by these short video users within the target time period are also analyzed to analyze the attention degree of these short video users to other videos related to the customer's products, so as to accurately grasp potential customers, prevent the loss of potential customers, and thus increase the customer's sales volume.

[0067] Step 4. User address analysis: Obtain the regions to which each permitted user of each promotional video of the customer belongs, analyze each permitted user in each region of each promotional video of the customer, evaluate the adaptation coefficients of each region of each promotional video of the customer, analyze the regions where each video of the customer is pushed, determine whether the customer has a plan to increase offline merchants. If so, obtain the per capita GDP values of each video push region of the customer and the ratio values of the online average price to the offline average price of each other relevant customer, analyze each recommended development region of the customer, and evaluate the estimated number of increased offline merchants in each recommended development region of the customer.

[0068] In a specific embodiment, the specific method for obtaining the per capita GDP values of each video push region of the customer and the ratio values of the online average price to the offline average price of each other relevant customer is as follows: Through the financial management platform of each video push region, the per capita GDP values of each video push region of the customer can be obtained, and through the short video platform terminal, the ratio values of the online average price to the offline average price of each other relevant customer in each video push region of the customer can be obtained.

[0069] In a specific embodiment, the specific method for obtaining the regions to which each permitted user of each promotional video of the customer belongs is as follows: Obtain the IP addresses of each permitted user of each promotional video of the customer from the short video platform terminal, obtain the IP address ranges included in each region from the local database, and map to obtain the regions to which each permitted user of each promotional video of the customer belongs.

[0070] In a specific embodiment, the specific analysis method for analyzing each permitted user in each region of each promotional video of the customer is as follows: Based on the regions to which each permitted user of each promotional video of the customer belongs, map to obtain each permitted user in each region of each promotional video of the customer.

[0071] In a specific embodiment of the present invention, the specific evaluation method for evaluating the adaptation coefficients of each region of each promotional video of the customer is as follows: Based on the short video attention coefficient ε of each permitted user of each promotional video of the customer xn , and according to the video attention coefficient β of each permitted user of each promotional video of the customer xn , calculate the personal adaptation coefficient φ of each permitted user of each promotional video of the customer xn = εxn +β xn 。

[0072] Map the personal adaptation coefficients of the permitted users in each region of each promotion video of the customer to obtain the personal adaptation coefficients of the permitted users in each region of each promotion video of the customer, and count the personal adaptation coefficients of all permitted users in each region of each promotion video of the customer, and use them as the adaptation coefficients of each region of each promotion video of the customer.

[0073] In a specific embodiment of the present invention, for analyzing the regions of each video push stream of the customer, the specific analysis method is as follows: According to the adaptation coefficient u of each region of each promotion video of the customer xp , where p represents the number of each region, p = 1, 2,..., q, q is a positive integer greater than 2, calculate the average value of the adaptation coefficients of each region of the customer where y represents the number of promotion videos.

[0074] Obtain the threshold value of the average adaptation coefficient from the local database, compare the average value of the adaptation coefficients of each region of the customer with the threshold value of the average adaptation coefficient. If the average value of the adaptation coefficient of a certain region of the customer is greater than the threshold value of the average adaptation coefficient, mark this region as the video push stream region, so as to screen the regions of each video push stream of the customer.

[0075] In a specific embodiment of the present invention, for analyzing the recommended development regions of each customer, the specific analysis method is as follows: According to the average value of the adaptation coefficients of each region of the customer, extract the average value of the adaptation coefficients T of the regions of each video push stream of the customer N , and analyze the offline merchant recommendation reference coefficient D of the customer in each video push stream region accordingly N , where N represents the number of each video push stream region, N = 1, 2,..., M, M is a positive integer greater than 2.

[0076] Obtain the average per capita GDP value A and the ratio value B of the online average price to the offline average price of the customer from the local database. According to the per capita GDP value P of each video push stream region of the customer N , the ratio value Q of the online average price to the offline average price of each other relevant customer NR , where R represents the number of each other relevant customer, R = 1, 2,..., S, S is a positive integer greater than 2, calculate the recommended development coefficient of each video push stream region of the customer where S is the number of other relevant customers.

[0077] Obtain the recommended development coefficient threshold from the local database, compare the recommended development coefficients of each video streaming region of the customer with the recommended development coefficient threshold. If the recommended development coefficient of a certain video streaming region of the customer is greater than the recommended development coefficient threshold, mark this video streaming region as a recommended development region, so as to screen each recommended development region of the customer.

[0078] In a specific embodiment of the present invention, for analyzing the offline merchant recommendation reference coefficient of the customer in each video streaming region, the specific analysis method is as follows: Obtain the ideal number of offline merchants corresponding to each adaptation coefficient interval from the local database, and map to obtain the ideal number of offline merchants E in each video streaming region of the customer. N 。

[0079] Obtain the number of offline merchants F of the customer in each video streaming region from the local database. N The average sales amount G per unit time. N And the average passenger flow H. N The average sales amount J of the offline merchants of the customer in all regions. N And the average passenger flow K. N Analyze the offline merchant recommendation reference coefficient of the customer in each video streaming region.

[0080]

[0081] In a specific embodiment of the present invention, for evaluating the estimated increase in the number of offline merchants in each recommended development region of the customer, the specific evaluation method is as follows: According to the recommended development coefficients of each video streaming region of the customer, extract the recommended development coefficients of each recommended development region of the customer.

[0082] Obtain the estimated increase in the number of offline merchants in each recommended development coefficient interval from the local database, and map to obtain the estimated increase in the number of offline merchants in each recommended development region of the customer.

[0083] Step 4. User address analysis of the present invention: By analyzing the IP address of the short video user, judge the region where the short video user is located, so as to judge which regions' short video users are sufficiently concerned about the customer's products, and comprehensively analyze the actual offline situation in these regions. Use the competitiveness of the purchasing power and the discount strength of other relevant merchants' products as a reference for the customer's development plan. If the customer already has stores in these regions, the actual situation of these stores will be analyzed, so as to reduce the incidence of the situation of oversupply due to too many offline stores, and reduce the customer's operating costs.

[0084] Step 5. Platform recommendation processing: The short video platform sends each video streaming region of the customer, each recommended development region and the corresponding estimated increase in the number of offline merchants to the customer's email.

[0085] Step 5. Platform recommendation processing of the present invention. By sending the analyzed data to the customer, it is convenient for the customer to carry out development planning.

[0086] Referring to Figure 2 As shown, the second aspect of the present invention provides a customer mining system for executing the above-mentioned customer mining method based on short videos, including: a short video data acquisition module, a user viewing behavior analysis module, a user home page analysis module, a user address analysis module, a platform recommendation processing module, and a local database.

[0087] It should be noted that the short video data acquisition module is connected to the user viewing behavior analysis module, the user viewing behavior analysis module is connected to the user home page analysis module, the user home page analysis module is connected to the user address analysis module, the user address analysis module is connected to the platform recommendation processing module, and the local database is connected to the short video data acquisition module, the user viewing behavior analysis module, the user home page analysis module, and the user address analysis module.

[0088] The short video data acquisition module is used to obtain the IP address consent sharing status of each viewing user of each promotional video of the customer, so as to screen each permitted user of each promotional video of the customer, obtain the like status, favorite status, number of views, and viewing duration of each permitted user of each promotional video of the customer, and obtain each viewing video of each permitted user of each promotional video of the customer within the target time period.

[0089] The user viewing behavior analysis module is used to analyze the video attention coefficient of each permitted user of each promotional video of the customer.

[0090] The user home page analysis module is used to analyze the image correlation coefficient of each viewing video of each permitted user of each promotional video of the customer within the target time period, and evaluate the short video attention coefficient of each permitted user of each promotional video of the customer for related products.

[0091] The user address analysis module is used to obtain the region to which each permitted user of each promotional video of the customer belongs, analyze each permitted user in each region of each promotional video of the customer, evaluate the adaptation coefficient of each region of each promotional video of the customer, analyze each video push region of the customer, judge whether the customer has a plan to increase offline merchants, if so, obtain the per capita GDP value of each video push region of the customer, the ratio of the online average price to the offline average price of each other related customer, analyze each recommended development region of the customer, and evaluate the estimated number of increased offline merchants in each recommended development region of the customer.

[0092] The platform recommendation processing module is used for the short video platform to send each video push region of the customer, each recommended development region, and the corresponding estimated number of increased offline merchants to the customer's email.

[0093] The above content is only an example and illustration of the concept of the present invention. Those skilled in the art of the present technology can make various modifications or supplements to the described specific embodiments or use similar ways to replace them. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A customer mining method based on short videos, characterized in that: include: Step 1. Acquisition of short video data: Acquire the IP address consent sharing status of each viewing user of each promotional video of the client, thereby screening each user allowed to view each promotional video of the client, acquire the like status, collection status, number of views and viewing time of each user allowed to view each promotional video of the client, and acquire each viewing video of each promotional video of the client that each user allowed to view within the target time period; Step 2. User viewing behavior analysis: Analyze the video attention coefficient of each user allowed by each promotional video of the client, wherein the video attention coefficient is obtained according to the like attention adjustment parameter value, favorite attention adjustment parameter value, number of views, viewing time of each promotional video of the client, and the playback time and total number of views of each promotional video of the client; Step 3. User homepage analysis: Analyze the image correlation coefficients of each promotional video of the customer that allows the user to watch the videos within the target time period, evaluate the short video attention coefficients of each promotional video of the customer that allows the user to the relevant products, wherein the image correlation coefficients are obtained according to the number of images of each video that allows the user to watch the videos within the target time period and the target number of images, obtain the tags of each promotional video of the customer that allows the user to watch the videos within the target time period and the target tags of the customer from the local database, if a tag of a video that allows the user to watch the videos within the target time period of a promotional video of the customer is consistent with a target tag, then mark the tag as a relevant tag, and calculate the short video attention coefficient according to the like attention adjustment parameter value and the collection attention adjustment parameter value of each promotional video of the customer that allows the user to watch the videos within the target time period, the number of tags and the number of relevant tags of each promotional video of the customer that allows the user to watch the videos within the target time period, and the image correlation coefficients of each promotional video of the customer that allows the user to watch the videos within the target time period; Step 4. User address analysis: obtain the regions to which each user of each promotional video of the customer belongs, analyze each user of each region of each promotional video of the customer, evaluate the adaptability coefficient of each region of each promotional video of the customer, analyze each video streaming region of the customer, determine whether the customer has plans to add offline merchants, if so, obtain the per capita GDP value of each video streaming region of the customer, the ratio of the online average price to the offline average price of each other related customer, analyze each recommended development region of the customer, evaluate the estimated number of offline merchants to be added in each recommended development region of the customer, among which, based on the short video attention coefficient of each user allowed by each promotional video of the customer for related products , and based on the video attention coefficient of each user allowed by each promotional video of the customer , calculate the personal adaptation coefficient of each user that can be used for each promotional video of the customer , according to each user allowed in each region of each promotional video of the client, mapping obtains the personal adaptation coefficient of each user allowed in each region of each promotional video of the client, and counting all the personal adaptation coefficients of the users allowed in each region of each promotional video of the client, and taking them as the adaptation coefficient of each region of each promotional video of the client; Step 5. Platform recommendation processing: The short video platform sends the customer’s video streaming areas, recommended development areas and their corresponding estimated number of offline merchants to the customer’s mailbox.

2. The customer mining method based on short videos according to claim 1 is characterized in that: The specific analysis method of analyzing the video attention coefficient of each user of each promotional video of the client is as follows: Obtain the like and attention adjustment parameter values ​​corresponding to each like status and the collection and attention adjustment parameter values ​​corresponding to each collection status from the local database, and map the like and attention adjustment parameter values ​​corresponding to each promotional video of the customer based on the like status and collection status of each user allowed for each promotional video of the customer. 、Collect and follow the parameter value , where x represents the number of each promotional video, , y is a positive integer greater than 2, n represents the number of each user allowed, , m is a positive integer greater than 2; Get the playing time of each promotional video of the customer from the local database , total views , based on the number of views allowed by each user for each of the client's promotional videos and viewing time , analyze the video attention coefficient of each promotional video of the client that can be used by users .

3. The customer mining method based on short videos according to claim 1 is characterized in that: The specific analysis method of analyzing the image correlation coefficients of each promotional video of the client that allows the user to watch each video within the target time period is as follows: Extracting images of videos that are allowed to be viewed by users within a target time period from each promotional video of the client; Obtain each image feature of the customer's related products from the local database, determine whether each image of each video that the user is allowed to watch in each promotional video of the customer within the target time period has each image feature of the related product; if a certain image of a certain video that the user is allowed to watch in a certain promotional video of the customer within the target time period has a certain image feature of the related product, then mark the image as a target image, thereby screening each target image of each video that the user is allowed to watch in each promotional video of the customer within the target time period, and counting the number of images of each video that the user is allowed to watch in each promotional video of the customer within the target time period and the number of target images , where i represents the number of each video watched, , j is a positive integer greater than 2; Analyze the image correlation coefficient of each promotional video of the client, which allows users to watch each video within the target time period .

4. The customer mining method based on short videos according to claim 1 is characterized in that: The specific evaluation method of evaluating the short video attention coefficient of each promotional video of the client that allows users to pay attention to the relevant products is as follows: Obtain the like status and collection status of each promotional video of the client that allows the user to watch each video within the target time period from the local database, and map the like and attention adjustment parameter values ​​of each promotional video of the client that allows the user to watch each video within the target time period according to the like and attention adjustment parameter values ​​corresponding to each like status and the collection and attention adjustment parameter values ​​corresponding to each collection status. 、Collect and follow the parameter value ; Filter the relevant tags of each promotional video of the customer that allows users to watch each video within the target time period, and count the number of tags of each promotional video of the customer that allows users to watch each video within the target time period and the number of related tags ; Based on the image correlation coefficient of each promotional video of the client, each video that allows the user to watch within the target time period , calculate the short video attention coefficient of each promotional video of the customer that allows users to pay attention to the relevant products .

5. The customer mining method based on short videos according to claim 2 is characterized in that: The specific analysis method of analyzing each video streaming area of ​​the customer is as follows: Based on the adaptability coefficient of each area of ​​each customer's promotional video , where p represents the number of each region, , q is a positive integer greater than 2, and the average adaptation coefficient of each area of ​​the customer is calculated , where y represents the number of promotional videos; The adaptation coefficient average value threshold is obtained from the local database, and the adaptation coefficient average value of each area of ​​the customer is compared with the adaptation coefficient average value threshold. If the adaptation coefficient average value of a certain area of ​​the customer is greater than the adaptation coefficient average value threshold, the area is marked as a video streaming area, thereby screening the video streaming areas of the customer.

6. The customer mining method based on short videos according to claim 1 is characterized in that: The specific analysis method for analyzing the recommended development areas of customers is as follows: Based on the average adaptation coefficient of each area of ​​the customer, extract the average adaptation coefficient of each video streaming area of ​​the customer , and analyze the reference coefficients of offline merchants recommended by customers in each video streaming area based on this , where N represents the number of each video streaming area. , M is a positive integer greater than 2; obtain the average per capita GDP value A, the ratio value B of the customer's online average price to the offline average price from the local database, and the per capita GDP value of each video streaming area of ​​the customer , the ratio of the average online price to the average offline price of other relevant customers , where R represents the number of other related customers, , S is a positive integer greater than 2, and the recommended development coefficient of each video streaming area of ​​the customer is calculated , where S is the number of other relevant customers; The recommended development coefficient threshold is obtained from the local database, and the recommended development coefficient of each video streaming area of ​​the customer is compared with the recommended development coefficient threshold. If the recommended development coefficient of a video streaming area of ​​the customer is greater than the recommended development coefficient threshold, the video streaming area is marked as a recommended development area, thereby screening the recommended development areas of the customer.

7. The customer mining method based on short videos according to claim 6 is characterized in that: The specific analysis method of analyzing the reference coefficients of offline merchants recommended by customers in each video streaming area is as follows: Obtain the ideal number of offline merchants corresponding to each adaptation coefficient interval from the local database, and map it to obtain the ideal number of offline merchants in each video streaming area of ​​the customer ; Get the number of offline merchants in each video streaming area from the local database , average sales per unit time and average passenger flow , average sales of offline merchants in all regions and average passenger flow , analyze the reference coefficients of offline merchants recommended by customers in each video streaming area 。 8. The customer mining method based on short videos according to claim 6 is characterized in that: The specific evaluation method for the estimated increase in the number of offline merchants in each recommended development area of ​​the evaluation client is as follows: Extract the recommended development coefficients of each recommended development area of ​​the customer based on the recommended development coefficients of each video streaming area of ​​the customer; The estimated number of offline merchants to be added in each recommended development coefficient interval is obtained from the local database, and the estimated number of offline merchants to be added in each recommended development area of ​​the customer is mapped.

9. A customer mining system for executing the short video-based customer mining method according to any one of claims 1 to 8, comprising: The short video data acquisition module is used to obtain the IP address consent sharing status of each viewing user of each promotional video of the customer, so as to screen each allowed user of each promotional video of the customer, obtain the like status, collection status, number of views and viewing time of each user of each promotional video of the customer, and obtain each viewing video of each promotional video of the customer that each user is allowed to watch within a target time period; A user viewing behavior analysis module is used to analyze the video attention coefficient of each user allowed by each promotional video of the client, wherein the video attention coefficient is obtained according to the like attention adjustment parameter value, favorite attention adjustment parameter value, number of views, viewing time of each promotional video of the client, and the playback time and total number of views of each promotional video of the client; A user homepage analysis module is used to analyze the image correlation coefficients of each promotional video of the customer that allows the user to watch the video within a target time period, and evaluate the short video attention coefficients of each promotional video of the customer that allows the user to the relevant products, wherein the image correlation coefficient is obtained according to the number of images of each video that allows the user to watch the video within the target time period and the target number of images, and the tags of each promotional video of the customer that allows the user to watch the video within the target time period and the target tags of the customer are obtained from the local database. If a tag of a video that allows the user to watch the video within the target time period of a promotional video of the customer is consistent with a target tag, the tag is marked as a relevant tag, and the short video attention coefficient is calculated according to the like attention adjustment parameter value and the collection attention adjustment parameter value of each promotional video of the customer that allows the user to watch the video within the target time period, the number of tags and the number of relevant tags of each promotional video of the customer that allows the user to watch the video within the target time period, and the image correlation coefficient of each promotional video of the customer that allows the user to watch the video within the target time period; The user address analysis module is used to obtain the regions to which each user of each promotional video of the customer belongs, analyze each user of each region of each promotional video of the customer, evaluate the adaptability coefficient of each region of each promotional video of the customer, analyze each video streaming region of the customer, determine whether the customer has a plan to add offline merchants, and if so, obtain the per capita GDP value of each video streaming region of the customer, the ratio of the online average price to the offline average price of each other related customer, analyze each recommended development region of the customer, and evaluate the estimated number of offline merchants to be added in each recommended development region of the customer, among which, based on the short video attention coefficient of each user of each promotional video of the customer for the relevant product , and based on the video attention coefficient of each user allowed by each promotional video of the customer , calculate the personal adaptation coefficient of each user that can be used for each promotional video of the customer , according to each user allowed in each region of each promotional video of the client, mapping obtains the personal adaptation coefficient of each user allowed in each region of each promotional video of the client, and counting all the personal adaptation coefficients of the users allowed in each region of each promotional video of the client, and taking them as the adaptation coefficient of each region of each promotional video of the client; The platform recommendation processing module is used for the short video platform to send the customer's video streaming areas, recommended development areas and their corresponding estimated number of offline merchants to the customer's mailbox.

Images