Competitive product analysis methods and systems

Abstract

The present invention relates to the field of competitive product analysis technology, and in particular to a method and system for competitive product analysis. The present invention uses keyword information, based on social media accounts to publish works, comments, and voice data, and conducts delivery analysis, content analysis, and dissemination analysis. By collecting massive amounts of data to analyze data information that matches keywords, the matching data is organized into analysis reports to achieve competitive product analysis. The system includes a competitive product analysis task creation and maintenance unit, a social media account publication work, comment, and voice data collection and storage unit, and a competitive product analysis report classification and display unit. The beneficial effect of the present invention is that the competitive product analysis technology for social media account data is comprehensive, enabling enterprises to make strategic positioning and product optimization more detailed.

Description

Technical Field

[0001] The present invention relates to the technical field of competitive product analysis, and in particular to a method and system for competitive product analysis. Background Art

[0002] With the development of social media, more and more companies are creating and publishing content, covering a wide range of fields and topics, either individually or as teams. This convenience and real-time nature of social media have made it a crucial platform for marketing, branding, customer service, and other activities. Companies can directly interact with users through social media, understanding their needs and feedback, while also leveraging social media's advertising and promotional features to precisely reach their target audiences.

[0003] In the process of enterprise development, enterprises are constantly launching and improving products to occupy the market. Competitive product analysis is an important means to help improve corporate products in the market. By observing competitors' promotional works on social media, we can understand their product features, functional advantages, etc., and thus compare the advantages and disadvantages of our own products, providing a reference for product improvement and market positioning.

[0004] User reviews of promoted products often reflect real user needs and feedback. Analyzing user comments and feedback on competing products on social media can provide a more accurate understanding of user attitudes and satisfaction. This review data can help companies promptly identify problems with competing products and improve their own products or services accordingly, enhancing user experience and satisfaction.

[0005] Competitive analysis on social media can provide companies with rich market information and user feedback, helping them better understand market trends, optimize products and services, and develop effective marketing strategies, thereby increasing user loyalty and enhancing brand competitiveness.

[0006] Chinese Patent Publication No.: CN105608593A discloses monitoring and responding to social media posts using social relevance comparisons, wherein a computing device comprising at least one processor monitors a plurality of social media posts for references to one or more keywords related to a brand; the computing device determines, by the computing device, at least one topic related to the brand mentioned in the plurality of social media posts; the computing device identifies, by the computing device, whether the plurality of social media posts have positive or negative sentiment with respect to the at least one topic; and upon identifying a social media post with negative sentiment with respect to the at least one related topic, replying to the social media post with negative sentiment with a response based on at least one social media post from the plurality of social media posts that has positive sentiment with respect to the at least one topic.

[0007] It can be seen that the existing technology has the following problems: due to the incompleteness of the competitive product analysis technology for social media account data, the company's strategic positioning and product optimization are not detailed. Summary of the Invention

[0008] To this end, the present invention provides a method and system for competitive product analysis to overcome the problem in the prior art that the competitive product analysis technology for social media account data is not comprehensive, resulting in the lack of detailed strategic positioning and product optimization for enterprises.

[0009] To achieve the above objectives, the present invention provides a competitive product analysis method. Based on the works, comments, and buzz data published by social media accounts, the method screens out the accounts, content, and dissemination of competing products, analyzes the product features, functional advantages and disadvantages of competing products, and analyzes the real needs and feedback of users.

[0010] Create an analysis task to identify keywords for your product and related competitors, excluding your own product keywords and time range;

[0011] Collect works, comments, volume, fans and interactive user data of social media accounts and store them via storage media;

[0012] Using a competitive product analysis toolkit to analyze the collected data stored in the storage medium, performing data analysis based on three dimensions: placement analysis, content analysis, and communication analysis, and storing the analyzed data in the storage medium;

[0013] Present the analysis results in three dimensions: the delivery analysis, the content analysis, and the communication analysis; formulate marketing and promotion strategies and predict industry development trends based on the analysis results;

[0014] Determine the competitor's rating based on the number of likes, reposts, and comments on the competitor's video;

[0015] Set the compensation parameters for the number of first-level traffic likes on competitor scores, the compensation parameters for the number of second-level traffic likes on competitor scores, the number of first-class likes for first-level traffic, the number of second-class likes for first-level traffic, the number of first-class likes for second-level traffic, and the number of second-class likes for second-level traffic;

[0016] Based on the comparison between the above preset parameters and the actual number of likes, we determine the supplementary parameters for the impact of the number of likes on the competitor's rating, and calculate the corresponding competitor's rating;

[0017] Determine whether to include the competitor product in the detection scope based on the comparison result between the competitor product score and the preset competitor product score;

[0018] Set competitor rating to , where n is the number of competitor videos, i = 1, 2, ... n, Di is the number of likes for the competitor's i-th video, K1 is the compensation parameter for the impact of the competitor's likes on the competitor's rating, Zi is the number of forwardings for the competitor's i-th video, K2 is the compensation parameter for the impact of the forwardings on the competitor's rating, Pi is the number of comments on the competitor's i-th video, and K3 is the compensation parameter for the impact of the comments on the competitor's rating;

[0019] Set K1 = K10 + K11, where K10 is the compensation parameter for the number of first-level traffic likes on the competitor's score; K11 is the compensation parameter for the number of second-level traffic likes on the competitor's score;

[0020] The system sets the first-class like number Dz1 for first-level traffic, the second-class like number Dz2 for first-level traffic; the first-class like number Di 1 for second-level traffic, the second-class like number Di2 for second-level traffic,

[0021] In this embodiment, if 0≤Di<Dz1, then K10=K101, where K101 is a supplementary parameter for the impact of the number of first-level traffic likes on the competitor's score when the number of likes is 0≤D101<Dz1, and D101 is set to 0.2;

[0022] If Dz1≤Di≤Dz2, then K10=K102, where K102 is the supplementary parameter for the impact of the number of first-level traffic likes on the competitor's score when the number of likes Dz1≤Di≤Dz2, and D102=0.5;

[0023] If Di>Dz2, then K10=K103, where K103 is a supplementary parameter for the impact of the number of first-level traffic likes on the competitor's score when the number of likes Di>Dz2, and D103 is set to 0.8;

[0024] If 0≤Di<Di 1, then K11=K111, where K111 is a supplementary parameter for the impact of the number of secondary traffic likes on the competitor's score when the number of likes is 0≤Di<Di 1, and D111=0.3;

[0025] If Di 1<Di<Di2, then K11=K112, where K112 is a supplementary parameter for the impact of the number of secondary traffic likes on the competitor's score when the number of likes Di 1<Di<Di2, and D112=0.6;

[0026] If Di>Di2, then K11=K113, where K113 is a supplementary parameter for the impact of the number of secondary traffic likes on the competitor's score when the number of likes Di>Di2, and D113=0.9;

[0027] The system is provided with a first competitor score F1 and a second competitor score F2.

[0028] If F < F1, the competitor is a third-class competitor and is not included in the monitoring scope;

[0029] If F1≤F≤F2, then this competitor is a second-class competitor and is included in the monitoring scope;

[0030] If F>F2, then this competitor is a first-class competitor and is included in the monitoring scope and analyzed.

[0031] Furthermore, a task management system is established, which is used to plan, execute and monitor the competitive product analysis process. Based on the product introduction and product nickname, the keywords of the competitive product analysis task are determined, and task fields are generated based on the keywords. The task fields include: unique ID, task status, analysis time, keywords, and analysis dimensions.

[0032] Furthermore, through data mining technology and open application programming interface technology, the account's work data, comment data, voice data and interaction data are obtained and stored on storage media as a data source for competitive product analysis;

[0033] The collected data is collated daily, and the data is collected and maintained regularly. The collected data includes: account information, work information, comment information, volume information and interaction information, and corresponding fields are generated. The corresponding fields include: unique ID, collection content, collection type and collection time

[0034] Furthermore, the collected data is analyzed in multiple dimensions according to the keywords and time range of the task, including:

[0035] Advertising analysis: Analyze the advertising placement of competitor accounts on social media. The analysis results include: advertising channels, advertising time, advertising format, advertising accounts, advertising volume, and account operators;

[0036] Content analysis: Analyze the works published by the delivery account that match the task keywords and the corresponding comments. Use natural language processing technology to extract key paragraphs from the works, classify them according to analysis tags, and perform sentiment analysis on the key paragraphs and comments. The analysis results include: the number of works, the type and proportion of works, the analysis tags and the corresponding work paragraphs, and the sentiment analysis and proportion of the work paragraphs and the corresponding comments.

[0037] Communication analysis: analyze the volume data and interactive user information of works that meet the task keywords. The volume data includes: reading, commenting, sharing, forwarding, coining and interactive data; the interactive user information includes: the user's geographic location, age group, and gender. The analysis results include: the top value of the volume, the average value, and the regional distribution of interactive users, age distribution, and fan portraits.

[0038] Furthermore, the task is divided into multiple subtasks through the dimension, and distributed technology is used for parallel analysis, and subtask fields are generated, including: subtask unique ID, analysis task unique ID, status and time. The status will be updated after the subtask analysis is completed, and the analysis task can view the subtask analysis progress through the unique ID associated with the subtask.

[0039] Furthermore, when the analysis task is performed, the analysis result can be saved and updated through a storage medium to generate a task result field, which includes: a task result unique ID, an analysis task unique ID, an analysis result, and a storage time.

[0040] The present invention also provides a competitive product analysis system, comprising:

[0041] The task management module is used to manage and monitor the entire competitive product analysis process, including task creation, assignment, status tracking, reminders, and notifications;

[0042] The data collection module collects data on works, comments, buzz, and interactions from accounts selected for competitor placements on social media platforms. It uses data scraping tools or application programming interfaces to periodically or in real time obtain relevant data from target social media platforms, store it, and process it to provide data support for subsequent competitor analysis.

[0043] The competitive product analysis module analyzes the collected data according to three dimensions: delivery analysis, content analysis, and communication analysis. It uses distributed technology for parallel analysis, creates subtask information and maintains subtask status through storage media, and stores the analysis results for data display after completion.

[0044] The data display module displays the results of the competitive product analysis to the user, including reports, charts and data visualization.

[0045] The present invention also provides a storage medium storing a plurality of instructions, which are loaded by a processor to execute the steps of the competitive product analysis method.

[0046] The present invention also provides an electronic device, comprising: the aforementioned storage medium and a processor for executing instructions in the storage medium.

[0047] Compared with the existing technology, the beneficial effect of the present invention is that the competitive product analysis system relies on the data released by social media accounts to perform data analysis based on multiple dimensions such as delivery analysis, content analysis, and communication analysis. The large user scale of social media accounts, promotional works and comment data can intuitively help us understand the promotion status of competitive products, thereby improving the practicality of the invention.

[0048] Furthermore, we analyze the interactions of competitor accounts on social media, including likes, comments, reposts, and coins, to help users understand the interaction patterns and effects between competitor accounts and users, thereby optimizing their own social interaction strategies.

[0049] Furthermore, we analyze the audience characteristics of competitor accounts, including age, gender, interests and hobbies, to help users more accurately locate their target audiences, adjust their own content positioning and marketing strategies accordingly, and recommend suitable content and marketing strategies to users to help them seize the initiative and maintain their competitive advantage.

[0050] Furthermore, the system provides user-friendly data reports and visual charts, allowing users to easily view and understand data analysis results, quickly make decisions and adjust strategies.

[0051] Specifically, scoring competitors can screen out competitors that are closer to the current product and analyze them, thereby improving the efficiency of competitor analysis and avoiding wasting time analyzing all competitors. Among them, setting a first competitor score and a second competitor score for competitor scoring, and classifying competitors through scoring can better monitor and analyze first-class competitors.

[0052] Specifically, the competitor rating can effectively capture current competitors based on their number of likes, reposts, and comments, and make competitor analysis more accurate. Among them, the competitor likes are divided into first-level traffic likes and second-level traffic likes. The first-level traffic likes are the number of natural traffic and likes, and the second-level traffic likes are the number of forwarded videos and likes. It can make a more accurate judgment on the popularity of competitors, avoid the lack of likes after reposting to have a greater impact on the competitor rating, and thus affect the competitor analysis results.

[0053] Specifically, the compensation parameters for the number of likes on competitor scores are divided into compensation parameters for the number of first-level traffic likes on competitor scores and compensation parameters for the number of second-level traffic likes on competitor scores. Different numbers of first-level traffic likes correspond to different compensation parameters for competitor scores for first-level traffic likes, and different numbers of second-level traffic likes correspond to different compensation parameters for competitor scores for second-level traffic likes. This can effectively analyze competitors more accurately and avoid the situation where different numbers of likes for different competitors are different but the compensation parameters for competitor scores for different competitors are the same, resulting in the competitor scores not reflecting the differences between different competitors, which affects the selection and analysis of competitors.

[0054] Furthermore, the social media account competitor analysis system provides users with comprehensive and timely competitor intelligence and data support, helping them better understand the market environment, optimize their own operating strategies, and enhance their competitiveness.

[0055] Furthermore, competitive product analysis requires reading massive amounts of data for analysis, and uses parallelization and distributed computing technologies to divide data and tasks into small blocks according to the displayed categories for parallel processing to improve analysis speed and efficiency. The entire analysis task is split into modules according to categories for separate calculations. After the modules are calculated separately, the status is reported. After the calculation modules of the entire task are completed, they are uniformly reported to the task management module, thereby achieving high cohesion and low coupling of the system, and improving the system's scalability and parallel processing capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a flow chart of the competitive product analysis method in this embodiment;

[0057] Figure 2 This is a flow chart of the operation process of the competitive product analysis system in this embodiment;

[0058] Figure 3 This is a schematic diagram of the structure of electronic device components used for competitive product analysis in this embodiment;

[0059] Figure 4 Flowchart of the data comparison process obtained by the competitive product analysis method in this embodiment. DETAILED DESCRIPTION

[0060] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0061] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0062] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0063] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "installed," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0064] See also Figure 1 As shown, it is a flow chart of the competitive product analysis method in this embodiment, including:

[0065] Step S100: Create a competitive product analysis task, determine competitive product analysis keywords, keywords not included, time range, and analysis dimensions, establish relevant fields in the task table, manage tasks by maintaining data fields, and check analysis progress;

[0066] Step S200: Competitive product analysis data is based on social media work-related data. Account data with high popularity and high follower counts are selected for daily monitoring and collection. The scope of data collection includes the account's works, comments, and promotion status, which serve as the data source for competitive product analysis.

[0067] Perform preliminary cleaning of the collected data, using regular expressions or text processing tools to identify images, emoticons, and hyperlinks in works and comments, remove or transfer them as needed, remove special characters, punctuation marks, and other non-text characters, and use hashing algorithms or text similarity calculations to identify duplicate comments;

[0068] Generate a unique ID for the processed account and work data, bind the work data to the account's unique ID, bind the comments and promotion data to the work's unique ID, maintain the data according to the collection time, and perform historical data comparison and trend analysis based on time;

[0069] Step S300: Analyze the collected account data according to the task indicators. The analysis dimensions include the account data selected for competitive product placement, the works and comments data published by the account, and the dissemination of the works. Finally, generate data reports and recommend operational strategies based on the above.

[0070] Analyze the placement location, placement time, account type, placement quantity, and account operating entity of the placement account;

[0071] Work and comment data analysis includes published works, proportion of original works, proportion of single-image text, proportion of articles with more than 100,000 views, proportion of deleted articles, duplicate titles, original links, sentences related to competitors in the works, comment word cloud, high-frequency keywords, and comment sentiment score;

[0072] Work dissemination data analysis is to sort out the highest and average data of work reading, likes, comments, viewing, and interaction, and generate fan profiles, age distribution, and regional distribution based on the data of participating users;

[0073] Step S400: Save the analysis results based on the storage medium and bind the result data to the unique ID of the task to facilitate query when displaying the data;

[0074] Step S500: Display the results of the competitor analysis. The result data is displayed in the form of tables and graphs according to the above classification standards to intuitively display the various indicators and analysis results of the competitor. Each classification of data supports a separate download function, and the complete analysis report can be downloaded.

[0075] Specifically, competitor ratings are set and the competitor ratings are classified according to likes, reposts, and comments.

[0076] Specifically, in order to conduct potential analysis on competitor data,

[0077] Set competitor rating to Where n is the number of competitor videos, i=1,2,...n, Di is the number of likes for the competitor's i-th video, K1 is the compensation parameter for the impact of the competitor's likes on the competitor's rating, Zi is the number of forwardings for the competitor's i-th video, K2 is the compensation parameter for the impact of the forwardings on the competitor's rating, Pi is the number of comments on the competitor's i-th video, and K3 is the compensation parameter for the impact of the comments on the competitor's rating;

[0078] Set K1=K10+K11, where K10 is the compensation parameter for the number of first-level traffic likes on the competitor's score; K11 is the compensation parameter for the number of second-level traffic likes on the competitor's score;

[0079] The system sets the first-class likes number Dz1 for first-class traffic, the second-class likes number Dz2 for first-class traffic; the first-class likes number Di1 for second-class traffic, the second-class likes number Di2 for second-class traffic,

[0080] In this embodiment, if 0≤Di<Dz1, then K10=K101, where K101 is a supplementary parameter for the impact of the number of first-level traffic likes on the competitor's score when the number of likes is 0≤D101<Dz1, and D101 is set to 0.2;

[0081] If Dz1≤Di≤Dz2, then K10=K102, where K102 is a supplementary parameter for the impact of the number of first-level traffic likes on the competitor's score when the number of likes Dz1≤Di≤Dz2, and D102 is set to 0.5;

[0082] If Di>Dz2, then K10=K103, where K103 is a supplementary parameter for the impact of the number of first-level traffic likes on the competitor's score when the number of likes Di>Dz2, and D103 is set to 0.8;

[0083] If 0≤Di<Di1, then K11=K111, where K111 is the supplementary parameter for the impact of the number of secondary traffic likes on the competitor's score when the number of likes is 0≤Di<Di1, and D111=0.3;

[0084] If Di1<Di<Di2, then K11=K112, where K112 is a supplementary parameter for the impact of the number of secondary traffic likes on the competitor's score when the number of likes Di1<Di<Di2, and D112=0.6;

[0085] If Di>Di2, then K11=K113, where K113 is a supplementary parameter for the impact of the number of secondary traffic likes on the competitor's score when the number of likes Di>Di2, and D113 is set to 0.9;

[0086] The system is provided with a first competitor score F1 and a second competitor score F2.

[0087] If F < F1, the competitor is a third-class competitor and is not included in the monitoring scope;

[0088] If F1≤F≤F2, then this competitor is a second-class competitor and is included in the monitoring scope;

[0089] If F>F2, then this competitor is a first-class competitor and is included in the monitoring scope and analyzed.

[0090] The beneficial effect of the present invention is that the competitive product analysis system relies on the data released by social media accounts to perform data analysis based on multiple dimensions such as delivery analysis, content analysis, and communication analysis. The large user scale of social media accounts, promotional works and comment data can intuitively help us understand the promotion status of competitive products, thereby improving the practicality of the invention.

[0091] Specifically, analyzing the interactions of competitor accounts on social media, including likes, comments, reposts, and coins, helps users understand the interaction patterns and effects between competitor accounts and users, thereby optimizing their own social interaction strategies.

[0092] Specifically, we analyze the audience characteristics of competitor accounts, including age, gender, interests and hobbies, to help users more accurately locate their target audiences, adjust their own content positioning and marketing strategies accordingly, and recommend suitable content and marketing strategies to users to help them seize the initiative and maintain their competitive advantage.

[0093] Specifically, the system provides user-friendly data reports and visual charts, allowing users to easily view and understand data analysis results, quickly make decisions and adjust strategies.

[0094] Specifically, scoring competitors can screen out competitors that are closer to the current product and analyze them, thereby improving the efficiency of competitor analysis and avoiding wasting time analyzing all competitors. Among them, setting a first competitor score and a second competitor score for competitor scoring, and classifying competitors through scoring can better monitor and analyze first-class competitors.

[0095] Specifically, the competitor rating can effectively capture current competitors based on their number of likes, reposts, and comments, and make competitor analysis more accurate. Among them, the competitor likes are divided into first-level traffic likes and second-level traffic likes. The first-level traffic likes are the number of natural traffic and likes, and the second-level traffic likes are the number of forwarded videos and likes. It can make a more accurate judgment on the popularity of competitors, avoid the lack of likes after reposting to have a greater impact on the competitor rating, and thus affect the competitor analysis results.

[0096] Specifically, the compensation parameters for the number of likes on competitor scores are divided into compensation parameters for the number of first-level traffic likes on competitor scores and compensation parameters for the number of second-level traffic likes on competitor scores. Different numbers of first-level traffic likes correspond to different compensation parameters for competitor scores for first-level traffic likes, and different numbers of second-level traffic likes correspond to different compensation parameters for competitor scores for second-level traffic likes. This can effectively analyze competitors more accurately and avoid the situation where different numbers of likes for different competitors are different but the compensation parameters for competitor scores for different competitors are the same, resulting in the competitor scores not reflecting the differences between different competitors, which affects the selection and analysis of competitors.

[0097] See also Figure 2 As shown, it is a flow chart of the operation process of the competitive product analysis system in this embodiment, including:

[0098] The task management module is used to create and manage competitive product analysis tasks, including:

[0099] Create an analysis task unit to set the task name, analysis type, time range, and analysis dimension. After the task is created, the system will generate a unique task ID.

[0100] Manage analysis task unit: View all analysis tasks, including task name, status, start time, and end time. Users can edit, pause, resume, and delete the tasks.

[0101] The data collection module is used to obtain the account's work data, comment data, and dissemination data through collection technology and open application programming interface technology;

[0102] The work data includes: various contents published by the account, such as text, pictures, videos, etc. The main information collected includes work ID, publishing time, content text, picture / video link, number of likes, number of reposts, and number of comments. By collecting work data, it is possible to analyze the content type, publishing frequency, and popularity of the account;

[0103] The review data includes: review ID, review time, review content, reviewer ID, and number of likes. By collecting the review data, it is possible to analyze the user's feedback and emotional tendencies on the work, as well as the interaction between users;

[0104] The dissemination details data includes: the forwarding and sharing of the work, and the behavior of related users. The collected information includes: forwarder / sharer ID, forwarding / sharing time, forwarding / sharing content, forwarding / sharing path, etc. By collecting dissemination details data, it is possible to analyze the dissemination path, influence range and dissemination effect of the work;

[0105] The data collection methods and interfaces may vary for different social media platforms and need to be implemented according to the platform-specific application programming interface documentation;

[0106] The data analysis module is used to analyze the account data of the data collection module, read the account's works, comments, and dissemination data for delivery analysis, content analysis, and dissemination analysis;

[0107] Competitive product analysis requires reading massive amounts of data for analysis. Parallelization and distributed computing technologies are used to divide data and tasks into small blocks based on displayed categories for parallel processing, thereby improving analysis speed and efficiency.

[0108] The entire analysis task is divided into modules according to classification and calculated separately. The status of each module is reported after the calculation is completed. After the calculation module of the entire task is completed, it is reported to the task management module in a unified manner;

[0109] Data storage is designed as asynchronous operation, and queues are used to reduce the pressure on data storage;

[0110] Data display module, which analyzes data display by converting abstract data into intuitive visual information through charts, graphs, and maps;

[0111] The analyzed data is stored according to the results of the task, stored separately according to the analysis dimension and bound to the task unique ID. The analysis results must support operations such as data screening, sorting, and filtering. The design of the analysis result table must ensure the system response speed and stability.

[0112] Specifically, we analyze the audience characteristics of competitor accounts, including age, gender, interests and hobbies, to help users more accurately locate their target audiences, adjust their own content positioning and marketing strategies accordingly, and recommend suitable content and marketing strategies to users to help them seize the initiative and maintain their competitive advantage.

[0113] Specifically, the system provides user-friendly data reports and visual charts, allowing users to easily view and understand data analysis results, quickly make decisions and adjust strategies.

[0114] Specifically, the social media account competitor analysis system provides users with comprehensive and timely competitor intelligence and data support, helping them better understand the market environment, optimize their own operating strategies, and enhance their competitiveness.

[0115] Specifically, competitive product analysis requires reading massive amounts of data for analysis, and using parallelization and distributed computing technologies to divide data and tasks into small blocks according to the displayed categories for parallel processing to improve analysis speed and efficiency. The entire analysis task is split into modules according to categories for separate calculations. After the modules are calculated separately, the status is reported. After the calculation modules of the entire task are completed, they are uniformly reported to the task management module, thereby achieving high cohesion and low coupling of the system, and improving the system's scalability and parallel processing capabilities.

[0116] See also Figure 3 As shown, this is a schematic diagram of the structure of electronic device components used for competitive product analysis in this embodiment.

[0117] The processor 601 and the memory 602 communicate with each other via the bus 603.

[0118] Processor 601 is used to call program instructions in memory 602 to execute the methods provided by the above-mentioned method embodiments, such as: creating and managing tasks; regularly updating and organizing source data based on the collection scope; performing competitive product analysis based on the source data; recording the analyzed data in the memory 602 in a display report format; and displaying and customizing data exports based on the data in memory 602.

[0119] See also Figure 4 As shown, it is a flow chart of the data comparison process of the competitive product analysis method in this embodiment, including:

[0120] Step S310: determining analysis dimensions, generating data reports based on the analysis dimensions, and recommending operation strategies based on the data reports;

[0121] Step S320: Analyze the account, including the following: placement location, placement period, account type, placement amount, and account operator;

[0122] Step S330: Based on the work dissemination data, the highest and average data are sorted out, and fan portraits, age distribution, and regional distribution are generated based on the data of participating users.

[0123] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0124] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. Competitive product analysis method, characterized by: Based on the works, comments, and buzz data posted by social media accounts, we can identify the accounts, content, and dissemination of competing products, and analyze their product features, functional advantages and disadvantages, and real user needs and feedback. Create an analysis task to identify keywords for your product and related competitors, excluding your own product keywords and time range; Collect works, comments, volume, fans and interactive user data of social media accounts and store them via storage media; Using a competitive product analysis toolkit to analyze the collected data stored in the storage medium, performing data analysis based on three dimensions: placement analysis, content analysis, and communication analysis, and storing the analyzed data in the storage medium; Present the analysis results in three dimensions: the delivery analysis, the content analysis, and the communication analysis; formulate marketing and promotion strategies and predict industry development trends based on the analysis results; Determine the competitor's rating based on the number of likes, reposts, and comments on the competitor's video; Set the compensation parameters for the number of first-level traffic likes on competitor scores, the compensation parameters for the number of second-level traffic likes on competitor scores, the number of first-class likes for first-level traffic, the number of second-class likes for first-level traffic, the number of first-class likes for second-level traffic, and the number of second-class likes for second-level traffic; Based on the comparison between the above preset parameters and the actual number of likes, we determine the supplementary parameters for the impact of the number of likes on the competitor's rating, and calculate the corresponding competitor's rating; Determine whether to include the competitor product in the detection scope based on the comparison result between the competitor product score and the preset competitor product score; Set competitor rating to , where n is the number of competitor videos, i = 1, 2, ... n, Di is the number of likes for the competitor's i-th video, K1 is the compensation parameter for the impact of the competitor's likes on the competitor's rating, Zi is the number of forwardings for the competitor's i-th video, K2 is the compensation parameter for the impact of the forwardings on the competitor's rating, Pi is the number of comments on the competitor's i-th video, and K3 is the compensation parameter for the impact of the comments on the competitor's rating; Set K1 = K10 + K11, where K10 is the compensation parameter for the number of first-level traffic likes on the competitor's score; K11 is the compensation parameter for the number of second-level traffic likes on the competitor's score; The system sets the first-class like number Dz1 for first-level traffic, the second-class like number Dz2 for first-level traffic; the first-class like number Di 1 for second-level traffic, the second-class like number Di2 for second-level traffic, In this embodiment, if 0≤Di<Dz1, then K10=K101, where K101 is a supplementary parameter for the impact of the number of first-level traffic likes on the competitor's score when the number of likes is 0≤D101<Dz1, and D101 is set to 0.2; If Dz1≤Di≤Dz2, then K10=K102, where K102 is the supplementary parameter for the impact of the number of first-level traffic likes on the competitor's score when the number of likes Dz1≤Di≤Dz2, and D102=0.5; If Di>Dz2, then K10=K103, where K103 is a supplementary parameter for the impact of the number of first-level traffic likes on the competitor's score when the number of likes Di>Dz2, and D103 is set to 0.8; If 0≤Di<Di 1, then K11=K111, where K111 is a supplementary parameter for the impact of the number of secondary traffic likes on the competitor's score when the number of likes is 0≤Di<Di 1, and D111=0.3; If Di 1<Di<Di2, then K11=K112, where K112 is a supplementary parameter for the impact of the number of secondary traffic likes on the competitor's score when the number of likes Di 1<Di<Di2, and D112=0.6; If Di>Di2, then K11=K113, where K113 is a supplementary parameter for the impact of the number of secondary traffic likes on the competitor's score when the number of likes Di>Di2, and D113=0.9; The system is provided with a first competitor score F1 and a second competitor score F2. If F < F1, the competitor is a third-class competitor and is not included in the monitoring scope; If F1≤F≤F2, then this competitor is a second-class competitor and is included in the monitoring scope; If F>F2, then this competitor is a first-class competitor and is included in the monitoring scope and analyzed.

2. The competitive product analysis method according to claim 1, characterized in that: Establish a task management system for planning, executing and monitoring the competitive product analysis process. Determine the keywords of the competitive product analysis task based on the product introduction and product nickname, and generate task fields based on the keywords. The task fields include: unique ID, task status, analysis time, keywords, and analysis dimensions.

3. The competitive product analysis method according to claim 2, characterized in that: Through data mining and open application programming interface technology, we can obtain the account's work data, comment data, voice data, and interaction data and store them on storage media as a data source for competitive product analysis. The collected data is sorted every day, and the data is collected and maintained regularly. The collected data includes: account information, work information, comment information, volume information and interaction information, and corresponding fields are generated. The corresponding fields include: unique ID, collection content, collection type and collection time.

4. The competitive product analysis method according to claim 3, characterized in that: Perform multi-dimensional analysis of the collected data based on the keywords and time range of the task, including: Advertising analysis: Analyze the advertising placement of competitor accounts on social media. The analysis results include: advertising channels, advertising time, advertising format, advertising accounts, advertising volume, and account operators; Content analysis: Analyze the works published by the delivery account that match the task keywords and the corresponding comments. Use natural language processing technology to extract key paragraphs from the works and classify them according to analysis tags. Perform sentiment analysis on the key paragraphs and comments. The analysis results include: the number of works, the type and proportion of works, the analysis tags and the corresponding work paragraphs, and the sentiment analysis and proportion of the work paragraphs and the corresponding comments. Communication analysis: analyze the volume data and interactive user information of works that meet the task keywords. The volume data includes: reading, commenting, sharing, forwarding, coining and interactive data; the interactive user information includes: the user's geographic location, age group, and gender. The analysis results include: the top value of the volume, the average value, and the regional distribution of interactive users, age distribution, and fan portraits.

5. The competitive product analysis method according to claim 4, characterized in that: The task is divided into multiple subtasks through the dimension, and distributed technology is used for parallel analysis, and subtask fields are generated, including: subtask unique ID, analysis task unique ID, status and time. The status will be updated after the subtask analysis is completed, and the analysis task can view the subtask analysis progress through the unique ID associated with the subtask.

6. The competitive product analysis method according to claim 5, characterized in that: When the analysis task is performed, the analysis result can be saved and updated through the storage medium, and a task result field is generated. The field includes: a task result unique ID, an analysis task unique ID, an analysis result, and a storage time.

7. A competitive product analysis system, characterized in that: Used to implement the competitive product analysis method according to any one of claims 1 to 6, comprising: The task management module is used to manage and monitor the entire competitive product analysis process, including task creation, assignment, status tracking, reminders, and notifications; The data collection module collects data on works, comments, buzz, and interactions from accounts selected for competitor placements on social media platforms. Using data scraping tools or application programming interfaces, it periodically or in real time retrieves relevant data from target social media platforms, stores it, and processes it to provide data support for subsequent competitor analysis. The competitive product analysis module analyzes the collected data according to three dimensions: delivery analysis, content analysis, and communication analysis. It uses distributed technology for parallel analysis, creates subtask information and maintains subtask status through storage media, and stores the analysis results for data display after completion. The data display module displays the results of the competitive product analysis to the user, including reports, charts and data visualization.

8. A storage medium storing a plurality of instructions, characterized in that: The instructions are loaded by the processor to execute the steps of the competitive product analysis method described in any one of claims 1-6.

9. An electronic device, characterized in that: include: The storage medium and processor are used to execute the instructions in the storage medium of claim 8.

Images