We-media account business intelligent quotation method and system

Abstract

The invention belongs to the technical field of self-media operation and business decision, and particularly relates to a self-media account business intelligent quotation method and system, and the method comprises the following specific steps: S1, collecting self-media account basic data, user portrait data, commercial value data and market dynamic data; s2, encrypting and storing the sensitive data through AES-256; s3, adopting a random forest algorithm to construct a basic quotation model, and combining account operation fluctuation and market nodes to realize dynamic adjustment; s4, displaying quotation composition details to the account party and supporting parameter adjustment preview; and S5, generating a multi-format personalized quotation list, and negotiating and recording full-link data based on the quotation and the cooperation effect. According to the method and the system, through integrating the self-media account basic data, the user portrait data, the commercial value data and the market dynamic data, the key information influencing the quotation is covered in multiple dimensions, the quotation association factors are comprehensively considered, the deviation caused by single data limitation is reduced, and the quotation accuracy is improved.

Description

Technical Field

[0001] This invention relates to the field of self-media operation and business decision-making technology, specifically to a self-media account business intelligence pricing method and system. Background Technology

[0002] With the rapid development of the self-media industry, self-media accounts have become an important platform for brands to conduct marketing and promotion, with business cooperation encompassing various types such as advertising placement, content customization, and live-streaming e-commerce. Currently, the pricing for collaborations between self-media accounts and brands mainly relies on two methods: one is to manually estimate the price based on basic information such as the number of followers and past collaboration cases; the other is to use simple spreadsheet tools to generate a price based on a fixed formula (such as "number of followers × price coefficient per follower").

[0003] However, the existing pricing methods have obvious flaws and cannot meet the industry's needs for refined cooperation:

[0004] 1. Limited Data Dimensions and Poor Pricing Accuracy: Current methods focus only on surface-level data such as follower count and view count, neglecting key dimensions such as interaction quality (e.g., comment conversion rate, like retention rate), user profile matching (e.g., overlap between account users and brand target audience), and content commercial value (e.g., product click-through rate of historical ads). For example, a beauty-related short video account (1 million followers) and a maternal and infant-related short video account (1 million followers) might both be priced at 50,000 yuan per video based solely on follower count. However, the beauty account's user base overlaps 85% with a skincare brand's target audience, and its historical ad click-through rate is 12%, while the maternal and infant account's overlap is only 30%, with a conversion rate of only 3%. In this case, a uniform pricing strategy would result in reduced revenue for the beauty account and inflated costs for the brand.

[0005] 2. Lack of dynamic adjustment capability and insufficient timeliness: Existing prices are mostly fixed values, unable to be adjusted according to real-time market changes, account operation fluctuations, and differences in cooperation scenarios. For example, during the "618" e-commerce promotion, a food-related live streaming account saw a 200% increase in viewers and a 150% increase in product conversion rate compared to normal days. However, because the pricing system could not capture this dynamic in real time, it still cooperated with brands at the usual price of 40,000 yuan per session, causing the account to miss out on premium revenue. Conversely, an account experienced a 15% loss of followers due to a recent decline in content quality, but the price was not adjusted in time, leading to a decrease in brands' willingness to cooperate.

[0006] 3. Poor adaptability and lack of personalization in cooperation types: Different cooperation types (such as short video hard advertising, soft product placement, live streaming e-commerce, and long-term brand endorsement) have vastly different requirements for account resource consumption, content creation costs, and commercial conversion goals, but existing systems mostly adopt a uniform pricing logic. For example, if a travel account accepts a brand's "short video soft product placement" cooperation (simply showcasing the product naturally in the travel vlog) and a "live streaming e-commerce" cooperation (requiring dedicated live streaming preparation, product explanation, and after-sales support), and the system gives the same price (30,000 yuan / time), it fails to reflect the higher cost and value of the live streaming cooperation, resulting in damage to the account's interests.

[0007] Based on the above, a business intelligence pricing method and system for self-media accounts is invented. Summary of the Invention

[0008] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0009] A business intelligence pricing method for self-media accounts includes the following specific steps:

[0010] S1 collects basic data, user profile data, commercial value data, and market dynamic data of self-media accounts;

[0011] S2 uses AES-256 encryption to store sensitive data, sets up a three-level hierarchical control system for account holders, brand holders, and administrators, and retains data access logs for more than 6 months.

[0012] S3 uses the random forest algorithm to build a basic pricing model and dynamically adjusts it based on account operation fluctuations and market nodes, and customizes weight rules for different cooperation types.

[0013] S4 displays a detailed breakdown of the quote to the account holder and supports parameter adjustment previews, while showing the brand the basis for the quote's reasonableness.

[0014] S5 generates personalized quotations in multiple formats and iterates and optimizes the quotation model weights and rules monthly based on the full-link data of quotations, cooperation results, and negotiation records.

[0015] As a preferred embodiment of the self-media account business intelligence pricing method described in this invention, the specific steps of S2 are as follows:

[0016] S21 uses the AES-256 encryption algorithm to encrypt and store the collected user profile data and commercial value data to prevent data leakage;

[0017] S22 allows for setting three levels of permissions: account holder, brand owner, and administrator.

[0018] S23, record the data access behavior of all roles, and retain the logs for no less than 6 months.

[0019] As a preferred embodiment of the self-media account business intelligence pricing method described in this invention, the specific steps of S3 are as follows:

[0020] S31 employs the Random Forest algorithm, incorporating multi-dimensional data into the model training according to weights. These weights are iteratively optimized using historical cooperation quotes and performance data. Its basic quote formula is:

[0021] Base price = (Basic data score × 30% + User profile matching score × 25% + Business value score × 35% + Market dynamics score × 10%) × Account level coefficient;

[0022] S32 monitors account operation data fluctuations and market node changes in real time;

[0023] S33, preset weight adjustment rules for different cooperation types;

[0024] S34 sets up scenario integration coefficients, public welfare discount coefficients, and package discount tiers for three special scenarios: cross-industry cooperation, public welfare cooperation, and long-term package cooperation.

[0025] The specific steps of S34 are as follows:

[0026] S341, for cross-industry collaboration scenarios, increases the scenario integration coefficient and adjusts the price according to the scale of offline activities;

[0027] S342, for public welfare cooperation scenarios, sets a public welfare discount coefficient, automatically reduces the commercial value weight to 10%, and prioritizes the calculation of quotation based on basic operating costs;

[0028] S343 sets up tiered discount levels for long-term package cooperation scenarios, with higher discounts for more cooperation sessions.

[0029] As a preferred embodiment of the self-media account business intelligence pricing method described in this invention, the specific steps of step S4 are as follows:

[0030] S41 displays a detailed breakdown of the price quote to social media accounts, presenting the contribution of each data dimension to the price quote in chart form. Account owners can manually adjust key parameters and view price changes in real time.

[0031] S42 demonstrates the rationale behind the price quote to the brand, providing a report on the match between the account and the brand's target customer group, as well as historical collaboration performance data, to enhance the persuasiveness of the quote.

[0032] As a preferred embodiment of the self-media account business intelligence pricing method described in this invention, the specific steps of S5 are as follows:

[0033] S51, outputs detailed quotation sheets according to cooperation type, supports export in PDF and Excel formats;

[0034] S52 records points of contention and feedback between the two parties, generates historical versions of quotations with version numbers, and provides an electronic signature confirmation function to lock in the consensus quotation;

[0035] S53 records the quote, actual amount of cooperation, cooperation results, and negotiation record data for each cooperation, and regularly retrains the intelligent analysis model to optimize data weights and adjustment rules to improve the accuracy of quotes;

[0036] The specific steps of S52 are as follows:

[0037] S521 supports account holders and brand owners in marking up pricing disputes online and automatically recording negotiation content;

[0038] S522 generates a new quotation version after each negotiation and adjustment, and supports reviewing historical versions to avoid disputes;

[0039] S523: After both parties reach an agreement, a negotiation confirmation letter is generated, which supports electronic signatures. Once signed, the quotation plan is locked and cannot be modified.

[0040] A self-media account business intelligence pricing system includes:

[0041] The multi-dimensional data collection module is used to collect basic data of self-media accounts, user profile data, commercial value data, and market dynamic data.

[0042] The data security and access control module is used to store sensitive data using AES-256 encryption, set up three-level access control for account holders, brand holders, and administrators, and retain data access logs for more than 6 months.

[0043] The intelligent analysis and modeling module is used to build a basic pricing model using the random forest algorithm, and dynamically adjust it by combining account operation fluctuations and market nodes, and customize weight rules for different cooperation types.

[0044] The visual interaction module is used to show account owners the detailed breakdown of the quote and support parameter adjustment previews, and to show brand owners the basis for the reasonableness of the quote;

[0045] The quotation output and iteration module is used to generate personalized quotation sheets in multiple formats, and to iterate and optimize the quotation model weights and rules monthly based on the quotation, cooperation effect, negotiation record and full-link data.

[0046] As a preferred embodiment of the self-media account business intelligence pricing system described in this invention, the data security and access control module includes:

[0047] The data encryption processing module is used to encrypt and store the collected user profile data and commercial value data using the AES-256 encryption algorithm to prevent data leakage.

[0048] The permission hierarchy control module is used to set three levels of permissions: account holder, brand holder, and administrator.

[0049] The data access log module is used to record the data access behavior of all roles, and the logs are retained for no less than 6 months.

[0050] As a preferred embodiment of the self-media account business intelligence pricing system described in this invention, the intelligent analysis and modeling module includes:

[0051] A basic pricing model module is constructed to incorporate multi-dimensional data into the model training using the random forest algorithm, with weights optimized iteratively through historical cooperation pricing and performance data. The basic pricing formula is as follows:

[0052] Base price = (Basic data score × 30% + User profile matching score × 25% + Business value score × 35% + Market dynamics score × 10%) × Account level coefficient;

[0053] The dynamic adjustment module is used to monitor account operation data fluctuations and market changes in real time.

[0054] The cooperation type adaptation module is used to preset the weight adjustment rules for different cooperation types;

[0055] The special cooperation scenario adaptation module is used to set scenario integration coefficient, public welfare discount coefficient, and package discount tier for three special scenarios: cross-border cooperation, public welfare cooperation, and long-term package cooperation.

[0056] The special cooperation scenario adaptation module includes:

[0057] The cross-industry collaboration scenario module is used to increase the scenario integration coefficient for cross-industry collaboration scenarios and adjust the price according to the scale of offline activities;

[0058] The public welfare cooperation scenario module is used to set a public welfare discount coefficient for public welfare cooperation scenarios, automatically reduce the commercial value weight to 10%, and prioritize the calculation of the quotation based on the basic operating cost.

[0059] The long-term package cooperation scenario module is used to set package discount tiers for long-term package cooperation scenarios, with higher discounts for more cooperation sessions.

[0060] As a preferred embodiment of the self-media account business intelligence pricing system described in this invention, the visual interaction module includes:

[0061] The module that displays the detailed breakdown of the price quote is used to show the self-media account owner the detailed breakdown of the price quote. It presents the contribution percentage of each data dimension to the price quote in the form of charts, and allows the account owner to manually adjust key parameters and view price quote changes in real time.

[0062] The module for demonstrating the rationale behind a quote is used to show brands the reasons for the quote's reasonableness, providing a report on the match between the account and the brand's target customer group, as well as historical cooperation performance data, to enhance the persuasiveness of the quote.

[0063] As a preferred embodiment of the self-media account business intelligence pricing system described in this invention, the pricing output and iteration module includes:

[0064] The module for generating personalized quotation proposals is used to output detailed quotation sheets according to cooperation type, and supports export in PDF and Excel formats.

[0065] The quotation negotiation and version management module is used to record the points of contention and feedback between the two parties, generate historical quotation versions with version numbers, and provide an electronic signature confirmation function to lock the consensus quotation;

[0066] The iterative optimization model module is used to record the price, actual amount of cooperation, cooperation effect, and negotiation record data for each cooperation, and to retrain the intelligent analysis model regularly to optimize data weights and adjustment rules, thereby improving the accuracy of pricing.

[0067] The quotation negotiation and version management module includes:

[0068] The negotiation record module allows account holders and brands to mark disputed pricing points online and automatically record the negotiation content.

[0069] The version tracking module is used to generate a new quote version after each negotiation and adjustment, and supports backtracking to view historical versions to avoid disputes;

[0070] The consensus confirmation module is used to generate a negotiation confirmation document after both parties reach an agreement. It supports electronic signatures, and the quotation plan is locked after signing and cannot be modified.

[0071] Compared with existing technologies:

[0072] 1. By integrating basic data from self-media accounts, user profile data, commercial value data, and market dynamic data, it covers key information affecting pricing from multiple dimensions, enabling a comprehensive consideration of pricing-related factors, reducing biases caused by the limitations of single data points, and improving pricing accuracy.

[0073] 2. By monitoring account operation data fluctuations and market node changes in real time, and automatically triggering a price adjustment mechanism, it can promptly match the real-time account operation status with market trends, avoid rigid pricing, and enhance the timeliness of pricing.

[0074] 3. By pre-setting weight adjustment rules for different cooperation types, and setting exclusive adaptation coefficients based on the differences in resource consumption, creation costs, and commercial value of various cooperation types, it can realize customized pricing logic according to the characteristics of cooperation scenarios, meet the personalized needs of different cooperation types, and improve the adaptability of cooperation types. Attached Figure Description

[0075] Figure 1 This is a schematic diagram of the overall framework of the present invention;

[0076] Figure 2 This is a schematic diagram of the data security and access control module framework of the present invention;

[0077] Figure 3 This is a schematic diagram of the intelligent analysis and modeling module framework of the present invention;

[0078] Figure 4 This is a schematic diagram of the visual interaction module framework of the present invention;

[0079] Figure 5 This is a schematic diagram of the quotation output and iteration module framework of the present invention. Detailed Implementation

[0080] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0081] This invention provides a business intelligence pricing method for self-media accounts, including the following specific steps:

[0082] S1 collects basic data, user profile data, commercial value data, and market dynamic data of self-media accounts;

[0083] S2 uses AES-256 encryption to store sensitive data, sets up a three-level hierarchical control system for account holders, brand holders, and administrators, and retains data access logs for more than 6 months.

[0084] The specific steps of S2 are as follows:

[0085] S21 uses the AES-256 encryption algorithm to encrypt and store the collected user profile data and commercial value data to prevent data leakage;

[0086] S22 allows for setting three levels of permissions: account holder, brand owner, and administrator.

[0087] S23, record the data access behavior of all roles (access time, access content, operation type), and retain the logs for no less than 6 months.

[0088] S3 uses the random forest algorithm to build a basic pricing model and dynamically adjusts it based on account operation fluctuations and market nodes, and customizes weight rules for different cooperation types.

[0089] The specific steps of S3 are as follows:

[0090] S31 employs the Random Forest algorithm, incorporating multi-dimensional data into the model training according to weights. These weights are iteratively optimized using historical cooperation quotes and performance data. Its basic quote formula is:

[0091] Base price = (Basic data score × 30% + User profile matching score × 25% + Commercial value score × 35% + Market dynamics score × 10%) × Account level coefficient (Account level is divided according to fan base and platform certification level).

[0092] S32 monitors account operation data fluctuations and market node changes in real time;

[0093] S33, preset weight adjustment rules for different cooperation types;

[0094] S34 sets up scenario integration coefficients, public welfare discount coefficients, and package discount tiers for three special scenarios: cross-industry cooperation, public welfare cooperation, and long-term package cooperation.

[0095] The specific steps of S34 are as follows:

[0096] S341, for cross-industry collaboration scenarios, increases the scenario integration coefficient and adjusts the price according to the scale of offline activities;

[0097] S342, for public welfare cooperation scenarios, sets a public welfare discount coefficient, automatically reduces the commercial value weight to 10%, and prioritizes the calculation of quotation based on basic operating costs;

[0098] S343 sets up tiered discount levels for long-term package cooperation scenarios, with higher discounts for more cooperation sessions.

[0099] S4 displays a detailed breakdown of the quote to the account holder and supports parameter adjustment previews, while showing the brand the basis for the quote's reasonableness.

[0100] The specific steps of S4 are as follows:

[0101] S41 displays a detailed breakdown of the price quote to social media accounts, presenting the contribution of each data dimension to the price quote in chart form. Account owners can manually adjust key parameters and view price changes in real time.

[0102] S42 demonstrates the rationale behind the price quote to the brand, providing a report on the match between the account and the brand's target customer group, as well as historical collaboration performance data, to enhance the persuasiveness of the quote.

[0103] S5 generates personalized quotations in multiple formats and iterates and optimizes the quotation model weights and rules monthly based on the full-link data of quotations, cooperation results, and negotiation records.

[0104] The specific steps of S5 are as follows:

[0105] S51, outputs detailed quotation sheets according to cooperation type, supports export in PDF and Excel formats;

[0106] S52 records points of contention and feedback between the two parties, generates historical versions of quotations with version numbers, and provides an electronic signature confirmation function to lock in the consensus quotation;

[0107] S53 records the quote, actual amount of cooperation, cooperation results, and negotiation record data for each cooperation, and regularly retrains the intelligent analysis model to optimize data weights and adjustment rules to improve the accuracy of quotes;

[0108] The specific steps of S52 are as follows:

[0109] S521 supports account holders and brand owners in marking up pricing disputes online and automatically recording negotiation content;

[0110] S522 generates a new quotation version after each negotiation and adjustment, and supports reviewing historical versions to avoid disputes;

[0111] S523: After both parties reach an agreement, a negotiation confirmation letter is generated, which supports electronic signatures. Once signed, the quotation plan is locked and cannot be modified.

[0112] Please see Figures 1-5 A self-media account business intelligence pricing system, comprising:

[0113] The multi-dimensional data collection module is used to collect basic data, user profile data, commercial value data, and market dynamic data of self-media accounts. The basic data of self-media accounts includes the number of followers (including follower growth / churn rate), content views / reads, and interaction data (likes, comments, shares, comment conversion rate (comments / views), and like retention rate (second likes within 72 hours / total likes)). The user profile data is obtained by connecting to the self-media platform backend, acquiring the account user's age, gender, region, spending power, and interest tags, and calculating... The overlap with the brand's target customer group (number of overlapping users / total number of account users); the commercial value data includes the product click-through rate (number of product link clicks / content exposure), transaction conversion rate (product sales volume / number of clicks), and brand repurchase rate (number of brands with secondary cooperation / total number of cooperative brands) of historical cooperation cases; the market dynamic data collection involves connecting to industry databases to obtain the real-time price range of similar accounts (same field, same fan base), and the industry premium coefficient for holidays / major promotional periods (such as the premium coefficient of 1.5-2.0 for live streaming accounts during "Double 11").

[0114] The data security and access control module is used to store sensitive data using AES-256 encryption, set up three-level access control for account holders, brand holders, and administrators, and retain data access logs for more than 6 months.

[0115] The intelligent analysis and modeling module is used to build a basic pricing model using the random forest algorithm, and dynamically adjust it by combining account operation fluctuations and market nodes, and customize weight rules for different cooperation types.

[0116] The visual interaction module is used to show account owners the detailed breakdown of the quote and support parameter adjustment previews, and to show brand owners the basis for the reasonableness of the quote;

[0117] The quotation output and iteration module is used to generate personalized quotation sheets in multiple formats, and to iterate and optimize the quotation model weights and rules monthly based on the quotation, cooperation effect, negotiation record and full-link data.

[0118] The data security and access control module includes:

[0119] The data encryption processing module is used to encrypt and store the collected user profile data (such as user age and spending power) and commercial value data (such as historical transaction conversion rate) using the AES-256 encryption algorithm to prevent data leakage.

[0120] The access control module is used to set three levels of permissions for account holders, brands, and administrators. Account holders can only view all data and pricing details of their own accounts and cannot view data from other accounts. Brands can view the "non-privacy data" (such as interaction data and user profile overlap results) and pricing basis of partner accounts, but cannot view the specific age / region of account users, and cannot modify the data. Administrators are only responsible for permission allocation and data maintenance and cannot participate in pricing generation.

[0121] The data access log module is used to record the data access behavior (access time, access content, operation type) of all roles, and the logs are retained for no less than 6 months.

[0122] The intelligent analysis and modeling module includes:

[0123] A basic pricing model module is constructed to incorporate multi-dimensional data into the model training using the random forest algorithm. The weights are iteratively optimized through historical collaborative pricing and performance data (such as pricing reasonableness scores, brand satisfaction, and account revenue achievement rates). The basic pricing formula is as follows:

[0124] Base price = (Basic data score × 30% + User profile matching score × 25% + Commercial value score × 35% + Market dynamics score × 10%) × Account level coefficient (Account level is divided according to fan base and platform certification level).

[0125] The dynamic adjustment module is used to monitor account operation data fluctuations in real time (such as automatically lowering the base price by 5%-10% when the fan churn rate exceeds 10%) and market node changes (such as adjusting the price according to the industry premium coefficient when "Spring Festival" or "618" is detected).

[0126] The collaboration type adaptation module is used to preset weight adjustment rules for different collaboration types. For example, for "short video hard advertising", the weight of basic data is increased to 40% and the weight of commercial value is reduced to 25%; for "live streaming e-commerce", the weight of commercial value is increased to 50% and the "live streaming preparation cost coefficient" is increased (set to 1.2-1.8 according to the live streaming duration and the number of products); for "long-term brand endorsement", the "account exclusivity coefficient" is increased (coefficient of 1.5 for exclusive collaborations).

[0127] The special cooperation scenario adaptation module is used to set scenario integration coefficient, public welfare discount coefficient, and package discount tier for three special scenarios: cross-border cooperation, public welfare cooperation, and long-term package cooperation.

[0128] The special cooperation scenario adaptation module includes:

[0129] The cross-industry collaboration scenario module is used to increase the scenario integration coefficient for cross-industry collaboration scenarios (such as self-media accounts + offline activities, such as beauty accounts participating in brand offline launch live broadcasts), and adjust the price according to the scale of the offline event (small 1.1, medium 1.3, large 1.5);

[0130] The public welfare cooperation scenario module is used to set a public welfare discount coefficient (0.3-0.5) for public welfare cooperation scenarios (such as the account creating content for public welfare projects, and the brand only bearing the basic cost), automatically reduce the commercial value weight to 10%, and prioritize the calculation of the price based on the basic operating cost (such as content creation time and manpower input);

[0131] The Long-Term Package Cooperation Module is used to set package discount tiers for long-term package cooperation scenarios (such as a brand signing a 3-month, 10-livestream cooperation agreement with an account). The more cooperation sessions, the higher the discount (0.8 for 10 or more sessions, 0.9 for 5-9 sessions, and no discount for 1-4 sessions).

[0132] The visual interaction module includes:

[0133] The module that displays the detailed breakdown of the price quote is used to show the self-media account owner the detailed breakdown of the price quote. It presents the contribution percentage of each data dimension to the price quote in the form of charts (such as "User profile matching degree contributes 12,000 yuan" and "Commercial value contributes 18,000 yuan"). It allows the account owner to manually adjust key parameters (such as increasing the weight of the user profile under special cooperation needs) and view the price quote changes in real time.

[0134] The module for demonstrating the rationale behind a quote is used to show brands the reasons for the quote's reasonableness, providing a report on the match between the account and the brand's target customer group, as well as historical cooperation performance data, to enhance the persuasiveness of the quote.

[0135] The quotation output and iteration module includes:

[0136] The module for generating personalized pricing proposals is used to output detailed price lists (including basic price, dynamic adjustment items, adaptation adjustment items, and final price) according to the cooperation type, and supports export in PDF and Excel formats.

[0137] The quotation negotiation and version management module is used to record the points of contention and feedback between the two parties, generate historical quotation versions with version numbers, and provide an electronic signature confirmation function to lock the consensus quotation;

[0138] The iterative optimization model module is used to record the quotation, actual cooperation amount, cooperation effect, and negotiation record data for each cooperation, and to retrain the intelligent analysis model regularly (monthly) to optimize data weights and adjustment rules, thereby improving the accuracy of quotations.

[0139] The quotation negotiation and version management module includes:

[0140] The negotiation record module is used to support account owners and brand owners in marking up pricing disputes online (such as brand owners having objections to the "Double 11 premium coefficient"), and automatically record the negotiation content (modification suggestions, feedback from both parties, and adjustments reached in consensus).

[0141] The version tracking module is used to generate a new quotation version (marked with version number, modification time, and modifier) ​​after each negotiation and adjustment, and supports backtracking to view historical versions (such as the initial quotation of V1.0 and the quotation after negotiation and adjustment of V2.0) to avoid disputes;

[0142] The consensus confirmation module is used to generate a negotiation confirmation document after both parties reach an agreement. It supports electronic signatures, and the quotation plan is locked after signing and cannot be modified.

[0143] Although the present invention has been described above with reference to embodiments, various modifications can be made and components can be replaced with equivalents without departing from the scope of the invention. In particular, as long as there is no structural conflict, the features in the disclosed embodiments can be combined with each other in any manner. The lack of an exhaustive description of these combinations in this specification is merely for the sake of brevity and resource conservation. Therefore, the present invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A business intelligence pricing method for self-media accounts, characterized in that, The specific steps are as follows: S1 collects basic data, user profile data, commercial value data, and market dynamic data of self-media accounts; S2 uses AES-256 encryption to store sensitive data, sets up a three-level hierarchical control system for account holders, brand holders, and administrators, and retains data access logs for more than 6 months. S3 uses the random forest algorithm to build a basic pricing model and dynamically adjusts it based on account operation fluctuations and market nodes, and customizes weight rules for different cooperation types. S4 displays a detailed breakdown of the quote to the account holder and supports parameter adjustment previews, while showing the brand the basis for the quote's reasonableness. S5 generates personalized quotations in multiple formats and iterates and optimizes the quotation model weights and rules monthly based on the full-link data of quotations, cooperation results, and negotiation records.

2. The self-media account business intelligence pricing method according to claim 1, characterized in that, The specific steps of S2 are as follows: S21 uses the AES-256 encryption algorithm to encrypt and store the collected user profile data and commercial value data to prevent data leakage; S22 allows for setting three levels of permissions: account holder, brand owner, and administrator. S23, record the data access behavior of all roles, and retain the logs for no less than 6 months.

3. The self-media account business intelligence pricing method according to claim 1, characterized in that, The specific steps of S3 are as follows: S31 employs the Random Forest algorithm, incorporating multi-dimensional data into the model training according to weights. These weights are iteratively optimized using historical cooperation quotes and performance data. Its basic quote formula is: Base price = (Basic data score × 30% + User profile matching score × 25% + Business value score × 35% + Market dynamics score × 10%) × Account level coefficient; S32 monitors account operation data fluctuations and market node changes in real time; S33, preset weight adjustment rules for different cooperation types; S34 sets up scenario integration coefficients, public welfare discount coefficients, and package discount tiers for three special scenarios: cross-industry cooperation, public welfare cooperation, and long-term package cooperation. The specific steps of S34 are as follows: S341, for cross-industry collaboration scenarios, increases the scenario integration coefficient and adjusts the price according to the scale of offline activities; S342, for public welfare cooperation scenarios, sets a public welfare discount coefficient, automatically reduces the commercial value weight to 10%, and prioritizes the calculation of quotation based on basic operating costs; S343 sets up tiered discount levels for long-term package cooperation scenarios, with higher discounts for more cooperation sessions.

4. The self-media account business intelligence pricing method according to claim 1, characterized in that, The specific steps of S4 are as follows: S41 displays a detailed breakdown of the price quote to social media accounts, presenting the contribution of each data dimension to the price quote in chart form. Account owners can manually adjust key parameters and view price changes in real time. S42 demonstrates the rationale behind the price quote to the brand, providing a report on the match between the account and the brand's target customer group, as well as historical collaboration performance data, to enhance the persuasiveness of the quote.

5. The self-media account business intelligence pricing method according to claim 1, characterized in that, The specific steps of S5 are as follows: S51, outputs detailed quotation sheets according to cooperation type, supports export in PDF and Excel formats; S52 records points of contention and feedback between the two parties, generates historical versions of quotations with version numbers, and provides an electronic signature confirmation function to lock in the consensus quotation; S53 records the quote, actual amount of cooperation, cooperation results, and negotiation record data for each cooperation, and regularly retrains the intelligent analysis model to optimize data weights and adjustment rules to improve the accuracy of quotes; The specific steps of S52 are as follows: S521 supports account holders and brand owners in marking up pricing disputes online and automatically recording negotiation content; S522 generates a new quotation version after each negotiation and adjustment, and supports reviewing historical versions to avoid disputes; S523: After both parties reach an agreement, a negotiation confirmation letter is generated, which supports electronic signatures. Once signed, the quotation plan is locked and cannot be modified.

6. A self-media account business intelligence pricing system, characterized in that, include: The multi-dimensional data collection module is used to collect basic data of self-media accounts, user profile data, commercial value data, and market dynamic data. The data security and access control module is used to store sensitive data using AES-256 encryption, set up three-level access control for account holders, brand holders, and administrators, and retain data access logs for more than 6 months. The intelligent analysis and modeling module is used to build a basic pricing model using the random forest algorithm, and dynamically adjust it by combining account operation fluctuations and market nodes, and customize weight rules for different cooperation types. The visual interaction module is used to show account owners the detailed breakdown of the quote and support parameter adjustment previews, and to show brand owners the basis for the reasonableness of the quote; The quotation output and iteration module is used to generate personalized quotation sheets in multiple formats, and to iterate and optimize the quotation model weights and rules monthly based on the quotation, cooperation effect, negotiation record and full-link data.

7. The self-media account business intelligence pricing system according to claim 6, characterized in that, The data security and access control module includes: The data encryption processing module is used to encrypt and store the collected user profile data and commercial value data using the AES-256 encryption algorithm to prevent data leakage. The permission hierarchy control module is used to set three levels of permissions: account holder, brand holder, and administrator. The data access log module is used to record the data access behavior of all roles, and the logs are retained for no less than 6 months.

8. A self-media account business intelligence pricing system according to claim 6, characterized in that, The intelligent analysis and modeling module includes: A basic pricing model module is built to incorporate multi-dimensional data into the model training using the random forest algorithm, with the weights being iteratively optimized through historical cooperation pricing and performance data. The dynamic adjustment module is used to monitor account operation data fluctuations and market changes in real time. The cooperation type adaptation module is used to preset the weight adjustment rules for different cooperation types; The special cooperation scenario adaptation module is used to set scenario integration coefficient, public welfare discount coefficient, and package discount tier for three special scenarios: cross-border cooperation, public welfare cooperation, and long-term package cooperation. The special cooperation scenario adaptation module includes: The cross-industry collaboration scenario module is used to increase the scenario integration coefficient for cross-industry collaboration scenarios and adjust the price according to the scale of offline activities; The public welfare cooperation scenario module is used to set a public welfare discount coefficient for public welfare cooperation scenarios, automatically reduce the commercial value weight to 10%, and prioritize the calculation of the quotation based on the basic operating cost. The long-term package cooperation scenario module is used to set package discount tiers for long-term package cooperation scenarios, with higher discounts for more cooperation sessions.

9. A self-media account business intelligence pricing system according to claim 6, characterized in that, The visual interaction module includes: The module that displays the detailed breakdown of the price quote is used to show the self-media account owner the detailed breakdown of the price quote. It presents the contribution percentage of each data dimension to the price quote in the form of charts, and allows the account owner to manually adjust key parameters and view price quote changes in real time. The module for demonstrating the rationale behind a quote is used to show brands the reasons for the quote's reasonableness, providing a report on the match between the account and the brand's target customer group, as well as historical cooperation performance data, to enhance the persuasiveness of the quote.

10. A self-media account business intelligence pricing system according to claim 6, characterized in that, The quotation output and iteration module includes: The module for generating personalized quotation proposals is used to output detailed quotation sheets according to cooperation type, and supports export in PDF and Excel formats. The quotation negotiation and version management module is used to record the points of contention and feedback between the two parties, generate historical quotation versions with version numbers, and provide an electronic signature confirmation function to lock the consensus quotation; The iterative optimization model module is used to record the price, actual amount of cooperation, cooperation effect, and negotiation record data for each cooperation, and to retrain the intelligent analysis model regularly to optimize data weights and adjustment rules, thereby improving the accuracy of pricing. The quotation negotiation and version management module includes: The negotiation record module allows account holders and brands to mark disputed pricing points online and automatically record the negotiation content. The version tracking module is used to generate a new quote version after each negotiation and adjustment, and supports backtracking to view historical versions to avoid disputes; The consensus confirmation module is used to generate a negotiation confirmation document after both parties reach an agreement. It supports electronic signatures, and the quotation plan is locked after signing and cannot be modified.

Images