Advertising effect analysis system and method for different regions based on big data

Abstract

The present invention relates to the technical field of advertising management, and discloses a system and method for analyzing advertising effects in different regions based on big data. The system comprises a product advertising parameter collection module, a product advertising case search module, and a product advertising effect analysis module. The system can intelligently search for advertising cases of products in different regions that are similar to product advertising by accurately presetting product advertising databases in different regions, thereby realizing the collection of advertising cases of similar products in different regions. Specific regional parameters are introduced to realize accurate retrieval and screening of advertising cases of similar products in different specific regions, thereby realizing scientific prediction and analysis of advertising effects of similar products in different regions, and reducing the management risk and economic cost of advertising effect analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of advertising management, and specifically to a system and method for analyzing advertising effects in different regions based on big data. Background Art

[0002] Advertising refers to the activities in which advertisers, including industrial and commercial enterprises, institutions, groups, and individuals, use the strategies and means of advertising operators to publicize and disseminate advertising information to the public through certain media or forms; the focus of advertising is determined by the specific content of the advertisement. Among them, the focus of concept advertising is to promote the concepts and ideas advocated by the publicity and guide the public to establish new concepts; the focus of product advertising is to promote and introduce the functions and quality of the products and guide consumers' consumption. The publicity is mainly carried out through various media such as radio, television, newspapers and periodicals. In order to ensure the effectiveness of publicity, it is necessary to select appropriate media, adopt appropriate methods, and produce high-quality advertisements, and at the same time, it must be carried out in accordance with the law. Among them, commercial advertising is the most widely used. Commercial advertising publications include wallpaper, signs, street furniture, flyers, radio, film and television advertisements, web banners, mobile phone screens, shopping carts, network pop-up ads, skylights, bus stand chairs, human signs, magazines, newspapers, bus sides, taxi doors, passenger screens, music stage performances, subway platforms and trains, supermarket stickers, streaming audio, video openings, posters, tickets and the back of supermarket receipts, etc.; authorized sponsors can deliver messages anywhere through media advertising. This advertising research method can measure the perceived changes of brands, products and services in the target market. This shift is tailored to the consumer's exposure to the company's advertising and promotions. The purpose of advertising tracking is usually to measure the weight and consumption level of the media, the results of advertising media selection, the effectiveness of advertising, and the quality of advertising materials. Current commercial advertising mainly relies on advertising planners to decide the advertising methods used in different regions, the number of people and funds to be invested based on personal experience, and to choose the advertising methods, number of people and funds suitable for the product based on the advertising effect; the process of planners finding the advertising methods, number of people and funds suitable for the product in different regions is not only long but also economically costly.

[0003] The Chinese invention patent application with publication number CN114626870A discloses an enterprise data intelligent analysis system and its analysis method, which includes a user ordering module, a user order query module, a user order classification storage module, a user business query module and an advertisement directional push module; the user ordering module is used to specify a customer to place an order with the enterprise through the user system. When a customer generates a business order for the enterprise, the present invention records all orders of the customer and performs intelligent analysis on all orders of the customer, that is, periodic statistics are performed according to the customer's periodic orders, and when the customer's order quantity base in this period is lower than that of the previous period or lower than that of the previous periods at the same time, the business advertisement will be automatically controlled to be regularly delivered to the customer, so as to increase the advertising publicity for the customer. The above technical scheme cannot predict and analyze the advertising publicity method and the amount of personnel and capital investment suitable for the product according to regional characteristics during the product advertising delivery process, and cannot guarantee the effect of advertising delivery, thereby increasing the cost and risk of advertising delivery. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In order to solve the above-mentioned problem that current commercial advertising mainly relies on advertising planners to decide the advertising methods to be used in different regions as well as the number of personnel and funds to be invested based on their personal experience, and at the same time select advertising methods, number of personnel and funds suitable for the products based on the advertising effects; through planners searching for advertising methods, number of personnel and funds suitable for products in different regions, which not only has a long cycle but also high economic cost, the above purpose of accurately analyzing the advertising methods with high sales volume for similar products in different regions, formulating the best advertising methods for products in different regions in advance, and ensuring the advertising effects can be achieved.

[0006] (II) Technical solution

[0007] The present invention is implemented by the following technical solution: a method for analyzing the advertising effects in different regions based on big data, the method comprising the following steps:

[0008] S1. Collect data on the characteristics of advertising products, the number of people involved in advertising, and the amount of funds invested in advertising;

[0009] S2, combining and processing the advertising product characteristic data, the advertising investment personnel number data, and the advertising investment capital amount data to generate advertising product, personnel, and capital characteristic data;

[0010] S3, using a data recognition algorithm to perform keyword analysis on the advertising product, personnel, and capital feature data and the product advertising case data in different regions according to product features, number of personnel involved, and capital features, to identify advertising case data that matches the product features, number of personnel involved, and capital features of the advertisement, and to identify and generate advertising case data for similar products in different regions;

[0011] S4. Collecting product advertising specific regional feature data, using a data search algorithm to search the product advertising specific regional feature data and the advertising case data of similar products in different regions according to specific regional feature keywords to find advertising case data of similar products in different regions in the same region and identify and generate advertising case data of similar products in specific regions;

[0012] S5. Acquire the advertising case data of similar products in the specific region, search for the product sales volume corresponding to each advertising case data of similar products using a data search algorithm, and sort them in ascending order according to the product sales volume values ​​to construct advertising sales volume data of similar products in the specific region;

[0013] S6. Use a data search algorithm to search for the advertising sales data of similar products in the specific region with the maximum sales value in the advertising sales data of similar products in the specific region, and mark and generate the best advertising sales data of similar products in the specific region; search for the advertising method used by the product with the best advertising sales volume of similar products in the specific region according to the advertising case number of similar products in the specific region based on the best advertising sales data of similar products in the specific region and the advertising case data of similar products in the specific region, and mark and generate the best advertising method data of similar products in the specific region;

[0014] S7, identifying the best advertising method for similar products in the specific region, generating product advertising data to determine the best method and outputting it.

[0015] Preferably, the steps for collecting the advertising product feature data, the advertising investment personnel data, and the advertising investment capital data are as follows:

[0016] S11, using a data entry dialog box to collect product feature data for advertisements and generate product feature data A for advertisements, wherein the product feature data includes one or more of product name, model specification, function, and technical specification;

[0017] Use the data entry dialog box to collect the interval of the number of staff invested in advertising and generate the interval data of the number of staff invested in advertising [m1, m2], where m1 represents the minimum number of staff invested in advertising; m2 represents the maximum number of staff invested in advertising;

[0018] Use the data entry dialog box to collect the advertising investment amount range and generate advertising investment amount range data [n1, n2], where n1 represents the minimum advertising investment amount; n2 represents the maximum advertising investment amount, and the units of n1 and n2 are both ten thousand yuan.

[0019] Preferably, the steps of combining and processing the advertising product characteristic data, the advertising investment personnel number data, and the advertising investment capital amount data to generate the advertising product, personnel, and capital characteristic data are as follows:

[0020] S21. Combine and process the advertising product characteristic data A, the advertising investment personnel number interval data [m1, m2], and the advertising investment capital amount interval data [n1, n2] to generate an advertising product, personnel, and capital characteristic data set B = (A, [m1, m2], [n1, n2]).

[0021] Preferably, the data recognition algorithm is used to perform keyword analysis on the advertising product, personnel, and capital feature data and the advertising case data of products in different regions according to product features, number of personnel features, and capital features to identify advertising case data that matches the advertising product features, number of personnel features, and capital features, and to identify and generate advertising case data of similar products in different regions as follows:

[0022] S31 、 Establish a product advertising case data set C = (c1, ..., c u , …, c ε ), u=1, 2, 3,...,ε; where c n represents the u-th product advertising case data in different regions, ε represents the maximum number of product advertising case data, the product advertising case data includes product feature data, the number of personnel involved in product advertising, the amount of funds invested in product advertising, the sales volume after product advertising, the regional characteristics of the promotion, and the product advertising method; the product advertising method includes one or more of offline outdoor advertising, media advertising, search advertising, social advertising, and short video advertising;

[0023] S32, using a data recognition algorithm, the advertising product feature data A, the advertising investment personnel number interval data [m1, m2], and the advertising investment fund amount interval data [n1, n2] in the advertising product, personnel, and fund feature data set B are compared with the different regional product advertising case data c in the different regional product advertising case data set C. u According to the product characteristics, the number of personnel involved, and the amount of funds invested, keyword recognition is performed to analyze the advertising case data of products in different regions that match the advertised products. u The specific steps of the data recognition algorithm to identify matching advertising cases are as follows:

[0024] S321, dissemination: Synchronously set the advertising product feature data A, the advertising investment personnel number interval data [m1, m2], and the advertising investment capital interval data [n1, n2] as water waves. Each water wave is an independent individual, so each water wave will have three attributes: position, wavelength α, and wave height β;

[0025] In each iteration, each water wave will propagate to the different regions of the product advertising case data set C in the search space. u Search is performed, and the height β of the water wave will decrease by 1. The position update formula is as follows:

[0026] in It represents the position of water wave i in the search space of product advertising case data set C in different regions after t iterations; represents the position of water wave i in the search space of product advertising case data set C in different regions before t iterations; χ and δ are the upper and lower bounds of the search space of product advertising case data set C in different regions, respectively; rand(-1,1) represents a random function with the value (-1,1);

[0027] S322, refraction: after a water wave propagates, the water wave refracts and searches for different regions of product advertising case data set C in the space of different regions of product advertising case data set C. u For identification, each time the water wave propagates, the height β of the water wave will decrease by 1. When β decreases to 0, the water wave will be refracted, and its height and wavelength will change. The position after refraction is normally distributed at a position with the current water wave and the midpoint of the optimal water wave as the mean and the distance between the current water wave and the optimal water wave as the variance. After refraction, the height of the water wave will be reinitialized to the maximum height β = β max ; After refraction, recalculate the wavelength α of the water wave;

[0028] S322, breaking waves: After the water wave propagates in the search space of the product advertising case data set C in different regions, it reaches a position that is better than the current optimal water wave, that is, it searches for the product advertising case data c in different regions that matches the advertising product feature data A, the interval data of the number of advertising investment personnel [m1, m2], and the interval data of the amount of advertising investment funds [n1, n2]. u , then the water wave will break and propagate the current optimal water wave to the location where the breaking waves are generated, that is, output the advertising case data c of different regional products that match the advertising product feature data A, the advertising investment personnel interval data [m1, m2], and the advertising investment capital interval data [n1, n2] u , the formula for generating the breaking wave position is as follows:

[0029] Where rand(0, 1) represents a random function with the value (0, 1), r1 to k represent the spatial dimension numbers randomly selected for each wave break, d represents the specific spatial dimension actually randomly selected for each wave break, and d r1 to d k The specific spatial dimension parameter randomly selected for each breaking wave, σ is a constant;

[0030] S324, outputting the product advertising case data c in different regions that match the advertising product feature data A, the advertising investment personnel number interval data [m1, m2], and the advertising investment capital interval data [n1, n2] u ;

[0031] S33, all the product advertising case data of different regions outputted in step S324 c u Identify and generate advertising case data of similar products in different regions and establish a collection of advertising case data of similar products in different regions C′=(c′ u1 ,…,c′ u2 ), 1≤u1≤u≤u2≤ε; where c′ u1 represents u1 advertising case data of similar products in different regions; c′ u2 It represents advertising case data of similar products in u2 different regions, where the similar products include at least one of the same product and similar products.

[0032] Preferably, the steps of collecting the specific regional characteristic data of product advertising and using a data search algorithm to search the specific regional characteristic data of product advertising and the advertising case data of similar products in different regions according to specific regional characteristic keywords to obtain advertising case data of similar products in different regions in the same region and identify and generate the advertising case data of similar products in specific regions are as follows:

[0033] S41, using a data entry dialog box to collect specific regional feature data of the advertising location and generate specific regional feature data D of the product advertising, wherein the regional feature includes any one of a province, autonomous region, municipality directly under the central government, prefecture-level city, autonomous prefecture, county, autonomous county, municipal district, and county-level city;

[0034] S42, using a depth-restricted search algorithm to compare the product advertising specific regional feature data D with the different regional similar product advertising case data c′ in the different regional similar product advertising case data set C′. u1 to c′ u2 According to the specific regional characteristic keywords, the advertising case data of similar products in different regions of the same region are searched and filtered out, and the advertising case data of similar products in different regions that are searched and filtered out are identified to generate advertising case data of similar products in specific regions and establish a collection of advertising case data of similar products in specific regions C″=(c″ u3 ,…,c″ u4 ), 1≤u3≤u≤u4≤ε; where c″ u3 Indicates advertising case data of similar products in u3 specific regions; c″ u4 Represents advertising case data of similar products in 4 specific regions.

[0035] Preferably, the steps of obtaining the advertising case data of similar products in the specific region and combining it with the data search algorithm to search for the product sales volume corresponding to each advertising case data of similar products and arranging them in ascending order according to the product sales volume values ​​to construct the advertising sales volume data of similar products in the specific region are as follows:

[0036] S51, obtaining a data set C″ of advertisement cases of similar products in the specific region;

[0037] S52, using the deep restricted search algorithm in step S42, orderly search for the product sales volume corresponding to each advertising case data of similar products in the specific region according to the advertising case numbers u3 to u4 of similar products, and arrange the product sales volume values ​​in ascending order, to construct a specific region similar product advertising sales volume data set E = (e u3 ,…,e u4 ), where e u3 Indicates the advertising case data of similar products in a specific region c″ u3 Advertising and sales data of similar products in corresponding specific regions; u4 Indicates the advertising case data of similar products in a specific region c″ u4 The corresponding specific region similar product advertising sales data, e u3 <e u4 .

[0038] Preferably, the data search algorithm is used to search for the advertising sales data of similar products in the specific region with the maximum sales value in the advertising sales data of similar products in the specific region, and mark and generate the best advertising sales data of similar products in the specific region; the advertising method used for the product corresponding to the best advertising sales volume of similar products in the specific region is searched according to the advertising case number of similar products in the specific region based on the best advertising sales data of similar products in the specific region and the advertising case data of similar products in the specific region, and the operation steps of marking and generating the best advertising method data of similar products in the specific region are as follows:

[0039] S61, using the deep restricted search algorithm in step S42 to search for the specific region similar product advertising sales data with the largest sales value in the specific region similar product advertising sales data set E according to the sales value, and identify and generate the specific region similar product advertising best sales data e zuijia ;

[0040] S62, based on the best sales volume data of similar products in the specific region zuijia The specific region similar product advertising case data set C″ is combined with the depth restricted search algorithm zuijia Search for the advertising case number of similar products in a specific region zuijia The advertising method of the same product in the specific region in the corresponding advertising case data of the same product in the specific region is identified to generate the best advertising method data F of the same product in the specific region zuijia .

[0041] Preferably, the steps of generating and outputting the data of the best advertising method for similar products in the specific region by identifying the data of the best advertising method for the product are as follows:

[0042] S71. The best advertising method data for similar products in specific regions zuijia Generate data to determine the best way to advertise a product And output through the display screen.

[0043] A system for implementing the method for analyzing the advertising effects in different regions based on big data, the system comprising a product advertising parameter collection module, a product advertising case search module, and a product advertising effect analysis module;

[0044] The product advertising parameter collection module includes an advertising product feature collection unit, an advertising investment personnel collection unit, an advertising investment fund collection unit, and an advertising product, personnel, and fund parameter processing unit;

[0045] The advertising product feature collection unit collects advertising product feature data through a data entry dialog box; the advertising investment personnel collection unit collects advertising investment personnel quantity data through a data entry dialog box; the advertising investment funds collection unit collects advertising investment funds amount data through a data entry dialog box; the advertising product, personnel, and funds parameter processing unit combines the advertising product feature data, the advertising investment personnel quantity data, and the advertising investment funds amount data to generate advertising product, personnel, and funds feature data;

[0046] The product advertising case search module includes a storage unit for product advertising cases in different regions, a unit for identifying product advertising cases of the same type, a unit for collecting product advertising regional information, and a unit for retrieving product advertising cases in specific regions;

[0047] The product advertising case storage unit of different regions is used to store product advertising case data of different regions; the product advertising case identification unit of similar products adopts a data identification algorithm to perform keyword analysis on the advertising product, personnel, and capital feature data and the product advertising case data of different regions according to product features, number of personnel features, and capital features, to identify the advertising case data that matches the product features, number of personnel features, and capital features of the advertisement, and to identify and generate advertising case data of similar products in different regions; the product advertising regional information collection unit collects specific regional feature data of product advertising through a data entry dialog box; the product advertising case retrieval unit of specific regional products adopts a data search algorithm to perform keyword search on the product advertising specific regional feature data and the product advertising case data of similar products in different regions according to specific regional feature keywords, to identify and generate advertising case data of similar products in different regions in the same region, and to identify and generate advertising case data of similar products in specific regions;

[0048] The product advertising effect analysis module includes a unit for acquiring advertising cases of similar products, a unit for searching and sorting product sales volume of advertising cases of similar products, a unit for searching the best product sales volume and advertising method of advertising cases of similar products, and a unit for outputting the best product advertising method;

[0049] The unit for acquiring advertising cases for similar products is used to acquire advertising case data for similar products in the specific region; the unit for searching and sorting product sales volume for advertising cases for similar products combines the advertising case data for similar products in the specific region with a data search algorithm to search for the product sales volume corresponding to each advertising case data for similar products and arranges them in ascending order according to the product sales volume values, thereby constructing advertising sales volume data for similar products in the specific region; the unit for searching for product best sales volume and advertising methods for advertising cases for similar products uses a data search algorithm to search for the maximum sales volume value in the advertising sales volume data for similar products in the specific region. The advertising sales volume data of similar products in the specific region are identified and generated as the best advertising sales volume data of similar products in the specific region; according to the best advertising sales volume data of similar products in the specific region and the advertising case data of similar products in the specific region, the advertising method used for the product with the best advertising sales volume of similar products in the specific region is searched according to the advertising case number of similar products in the specific region, and the advertising method is identified and generated as the best advertising method data of similar products in the specific region; the product advertising best method output unit identifies the best advertising method data of similar products in the specific region to generate product advertising best method data and outputs it through the display screen.

[0050] (III) Beneficial effects

[0051] The present invention provides a system and method for analyzing the advertising effects in different regions based on big data. It has the following beneficial effects:

[0052] 1. Accurately collect relevant product feature information of the advertising products through the advertising product feature collection unit to provide data support for accurately searching for advertising cases of similar products; the advertising investment personnel collection unit and the advertising investment funds collection unit cooperate with each other to scientifically collect the personnel and capital investment of the advertising products to ensure that the analysis results of the product advertising cases are more authentic and reliable; the advertising product, personnel, and capital parameter processing unit effectively integrates the relevant data of product advertising to improve the efficiency and quality of product advertising effect analysis.

[0053] 2. Through the cooperation between the product advertising case storage unit in different regions and the product advertising case identification unit of similar products, the product advertising database in different regions can be accurately preset to intelligently search for product advertising cases in different regions that are similar to the product advertising, so as to realize the collection of advertising cases of similar products in different regions; the product advertising regional information collection unit and the specific regional product advertising case retrieval unit cooperate with each other to introduce specific regional parameters to realize the accurate retrieval of advertising cases of similar products in different specific regions, so as to realize the scientific prediction and analysis of the advertising effects of similar products in different regions, and reduce the management risk and economic cost of advertising effect analysis.

[0054] 3. The product sales volume search and ranking unit of similar product advertising cases uses product advertising sales volume parameters to intuitively and accurately feedback the advertising effects of similar products in specific regions, thereby improving the scientific nature of the product advertising effect results; the product best sales volume and advertising method search unit of similar product advertising cases and the product advertising best method output unit cooperate with each other to intelligently screen out the advertising methods corresponding to the maximum sales volume of similar products in specific regions, thereby realizing early prediction of the optimal advertising methods for specific products in different regions, thereby improving the accuracy of product advertising effect analysis and corporate product sales. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A schematic diagram of the modules of the big data-based advertising effect analysis system for different regions provided by the present invention;

[0056] Figure 2 A flow chart of the method for analyzing advertising effectiveness in different regions based on big data provided by the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] The embodiments of the system and method for analyzing the advertising effects in different regions based on big data are as follows:

[0059] See also Figure 1 - Figure 2 , a method for analyzing the advertising effects in different regions based on big data, the method comprises the following steps:

[0060] S1. Collect data on the characteristics of advertising products, the number of people involved in advertising, and the amount of funds invested in advertising;

[0061] S2. Combine and process the advertising product feature data, the number of advertising investment personnel data, and the advertising investment capital data to generate advertising product, personnel, and capital feature data;

[0062] S3. Use data recognition algorithms to perform keyword analysis on the advertising product, personnel, and capital feature data and the product advertising case data in different regions according to product features, number of personnel involved, and capital features to identify advertising case data that matches the product features, number of personnel involved, and capital features of the advertisements, and identify and generate advertising case data for similar products in different regions;

[0063] S4. Collect product advertising specific regional feature data, use data search algorithm to search the product advertising specific regional feature data and advertising case data of similar products in different regions according to specific regional feature keywords to find advertising case data of similar products in different regions in the same region and identify and generate advertising case data of similar products in specific regions;

[0064] S5. Obtain advertising case data of similar products in a specific region, and use a data search algorithm to search for the product sales volume corresponding to each advertising case data of similar products, and sort them in ascending order according to the product sales volume values, to construct advertising sales volume data of similar products in a specific region;

[0065] S6. Use a data search algorithm to search for the advertising sales data of similar products in a specific region with the maximum sales value in the advertising sales data of similar products in the specific region, and identify and generate the best advertising sales data of similar products in the specific region; based on the best advertising sales data of similar products in the specific region and the advertising case data of similar products in the specific region, search for the advertising method used by the product with the best advertising sales of similar products in the specific region according to the advertising case number of similar products in the specific region, and identify and generate the best advertising method data of similar products in the specific region;

[0066] S7. Identify the best advertising method data for similar products in a specific region to generate product advertising best method data and output it.

[0067] For further information, see Figure 1-Figure 2 The steps for collecting data on advertising product characteristics, the number of people involved in advertising, and the amount of funds invested in advertising are as follows:

[0068] S11, using a data entry dialog box to collect product feature data for advertisements and generate product feature data A for advertisements, wherein the product feature data includes one or more of product name, model specification, function, and technical specification;

[0069] Use the data entry dialog box to collect the interval of the number of staff invested in advertising and generate the interval data of the number of staff invested in advertising [m1, m2], where m1 represents the minimum number of staff invested in advertising; m2 represents the maximum number of staff invested in advertising;

[0070] Use the data entry dialog box to collect the advertising investment amount range and generate advertising investment amount range data [n1, n2], where n1 represents the minimum advertising investment amount; n2 represents the maximum advertising investment amount, and the units of n1 and n2 are both ten thousand yuan.

[0071] The steps for combining and processing the advertising product characteristic data, the number of advertising investment personnel data, and the advertising investment capital data to generate advertising product, personnel, and capital characteristic data are as follows:

[0072] S21. Combine and process the advertising product characteristic data A, the advertising investment personnel number interval data [m1, m2], and the advertising investment capital amount interval data [n1, n2] to generate an advertising product, personnel, and capital characteristic data set B = (A, [m1, m2], [n1, n2]).

[0073] The advertising product feature collection unit accurately collects relevant product feature information of the advertising products, providing data support for accurately searching for advertising cases of similar products; the advertising investment personnel collection unit and the advertising investment funds collection unit cooperate with each other to scientifically collect the personnel and capital investment of the advertising products, ensuring that the analysis results of the product advertising cases are more authentic and reliable; the advertising product, personnel, and capital parameter processing unit effectively integrates the relevant data of product advertising, improving the efficiency and quality of product advertising effect analysis.

[0074] For further information, see Figure 1-Figure 2 , using data recognition algorithms to analyze the advertising product, personnel, and capital feature data with the advertising case data of products in different regions according to product features, number of personnel features, and capital features, identify advertising case data that matches the advertising product features, number of personnel features, and capital features, and identify and generate advertising case data of similar products in different regions. The steps are as follows:

[0075] S31 、 Establish a product advertising case data set C = (c1, ..., c u , …, c ε ), u=1, 2, 3,...,ε; where c urepresents the u-th product advertising case data in different regions, ε represents the maximum number of product advertising case data, the product advertising case data includes product feature data, the number of personnel involved in product advertising, the amount of funds invested in product advertising, the sales volume after product advertising, the regional characteristics of the promotion, and the product advertising method; the product advertising method includes one or more of offline outdoor advertising, media advertising, search advertising, social advertising, and short video advertising;

[0076] S32, using a data recognition algorithm, the advertising product feature data A, the advertising investment personnel number interval data [m1, m2], and the advertising investment fund amount interval data [n1, n2] in the advertising product, personnel, and fund feature data set B are compared with the different regional product advertising case data c in the different regional product advertising case data set C. u According to the product characteristics, the number of personnel involved, and the amount of funds invested, keyword recognition is performed to analyze the advertising case data of products in different regions that match the advertised products. u The specific steps of the data recognition algorithm to identify matching advertising cases are as follows:

[0077] S321, dissemination: Synchronously set the advertising product feature data A, the advertising investment personnel number interval data [m1, m2], and the advertising investment capital interval data [n1, n2] as water waves. Each water wave is an independent individual, so each water wave will have three attributes: position, wavelength α, and wave height β;

[0078] In each iteration, each water wave will propagate to the different regions of the product advertising case data set C in the search space. u Search is performed, and the height β of the water wave will decrease by 1. The position update formula is as follows:

[0079] in It represents the position of water wave i in the search space of product advertising case data set C in different regions after t iterations; represents the position of water wave i in the search space of product advertising case data set C in different regions before t iterations; χ and δ are the upper and lower bounds of the search space of product advertising case data set C in different regions, respectively; rand(-1,1) represents a random function with the value (-1,1);

[0080] S322, refraction: after a water wave propagates, the water wave refracts and searches for different regions of product advertising case data set C in the space of different regions of product advertising case data set C. u For identification, each time the water wave propagates, the height β of the water wave will decrease by 1. When β decreases to 0, the water wave will be refracted, and its height and wavelength will change. The position after refraction is normally distributed at a position with the current water wave and the midpoint of the optimal water wave as the mean and the distance between the current water wave and the optimal water wave as the variance. After refraction, the height of the water wave will be reinitialized to the maximum height β = β max ; After refraction, recalculate the wavelength α of the water wave;

[0081] S322, breaking waves: After the water wave propagates in the search space of the product advertising case data set C in different regions, it reaches a position that is better than the current optimal water wave, that is, it searches for the product advertising case data c in different regions that matches the advertising product feature data A, the interval data of the number of advertising investment personnel [m1, m2], and the interval data of the amount of advertising investment funds [n1, n2]. u , then the water wave will break and propagate the current optimal water wave to the location where the breaking waves are generated, that is, output the advertising case data c of different regional products that match the advertising product feature data A, the advertising investment personnel interval data [m1, m2], and the advertising investment capital interval data [n1, n2] u , the formula for generating the breaking wave position is as follows:

[0082] Where rand(0, 1) represents a random function with the value (0, 1), r1 to k represent the spatial dimension numbers randomly selected for each wave break, d represents the specific spatial dimension actually randomly selected for each wave break, and d r1 to d k The specific spatial dimension parameter randomly selected for each breaking wave, σ is a constant;

[0083] S324, outputting the product advertising case data c in different regions that match the advertising product feature data A, the advertising investment personnel number interval data [m1, m2], and the advertising investment capital interval data [n1, n2] u ;

[0084] S33, all the product advertising case data of different regions outputted in step S324 c u Identify and generate advertising case data of similar products in different regions and establish a collection of advertising case data of similar products in different regions C′=(c′ u1 ,…,c′ u2 ), 1≤u1≤u≤u2≤ε; where c′ u1represents u1 advertising case data of similar products in different regions; c′ u2 It represents advertising case data of similar products in u2 different regions, where the similar products include at least one of the same product and similar products.

[0085] The specific regional characteristic data of product advertising is collected, and the data search algorithm is used to search the specific regional characteristic data of product advertising with the advertising case data of similar products in different regions according to the specific regional characteristic keywords to obtain the advertising case data of similar products in different regions in the same region and mark and generate the advertising case data of similar products in specific regions. The operation steps are as follows:

[0086] S41, using a data entry dialog box to collect specific regional feature data of the advertising location and generate specific regional feature data D of the product advertising, wherein the regional feature includes any one of a province, autonomous region, municipality directly under the central government, prefecture-level city, autonomous prefecture, county, autonomous county, municipal district, and county-level city;

[0087] S42, using a depth-restricted search algorithm to compare the product advertising specific regional feature data D with the different regional similar product advertising case data c′ in the different regional similar product advertising case data set C′. u1 to c′ u2 According to the specific regional characteristic keywords, the advertising case data of similar products in different regions of the same region are searched and filtered out, and the advertising case data of similar products in different regions that are searched and filtered out are identified to generate advertising case data of similar products in specific regions and establish a collection of advertising case data of similar products in specific regions C″=(c″ u3 ,…,c″ u4 ), 1≤u3≤u≤u4≤ε; where c″ u3 Indicates advertising case data of similar products in u3 specific regions; c″ u4 Represents advertising case data of similar products in 4 specific regions.

[0088] Through the cooperation between the different regional product advertising case storage unit and the similar product advertising case identification unit, the different regional product advertising databases are accurately preset to intelligently search for the different regional product advertising cases similar to the product advertising, so as to realize the collection of advertising cases of similar products in different regions; the product advertising regional information collection unit and the specific regional product advertising case retrieval unit cooperate with each other to introduce specific regional parameters to realize the accurate retrieval of different specific regional similar product advertising case screening, so as to realize the scientific prediction and analysis of the advertising effects of similar products in different regions, and reduce the management risk and economic cost of advertising effect analysis.

[0089] For further information, see Figure 1-Figure 2, obtain the advertising case data of similar products in a specific region, and use the data search algorithm to search for the product sales volume corresponding to each advertising case data of similar products and sort them in ascending order according to the product sales volume value. The steps to construct the advertising sales volume data of similar products in a specific region are as follows:

[0090] S51, obtaining a data set C″ of advertisement cases of similar products in the specific region;

[0091] S52, using the deep restricted search algorithm in step S42, orderly search for the product sales volume corresponding to each advertising case data of similar products in the specific region according to the advertising case numbers u3 to u4 of similar products, and arrange the product sales volume values ​​in ascending order, to construct a specific region similar product advertising sales volume data set E = (e u3 ,…,e u4 ), where e u3 Indicates the advertising case data of similar products in a specific region c″ u3 Advertising and sales data of similar products in corresponding specific regions; u4 Indicates the advertising case data of similar products in a specific region c″ u4 The corresponding specific region similar product advertising sales data, e u3 <e u4 .

[0092] The data search algorithm is used to search for the advertising sales data of similar products in a specific region with the maximum sales value in the advertising sales data of similar products in a specific region, and mark and generate the best advertising sales data of similar products in a specific region; based on the best advertising sales data of similar products in a specific region and the advertising case data of similar products in a specific region, the advertising method corresponding to the best advertising sales of similar products in a specific region is searched according to the advertising case number of similar products in a specific region, and the operation steps of marking and generating the best advertising method data of similar products in a specific region are as follows:

[0093] S61, using the deep restricted search algorithm in step S42 to search for the specific region similar product advertising sales data with the largest sales value in the specific region similar product advertising sales data set E according to the sales value, and identify and generate the specific region similar product advertising best sales data e zuijia ;

[0094] S62, based on the best sales volume data of similar products in the specific region zuijia The specific region similar product advertising case data set C″ is combined with the depth restricted search algorithm zuijiaSearch for the advertising case number of similar products in a specific region zuijia The advertising method of the same product in the specific region in the corresponding advertising case data of the same product in the specific region is identified to generate the best advertising method data F of the same product in the specific region zuijia .

[0095] The steps for identifying the best advertising method data for similar products in a specific region to generate the best advertising method data for products and outputting it are as follows:

[0096] S71. The best advertising method data for similar products in specific regions zuijia Generate data to determine the best way to advertise a product And output through the display screen.

[0097] The product sales volume search and ranking unit of similar product advertising cases uses product advertising sales volume parameters to intuitively and accurately feedback the advertising effects of similar products in specific regions, thereby improving the scientific nature of the product advertising effect results; the product best sales volume and advertising method search unit of similar product advertising cases and the product advertising best method output unit cooperate with each other to intelligently screen out the advertising methods corresponding to the maximum sales volume of similar products in specific regions, thereby realizing early prediction of the optimal advertising methods for specific products in different regions, thereby improving the accuracy of product advertising effect analysis and corporate product sales.

[0098] A system for analyzing the advertising effects in different regions based on big data, the system includes a product advertising parameter collection module, a product advertising case search module, and a product advertising effect analysis module;

[0099] The product advertising parameter collection module includes an advertising product feature collection unit, an advertising investment personnel collection unit, an advertising investment fund collection unit, and an advertising product, personnel, and fund parameter processing unit;

[0100] The advertising product feature collection unit collects advertising product feature data through the data entry dialog box; the advertising investment personnel collection unit collects advertising investment personnel quantity data through the data entry dialog box; the advertising investment funds collection unit collects advertising investment funds quantity data through the data entry dialog box; the advertising product, personnel, and funds parameter processing unit combines and processes the advertising product feature data, the advertising investment personnel quantity data, and the advertising investment funds quantity data to generate advertising product, personnel, and funds feature data;

[0101] The product advertising case search module includes a storage unit for product advertising cases in different regions, a unit for identifying product advertising cases of the same type, a unit for collecting product advertising regional information, and a unit for retrieving product advertising cases in specific regions;

[0102] A storage unit for product advertising cases in different regions, used to store product advertising case data in different regions; a unit for identifying product advertising cases of similar products, using a data identification algorithm to perform keyword analysis on advertising product, personnel, and capital feature data and product advertising case data in different regions according to product features, number of personnel involved, and amount of capital involved, to identify advertising case data that matches the product features, number of personnel involved, and amount of capital involved in the advertisement, and to identify and generate advertising case data for similar products in different regions; a unit for collecting product advertising regional information, used to collect product advertising specific regional feature data through a data entry dialog box; a unit for retrieving product advertising cases in specific regions, using a data search algorithm to perform keyword search on product advertising specific regional feature data and advertising case data for similar products in different regions, to identify and generate advertising case data for similar products in specific regions;

[0103] The product advertising effect analysis module includes a unit for acquiring advertising cases of similar products, a unit for searching and ranking product sales volume of advertising cases of similar products, a unit for searching the best sales volume and advertising method of advertising cases of similar products, and a unit for outputting the best product advertising method;

[0104] The unit for acquiring advertising cases for similar products is used to acquire advertising case data for similar products in a specific region; the unit for searching and sorting product sales volume of advertising cases for similar products combines the advertising case data for similar products in a specific region with a data search algorithm to search out the product sales volume corresponding to each advertising case data for similar products and arranges them in ascending order according to the product sales volume values, thereby constructing the advertising sales volume data for similar products in a specific region; the unit for searching for the best sales volume and advertising method of products in advertising cases for similar products uses a data search algorithm to search out the advertising sales volume data for similar products in a specific region with the maximum sales volume value among the advertising sales volume data for similar products in a specific region and identifies and generates the best advertising sales volume data for similar products in a specific region; based on the best advertising sales volume data for similar products in a specific region and the advertising case data for similar products in a specific region, the unit searches out the advertising method used for the product corresponding to the best advertising sales volume of similar products in a specific region according to the advertising case number of similar products in a specific region and identifies and generates the best advertising method data for similar products in a specific region; the unit for outputting the best advertising method for products identifies the best advertising method data for similar products in a specific region, generates the best advertising method data for products, and outputs it through a display screen.

[0105] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for analyzing the advertising effects in different regions based on big data, characterized in that: The method comprises the following steps: S1. Collect data on the characteristics of advertising products, the number of people involved in advertising, and the amount of funds invested in advertising; S2, combining and processing the advertising product characteristic data, the advertising investment personnel number data, and the advertising investment capital amount data to generate advertising product, personnel, and capital characteristic data; S3, using a data recognition algorithm to perform keyword analysis on the advertising product, personnel, and capital feature data and the product advertising case data in different regions according to product features, number of personnel involved, and capital features, to identify advertising case data that matches the product features, number of personnel involved, and capital features of the advertisement, and to identify and generate advertising case data for similar products in different regions; S4. Collecting product advertising specific regional feature data, using a data search algorithm to search the product advertising specific regional feature data and the advertising case data of similar products in different regions according to specific regional feature keywords to find advertising case data of similar products in different regions in the same region and identify and generate advertising case data of similar products in specific regions; S5. Acquire the advertising case data of similar products in the specific region, search for the product sales volume corresponding to each advertising case data of similar products using a data search algorithm, and sort them in ascending order according to the product sales volume values ​​to construct advertising sales volume data of similar products in the specific region; S6. Use a data search algorithm to search for the advertising sales data of similar products in the specific region with the maximum sales value in the advertising sales data of similar products in the specific region, and mark and generate the best advertising sales data of similar products in the specific region; search for the advertising method used by the product with the best advertising sales volume of similar products in the specific region according to the advertising case number of similar products in the specific region based on the best advertising sales data of similar products in the specific region and the advertising case data of similar products in the specific region, and mark and generate the best advertising method data of similar products in the specific region; S7, identifying the best advertising method for similar products in the specific region, generating product advertising data to determine the best method and outputting it.

2. The method for analyzing the advertising effects in different regions based on big data according to claim 1 is characterized by: The steps for collecting the advertising product feature data, the number of advertising investment personnel data, and the advertising investment capital data are as follows: S11, using a data entry dialog box to collect product feature data for advertisements and generate product feature data A for advertisements, wherein the product feature data includes one or more of product name, model specification, function, and technical specification; Use the data entry dialog box to collect the interval of the number of staff invested in advertising and generate the interval data of the number of staff invested in advertising [m1, m2], where m1 represents the minimum number of staff invested in advertising; m2 represents the maximum number of staff invested in advertising; Use the data entry dialog box to collect the advertising investment amount range and generate advertising investment amount range data [n1, n2], where n1 represents the minimum advertising investment amount; n2 represents the maximum advertising investment amount, and the units of n1 and n2 are both ten thousand yuan.

3. The method for analyzing the advertising effects in different regions based on big data according to claim 2 is characterized by: The steps of combining and processing the advertising product characteristic data, the advertising investment personnel number data, and the advertising investment capital amount data to generate advertising product, personnel, and capital characteristic data are as follows: S21. Combine and process the advertising product characteristic data A, the advertising investment personnel number interval data [m1, m2], and the advertising investment capital amount interval data [n1, n2] to generate an advertising product, personnel, and capital characteristic data set B = (A, [m1, m2], [n1, n2]).

4. The method for analyzing the advertising effects in different regions based on big data according to claim 3 is characterized by: The data recognition algorithm is used to perform keyword analysis on the advertising product, personnel, and capital feature data and the advertising case data of products in different regions according to product features, number of personnel features, and capital features to identify advertising case data that matches the advertising product features, number of personnel features, and capital features, and to identify and generate advertising case data of similar products in different regions as follows: S31. Establish a product advertising case data set C = (c1, ..., c u , …, c ε ), u=1, 2, 3,...,ε; where c u represents the u-th product advertising case data in different regions, ε represents the maximum number of product advertising case data, the product advertising case data includes product feature data, the number of personnel involved in product advertising, the amount of funds invested in product advertising, the sales volume after product advertising, the regional characteristics of the promotion, and the product advertising method; the product advertising method includes one or more of offline outdoor advertising, media advertising, search advertising, social advertising, and short video advertising; S32, using a data recognition algorithm, the advertising product feature data A, the advertising investment personnel number interval data [m1, m2], and the advertising investment fund amount interval data [n1, n2] in the advertising product, personnel, and fund feature data set B are compared with the different regional product advertising case data c in the different regional product advertising case data set C. u According to the product characteristics, the number of personnel involved, and the amount of funds invested, keyword recognition is performed to analyze the advertising case data of products in different regions that match the advertised products. u The specific steps of the data recognition algorithm to identify matching advertising cases are as follows: S321, communication: Synchronously set the advertising product feature data A, the advertising investment personnel number interval data [m1, m2], and the advertising investment capital interval data [n1, n2] as water waves. Each water wave is an independent individual, so each water wave will have three attributes: position, wavelength α, and wave height β; In each iteration, each water wave will propagate to the different regions of the product advertising case data set C in the search space. u Search is performed, and the height β of the water wave will decrease by 1. The position update formula is as follows: in It represents the position of water wave i in the search space of product advertising case data set C in different regions after t iterations; represents the position of water wave i in the search space of product advertising case data set C in different regions before t iterations; χ and δ are the upper and lower bounds of the search space of product advertising case data set C in different regions, respectively; rand(-1,1) represents a random function with the value (-1,1); S322, refraction: after a water wave propagates, the water wave refracts and searches for different regions of product advertising case data set C in the space of different regions of product advertising case data set C. u For identification, each time the water wave propagates, the height β of the water wave will decrease by 1. When β decreases to 0, the water wave will be refracted, and its height and wavelength will change. The position after refraction is normally distributed at a position with the current water wave and the midpoint of the optimal water wave as the mean and the distance between the current water wave and the optimal water wave as the variance. After refraction, the height of the water wave will be reinitialized to the maximum height β = β max ; After refraction, recalculate the wavelength α of the water wave; S322, breaking waves: After the water wave propagates in the search space of the product advertising case data set C in different regions, it reaches a position that is better than the current optimal water wave, that is, it searches for the product advertising case data c in different regions that matches the advertising product feature data A, the interval data of the number of advertising investment personnel [m1, m2], and the interval data of the amount of advertising investment funds [n1, n2]. u , then the water wave will break and propagate the current optimal water wave to the location where the breaking waves are generated, that is, output the advertising case data c of different regional products that match the advertising product feature data A, the advertising investment personnel interval data [m1, m2], and the advertising investment capital interval data [n1, n2] u , the formula for generating the breaking wave position is as follows: Where rand(0, 1) represents a random function with the value (0, 1), r1 to k represent the spatial dimension numbers randomly selected for each wave break, d represents the specific spatial dimension actually randomly selected for each wave break, and d r1 to d k The specific spatial dimension parameter randomly selected for each breaking wave, σ is a constant; S324, outputting the product advertising case data c in different regions that match the advertising product feature data A, the advertising investment personnel number interval data [m1, m2], and the advertising investment capital interval data [n1, n2] u ; S33, all the product advertising case data of different regions outputted in step S324 c u Identify and generate advertising case data of similar products in different regions and establish a collection of advertising case data of similar products in different regions C′=(c′ u1 ,…,c′ u2 ), 1≤u1<u≤u2≤ε; where c′ u1 represents u1 advertising case data of similar products in different regions; c′ u2 It represents advertising case data of similar products in u2 different regions, where the similar products include at least one of the same product and similar products.

5. The method for analyzing the advertising effects in different regions based on big data according to claim 4 is characterized by: The steps of collecting the specific regional characteristic data of product advertisements, using a data search algorithm to search the specific regional characteristic data of product advertisements and the advertising case data of similar products in different regions according to specific regional characteristic keywords to obtain advertising case data of similar products in different regions in the same region and identify and generate advertising case data of similar products in specific regions are as follows: S41, using a data entry dialog box to collect specific regional feature data of the advertising location and generate specific regional feature data D of the product advertising, wherein the regional feature includes any one of a province, autonomous region, municipality directly under the central government, prefecture-level city, autonomous prefecture, county, autonomous county, municipal district, and county-level city; S42, using a depth-restricted search algorithm to compare the product advertising specific regional feature data D with the different regional similar product advertising case data c′ in the different regional similar product advertising case data set C′. u1 to c′ u2 According to the specific regional characteristic keywords, the advertising case data of similar products in different regions of the same region are searched and filtered out, and the advertising case data of similar products in different regions that are searched and filtered out are identified to generate advertising case data of similar products in specific regions and establish a collection of advertising case data of similar products in specific regions C″=(c″ u3 ,…,c″ u4 ), 1≤u3≤u≤u4≤ε; where c″ u3 Indicates advertising case data of similar products in u3 specific regions; c″ u4 Represents advertising case data of similar products in 4 specific regions.

6. The method for analyzing the advertising effects in different regions based on big data according to claim 5 is characterized by: The steps for obtaining the advertising case data of similar products in the specific region and searching for the product sales volume corresponding to each advertising case data of similar products in combination with the data search algorithm and arranging them in ascending order according to the product sales volume values ​​are as follows: S51, obtaining a data set C″ of advertisement cases of similar products in the specific region; S52, using the deep restricted search algorithm in step S42, orderly search for the product sales volume corresponding to each advertising case data of similar products in the specific region according to the advertising case numbers u3 to u4 of similar products, and arrange the product sales volume values ​​in ascending order, to construct a specific region similar product advertising sales volume data set E = (e u3 ,…,e u4 ), where e u3 Indicates the advertising case data of similar products in a specific region c″ u3 Advertising and sales data of similar products in corresponding specific regions; u4 Indicates the advertising case data of similar products in a specific region c″ u4 The corresponding specific region similar product advertising sales data, e u3 <e u4 .

7. The method for analyzing the advertising effects in different regions based on big data according to claim 6 is characterized by: The steps of using a data search algorithm to search for the specific region's similar product advertising sales data with the maximum sales value in the specific region's similar product advertising sales data and marking and generating the specific region's similar product advertising best sales data; searching for the advertising method used by the product corresponding to the specific region's similar product advertising best sales volume according to the specific region's similar product advertising case number and marking and generating the specific region's similar product advertising best sales data are as follows: S61, using the deep restricted search algorithm in step S42 to search for the specific region similar product advertising sales data with the largest sales value in the specific region similar product advertising sales data set E according to the sales value, and identify and generate the specific region similar product advertising best sales data e zuijia ; S62, based on the best sales volume data of similar products in the specific region zuijia The specific region similar product advertising case data set C″ is combined with the depth restricted search algorithm zuijia Search for the advertising case number of similar products in a specific region zuijia The advertising method of the same product in the specific region in the corresponding advertising case data of the same product in the specific region is identified to generate the best advertising method data F of the same product in the specific region zuijia .

8. The method for analyzing the advertising effects in different regions based on big data according to claim 7 is characterized by: The steps of generating and outputting the data of the best advertising method for similar products in the specific region and determining the best method for product advertising are as follows: S71. The best advertising method data for similar products in specific regions zuijia Generate data to determine the best way to advertise a product And output through the display screen.

9. A system for implementing the method for analyzing advertising effects in different regions based on big data as described in any one of claims 1 to 8, characterized in that: The system includes a product advertising parameter collection module, a product advertising case search module, and a product advertising effect analysis module.

Images