Driver recommendation method and server based on short video platform commodity data

Abstract

The invention discloses a short video platform commodity data-based arrival recommendation method and a server, and relates to the field of big data analysis, and the method comprises the steps: obtaining commodity-carrying arrival data of a target commodity on a preset ranking list, and extracting crowd portrait data and fan age distribution data of the commodity-carrying arrival data as an original data set; performing data filtering on the original data set to obtain commodity portrait data of the target commodity; performing feature dimension extraction on the to-be-detected portrait data of the to-be-matched person to obtain the person portrait data of the to-be-matched person; performing difference degree calculation on the arrival person portrait data and commodity portrait data of the target commodity to obtain a recommendation degree index of the to-be-matched arrival person for the target commodity; and sorting and screening the to-be-matched arriving persons based on the recommendation degree indexes, and displaying an arriving person recommendation list comprising a ranking sequence of the plurality of to-be-matched arriving persons. According to the invention, the method can achieve the precise matching of commodities, and avoids the unsatisfactory popularization effect to a greater extent.

Description

Technical Field

[0001] The present application relates to the field of big data analysis, and in particular to a method and server for recommending experts based on product data of a short video platform. Background Art

[0002] With the rapid development of short video platforms, live streaming has become an important sales channel for e-commerce. According to statistics, the scale of my country's live streaming e-commerce market will exceed 4.9 trillion yuan in 2023, of which short video platforms account for the majority. In this rapidly growing market, merchants and brands need to accurately find the right anchors for their products to achieve the best marketing effect and sales conversion.

[0003] At present, product promotion on short video platforms is mainly done through manual operation to match influencers. The operation team selects appropriate influencers for product promotion by observing the influencer's historical sales data, fan profile, content style and other dimensions, and combining experience and judgment. At the same time, some e-commerce platforms have developed basic influencer recommendation systems, which mainly perform simple matching based on surface data such as the influencer's number of fans and interaction rate.

[0004] However, with the rapid growth in the number of influencers, manual screening methods are unable to cope with the ever-expanding scale of information; and matching systems that rely solely on surface data find it difficult to deeply analyze the compatibility between influencers and products, which can easily lead to unsatisfactory promotion effects. Summary of the invention

[0005] The present application provides an expert recommendation method and server based on product data of a short video platform, which is used to accurately match experts with products and avoid unsatisfactory promotion effects to a greater extent.

[0006] In the first aspect, the present application provides an expert recommendation method based on short video platform product data, which is applied to a server, and the method includes: obtaining the data of influencers who sell the target product on a preset ranking list, and extracting the crowd portrait data and fan age distribution data of the influencer data as the original data set; filtering the original data set to obtain the product portrait data of the target product including the crowd distribution characteristics and the fan age distribution characteristics; extracting the feature dimensions of the portrait data to be matched, and obtaining the expert portrait data of the expert to be matched; calculating the difference between the expert portrait data and the product portrait data of the target product, and obtaining the recommendation index of the expert to be matched for the target product; sorting and screening the influencers to be matched based on the recommendation index, and displaying an expert recommendation list including a ranking sequence of multiple influencers to be matched.

[0007] In the above embodiment, the server obtains the data of the influencers who bring goods to the target goods and extracts the portrait features, and combines the difference calculation to perform the influencer recommendation sorting method, thereby achieving accurate matching between goods and influencers. Through multi-dimensional data analysis, it not only takes into account the user group characteristics of the influencer, but also combines the target audience attributes of the goods, so as to find the most suitable influencer for bringing goods, improve the conversion effect of bringing goods, and reduce the trial and error cost of merchants in selecting influencers.

[0008] In combination with some embodiments of the first aspect, in some embodiments, the step of filtering the original data set to obtain product portrait data of the target product including crowd distribution characteristics and fan age distribution characteristics specifically includes: respectively calculating the data averages of the crowd portrait data and the fan age distribution data in the original data set to obtain data benchmark values ​​in multiple dimensions; calculating the standard deviation of the data benchmark value, and determining the target value range in multiple dimensions based on the data benchmark value and the standard deviation; removing abnormal data in the original data set that does not belong to the target value range to obtain a standard data set; performing weight calculation on the data of each dimension in the standard data set to obtain product portrait data of the target product including crowd distribution characteristics and fan age distribution characteristics.

[0009] In the above embodiment, the server establishes more accurate product portrait data by filtering and calculating weights on the original data set, uses data baseline values ​​and standard deviations to identify abnormal data, obtains a standard data set by removing outliers, and then performs weight calculations to make the product portrait more realistic and reliable.

[0010] In combination with some embodiments of the first aspect, in some embodiments, the step of extracting feature dimensions of the portrait data to be tested of the expert to be matched to obtain the expert portrait data of the expert to be matched specifically includes: obtaining the portrait data to be tested of the expert to be matched, and determining multiple dominant dimension data in a preset pre-sequence among multiple dimensions of the portrait data to be tested; normalizing the multiple dominant dimension data and performing weight assignment to obtain a standard dimension array; calculating the dominant proportion of data on each dimension in the standard dimension array, and determining the expert portrait data of the expert to be matched based on the standard dimension array and the dominant proportion.

[0011] In the above embodiment, the server extracts the advantage dimensions from the portrait data to be tested and performs normalization processing through the feature dimension extraction method, thereby establishing a complete expert portrait system. Through normalization processing and weight allocation, the core advantage characteristics of the expert can be accurately identified.

[0012] In combination with some embodiments of the first aspect, in some embodiments, the step of calculating the difference between the expert portrait data and the product portrait data of the target product to obtain the recommendation index of the target product by the expert to be matched specifically includes: extracting the product matching data corresponding to the expert portrait data in the product portrait data, calculating the difference between the expert portrait data and the product matching data to obtain an initial difference array; determining the difference weight array according to the weight ratio of each data in the expert portrait data and the product matching data; performing weighted summation on the initial difference array according to the difference weight array to obtain reliability data; scaling the data density of the reliability data to generate a recommendation index.

[0013] In the above embodiment, the server compares the expert portrait and the product portrait in multiple dimensions through a difference calculation method to obtain an accurate recommendation index, and achieves a more scientific expert recommendation ranking through data weight, difference calculation and density scaling of reliability data.

[0014] In combination with some embodiments of the first aspect, in some embodiments, before obtaining the data of influencers who sell goods for the target product on a preset ranking list and extracting the population portrait data and fan age distribution data of the influencer data as the original data set, the method also includes: constructing a sliding time series including multiple preset time windows, and counting the sales data, sales data and user evaluation data of the target product in each preset time window; performing time series analysis on the sales data, sales data and user evaluation data, and identifying the life cycle stage and market performance trend of the target product through growth rate, volatility and seasonal characteristics; determining the optimal time period for selling goods and the characteristics of the target audience group based on the life cycle stage and market performance trend, combined with the product category characteristics and price range; determining the preset benchmark dimensions and dimension weights of the target product based on the optimal time period for selling goods and the characteristics of the target audience group.

[0015] In the above embodiment, the server analyzes product performance by constructing a sliding time series, identifies product life cycle and market trends, and provides an optimization strategy in the time dimension for expert recommendations. By analyzing sales volume, sales revenue and user evaluation data, the server determines the optimal time to bring products and the target audience, thereby improving the accuracy of recommendations.

[0016] In combination with some embodiments of the first aspect, in some embodiments, it is characterized in that after the step of sorting and screening the experts to be matched based on the recommendation index and displaying the expert recommendation list including the ranking sequence of multiple experts to be matched, the method also includes: obtaining the historical sales data of each matched expert in the expert recommendation list, and calculating the sales success rate of the matched experts in different commodity categories; generating a historical performance score for the matched expert based on the time decay model of the sales success rate and historical sales data; weightedly integrating the historical performance score with the recommendation index, re-sorting the experts in the expert recommendation list, and obtaining a recommended optimization list.

[0017] In the above embodiment, the server realizes dynamic optimization of recommendation results by analyzing the historical sales data and success rate of influencers and combining it with the time decay model. It improves the accuracy of recommendations by analyzing the historical performance of influencers in different product categories.

[0018] In combination with some embodiments of the first aspect, in some embodiments, based on the time decay model of the success rate of bringing goods and historical data of bringing goods, the step of generating a historical performance score of a matched influencer specifically includes: grouping the historical data of bringing goods into multiple dimensions according to product categories, price ranges and time dimensions, and calculating the success rate of bringing goods and sales conversion rate of each grouping dimension combination in different time periods; based on the time decay model, assigning dynamically decreasing weight coefficients to the success rate of bringing goods and sales conversion rate in different time periods to obtain a bringing goods decay curve; determining the bringing goods experience coefficient according to the frequency distribution of bringing goods and sales performance of the matched influencer in each product category and price range; determining the historical performance score of the matched influencer according to the bringing goods decay curve and the bringing goods experience coefficient, combined with the recent activity and fan interaction indicators of the matched influencer.

[0019] In the above embodiment, the server conducts a comprehensive evaluation of the influencer's historical performance through multi-dimensional grouping and time decay model, and establishes a complete historical performance scoring system based on factors such as the frequency of bringing goods, sales performance, and recent activity, thereby improving the reliability of the recommendation results.

[0020] In a second aspect, an embodiment of the present application provides a server, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the server to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when executed on a server, enables the server to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions, which, when executed on a server, enable the server to execute the method described in the first aspect and any possible implementation of the first aspect.

[0023] It is understandable that the server provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Since a secondary integration method based on product dimension data is adopted to obtain the data of influencers who bring goods, and data filtering and feature extraction are performed through population portraits and fans' age distribution characteristics, a complete product influencer matching system can be established, which effectively solves the problem of low matching degree caused by relying solely on simple data indicators for influencer screening in existing technologies, thereby achieving more accurate influencer recommendations and improving the matching effect between products and influencers.

[0025] 2. Since a difference calculation method based on difference calculation and weight allocation is adopted, and the reliability data is calculated by combining the initial difference array and the difference weight array, it is possible to accurately measure the degree of adaptation between the influencer and the product, and effectively solve the problem that the existing technology cannot quantitatively evaluate the matching degree between the influencer and the product, thereby realizing a more scientific calculation of the recommendation index, making the influencer recommendation results more objective and reliable, and improving the accuracy and practical value of the recommendation.

[0026] 3. Due to the use of a scoring method based on historical sales data analysis and a time decay model, combined with a weighted fusion of sales success rate and historical performance, it is possible to dynamically optimize expert recommendation results, effectively solving the problem in existing technologies that recommendation results are static and cannot reflect the real-time performance of experts, thereby achieving more flexible and accurate expert recommendations and improving the practicality and reliability of recommendation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a flow chart of a method for recommending experts based on commodity data on a short video platform in an embodiment of the present application; Figure 2This is another flowchart of the expert recommendation method based on short video platform product data in an embodiment of the present application; Figure 3 It is a schematic diagram of a physical device structure of a server in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0030] For ease of understanding, here are some technical terms. Experts refer to creators who have a certain influence and fan base on short video platforms and can effectively guide fans to purchase goods through their own content creation and promotion capabilities. They demonstrate professional knowledge or unique charm in different fields, such as fashion, beauty, digital, and food, and play a key role in the e-commerce sales process by displaying, introducing, and recommending products.

[0031] The eight major groups refer to eight user groups with typical characteristics divided by short video platforms based on multi-dimensional data such as users' social attributes, consumption behaviors, and interest preferences. They are small town youth, urban blue-collar workers, small town middle-aged and elderly people, genz, urban silver-haired people, senior middle-class people, sophisticated mothers, and new white-collar workers. For example, small town youth usually live in urban areas, and their consumption concepts are relatively cost-effective. They have a high interest in fashion trends and entertainment and leisure products; urban blue-collar workers are mainly concentrated in cities to engage in physical or technical labor, and their consumption pays more attention to practicality and quality, and they have a greater demand for daily necessities, tools and equipment. These population classifications help to accurately analyze the target audience and provide a key basis for matching products with influencers.

[0032] For ease of understanding, the application scenarios of the embodiments of the present application are introduced below.

[0033] A clothing brand launched a new down jacket on an e-commerce platform and needed to quickly find suitable influencers to promote it. The operation team found that although some influencers had successfully brought products, they encountered difficulties in screening new influencers. For example, a fashion blogger with 2 million fans, although the fan portrait showed that they were mainly urban white-collar women aged 25-35, seemed very suitable, but the actual sales effect was not ideal. The team found that the method of selecting influencers based solely on the influencer's fan portrait and number of fans had a large deviation and could not accurately predict the sales effect. They needed a method that could scientifically analyze the matching degree between products and influencers based on existing successful cases.

[0034] In the related art, a simple matching method based on the influencer's fan base, interaction rate, and historical sales data can be used to achieve preliminary screening of products and influencers. The following describes a scenario in which an influencer recommendation method based on short video platform product data in the related art is used.

[0035] An e-commerce operation team uses the traditional method of selecting influencers, mainly relying on simple data and personal experience provided by influencer agencies. When they are looking for a suitable influencer for a skin care product, they first screen out influencers whose fans are aged 25-35 and more than 80% are women, and then make manual judgments based on the influencer's recent sales data. However, this method has obvious problems: the judgment criteria of different operators are inconsistent, and sometimes the selected influencers meet the requirements in all indicators, but the actual sales effect is unsatisfactory. For example, they found an influencer in the beauty field whose fan portrait fully meets the requirements, but the sales conversion rate is far lower than expected, resulting in a waste of marketing resources.

[0036] The expert recommendation method based on the commodity data of the short video platform in the embodiment of the present application is adopted, through the secondary integration of high-quality expert data and outlier filtering, a more accurate commodity expert matching is achieved, which not only improves the success rate of bringing goods, but also reduces operating costs. The following introduces the scenario of using the expert recommendation method based on the commodity data of the short video platform in the present application.

[0037] A beauty brand uses this solution to match influencers for its toner. First, the system collected data on the top ten influencers in terms of sales of the product, and analyzed through algorithms that the core audience of the product is sophisticated mothers and new white-collar workers aged 24-35. The system automatically filters out outliers. For example, although a certain influencer has a large volume of sales, his user portrait is seriously deviated from the mainstream. Then, the system matches this standardized product portrait with the influencers to be selected in multiple dimensions, considering factors such as population distribution and age characteristics, and finally recommends a list of influencers with the highest matching degree. After actual cooperation, the conversion rate of these influencers is generally more than 30% higher than that of influencers selected by traditional methods.

[0038] It can be seen that the expert recommendation method based on short video platform product data in the embodiment of the present application can not only achieve accurate expert matching, but also effectively solve the instability problem caused by subjective judgment in traditional methods, thereby achieving an improvement in the sales effect.

[0039] For ease of understanding, the following describes the process of the method provided by this implementation in combination with the above scenario. Figure 1 , which is a flow chart of the expert recommendation method based on short video platform product data in an embodiment of the present application.

[0040] S101. Obtain the data of influencers who sell the target product on a preset ranking list, and extract the population portrait data and fans age distribution data of the influencers as the original data set.

[0041] Among them, the target product refers to the specific product that needs to be matched with an influencer; the preset ranking list refers to a data list that sorts the influencers according to indicators such as sales volume and sales revenue; the influencer data refers to the relevant data of the influencer who successfully sells the product; the population portrait data refers to the multi-dimensional data that reflects the characteristics of the influencer's fan group, including the proportion data of eight major population types such as small town youth, urban blue-collar workers, and sophisticated mothers; the fan age distribution data represents the age composition of the influencer's fans, including the proportion data of multiple fan age ranges such as 18-23 years old and 24-30 years old; the original data set is used to represent the unprocessed initial data sample set.

[0042] After receiving the expert matching request, the server needs to first obtain the historical sales data of the target product as a basis. Specifically, the server first accesses the product sales database to obtain the data of the top ten experts in terms of sales of the target product; extracts the fan portrait information of these experts from the expert database, namely the proportion of the eight major groups and the age distribution of fans; and integrates this data into an original data set containing multiple dimensional features.

[0043] In some embodiments, the acquisition and organization of initial data can be achieved in a variety of ways: Optionally, the top 10 influencers are screened based on the sales data of the same type of goods in the past 30 days; the real-time fan portrait data of these influencers is extracted; the data is organized and stored in a unified format; and a timestamp is added to facilitate subsequent analysis. Optionally, multiple time windows are set to separately count the influencer sales data; a comprehensive score is obtained based on indicators such as the influencer interaction rate; the data of the 10 influencers with the highest comprehensive scores are selected; and their portrait data is extracted to form a sample set. It is understandable that other methods can also be used to acquire and organize initial data, such as through different ranking rules or data collection methods, which are not limited here.

[0044] For example, the server obtains the data of the top 10 sales figures: 1. In the eight population dimensions: 2. In terms of fans’ age: S102: Filter the original data set to obtain product portrait data of the target product including population distribution characteristics and fan age distribution characteristics.

[0045] Among them, the data baseline value refers to the average level of data in each dimension; the standard deviation is used to indicate the degree of discreteness of the data; the target value range indicates the valid range of the data; abnormal data refers to data points that deviate significantly from the normal distribution; and the standard data set refers to the set of valid data after screening.

[0046] After obtaining the original data set, the server needs to ensure data quality and reliability through data filtering. Specifically, the server first calculates the mean and standard deviation of each dimension data to determine a reasonable data range; then removes outliers that are out of range, such as data where the fan portrait deviates seriously from the mainstream; then standardizes the retained data; and finally calculates the final proportion of each dimension through weight calculation to form standardized product portrait data.

[0047] Continuing with the above example: 1. In the eight population dimensions, the processing is as follows: a. Calculate the average: b. Calculate the standard deviation: Data b 0.05 0.05 0.04 0.08 0.05 0.05 0.07 0.03 c. Calculate the filter interval: Upper range 0.29 0.23 0.16 0.19 0.11 0.13 0.21 0.11 Lower range 0.19 0.13 0.07 0.03 0.02 0.03 0.06 0.052. The data calculation method for the fan age dimension is the same as the above eight population dimensions, so it will not be repeated here.

[0048] It should be noted that in the process of data filtering, the standard deviation of the data baseline is calculated to measure the degree of discreteness of the data in each dimension. Taking the eight population dimension data as an example, assuming that the proportion of small town youth in the original data set is [0.21, 0.23, 0.25, 0.28, 0.19, 0.26, 0.24, 0.22, 0.27, 0.20], first calculate its average value as 0.235. Then calculate the square of the difference between each data and the average value, such as (0.21-0.235)2, (0.23-0.235)2, etc., sum these square differences and divide them by the number of data, and then square them to get the standard deviation. If the standard deviation is 0.03, combined with the average value of 0.235, the target value range can be determined to be [0.205, 0.265]. In this way, abnormal data that obviously deviates from the normal distribution, such as 0.15 or 0.30, can be effectively identified and removed, ensuring the reliability of the data and laying the foundation for the subsequent construction of accurate product portraits.

[0049] S103, extracting feature dimensions from the portrait data of the expert to be matched, and obtaining the expert portrait data of the expert to be matched.

[0050] Among them, the experts to be matched represent potential cooperative experts whose matching degree needs to be evaluated; the portrait data to be tested refers to the original data features of the experts to be matched; the feature dimension extraction is to determine their advantageous dimension data, which represents the most distinctive data dimensions of the experts.

[0051] After obtaining the product portrait, the server needs to standardize the candidate expert data for matching. Specifically, the server first obtains the original portrait data of the expert to be matched; then identifies the most representative first three dimensional features; then normalizes and weights these feature data; and finally generates standardized expert portrait data.

[0052] In some embodiments, feature extraction of expert portraits can be achieved in a variety of ways: Optionally, select the top three features in each dimension; calculate the relative proportion of these features; apply 4:3:3 weights for distribution; generate a final weight array. Optionally, calculate the contribution of each dimension to the expert features; select the three dimensions with the highest contribution; perform normalization; calculate relative weights. It is understandable that other methods can also be used to achieve the extraction and standardization of expert features, such as through different feature selection algorithms, which are not limited here.

[0053] Continuing with the above example, the profile data to be tested for a certain expert is: Eight major groups: Age of fans: 18-23 24-30 31-40 41-50 51+ 5.88% 25.88% 55.09% 8.98% 4.16% For the eight major groups, the processing steps are as follows: 1. In the eight demographics, the top three are: small town youth 24.95%, urban blue-collar workers 19.44%, and sophisticated mothers 13.4%; 2. Redistribution of proportions: Small town youth: 24.95% / (24.95%+19.44%+13.44%)=0.4314; Urban blue-collar workers: 19.44% / (24.95%+19.44%+13.44%)=0.3361; Exquisite mother: 13.44% / (24.95%+19.44%+13.44%)=0.2324.

[0054] 3. Weight distribution in proportion: Small town youth: 0.4314*0.4=0.1726; Urban blue-collar workers: 0.3361*0.3=0.1008; Exquisite mother: 0.2324*0.3=0.0697.

[0055] 4. Normalize the data to ensure that the sum of the proportions is 1: Small town youth: 0.1726 / (0.1726+0.1008+0.0697)=0.5031; Urban blue-collar workers: 0.1008 / (0.1726+0.1008+0.0697)=0.2938; Exquisite mother: 0.0697 / (0.1726+0.1008+0.0697)=0.2032.

[0056] The calculation method for the fan age dimension is the same as the above eight population dimensions, and the data obtained are: Fans’ age 31-40: 0.6783; fans’ age 24-30: 0.2314; fans’ age 41-50: 0.0827. The calculation process will not be elaborated here.

[0057] S104: Calculate the difference between the expert portrait data and the product portrait data of the target product to obtain the recommendation index of the expert to be matched for the target product.

[0058] Among them, the difference calculation represents the process of measuring the difference between two portrait data; the recommendation index represents the final matching score.

[0059] After the server completes the standardization of the influencer portrait and product portrait, it needs to calculate the matching degree between the two. Specifically, the server first extracts the data of the same dimension for comparison; then calculates the difference of each dimension; then weights the dimension according to its importance; and finally converts the result into an intuitive recommendation index through a mathematical model.

[0060] Continuing with the above example, the processing process is: 1. Calculate the difference of the corresponding dimensions: Eight population dimensions: Small town youth: 0.2795-0.5031=-0.2236; Urban blue-collar workers: 0.0645-0.2938=-0.2293; Exquisite Mom: 0.0043-0.2032=-0.1987.

[0061] Fans age dimension: Fan age 31-40: 0.4223-0.6783=-0.2560; Fan age 24-39: 0.1956-0.2314=-0.0358; Fans age 41-50: 0.2124-0.0827=0.1297.

[0062] 2. Calculation of the difference ratio (the difference divided by the data value in the expert portrait data): Eight population dimensions: Small town youth: -0.2236 / 0.5031=-0.4444; Urban blue-collar workers: -0.2293 / 0.2938=-0.7805; Exquisite Mom: -0.1987 / 0.2032=-0.9779.

[0063] Fan age dimension: The calculation process is omitted, and the results are -0.3774, -0.1547, and 1.568.

[0064] 3. Use the weight proportions after normalization of the data in the previous step to sum up: Eight major groups = -0.4444*0.5031+-0.7805*0.2938+-0.9779*0.2032=-0.6516; Fan age = -0.3774*0.6873+-0.1547*0.2314+1.568*0.0827=-0.1655.

[0065] 4. Calculate the recommendation level: Recommendation level = (((-0.6516+1) / 2)^0.5)+0.2*(((-0.1655+1) / 2)^0.5)=0.5465=54.65%.

[0066] S105 , sorting and screening the experts to be matched based on the recommendation index, and displaying an expert recommendation list including a ranking sequence of multiple experts to be matched.

[0067] Among them, sorting and filtering means sorting the experts according to the degree of recommendation; ranking sequence refers to the list of experts arranged in descending order of recommendation; and the expert recommendation list represents the recommendation results finally presented to the user.

[0068] After calculating the recommendation scores of all the talents to be matched, the server needs to generate a recommendation list that facilitates decision-making. Specifically, the server first sorts all talents in descending order of recommendation scores; then it may set a recommendation score threshold for screening; and finally generates a sorted list containing the basic information of the talents and their recommendation scores.

[0069] In some embodiments, the generation of the recommendation list can be achieved in a variety of ways: optionally, setting a minimum recommendation threshold; screening qualified experts; sorting by recommendation; adding basic information of experts; generating a recommendation list. Optionally, dividing by recommendation; selecting a fixed number of experts in each grade; adjusting the order by comprehensively considering other indicators; generating a multi-level recommendation list. It is understandable that other methods can also be used to generate the recommendation list, such as through different sorting rules or display methods, which are not limited here.

[0070] For example, a sample recommendation list is: Expert A: 90.5% recommendation rate, 2 million fans, and sales of 500,000 in the past 30 days; Expert B: 85.3% recommendation rate, 1.5 million fans, and sales of 450,000 in the past 30 days; … In the above embodiment, by systematically analyzing and processing the data of the top ten influencers in terms of product sales, a quantifiable product portrait standard is established. In practical applications, this method can quickly screen out the most suitable potential influencers for the product, greatly improving the efficiency of influencer screening. The following is a supplement to the scenario of this embodiment.

[0071] A comprehensive e-commerce platform has further upgraded this solution by adding product life cycle and seasonal analysis. For example, for a sunscreen, the system not only analyzes the matching degree of influencers, but also combines the data characteristics of the product sales peak season (summer) and off-season (winter) to recommend different types of influencers for different periods. In summer, the system will give priority to outdoor sports and travel influencers; while in winter, it tends to recommend beauty and skin care influencers, and adjust the weight of the matching algorithm accordingly. This dynamic optimization makes the product's sales effect more stable throughout the year, increasing sales by more than 40% on average.

[0072] After combining the above scenarios, the following is a more detailed description of the process of the method provided by this implementation. Figure 2 , which is another flow chart of the expert recommendation method based on short video platform product data in an embodiment of the present application.

[0073] S201. Obtain the data of influencers who sell the target product on a preset ranking list, and extract the population portrait data and fans age distribution data of the influencers as the original data set.

[0074] Referring to step S101, the server collects the original data set. For example, the server obtains the data of the top 10 sales figures, 1. In the eight population dimensions: 2. In terms of fans’ age: In some embodiments, the server first constructs a sliding time series including multiple preset time windows, and counts the sales volume data, sales revenue data, and user evaluation data of the target product in each preset time window; performs time series analysis on the sales volume data, sales revenue data, and user evaluation data, and identifies the life cycle stage and market performance trend of the target product through growth rate, volatility, and seasonal characteristics; determines the optimal time interval for bringing goods to the target product and the characteristics of the target audience group based on the life cycle stage and market performance trends, combined with the product category characteristics and price range; determines the preset benchmark dimensions and dimension weights of the target product based on the optimal time interval for bringing goods to the target product and the characteristics of the target audience group.

[0075] Among them, the preset time window represents a time analysis unit of fixed length; the sliding time series refers to a continuously moving time analysis interval; the growth rate represents the speed of change of the data; volatility refers to the amplitude of change of the data; seasonal characteristics are used to represent the law of periodic changes; the life cycle stage represents the development stage of the product in the market; the market performance trend refers to the development direction of product sales; the optimal time interval for bringing goods is used to represent the time period most suitable for promotion; the characteristics of the target audience group represent the attributes of the potential purchasing group; the preset benchmark dimension refers to the standard feature dimension for evaluating products.

[0076] After obtaining the target product, the server needs to conduct a comprehensive data analysis to determine the optimal promotion strategy. Specifically, the server first establishes multiple fixed-length time windows, which slide in sequence at preset intervals; then collects and organizes sales volume, sales revenue, and user evaluation data in each window; then identifies the current market stage and development trend of the product by analyzing the growth rate, fluctuation range, and periodic changes of these data; then determines the best promotion time and target user group based on the product's category characteristics and price positioning; finally, based on these analysis results, sets the key dimensions for evaluating the product and assigns corresponding weights.

[0077] S202. Calculate the average values ​​of the crowd portrait data and the fan age distribution data in the original data set respectively to obtain data benchmark values ​​in multiple dimensions.

[0078] Among them, the data average value represents the arithmetic average result of the data in each dimension; the data benchmark value refers to the standard reference value used for subsequent analysis;.

[0079] After obtaining the original data set, the server needs to establish a benchmark standard for data analysis. Specifically, the server first classifies the original data set into eight major groups and age ranges; then sums the data of each dimension; then divides the sum by the number of samples to get the average value; finally, these average values ​​are used as the data benchmark values ​​of each dimension for subsequent data processing.

[0080] Continuing with the above example: 1. In the eight population dimensions, the processing is as follows: Calculate the average (data base value): 2. The data calculation method for the fan age dimension is the same as the above eight population dimensions and will not be repeated here.

[0081] S203: Calculate the standard deviation of the data reference value, and determine the target value range in multiple dimensions according to the data reference value and the standard deviation.

[0082] Among them, the standard deviation represents the statistic of the degree of data dispersion; the target value interval refers to the range limit of valid data, including the upper safety interval and the lower safety interval; the upper safety interval represents the result of adding the standard deviation to the data baseline value; the lower safety interval represents the result of subtracting the standard deviation from the data baseline value.

[0083] After obtaining the data benchmark value, the server needs to determine the reasonable distribution range of the data. Specifically, the server first calculates the sum of squares of the deviations between the data of each dimension and the benchmark value; then finds the average of the sum of squares of the deviations; then takes the square root to get the standard deviation; finally, adds and subtracts the standard deviation from the benchmark value to determine the target value range of each dimension.

[0084] Continuing with the above example: 1. In the eight population dimensions, the processing is as follows: a. Calculate the standard deviation: b. Calculate the filter interval based on the data baseline value and standard deviation: 2. The data calculation method for the fan age dimension is the same as the above eight population dimensions and will not be repeated here.

[0085] S204: Remove abnormal data that does not belong to the target value range in the original data set to obtain a standard data set.

[0086] Among them, abnormal data refers to data points that exceed the target value range; the standard data set refers to the screened valid data set.

[0087] After determining the target value range, the server needs to clean the original data. Specifically, the server first checks whether the data of each dimension is within the target range; then marks the outliers that exceed the range; then removes these outliers from the data set; and finally obtains the cleaned standard data set.

[0088] In some embodiments, abnormal data cleaning can be achieved in a variety of ways: optionally, traverse and check each dimension of data; mark data that exceeds the interval; delete abnormal data in batches; record the amount of data after cleaning; save the standard data set. Optionally, calculate the Z score of each data point; set the Z score threshold; remove data that exceeds the threshold; verify the data distribution characteristics; generate the final data set. It is understandable that other methods can also be used to clean abnormal data, such as through different anomaly detection algorithms, which are not limited here.

[0089] S205. Calculate the weight of the data of each dimension in the standard data set to obtain product portrait data of the target product including population distribution characteristics and fan age distribution characteristics.

[0090] Among them, weight calculation represents the process of determining the importance of data in each dimension; population distribution characteristics refer to the proportion distribution of the eight major populations; fan age distribution characteristics represent the proportion distribution of age groups; product portrait data is used to represent the standardized feature description of the product.

[0091] After obtaining the standard data set, the server needs to construct a standardized image of the product. Specifically, the server first calculates the new mean of each dimension data; then performs data normalization; then redistributes the weight of each dimension according to the 100% sum; and finally generates a complete product image that includes the population distribution and the fan age distribution.

[0092] Continuing with the above example: 1. In the eight population dimensions, the processing is as follows: After screening, the data benchmark value is calculated again based on the standard data set, and the re-ratio of the data benchmark value (the weight ratio of each data) is determined as follows: 2. The data calculation method for the fan age dimension is the same as the above eight population dimensions and will not be repeated here.

[0093] The above-mentioned collection of proportions is the product portrait data, which represents the standardized distribution of products.

[0094] S206: Obtain the portrait data to be tested of the expert to be matched, and determine a plurality of dominant dimension data in a preset preceding sequence among the multiple dimensions of the portrait data to be tested.

[0095] Among them, the portrait data to be tested represents the original feature data of the candidate talent; the dominant dimension data refers to the main feature dimensions with higher values; and the preset leading sequence represents the first few digits after being sorted by numerical value.

[0096] After building the product portrait, the server needs to analyze the characteristics of the talent to be matched. Specifically, the server first obtains the complete portrait data of the talent to be matched; then sorts all dimension data in descending order; then selects the top three dimensions as the dominant dimensions; and finally records the specific values ​​and ranking positions of these dominant dimensions.

[0097] Continuing with the above example, the profile data to be tested for a certain expert is: 1. Eight population dimensions: 2. Fans age dimension: 18-23 24-30 31-40 41-50 51+ 5.88% 25.88% 55.09% 8.98% 4.16% The data of advantage dimensions are the top three data. Among the eight population dimensions, the top three are: small town youth 24.95%, urban blue-collar workers 19.44%, and sophisticated mothers 13.40%.

[0098] S207, normalizing the plurality of dominant dimension data and performing weight assignment to obtain a standard dimension array.

[0099] Among them, normalization refers to the process of converting data to a uniform scale; weight allocation refers to assigning importance coefficients to different dimensions; and the standard dimension array is used to represent the processed standardized data set.

[0100] After determining the dominant dimension, the server needs to perform standardization. Specifically, the server first converts the dominant dimension data into a standard value in the [0, 1] interval; then allocates weights in a 4:3:3 ratio; then multiplies the standard value by the weight; and finally obtains a standardized dimension array.

[0101] Continuing with the above example, for the eight population dimensions: 1. Redistribution of proportions (normalization): Small town youth: 24.95% / (24.95%+19.44%+13.44%)=0.4314; Urban blue-collar workers: 19.44% / (24.95%+19.44%+13.44%)=0.3361; Exquisite mother: 13.44% / (24.95%+19.44%+13.44%)=0.2324.

[0102] 2. Weight distribution in proportion: Small town youth: 0.4314*0.4=0.1726; Urban blue-collar workers: 0.3361*0.3=0.1008; Exquisite mother: 0.2324*0.3=0.0697.

[0103] The standard dimension array for the eight major groups is [0.1726, 0.1008, 0.0697]; a similar calculation is performed on the age of fans, and the result is [0.2450, 0.0863, 0.0299].

[0104] S208, calculating the advantage ratio of the data on each dimension in the standard dimension array, and determining the expert portrait data of the expert to be matched based on the standard dimension array and the advantage ratio.

[0105] Among them, the advantage ratio indicates the weight ratio of each dimension in the whole; the expert portrait data refers to the standardized feature description of the expert.

[0106] After obtaining the standard dimension array, the server needs to construct a standard portrait of the expert. Specifically, the server first calculates the proportion of each dimension data in the total; then uses the proportion as the feature weight of the dimension; then combines the standard dimension array to generate a complete feature description; and finally forms the standardized portrait data of the expert.

[0107] Continuing with the above example, for the eight population dimensions, in order to ensure that the sum of the proportions is 1, the advantage proportions are calculated as follows: Small town youth: 0.1726 / (0.1726+0.1008+0.0697)=0.5031; Urban blue-collar workers: 0.1008 / (0.1726+0.1008+0.0697)=0.2938; Exquisite mother: 0.0697 / (0.1726+0.1008+0.0697)=0.2032; That is, the weight proportions of the eight major groups are [0.5031, 0.2938, 0.2032]; the weight proportions and the standard dimension array [0.1726, 0.1008, 0.0697] together constitute the portrait of the expert in the eight major group dimensions.

[0108] Similarly, in the fan age dimension, the standard dimension array is [0.2450, 0.0863, 0.0299], and the weight ratio is [0.6783, 0.2314, 0.0827].

[0109] S209, extracting the product matching data corresponding to the expert portrait data from the product portrait data, performing difference calculation between the expert portrait data and the product matching data, and obtaining an initial difference array.

[0110] Among them, the product matching data represents the product data of the dimension corresponding to the expert portrait; the initial difference array is used to represent the unweighted original difference value.

[0111] After obtaining the expert portrait data, the server needs to calculate the matching degree with the product portrait. Specifically, the server first extracts data with the same dimensions as the expert portrait from the product portrait; then matches the two sets of data one by one; then calculates the difference in each dimension; and finally forms an initial difference array containing all dimensional differences.

[0112] Continuing with the above example, calculate the difference of the corresponding dimensions: a. Eight major population dimensions: Small town youth: 0.2795-0.5031=-0.2236; Urban blue-collar workers: 0.0645-0.2938=-0.2293; Exquisite Mom: 0.0043-0.2032=-0.1987.

[0113] The initial difference array of the eight population dimensions is [-0.2236, -0.2293, -0.1987].

[0114] b. Fans age dimension: Fan age 31-40: 0.4223-0.6783=-0.2560; Fan age 24-39: 0.1956-0.2314=-0.0358; Fans age 41-50: 0.2124-0.0827=0.1297.

[0115] The initial difference value array of the fan age dimension d1 is [-0.2560, -0.0358, 0.1297].

[0116] S210. Determine a difference weight array according to the weight ratios of the respective data in the expert portrait data and the product matching data.

[0117] Among them, the weight ratio indicates the importance of each dimension in the overall feature; the difference weight array refers to the weight coefficient used to adjust the importance of the difference.

[0118] After obtaining the initial difference, the server needs to consider the importance of each dimension. Specifically, the server first obtains the dimension weights of the influencer and product portraits, then calculates the comprehensive weight of each dimension, then normalizes the weights, and finally generates a weight array for difference calculation.

[0119] Continuing with the above example, the difference ratio calculation (difference divided by the data value in the expert portrait data) is: Eight population dimensions: Small town youth: -0.2236 / 0.5031=-0.4444; Urban blue-collar workers: -0.2293 / 0.2938=-0.7805; Exquisite Mom: -0.1987 / 0.2032=-0.9779. Array [-0.4444, -0.7805, -0.9779].

[0120] Fan age dimension: The calculation process is omitted and the result is [-0.3774, -0.1547, 1.568].

[0121] S211. Perform weighted summation on the initial difference array according to the difference weight array to obtain reliability data.

[0122] Among them, weighted summation means the accumulation of weighted differences; reliability data refers to the final matching degree score; matching degree score is used to represent the numerical value of the overall matching degree.

[0123] After obtaining the difference weights, the server needs to calculate the final matching degree. Specifically, the server first multiplies the difference by the corresponding weight; then sums all weighted differences; then performs normalization processing; and finally obtains reliability data reflecting the matching degree.

[0124] Continuing with the above example, we use the weighted proportions of the normalized data in the previous step to sum up: The reliability data of the eight population dimensions are as follows: -0.4444*0.5031+-0.7805*0.2938+-0.9779*0.2032=-0.6516; The fan age dimension is: -0.3774*0.6873+-0.1547*0.2314+1.568*0.0827=-0.1655.

[0125] S212: Scaling the data density of the reliability data to generate a recommendation index.

[0126] Among them, data density represents the distribution characteristics of reliability data; scaling refers to the process of converting data into intervals; the recommendation index is used to represent the final matching score; numerical mapping represents the process of converting data to a new interval; and score standardization refers to the process of unifying the score scale.

[0127] After obtaining the reliability data, the server needs to convert it into a more intuitive recommendation index. Specifically, the server first performs a normal distribution test on the reliability data, then designs a suitable conversion function, then maps the data to the range of 0-100%, and finally generates a standardized recommendation index.

[0128] Continuing with the above example, the recommendation index of this expert is: (((-0.6516+1) / 2)^0.5)+0.2*(((-0.1655+1) / 2)^0.5)=0.5465=54.65%.

[0129] S213, sorting and screening the experts to be matched based on the recommendation index, and displaying an expert recommendation list including a ranking sequence of multiple experts to be matched.

[0130] Referring to step S105, the server generates an expert recommendation list.

[0131] For example, a sample recommendation list is: Expert A: 90.5% recommendation rate, 2 million fans, and sales of 500,000 in the past 30 days; Expert B: 85.3% recommendation rate, 1.5 million fans, and sales of 450,000 in the past 30 days; … S214. Obtain the historical sales data of each matched expert in the expert recommendation list, and calculate the sales success rate of the matched experts in different product categories.

[0132] Among them, historical sales data represents the influencer’s past sales records; sales success rate refers to the completion ratio of product sales; product categories represent the classification of different types of products; sales performance is used to represent the influencer’s historical performance; and the data statistical period refers to the time range for collecting historical data.

[0133] After generating the preliminary recommendation list, the server needs to evaluate the influencer's historical performance. Specifically, the server first obtains the influencer's recent sales records; then classifies and counts them by product category; then calculates the success rate of each category; and finally generates a performance report for the influencer in each category.

[0134] In some embodiments, the calculation of the success rate of bringing goods can be achieved in a variety of ways: optionally, collecting sales data; classifying and counting categories; calculating completion rate; weighted processing; generating a success rate report. Optionally, setting a statistical cycle; extracting valid data; classifying and summarizing; calculating conversion rate; outputting evaluation results. It is understandable that other methods can also be used to calculate the success rate of bringing goods, such as through different statistical methods or evaluation criteria, which are not limited here.

[0135] S215. Generate a historical performance score for the matched influencer based on the sales success rate and the time decay model of historical sales data.

[0136] Among them, the time decay model refers to a calculation model that takes into account the influence of time factors; the historical performance score refers to the final score of comprehensive historical data; the time weight represents the importance of data in different periods; and the decay coefficient is used to indicate the degree of influence of time on data.

[0137] After obtaining the success rate of bringing goods, the server needs to consider the influence of time factors. Specifically, the server first sets the time decay function; then applies the decay coefficient to the data of different periods; then calculates the weighted average score; and finally generates a comprehensive score that reflects historical performance.

[0138] It should be noted that the time decay model in this application uses historical sales data as a training set during training, including time series data such as product sales, sales, and conversion rates, and optimizes the decay parameters by minimizing the prediction error. The training standard is to minimize the mean square error between the sales performance predicted by the model and the actual performance, while considering the importance differences of data in different time periods. The core of the time decay model is an exponential decay function, which contains two key parameters: the basic decay rate and the time interval. The model structure includes a time weight calculation layer, a data weighting layer, and an output normalization layer. The basic form is W(t) = α^(t / T), where α is the basic decay rate, t is the time interval, and T is the characteristic time scale. The input data of the time decay model includes historical performance data such as the success rate of bringing goods, the sales conversion rate, and their corresponding timestamps; through model calculation, the weight coefficient of each time period can be obtained, and the goods decay curve can be output to characterize the timeliness contribution of the historical performance of the influencer.

[0139] The core of the time decay model is the exponential decay function W(t) = α^(t / T). Assuming the basic decay rate α is 0.9, the characteristic time scale T is 30 days, for the success rate data of a certain influencer 60 days ago, the time interval t is 60 days, and the weight coefficient W(60) = 0.9^(60 / 30)≈0.81 is calculated. If the success rate of bringing goods in this time period is 40% and the sales conversion rate is 30%, the weighted index value is 0.81*(0.4*0.5+0.3*0.5) = 0.2916 (assuming that the weights of the success rate of bringing goods and the sales conversion rate are 0.5 respectively). At the same time, the experience coefficient of bringing goods is determined based on the frequency distribution and sales performance of the influencer in each commodity category and price range. For example, if a certain influencer brings goods frequently in the beauty category and has good sales performance, the experience coefficient of bringing goods is 1.2. Combined with recent activity (such as a comprehensive evaluation of indicators such as the number of videos released in the past 30 days and the length of live broadcasts) and fan interaction indicators (likes, comments, sharing rates, etc.), if the recent activity score is 0.8 and the fan interaction index score is 0.9, through weighted fusion (assuming that the weight of the experience coefficient in bringing goods is 0.4, the weight of recent activity is 0.3, and the weight of the fan interaction index is 0.3), the final historical performance score = 0.4*1.2+0.3*0.8+0.3*0.9=0.87, in order to comprehensively and dynamically evaluate the historical performance of the expert and optimize the expert recommendation results.

[0140] In some embodiments, the server will group the historical sales data into multiple dimensions according to product categories, price ranges, and time dimensions, and calculate the sales success rate and sales conversion rate of each grouping dimension combination in different time periods; based on the time decay model, dynamically decreasing weight coefficients are assigned to the sales success rate and sales conversion rate in different time periods to obtain a sales decay curve; determine the sales experience coefficient based on the sales frequency distribution and sales performance of the matched influencer in each product category and price range; determine the historical performance score of the matched influencer based on the sales decay curve and sales experience coefficient, combined with the recent activity and fan interaction indicators of the matched influencer.

[0141] Among them, multi-dimensional grouping means data classification according to multiple features; the success rate of sales refers to the proportion of successful sales; the sales conversion rate refers to the proportion of purchase intentions converted into actual sales; the time decay model is used to represent the calculation method of time impact; the sales decay curve represents the performance curve that changes over time; the sales frequency distribution refers to the frequency distribution of sales activities; the sales experience coefficient is used to indicate the professional level of the influencer; the recent activity indicates the frequency of the influencer's activities; the fan interaction index refers to the degree of interaction with fans.

[0142] After obtaining the influencer's historical data, the server needs to conduct an in-depth performance analysis. Specifically, the server first classifies and organizes the historical data according to dimensions such as product type, price, and time; then calculates the sales performance indicators of each combination in different periods; then establishes a time decay model to assign decreasing weights to data in different periods; then calculates the professional level coefficient based on the influencer's experience in bringing goods and sales performance; finally, comprehensively considers the influencer's recent performance and fan interaction to generate the final historical performance score.

[0143] S216: Perform weighted fusion of the historical performance score and the recommendation index, re-sort the experts in the expert recommendation list, and obtain a recommended optimization list.

[0144] Among them, weighted fusion refers to the calculation process that comprehensively considers two indicators; the recommended optimization list refers to the final expert ranking result; the fusion weight represents the importance of different indicators; the sorting rule is used to indicate the basis for expert ranking; and the optimization coefficient refers to the parameter used to adjust the final ranking.

[0145] After obtaining the historical performance score and recommendation index, the server needs to generate the final recommendation ranking. Specifically, the server first sets the fusion weight of the two indicators; then calculates the weighted comprehensive score; then sorts all experts in descending order by score; and finally generates a recommendation optimization list containing complete information.

[0146] In the embodiments of the present application, due to the use of a secondary integration method based on product dimension data and a precise influencer matching algorithm, by systematically analyzing the user portraits of influencers with leading sales, processing outliers and calculating weights, it is possible to establish accurate product portrait standards and achieve precise matching with influencer data, effectively solving the problems of multiple subjective judgments, inconsistent standards and unstable effects in traditional influencer screening, thereby achieving improved sales effects and significantly improved operational efficiency, ensuring the accuracy and reliability of recommendation results, enabling products to find the most suitable influencer resources more quickly, reducing marketing costs and improving return on investment.

[0147] The following describes the server in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , is a schematic diagram of a physical device structure of a server in an embodiment of the present application.

[0148] It should be noted that Figure 3 The structure of the server shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0149] like Figure 3As shown, the server includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0150] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0151] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 309, and / or installed from a removable medium 311. When the computer program is executed by a central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0152] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0153] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0154] Specifically, the server of this embodiment includes a processor and a memory. A computer program is stored in the memory. When the computer program is executed by the processor, the expert recommendation method based on the short video platform product data provided in the above embodiment is implemented.

[0155] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the server described in the above embodiment; or may exist independently without being assembled into the server. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the server, the server implements the expert recommendation method based on short video platform product data provided in the above embodiment.

[0156] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0157] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0158] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A method for recommending experts based on commodity data on a short video platform, characterized in that: Applied to a server, the method comprises: Obtain the data of influencers who carry the target product on a preset ranking list, and extract the population portrait data and fans age distribution data of the influencers as the original data set; Filtering the original data set to obtain product portrait data of the target product including population distribution characteristics and fan age distribution characteristics; Extracting feature dimensions from the portrait data of the expert to be matched, and obtaining the expert portrait data of the expert to be matched; Calculate the difference between the expert portrait data and the product portrait data of the target product to obtain the recommendation index of the expert to be matched for the target product; The experts to be matched are sorted and screened based on the recommendation index, and an expert recommendation list including a ranking sequence of multiple experts to be matched is displayed.

2. The method according to claim 1, characterized in that The step of filtering the original data set to obtain product portrait data of the target product including population distribution characteristics and fan age distribution characteristics specifically includes: Calculate the data averages of the crowd portrait data and the fan age distribution data in the original data set respectively to obtain data benchmark values ​​in multiple dimensions; Calculating the standard deviation of the data reference value, and determining target value intervals in multiple dimensions according to the data reference value and the standard deviation; Removing abnormal data that does not belong to the target value interval in the original data set to obtain a standard data set; The data of each dimension in the standard data set is weighted to obtain product portrait data of the target product including population distribution characteristics and fan age distribution characteristics.

3. The method according to claim 1, characterized in that The step of extracting feature dimensions from the portrait data of the expert to be matched to obtain the expert portrait data of the expert to be matched specifically includes: Obtain the portrait data of the person to be matched, and determine a plurality of dominant dimension data in a preset preceding sequence among the plurality of dimensions of the portrait data to be tested; Normalizing the plurality of dominant dimension data and performing weight assignment to obtain a standard dimension array; The dominant proportion of data on each dimension in the standard dimension array is calculated, and the expert portrait data of the expert to be matched is determined according to the standard dimension array and the dominant proportion.

4. The method according to claim 1, characterized in that The step of calculating the difference between the expert portrait data and the product portrait data of the target product to obtain the recommendation index of the to-be-matched expert for the target product specifically includes: Extracting the commodity matching data corresponding to the expert portrait data from the commodity portrait data, performing difference calculation between the expert portrait data and the commodity matching data, and obtaining an initial difference array; Determine a difference weight array according to the weight proportions of each data in the expert portrait data and the product matching data; Performing weighted summation on the initial difference array according to the difference weight array to obtain reliability data; The data density of the reliability data is scaled to generate a recommendation index.

5. The method according to claim 1, characterized in that Before the step of obtaining the data of influencers who carry the target product on the preset ranking list and extracting the crowd portrait data and the fans age distribution data of the influencers as the original data set, the method further includes: Constructing a sliding time series including multiple preset time windows, and collecting statistics on the sales volume data, sales revenue data and user evaluation data of the target product in each of the preset time windows; Performing time series analysis on the sales volume data, the sales revenue data, and the user evaluation data, and identifying the life cycle stage and market performance trend of the target product through growth rate, volatility, and seasonality characteristics; According to the life cycle stage and the market performance trend, combined with product category characteristics and price range, determine the optimal time period for bringing the target product and the characteristics of the target audience group; The preset benchmark dimensions and dimension weights of the target product are determined according to the optimal time period for bringing the product and the characteristics of the target audience group.

6. The method according to claim 1, characterized in that After the step of sorting and screening the experts to be matched based on the recommendation index and displaying an expert recommendation list including a ranking sequence of multiple experts to be matched, the method further includes: Obtain the historical sales data of each matched expert in the expert recommendation list, and calculate the sales success rate of the matched experts in different product categories; Generate a historical performance score of the matched influencer based on the sales success rate and the time decay model of the historical sales data; The historical performance score is weightedly integrated with the recommendation index, and the experts in the expert recommendation list are reordered to obtain a recommended optimization list.

7. The method according to claim 6, characterized in that The step of generating the historical performance score of the matched influencer based on the product sales success rate and the time decay model of the historical product sales data specifically includes: The historical sales data is grouped into multiple dimensions according to product category, price range and time dimension, and the sales success rate and sales conversion rate of each grouping dimension combination in different time periods are calculated; Based on the time decay model, dynamically decreasing weight coefficients are assigned to the sales success rate and the sales conversion rate in the different time periods to obtain a sales decay curve; Determine the sales experience coefficient based on the matched influencer’s sales frequency distribution and sales performance in each product category and price range; The historical performance score of the matched influencer is determined based on the sales attenuation curve, the sales experience coefficient, and the recent activity and fan interaction index of the matched influencer.

8. A server, characterized in that: The server includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the server to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a server, the server is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a server, the server is caused to execute the method according to any one of claims 1 to 7.

Images