Method, apparatus, electronic device and storage medium for determining internet celebrity merchants

Abstract

The present application discloses a method, apparatus, electronic device and storage medium for determining an internet celebrity merchant. The method includes: obtaining user access data and user comment data of a merchant within a statistical period, and obtaining key calculation factors based on the user access data and the user comment data; setting a calculation model for identifying an internet celebrity merchant according to the key calculation factors; obtaining a calculation result according to the calculation model, the user access data and the user comment data; and determining the merchant as an internet celebrity merchant and / or a newly emerging internet celebrity merchant according to the score ranking of the calculation result. The present application realizes the automatic identification of internet celebrity merchants, no longer relying on manual identification, improving the identification efficiency. Moreover, determining whether a merchant is an internet celebrity merchant based on the score ranking of each merchant no longer relies on subjective judgment by humans, improving the accuracy of determining internet celebrity merchants.

Description

[0001] This application claims the priority of a Chinese patent application with the application number 201910465426.7, titled "Method, Apparatus, Electronic Device, and Storage Medium for Determining Internet Celebrity Merchants", which was filed with the Chinese Patent Office on May 30, 2019. The entire content of this application is incorporated herein by reference. Technical Field

[0002] This application relates to the field of computer technology, and particularly to a method, apparatus, electronic device, and storage medium for determining Internet celebrity merchants. Background Art

[0003] With the refinement and development of the current catering and entertainment market, more and more young people tend to choose "Internet celebrity elements" for catering and entertainment. Internet celebrity merchants have received more and more attention in recent years. However, there is currently no particularly authoritative method for identifying Internet celebrity merchants and recommendation channels.

[0004] In the prior art, the identification or recommendation of Internet celebrity merchants mainly relies on manual identification. The method relying on manual work for identification has low efficiency. Summary of the Invention

[0005] This application provides a method, apparatus, electronic device, and storage medium for determining Internet celebrity merchants, which helps to improve the identification efficiency and accuracy.

[0006] To solve the above problems, in a first aspect, an embodiment of this application provides a method for determining Internet celebrity merchants, including:

[0007] Obtain the user access data and user comment data of a merchant within a statistical period, and obtain key calculation factors based on the user access data and the user comment data;

[0008] Set a calculation model for identifying Internet celebrity merchants according to the key calculation factors;

[0009] Obtain a calculation result according to the calculation model, the user access data, and the user comment data;

[0010] Determine the merchant as an Internet celebrity merchant and / or a newly emerging Internet celebrity merchant according to the score ranking of the calculation result.

[0011] In a second aspect, an embodiment of this application provides an apparatus for determining Internet celebrity merchants, including:

[0012] A data acquisition module, configured to obtain the user access data and user comment data of a merchant within a statistical period, and obtain key calculation factors based on the user access data and the user comment data;

[0013] A calculation model setting module, configured to set a calculation model for identifying internet-famous merchants according to the key calculation factors;

[0014] A calculation result obtaining module, configured to obtain a calculation result according to the calculation model, the user access data, and the user comment data;

[0015] An internet-famous merchant determining module, configured to determine the merchant as an internet-famous merchant and / or a newly emerging internet-famous merchant according to the score ranking of the calculation result.

[0016] In a third aspect, an embodiment of the present application further discloses an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method for determining an internet-famous merchant according to the embodiment of the present application is implemented.

[0017] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of the method for determining an internet-famous merchant disclosed in the embodiment of the present application are implemented.

[0018] The method, device, electronic device, and storage medium for determining an internet-famous merchant disclosed in the embodiments of the present application obtain the user access data and user comment data of a merchant within a statistical period, obtain key calculation factors according to the user access data and the user comment data, set a calculation model for identifying an internet-famous merchant according to the key calculation factors, obtain a calculation result according to the calculation model, and determine the merchant as an internet-famous merchant and / or a newly emerging internet-famous merchant according to the score ranking of the calculation result, realizing the automatic identification of internet-famous merchants, no longer relying on manual identification, improving the identification efficiency, and determining whether a merchant is an internet-famous merchant based on the score ranking of each merchant, no longer relying on subjective human judgment, and improving the accuracy of determining internet-famous merchants. Description of the Drawings

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 is a flowchart of the method for determining an internet-famous merchant provided in Embodiment 1 of the present application;

[0021] Figure 2 is a flowchart of the method for determining an internet-famous merchant provided in Embodiment 2 of the present application;

[0022] Figure 3It is a flowchart of the method for determining Internet-famous merchants provided in Embodiment 3 of this application;

[0023] Figure 4 It is a flowchart of the method for determining Internet-famous merchants provided in Embodiment 4 of this application;

[0024] Figure 5 It is a flowchart of the method for determining Internet-famous merchants provided in Embodiment 5 of this application;

[0025] Figure 6 It is a schematic structural diagram of the device for determining Internet-famous merchants provided in Embodiment 6 of this application. Detailed implementation manners

[0026] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the protection scope of this application.

[0027] Embodiment 1

[0028] A method for determining Internet-famous merchants disclosed in this embodiment, as Figure 1 shown, the method includes: Step 110 to Step 140.

[0029] Step 110, obtain the user access data and user comment data of the merchant within the statistical period, and obtain the key calculation factors according to the user access data and the user comment data.

[0030] Among them, the statistical period is a time period calculated backward from the current time. For example, the statistical period can be, for example, the past 6 months or the past 6 weeks, etc. The merchant is a merchant that has created a POI (Point of Interest). In a geographic information system, a POI can be a house, a store, a mailbox, or a bus stop, etc. In the embodiments of this application, POI is a general term for a name that marks a merchant and a geographical location. The user access data can be the number of unique visitors (UV) of a certain merchant. The user comment data refers to the comment content data of the user, which is user-generated content (UGC).

[0031] Obtain the user access data and user comment data of all merchants with POIs every day within the statistical period. Obtain the values of the key calculation factors according to the user access data and the user comment data.

[0032] Among them, the key calculation factors include: the mention rate of internet celebrity keywords, the increase rate of the number of visitors in a preset period, the average value of the increase rate of the number of visitors in a preset period, the range of the number of visitors, and / or the average value of the number of visitors in a preset period. Among them, the statistical period includes at least two preset periods. The preset period can be, for example, one week. The mention rate of internet celebrity keywords refers to the proportion of the number of comments mentioning internet keywords in the user comment data of a certain merchant to the total number of all comments of the merchant. The increase rate of the number of visitors in a preset period refers to the increase rate of the number of visitors in each preset period compared to the previous preset period of the preset period. The average value of the increase rate of the number of visitors in a preset period is the average value of the increase rate of the number of visitors in a preset period within the statistical period. The range of the number of visitors refers to the difference between the maximum value and the minimum value of the number of visitors in a preset period within the statistical period. The average value of the number of visitors in a preset period refers to the average value of the number of visitors in each preset period within the statistical period.

[0033] In some embodiments of the present application, the step of determining the key calculation factor of the merchant according to the user access data and the user comment data includes:

[0034] According to the user comment data of the merchant, determine the number of comments including internet celebrity keywords, and determine the total number of user comments, and according to the number of comments including internet celebrity keywords and the total number of user comments, determine the mention rate of the internet celebrity keywords of the merchant according to the following formula:

[0035] f = m / M

[0036] Wherein, f is the mention rate of the internet celebrity keywords of the merchant, m is the number of comments including internet celebrity keywords, and M is the total number of user comments;

[0037] According to the number of visitors in a preset period and the number of visitors in the previous preset period in the user access data of the merchant, determine the increase rate of the number of visitors in the preset period of the merchant according to the following formula:

[0038] UV′ = (UV1 - UV2) / (UV1 + 1)

[0039] Wherein, UV′ is the increase rate of the number of visitors in a preset period, UV1 is the number of visitors in a preset period, and UV2 is the number of visitors in the previous preset period of the preset period;

[0040] According to the increase rate of the number of visitors in a preset period of the merchant within the statistical period, determine the average value of the increase rate of the number of visitors in a preset period of the merchant according to the following formula:

[0041]

[0042] Wherein, is the average value of the increase in the number of visitors in the preset period, UV' i is the increase in the number of visitors in the i-th period, and n is the total number of increases in the number of visitors;

[0043] Determine the range of the number of visitors of the merchant in the statistical period according to the number of visitors in the preset period in the user access data of the merchant; and / or,

[0044] Determine the average value of the number of visitors in the preset period of the merchant according to the number of visitors in the preset period in the user access data of the merchant.

[0045] Among them, the internet celebrity keywords include, but are not limited to: internet celebrity, internet celebrity store, internet celebrity check-in, internet celebrity destination, check-in holy land, check out internet celebrity, check-in, suitable for taking pictures, artistic atmosphere, check out, artistic, good-looking in pictures, take a check-in, Douyin, Xiaohongshu, WeChat Moments, official account, Weibo, and planting grass, etc., one or more of these words.

[0046] In some embodiments of the present application, the step of determining the average value of the increase in the number of visitors in the preset period of the merchant according to the increase in the number of visitors in the preset period of the merchant in the statistical period includes: determining the increase in the number of visitors in the statistical period of the merchant where the first increase in growth occurs; and, according to the increase in the number of visitors where the first increase in growth occurs and the subsequent increases in the number of visitors, determining the average value of the increase in the number of visitors in the preset period of the merchant. In order to determine whether the merchant statistically obtained at the current time is an internet celebrity merchant, therefore, determine the increase in the positive growth of the number of visitors, that is, first determine the increase in the number of visitors where the first increase in growth occurs in the increase in the number of visitors in the statistical period, and count the number of the increase in the number of visitors where the first increase in growth occurs and the subsequent increases in the number of visitors, and divide the sum of the increase in the number of visitors where the first increase in growth occurs and the subsequent increases in the number of visitors by the number to obtain the average value of the increase in the number of visitors in the preset period, that is, calculate the average value of the increase in the number of visitors in the preset period through the following formula:

[0047]

[0048] Among them, is the average value of the increase in the number of visitors in the preset period, UV' i is the increase in the number of visitors where the first increase in growth occurs and any subsequent increase in the number of visitors, and n is the total number of the increase in the number of visitors where the first increase in growth occurs and the subsequent increases in the number of visitors.

[0049] In some embodiments of the present application, the step of determining the range of the number of visitors of the merchant during the statistical period according to the number of visitors in the preset period in the user access data of the merchant includes: determining the maximum and minimum values of the number of visitors in the preset period of the merchant during the statistical period according to the number of visitors in the preset period in the user access data of the merchant; wherein, the occurrence time of the maximum value is after the occurrence time of the minimum value, and the multiple of the maximum value to the average value of the number of visitors in the preset period is less than or equal to a first preset multiple, and the data when the merchant was not yet opened has been excluded from the minimum value; and, determining the range of the number of visitors of the merchant during the statistical period according to the maximum value and the minimum value:

[0050] R = UV max -UV min

[0051] Wherein, R is the range of the number of visitors of the merchant during the statistical period, and UV max is the maximum value of the number of visitors in the preset period, and UV min is the minimum value of the number of visitors in the preset period.

[0052] In order to determine whether the merchant statistically obtained at the current time is an internet-famous merchant, therefore, the range of the positive growth of the number of visitors is determined, that is, the occurrence time of the maximum value is after the occurrence time of the minimum value. The first preset multiple is, for example, 5. If the multiple of the maximum value to the average value of the number of visitors in the preset period is greater than 5, then take the next maximum value until it does not exceed 5 times. After excluding abnormal data, the correctness of the range of the number of visitors is improved.

[0053] In some embodiments of the present application, the step of determining the average value of the number of visitors in the preset period of the merchant according to the number of visitors in the preset period in the user access data of the merchant includes: determining the weight of each number of visitors in the preset period according to the chronological order of each number of visitors in the preset period of the merchant during the statistical period; and, determining the average value of the number of visitors in the preset period of the merchant according to each number of visitors in the preset period and the corresponding weight according to the following formula:

[0054]

[0055] Wherein, is the average value of the number of visitors in the preset period of the merchant, UV i is the number of visitors in the i-th preset period, and α i is the weight of the i-th preset period of the number of visitors, and n is the total number of preset periods during the statistical period.

[0056] When calculating the average value of the number of visitors in a preset period within the statistical period, decay is performed according to time. The weight of the number of visitors in the preset period closer to the current time is higher. Thus, according to the number of visitors in each preset period and the corresponding weights, the average value of the number of visitors in the preset period within the statistical period is obtained. Assigning weights in this way can improve the accuracy of the internet celebrity merchants determined at the current time.

[0057] In some other embodiments of the present application, the key calculation factors include: the mention rate of internet celebrity keywords, the positive range of traffic, the negative range of traffic, the traffic growth trend, the average value of the number of visitors in a preset period, and / or the quality weight, where the statistical period includes at least two preset periods. The preset period can be, for example, one week. The mention rate of internet celebrity keywords refers to the proportion of the number of comments that mention internet celebrity keywords and do not contain internet celebrity negative words in the user comment data of a certain merchant to the total number of all comments of the merchant. The positive range of traffic refers to the difference between the maximum value of the number of visitors in a preset period within the statistical period and the minimum value that appeared before this maximum value. The negative range of traffic refers to the difference between the maximum value of the number of visitors in a preset period and the minimum value that appeared after this maximum value. The traffic growth trend is the difference between the positive range of traffic and the negative range of traffic. The average value of the number of visitors in a preset period refers to the average value of the number of visitors in each preset period within the statistical period. The quality weight is determined by the comprehensive quality score corresponding to the star rating of the merchant and the number of comments of the merchant.

[0058] In some embodiments of the present application, the step of determining the key calculation factors of the merchant according to the user access data and user comment data includes:

[0059] According to the user comment data of the merchant, determine the number of comments that include internet celebrity keywords and do not include internet celebrity negative words, and determine the total number of user comments. Then, according to the number of comments that include internet celebrity keywords and do not include internet celebrity negative words and the total number of user comments, determine the mention rate of internet celebrity keywords of the merchant according to the following formula:

[0060] f′ = m′ / M

[0061] where f′ is the mention rate of internet celebrity keywords of the merchant, m′ is the number of comments that include internet celebrity keywords and do not include internet celebrity negative words, and M is the total number of user comments;

[0062] According to the user access data of the merchant, determine the maximum value of the number of visitors in a preset period within the statistical period, determine the minimum value of the number of visitors in a preset period that appeared before this maximum value as the first minimum value, and determine the minimum value of the number of visitors in a preset period that appeared after this maximum value as the second minimum value;

[0063] Determine the positive traffic range of the merchant based on the maximum value and the first minimum value, and use the difference between the maximum value and the second minimum value as the negative traffic range of the merchant;

[0064] Use the difference between the positive traffic range and the negative traffic range as the traffic growth trend of the merchant;

[0065] Determine the average value of the preset-period visitor volume of the merchant based on the preset-period visitor volume in the user access data of the merchant; and / or

[0066] Determine the quality weight of the merchant based on the comprehensive quality score and the number of reviews of the merchant.

[0067] Among them, the internet celebrity keywords include, but are not limited to, one or more of the following words: internet celebrity, internet celebrity store, internet celebrity check-in, internet celebrity destination, check-in holy land, unweeding internet celebrity, check-in, suitable for taking pictures, artistic atmosphere, unweeding, artistic, good-looking in pictures, take a check-in, Douyin, Xiaohongshu, WeChat Moments, official account, Weibo, and planting grass, etc. The internet celebrity negative words are some keywords for activities, including, but not limited to, one or more of the following words: discount, x% off, promotion, event, free meal, discount, and preferential treatment, etc. A review that includes internet celebrity keywords and does not include internet celebrity negative words means that a review includes internet celebrity keywords and cannot contain internet celebrity negative words. If a review contains both internet celebrity keywords and internet celebrity negative words, then this review is not counted.

[0068] Before the minimum value of the preset-period visitor volume that appears after determining the maximum value, it is necessary to first exclude the preset-period visitor volume that has been punished for dishonesty. When counting the preset-period visitor volume within the statistical period, the visitor volume data when the merchant is not open for business should be removed. Before calculating the above key calculation factors, the user access data can also be filtered, and the abnormal values of the preset-period visitor volume can be filtered out. By determining the median of the preset-period visitor volume within the statistical period, if a preset-period visitor volume is greater than or equal to the second preset multiple of the median, then this preset-period visitor volume is filtered out. This is because this preset-period visitor volume is extremely large, and it may be because of activities to attract users, and such data needs to be excluded, so as to further improve the accuracy of determining internet celebrity merchants. Among them, the second preset multiple is, for example, 5.

[0069] Among them, the specific method for determining the average value of the preset-period visitor volume of the merchant is the same as that in the above embodiment, and will not be elaborated here.

[0070] In some embodiments of the present application, the step of determining the positive traffic range of the merchant according to the maximum value and the first minimum value includes: taking the difference between the maximum value and the first minimum value as the initial positive traffic range of the merchant; counting the number of comments containing negative influencer words in the user comment data of the merchant, and determining the total number of comments of the merchant in the statistical period; taking the ratio of the number of comments containing negative influencer words to the total number of comments as the proportion of negative influencer words corresponding to the merchant; counting the average value of the proportions of negative influencer words corresponding to all merchants; and, according to the proportion of negative influencer words corresponding to the merchant and the average value, performing a weight reduction process on the initial positive traffic range to obtain the positive traffic range of the merchant. By performing a weight reduction process on the initial positive traffic range through the average value of the proportions of negative influencer words of all merchants, the error caused by the merchant's activities can be eliminated, and the accuracy of subsequent identification of influencer merchants can be improved.

[0071] Among them, the step of performing a weight reduction process on the initial positive traffic range according to the proportion of negative influencer words corresponding to the merchant and the average value to obtain the positive traffic range of the merchant includes:

[0072] Calculating the difference between the proportion of negative influencer words and the average value as the weight reduction weight; if the weight reduction weight is less than or equal to 0, taking the initial positive traffic range as the positive traffic range of the merchant; if the weight reduction weight is greater than 0, performing a weight reduction process on the initial positive traffic range according to the following formula to obtain the positive traffic range of the merchant:

[0073] R1 = (1 - a)R1′

[0074] Wherein, R1 is the positive traffic range of the merchant, R1′ is the initial positive traffic range, and a is the weight reduction weight.

[0075] In some embodiments of the present application, the step of determining the quality weight of the merchant according to the comprehensive quality score and the number of comments of the merchant includes: if the number of comments is greater than or equal to a preset comment threshold, taking the comprehensive quality score of the merchant as the quality weight of the merchant; if the number of comments is less than the preset comment threshold, taking the product of the comprehensive quality score of the merchant and a preset coefficient as the quality weight of the merchant, where the preset coefficient is less than 1. Determining the quality weight of the merchant according to the star rating and the number of comments of the merchant, taking into account both the comprehensive quality score of the merchant and the popularity among users, can improve the accuracy of subsequent determination of influencer merchants.

[0076] Step 120, setting a calculation model for identifying influencer merchants according to the key calculation factors.

[0077] The calculation model for identifying popular online merchants and the calculation model for identifying newly emerging popular online merchants can be different models. Since popular online merchants are generally well-known with high public recognition and have a relatively long statistical period, while newly emerging popular online merchants are more inclined to new merchants. Therefore, newly emerging popular online merchants are mainly characterized by an increasing growth rate of the number of visitors in a recent period, and the statistical period is relatively short.

[0078] In some embodiments of the present application, the step of setting the calculation model for identifying popular online merchants according to the key calculation factors includes:

[0079] According to the key calculation factors, set the product of the average number of visitors in the preset period, the range of the number of visitors, and the mention rate of the popular online merchant keywords as the first calculation model for identifying popular online merchants; and / or

[0080] According to the key calculation factors, set the product of the average growth rate of the number of visitors in the preset period, the range of the number of visitors, and the mention rate of the popular online merchant keywords as the second calculation model for identifying newly emerging popular online merchants.

[0081] The visitor volume data of popular online merchants is generally relatively stable. Therefore, the average number of visitors in the preset period, the range of the number of visitors, and the mention rate of the popular online merchant keywords are set as the first calculation model for identifying popular online merchants. Newly emerging popular online merchants are characterized by a continuous increase in the number of visitors in a recent period. Therefore, the product of the average growth rate of the number of visitors in the preset period, the range of the number of visitors, and the mention rate of the popular online merchant keywords is used as the second calculation model for identifying newly emerging popular online merchants. Since the characteristics of popular online merchants and newly emerging popular online merchants are different, different calculation models are used to obtain the calculation results, thereby improving the identification accuracy of popular online merchants and newly emerging popular online merchants.

[0082] In other embodiments of the present application, the step of setting the calculation model for identifying popular online merchants according to the key calculation factors includes:

[0083] According to the key calculation factors, set the product of the average number of visitors in the preset period, the traffic growth trend, the mention rate of the popular online merchant keywords, and the quality weight as the first calculation model for identifying popular online merchants; and / or

[0084] According to the key calculation factors, set the product of the traffic growth trend, the mention rate of the popular online merchant keywords, and the quality weight as the second calculation model for identifying newly emerging popular online merchants.

[0085] The visitor volume data of online celebrity merchants is generally relatively stable. Therefore, the product of the average visitor volume over a preset period, the traffic growth trend, the mention rate of online celebrity keywords, and the quality weight is used as the first calculation model for identifying online celebrity merchants. Newly emerging online celebrity merchants show that the visitor volume has been increasing recently. Therefore, the product of the traffic growth trend, the mention rate of online celebrity keywords, and the quality weight is used as the second calculation model for identifying newly emerging online celebrity merchants. Since the characteristics of online celebrity merchants and newly emerging online celebrity merchants are different, different calculation models are used to obtain the calculation results, thereby improving the identification accuracy of online celebrity merchants and newly emerging online celebrity merchants.

[0086] Step 130, obtain a calculation result according to the calculation model, the user access data, and the user comment data.

[0087] Calculate the values of each key calculation factor based on the user access data and user comment data of each merchant, and substitute the values of each key calculation factor into the calculation model to obtain the calculation results of each merchant. The calculation results are a list of scores for each merchant as an online celebrity merchant.

[0088] In some embodiments of the present application, the step of obtaining a calculation result according to the calculation model, the user access data, and the user comment data includes:

[0089] For each merchant, calculate the product of the average visitor volume over the preset period, the visitor volume range, and the mention rate of online celebrity keywords according to the first calculation model to obtain the calculation result of each merchant as an online celebrity merchant, that is, calculate according to the following formula:

[0090]

[0091] where S1 is the calculation result of the merchant as an online celebrity merchant, is the average visitor volume over the preset period, R is the visitor volume range, and f is the mention rate of online celebrity keywords; and / or

[0092] For each merchant, calculate the product of the average value of the increase in visitor volume over the preset period, the visitor volume range, and the mention rate of online celebrity keywords according to the second calculation model to obtain the calculation result of each merchant as a newly emerging online celebrity merchant, that is, calculate according to the following formula:

[0093]

[0094] where S2 is the calculation result of the merchant as a newly emerging online celebrity merchant, is the average value of the increase in visitor volume over the preset period, R is the visitor volume range, and f is the mention rate of online celebrity keywords.

[0095] When determining that the current requirement is to identify popular merchant, for each merchant, according to the first calculation model, calculate the calculation result of each merchant as a popular merchant respectively. When determining that the current requirement is to identify newly emerging popular merchant, for each merchant, according to the second calculation model, calculate the calculation result of each merchant as a newly emerging popular merchant respectively.

[0096] In some other embodiments of the present application, the step of obtaining the calculation result according to the calculation model, the user access data and the user comment data includes:

[0097] For each of the merchants, according to the first calculation model, calculate the product of the average number of visitors in the preset period, the traffic growth trend, the mention rate of popular keywords and the quality weight to obtain the calculation result of each merchant as a popular merchant, that is, calculate according to the following formula:

[0098]

[0099] wherein, S1 is the calculation result of the merchant as a popular merchant, is the average number of visitors in the preset period, R′ is the traffic growth trend, f is the mention rate of popular keywords, ω is the quality weight; and / or

[0100] For each of the merchants, according to the second calculation model, calculate the product of the traffic growth trend, the mention rate of popular keywords and the quality weight to obtain the calculation result of each merchant as a newly emerging popular merchant, that is, calculate according to the following formula:

[0101] S2 = R′ * f * ω

[0102] wherein, S2 is the calculation result of the merchant as a newly emerging popular merchant, R′ is the traffic growth trend, f is the mention rate of popular keywords, ω is the quality weight.

[0103] Step 140, determine the merchant as a popular merchant and / or a newly emerging popular merchant according to the score ranking of the calculation result.

[0104] The statistical period of the popular merchant is longer than that of the newly emerging popular merchant, so as to better identify popular merchants and newly emerging popular merchants. For example, the statistical period of the popular merchant is the past 6 months, while the statistical period of the newly emerging popular merchant is the past 6 weeks.

[0105] Determine the merchant as a popular merchant and / or a newly emerging popular merchant according to the score ranking of the calculation result and the preset quantity. For example, when the preset quantity is 50, the top 50 merchants in the score ranking of the popular merchants are regarded as popular merchants, and the top 50 merchants in the score ranking of the newly emerging popular merchants are regarded as newly emerging popular merchants.

[0106] In some embodiments of the present application, the step of determining that the merchant is an Internet celebrity merchant according to the score ranking of the calculation result includes:

[0107] Determine merchants whose geographical locations are within the statistical area according to the geographical locations of the merchants;

[0108] Sorting the merchants located in the statistical area according to the scores of the merchants located in the statistical area as Internet celebrity merchants from high to low; and

[0109] Merchants that are ranked high and meet preset conditions are determined to be Internet celebrity merchants, and the Internet celebrity merchants are generated into an Internet celebrity list within the statistical area.

[0110] The statistical area may be a city, an administrative area within a city, or a preset area (such as an area where a business district is located). The preset condition may be a preset number or a preset ratio, or a minimum value of the preset number and the preset ratio.

[0111] When it is necessary to generate a list of Internet celebrities in a statistical area, it is necessary to determine the merchants whose geographical locations are in the statistical area, and obtain the calculation results of the merchants in the statistical area, and sort the scores of the merchants in the calculation results as Internet celebrity merchants in order from high to low to determine the merchants with the highest ranking and meeting the preset conditions as Internet celebrity merchants. For example, for merchants in the food category, the top 100 merchants can be selected as Internet celebrity merchants, or the top 5% of the merchants can be selected as Internet celebrity merchants, or the minimum value between 100 and 5% of the number of merchants in the statistical area can be taken, and the merchants within the minimum value can be determined as Internet celebrity merchants. For non-food merchants, the top 50 merchants can be selected as Internet celebrity merchants, or the top 5% of the merchants can be selected as Internet celebrity merchants, or the minimum value between 50 and 5% of the number of merchants in the statistical area can be taken, and the merchants within the minimum value can be determined as Internet celebrity merchants.

[0112] In some embodiments of the present application, the step of determining that the merchant is a new internet celebrity merchant according to the score ranking of the calculation result includes:

[0113] Determine merchants whose geographical locations are within the statistical area according to the geographical locations of the merchants;

[0114] Sorting the merchants located in the statistical area according to the scores of the merchants located in the statistical area as new internet celebrity merchants from high to low;

[0115] For the merchants in the ranking, merchants that do not meet the criteria for new internet celebrities are eliminated; and

[0116] For the merchants in the processed ranking, determine the merchants with a higher ranking and meeting the preset conditions as newly emerging internet-famous merchants, and generate a newly emerging internet-famous list within the statistical area for the said newly emerging internet-famous merchants.

[0117] Among them, the statistical area can be a city, or an administrative area within a city, or a preset area (such as the area where a business district is located). The preset conditions can be a preset quantity or a preset ratio, or the minimum value among the preset quantity and the preset ratio.

[0118] Among them, the merchants who do not meet the conditions of newly emerging internet-famous merchants include one or more of brand chain stores, merchants with an average number of visitors per preset period greater than a preset value, and merchants who have entered the internet-famous list. Because brand chain stores have brand characteristics, multiple chain branches, and relatively high popularity, they cannot become newly emerging internet-famous merchants. The preset value is generally set relatively high, for example, 3000. If the average number of visitors per preset period is greater than 3000, it is determined that the merchant has already gained public recognition and cannot become a newly emerging internet-famous merchant. To avoid duplication of merchants in the internet-famous list and the newly emerging internet-famous list, merchants who have already entered the internet-famous list cannot enter the newly emerging internet-famous list again. Merchants who do not meet the conditions of newly emerging internet-famous merchants also include scenic spot merchants with an earlier opening time among tourism merchants, such as scenic spot merchants with a POI creation time exceeding 90 days under the category of surrounding tours.

[0119] When it is necessary to generate a newly emerging internet-famous list within a statistical area, it is necessary to determine the merchants whose geographical locations are within the statistical area, obtain the calculation results of the merchants within the statistical area, sort the scores of the merchants who are newly emerging internet-famous merchants in the calculation results from high to low. For the merchants in the ranking, eliminate the merchants who do not meet the conditions of newly emerging internet-famous merchants. For the merchants in the processed ranking, determine the merchants with a higher ranking and meeting the preset conditions as internet-famous merchants. For example, for food merchants, 100 merchants with a higher ranking can be selected as newly emerging internet-famous merchants, or 5% of the merchants with a higher ranking can be selected as newly emerging internet-famous merchants, or, take the minimum value between 100 and 5% of the number of merchants in the statistical area, and determine the merchants within the said minimum value with a higher ranking as newly emerging internet-famous merchants. For non-food merchants, 50 merchants with a higher ranking can be selected as newly emerging internet-famous merchants, or 5% of the merchants with a higher ranking can be selected as newly emerging internet-famous merchants, or, take the minimum value between 50 and 5% of the number of merchants in the statistical area, and determine the merchants within the said minimum value with a higher ranking as newly emerging internet-famous merchants.

[0120] The method for determining an internet celebrity merchant disclosed in the embodiments of the present application obtains the user access data and user comment data of the merchant within a statistical period, obtains key calculation factors based on the user access data and the user comment data, sets a calculation model for identifying internet celebrity merchants according to the key calculation factors, obtains a calculation result according to the calculation model, and determines the merchant as an internet celebrity merchant and / or a newly emerging internet celebrity merchant according to the score ranking of the calculation result, realizing the automatic identification of internet celebrity merchants, no longer relying on manual identification, improving the identification efficiency, and determining whether a merchant is an internet celebrity merchant according to the score ranking of each merchant, no longer relying on subjective judgment of manual work, improving the accuracy of determining internet celebrity merchants, and being able to identify newly emerging internet celebrity merchants, reducing the lag of identifying internet celebrity merchants compared with manual judgment.

[0121] On the basis of the above technical solution, before the step of obtaining key calculation factors according to the user access data and the user comment data, it further includes: determining merchants that meet the preliminary screening conditions according to the user access data and the user comment data, where the preliminary screening conditions include: the number of comments including internet celebrity keywords in the user comment data is greater than or equal to a quantity threshold, and the average number of visitors in a preset period in the user access data is greater than or equal to a visitor volume threshold.

[0122] Before determining the key calculation factors of each merchant, first conduct a preliminary screening of the merchants according to the user access data and user comment data of each merchant to narrow the data range and improve the subsequent data processing speed. Among them, the quantity threshold can be, for example, 10, and the visitor volume threshold can be, for example, 100.

[0123] On the basis of the above technical solution, before the step of determining merchants that meet the preliminary screening conditions according to the user access data and the user comment data, it further includes: filtering out the access data determined to be cheating in integrity in the user access data; using the access data including access to a preset page in the filtered user access data as valid user access data. First, filter out the access data determined to be cheating in integrity in the user access data to avoid the problem of low accuracy caused by using cheating access data as the basis for determining internet celebrity merchants. For the access data of a certain merchant in the user access data that does not access the preset page, the access data is regarded as invalid user access data, and the access data that accesses the preset page is used as valid user access data. When calculating the value of the key calculation factor subsequently, all use the valid user access data as the basis for calculation, which can improve the accuracy of determining internet celebrity merchants. Among them, the preset page can be the merchant details page, that is, only when the user accesses the merchant details page of a merchant is it valid user access data.

[0124] Embodiment Two

[0125] A method for determining Internet celebrity merchants disclosed in this embodiment. On the basis of the above embodiment, this embodiment mainly determines whether a merchant is an Internet celebrity merchant. For example, Figure 2 As shown, the method includes: Step 210 to Step 260.

[0126] Step 210, obtain the user access data and user comment data of the merchant within the statistical period, and obtain key calculation factors according to the user access data and the user comment data.

[0127] When the current requirement is to determine whether a merchant is an Internet celebrity merchant, obtain the statistical period of Internet celebrity merchants, and obtain the user access data and user comment data of each merchant according to this statistical period. Among them, the statistical period of Internet celebrity merchants is longer than that of newly emerging Internet celebrity merchants.

[0128] When determining whether a merchant is an Internet celebrity merchant, the key calculation factors include: the average value of the number of visitors in a preset period, the range of the number of visitors, and the mention rate of Internet celebrity keywords. Among them, the statistical period includes at least two of the preset periods. For example, when determining whether a merchant is an Internet celebrity merchant, the statistical period can be 6 months, and the preset period is generally one week.

[0129] Step 220, according to the key calculation factors, set the product of the average value of the number of visitors in the preset period, the range of the number of visitors, and the mention rate of Internet celebrity keywords as the first calculation model for identifying Internet celebrity merchants.

[0130] Since Internet celebrity merchants are merchants unanimously recognized by the public, have an earlier opening time, and the number of visitors is relatively stable, when determining whether a merchant is an Internet celebrity merchant, the first calculation model can be set according to the average value of the number of visitors in the preset period instead of the increase rate of the number of visitors in the preset period.

[0131] Step 230, for each merchant, according to the first calculation model, calculate the product of the average value of the number of visitors in the preset period, the range of the number of visitors, and the mention rate of Internet celebrity keywords, and obtain the calculation result of each merchant as an Internet celebrity merchant.

[0132] For each merchant, calculate the score of each merchant as an Internet celebrity merchant according to the first calculation model respectively. After all merchants are calculated, obtain the calculation results of each merchant as an Internet celebrity merchant.

[0133] Step 240, according to the geographical location of the merchant, determine the merchants whose geographical location is within the statistical area.

[0134] Among them, the statistical area can be a city, or an administrative area within a city, or a preset area (such as the area where a business district is located). The preset condition can be a preset quantity or a preset ratio, or the minimum value of the preset quantity and the preset ratio.

[0135] Based on the geographical location of the merchants, determine the merchants whose geographical locations are within the statistical area, and subsequently determine whether these merchants are internet-famous merchants based on the data of these merchants.

[0136] Step 250: Sort the merchants whose geographical locations are within the statistical area in descending order of the scores of these merchants as internet-famous merchants.

[0137] Extract the calculation results of the merchants whose geographical locations are within the statistical area from the calculation results of each merchant as an internet-famous merchant, and sort them in descending order of the scores of each merchant as an internet-famous merchant in this calculation result.

[0138] Step 260: Determine the merchants with higher rankings and meeting the preset conditions as internet-famous merchants, and generate an internet-famous merchant list within the statistical area for these internet-famous merchants.

[0139] The method for determining internet-famous merchants disclosed in this embodiment obtains the user access data and user comment data of merchants within the statistical period, obtains key calculation factors based on the user access data and the user comment data, sets the product of the average value of the number of visitors in the preset period, the range of the number of visitors, and the mention rate of internet-famous keywords as the first calculation model for identifying internet-famous merchants according to the key calculation factors. For each merchant, according to the first calculation model, calculate the product of the average value of the number of visitors in the preset period, the range of the number of visitors, and the mention rate of internet-famous keywords to obtain the calculation result of each merchant as an internet-famous merchant. Based on the geographical location of the merchants, determine the merchants whose geographical locations are within the statistical area, sort the merchants whose geographical locations are within the statistical area in descending order of the scores of these merchants as internet-famous merchants, determine the merchants with higher rankings and meeting the preset conditions as internet-famous merchants, and generate an internet-famous merchant list within the statistical area for these internet-famous merchants, realizing the automatic identification of internet-famous merchants, no longer relying on manual identification, improving the identification efficiency, and determining whether a merchant is an internet-famous merchant based on the score ranking of each merchant, no longer relying on subjective judgment by humans, and improving the accuracy of determining internet-famous merchants.

[0140] Embodiment III

[0141] A method for determining internet-famous merchants disclosed in this embodiment, on the basis of the above embodiment, mainly determines that a merchant is a newly emerging internet-famous merchant, as Figure 3 shown, this method includes: Step 310 to Step 370.

[0142] Step 310: Obtain the user access data and user comment data of merchants within the statistical period, and obtain key calculation factors based on the user access data and the user comment data.

[0143] When the current requirement is to determine whether a merchant is a newly emerging internet-famous merchant, obtain the statistical period of newly emerging internet-famous merchants, and based on this statistical period, obtain the user access data and user review data of each merchant. Among them, the statistical period of newly emerging internet-famous merchants is less than that of internet-famous merchants.

[0144] When determining whether a merchant is a newly emerging internet-famous merchant, the key calculation factors include: the increase rate of the number of visitors in a preset period, the average value of the increase rate of the number of visitors in a preset period, the range of the number of visitors, and the mention rate of internet-famous keywords. Among them, the statistical period includes at least two of the preset periods. For example, when determining whether a merchant is a newly emerging internet-famous merchant, the statistical period can be 6 weeks, and the preset period is generally one week.

[0145] Step 320, according to the key calculation factors, set the product of the average value of the increase rate of the number of visitors in the preset period, the range of the number of visitors, and the mention rate of internet-famous keywords as the second calculation model for identifying newly emerging internet-famous merchants.

[0146] Newly emerging internet-famous merchants generally tend to be new merchants, and the number of visitors shows an increasing trend. Therefore, when determining whether a merchant is a newly emerging internet-famous merchant, set the second calculation model according to the average value of the increase rate of the number of visitors in the preset period.

[0147] Step 330, for each merchant, according to the second calculation model, calculate the product of the average value of the increase rate of the number of visitors in the preset period, the range of the number of visitors, and the mention rate of internet-famous keywords, and obtain the calculation result of each merchant as a newly emerging internet-famous merchant.

[0148] For each merchant, calculate the score of each merchant as a newly emerging internet-famous merchant according to the second calculation model respectively. After all merchants are calculated, obtain the calculation results of each merchant as a newly emerging internet-famous merchant.

[0149] Step 340, according to the geographical location of the merchant, determine the merchants whose geographical location is within the statistical area.

[0150] According to the geographical location of the merchant, determine the merchants whose geographical location is within the statistical area, and subsequently determine whether these merchants are newly emerging internet-famous merchants based on the data of these merchants.

[0151] Step 350, sort the merchants whose geographical location is within the statistical area in descending order according to the scores of the merchants whose geographical location is within the statistical area as newly emerging internet-famous merchants.

[0152] Extract the calculation results of the merchants whose geographical location is within the statistical area from the calculation results of each merchant as a newly emerging internet-famous merchant, and sort them in descending order according to the scores of each merchant as a newly emerging internet-famous merchant in this calculation result.

[0153] Step 360: For the merchants in the said ranking, eliminate the merchants that do not meet the conditions of newly emerging internet celebrities.

[0154] Among them, the merchants that do not meet the conditions of newly emerging internet celebrities include one or more of brand chain stores, merchants with an average number of visitors per preset period greater than a preset value, and merchants on the internet celebrity list.

[0155] Mainly eliminate some merchants with relatively high awareness. These merchants are generally not considered as newly emerging internet celebrity merchants.

[0156] Step 370: For the merchants in the processed ranking, determine the merchants with a higher ranking and meeting the preset conditions as newly emerging internet celebrity merchants, and generate a newly emerging internet celebrity list within the said statistical area for the said newly emerging internet celebrity merchants.

[0157] The method for determining internet celebrity merchants disclosed in this embodiment obtains the user access data and user comment data of merchants within a statistical period, obtains key calculation factors based on the user access data and the user comment data, sets the product of the average value of the increase rate of the number of visitors per preset period, the range of the number of visitors, and the mention rate of internet celebrity keywords as the second calculation model for identifying newly emerging internet celebrity merchants according to the key calculation factors. For each said merchant, calculate the product of the average value of the increase rate of the number of visitors per preset period, the range of the number of visitors, and the mention rate of internet celebrity keywords according to the second calculation model to obtain the calculation result of each merchant as a newly emerging internet celebrity merchant. Determine the merchants whose geographical locations are within the statistical area according to the geographical locations of the merchants, sort the merchants whose geographical locations are within the statistical area in descending order of the scores of the merchants as newly emerging internet celebrity merchants. For the merchants in the said ranking, eliminate the merchants that do not meet the conditions of newly emerging internet celebrities. For the merchants in the processed ranking, determine the merchants with a higher ranking and meeting the preset conditions as newly emerging internet celebrity merchants, and generate a newly emerging internet celebrity list within the said statistical area for the said newly emerging internet celebrity merchants. It can identify newly emerging internet celebrity merchants, realize the prediction of internet celebrity merchants, reduce the lag of identifying internet celebrity merchants compared with manual judgment, and improve the identification efficiency.

[0158] Embodiment 4

[0159] A method for determining internet celebrity merchants disclosed in this embodiment, on the basis of the above embodiment, mainly determines merchants as internet celebrity merchants. As Figure 4 shown, this method includes: Step 410 to Step 460.

[0160] Step 410: Obtain the user access data and user comment data of merchants within a statistical period, and obtain key calculation factors based on the user access data and the user comment data.

[0161] When the current requirement is to determine whether a merchant is an internet celebrity merchant, obtain the statistical period of internet celebrity merchants, and based on this statistical period, obtain the user access data and user review data of each merchant. Among them, the statistical period of internet celebrity merchants is longer than that of newly emerging internet celebrity merchants.

[0162] When determining whether a merchant is an internet celebrity merchant, the key calculation factors include: the mention rate of internet celebrity keywords, the positive extreme value of traffic, the negative extreme value of traffic, the traffic growth trend, the average value of visitors in a preset period, and the quality weight. Among them, the statistical period includes at least two of the preset periods. For example, when determining whether a merchant is an internet celebrity merchant, the statistical period can be 6 months, and the preset period is generally one week.

[0163] Step 420, according to the key calculation factors, set the product of the average value of visitors in the preset period, the traffic growth trend, the mention rate of internet celebrity keywords, and the quality weight as the first calculation model for identifying internet celebrity merchants.

[0164] Since internet celebrity merchants are merchants unanimously recognized by the public, have an earlier opening time, and relatively stable visitor volume, when determining whether a merchant is an internet celebrity merchant, the average value of visitors in the preset period is used as a key calculation factor for identifying internet celebrity merchants, and the first calculation model is set.

[0165] Step 430, for each merchant, according to the first calculation model, calculate the product of the average value of visitors in the preset period, the traffic growth trend, the mention rate of internet celebrity keywords, and the quality weight, and obtain the calculation result of each merchant as an internet celebrity merchant.

[0166] For each merchant, calculate the score of each merchant as an internet celebrity merchant according to the first calculation model respectively. After calculating each merchant, obtain the calculation results of each merchant as an internet celebrity merchant.

[0167] Step 440, according to the geographical location of the merchant, determine the merchants whose geographical location is within the statistical area.

[0168] Among them, the statistical area can be a city, or an administrative area within a city, or a preset area (such as the area where a business district is located).

[0169] According to the geographical location of the merchant, determine the merchants whose geographical location is within the statistical area, and subsequently determine whether these merchants are internet celebrity merchants based on the data of these merchants.

[0170] Step 450, sort the merchants whose geographical location is within the statistical area in descending order of the score of being an internet celebrity merchant.

[0171] The calculation results of the merchants whose geographical locations are within the statistical area are extracted from the calculation results of each merchant being an Internet celebrity merchant, and the merchants are sorted in descending order according to the score of each merchant being an Internet celebrity merchant in the calculation results.

[0172] Step 460, determining that merchants that are ranked high and meet preset conditions are Internet celebrity merchants, and generating an Internet celebrity list within the statistical area for the Internet celebrity merchants.

[0173] The preset condition may be a preset number or a preset ratio, or a minimum value of the preset number and the preset ratio.

[0174] The method for determining an Internet celebrity merchant disclosed in this embodiment obtains user access data and user comment data of the merchant within a statistical period, and obtains key calculation factors based on the user access data and the user comment data. According to the key calculation factors, the product of the average visitor volume in a preset period, the traffic growth trend, the Internet celebrity keyword mention rate and the quality weight is set as the first calculation model for identifying Internet celebrity merchants. For each of the merchants, according to the first calculation model, the product of the average visitor volume in a preset period, the traffic growth trend, the Internet celebrity keyword mention rate and the quality weight is calculated to obtain the calculation result of each merchant as an Internet celebrity merchant. , according to the geographical location of the merchant, the merchants whose geographical location is within the statistical area are determined, and the merchants whose geographical location is within the statistical area are ranked in descending order according to the scores of the merchants whose geographical location is within the statistical area as Internet celebrity merchants, and the merchants with high rankings and meeting preset conditions are determined as Internet celebrity merchants, and the Internet celebrity merchants are generated into an Internet celebrity list within the statistical area, thereby realizing automatic identification of Internet celebrity merchants, no longer relying on manual identification, and improving identification efficiency, and determining whether it is an Internet celebrity merchant based on the score ranking of each merchant, no longer relying on manual subjective judgment, and improving the accuracy of determining Internet celebrity merchants.

[0175] Embodiment 5

[0176] This embodiment discloses a method for determining a popular online merchant. Based on the above embodiments, this embodiment mainly determines whether a merchant is a newly-promoted popular online merchant, such as Figure 5 As shown, the method includes: steps 510 to 570.

[0177] Step 510, obtaining the user access data and user comment data of the merchant within the statistical period, and obtaining key calculation factors according to the user access data and the user comment data.

[0178] When the current demand is to determine whether a merchant is a new internet celebrity merchant, the statistical period of the new internet celebrity merchant is obtained, and the user access data and user comment data of each merchant are obtained according to the statistical period. Among them, the statistical period of the new internet celebrity merchant is shorter than the statistical period of the internet celebrity merchant.

[0179] When determining whether a merchant is a newly emerging online celebrity merchant, the key calculation factors include: the mention rate of online celebrity keywords, the positive range of traffic, the negative range of traffic, the traffic growth trend, and the quality weight. Among them, when calculating each key calculation factor, it is calculated based on the visitor volume in a preset period with the preset period as the unit, and the statistical period includes at least two such preset periods. For example, when determining whether a merchant is a newly emerging online celebrity merchant, the statistical period can be 6 weeks, and the preset period is generally one week.

[0180] Step 520: According to the key calculation factors, set the product of the traffic growth trend, the mention rate of online celebrity keywords, and the quality weight as the second calculation model for identifying newly emerging online celebrity merchants.

[0181] Newly emerging online celebrity merchants generally tend to be new merchants, and the visitor volume shows an increasing trend. Therefore, when determining whether a merchant is a newly emerging online celebrity merchant, the average value of the visitor volume in the preset period does not need to be considered, and the second calculation model is mainly set based on the traffic growth trend.

[0182] Step 530: For each merchant, according to the second calculation model, calculate the product of the traffic growth trend, the mention rate of online celebrity keywords, and the quality weight to obtain the calculation result of each merchant as a newly emerging online celebrity merchant.

[0183] For each merchant, calculate the score of each merchant as a newly emerging online celebrity merchant according to the second calculation model respectively. After calculating each merchant, obtain the calculation results of each merchant as a newly emerging online celebrity merchant.

[0184] Step 540: According to the geographical location of the merchant, determine the merchants whose geographical location is within the statistical area.

[0185] According to the geographical location of the merchant, determine the merchants whose geographical location is within the statistical area, and then determine whether these merchants are newly emerging online celebrity merchants based on the data of these merchants.

[0186] Step 550: Sort the merchants whose geographical location is within the statistical area in descending order of the scores of the merchants as newly emerging online celebrity merchants.

[0187] Extract the calculation results of the merchants whose geographical location is within the statistical area from the calculation results of each merchant as a newly emerging online celebrity merchant, and sort them in descending order of the scores of each merchant as a newly emerging online celebrity merchant in this calculation result.

[0188] Step 560: For the merchants in the sorting, eliminate the merchants who do not meet the conditions of newly emerging online celebrity merchants.

[0189] Among them, the merchants who do not meet the conditions of new internet celebrities include one or more of brand chain stores, merchants with an average number of visitors per preset period greater than a preset value, and merchants on the internet celebrity list.

[0190] It is mainly to eliminate some merchants with relatively high awareness, and these merchants are generally not considered as new internet celebrity merchants.

[0191] Step 570: For the merchants in the processed ranking, determine the merchants with a higher ranking and meeting the preset conditions as new internet celebrity merchants, and generate a new internet celebrity list for the statistical area with the new internet celebrity merchants.

[0192] Among them, the preset condition can be a preset quantity or a preset ratio, or the minimum value of the preset quantity and the preset ratio.

[0193] The method for determining internet celebrity merchants disclosed in this embodiment obtains the user access data and user comment data of merchants within a statistical period, obtains key calculation factors based on the user access data and the user comment data, sets the product of the traffic growth trend, the mention rate of internet celebrity keywords, and the quality weight as the second calculation model for identifying new internet celebrity merchants according to the key calculation factors. For each merchant, according to the second calculation model, calculate the product of the traffic growth trend, the mention rate of internet celebrity keywords, and the quality weight, obtain the calculation result of each merchant as a new internet celebrity merchant, determine the merchants whose geographical location is within the statistical area according to the geographical location of the merchants, sort the merchants whose geographical location is within the statistical area in descending order of the scores of the merchants as new internet celebrity merchants, eliminate the merchants who do not meet the conditions of new internet celebrities for the merchants in the ranking, determine the merchants with a higher ranking and meeting the preset conditions as new internet celebrity merchants for the merchants in the processed ranking, and generate a new internet celebrity list for the statistical area with the new internet celebrity merchants, which can identify new internet celebrity merchants, realize the prediction of internet celebrity merchants, reduce the lag of internet celebrity merchant identification compared with manual judgment, and improve the identification efficiency.

[0194] Embodiment Six

[0195] A device for determining internet celebrity merchants disclosed in this embodiment, as Figure 6 shown, the device 600 includes:

[0196] A data acquisition module 610, configured to acquire user access data and user comment data of merchants within a statistical period, and obtain key calculation factors according to the user access data and the user comment data;

[0197] A calculation model setting module 620, configured to set a calculation model for identifying internet celebrity merchants according to the key calculation factors;

[0198] A calculation result obtaining module 630, configured to obtain a calculation result according to the calculation model, the user access data, and the user comment data;

[0199] An internet celebrity merchant determining module 640, configured to determine the merchant as an internet celebrity merchant and / or a newly emerging internet celebrity merchant according to the score ranking of the calculation result.

[0200] Optionally, the device further includes:

[0201] A merchant preliminary screening module, configured to determine a merchant that meets the preliminary screening conditions according to the user access data and the user comment data, where the preliminary screening conditions include: the number of comments including internet celebrity keywords in the user comment data is greater than or equal to a quantity threshold, and the average value of the number of visitors in a preset period in the user access data is greater than or equal to a visitor volume threshold.

[0202] Optionally, the device further includes:

[0203] An access data filtering module, configured to filter out the access data with integrity determination cheating in the user access data;

[0204] A valid data determining module, configured to use the access data including accessing a preset page in the filtered user access data as valid user access data.

[0205] Optionally, the key calculation factors include: internet celebrity keyword mention rate, preset period visitor volume increase rate, average value of the preset period visitor volume increase rate, visitor volume range, and / or average value of the preset period visitor volume, where the statistical period includes at least two preset periods.

[0206] Optionally, the data acquisition module includes:

[0207] An internet celebrity keyword mention rate determining unit, configured to determine the number of comments including internet celebrity keywords according to the user comment data of the merchant, determine the total number of user comments, and determine the internet celebrity keyword mention rate of the merchant according to the number of comments including internet celebrity keywords and the total number of user comments;

[0208] A visitor volume increase rate determining unit, configured to determine the preset period visitor volume increase rate of the merchant according to the preset period visitor volume and the visitor volume in the previous preset period of the preset period in the user access data of the merchant;

[0209] An increase rate average value determining unit, configured to determine the average value of the preset period visitor volume increase rate of the merchant according to the preset period visitor volume increase rate of the merchant within the statistical period;

[0210] A visitor volume range determination unit, configured to determine the visitor volume range of the merchant during the statistical period according to the visitor volume in the preset period in the user access data of the merchant; and / or

[0211] A visitor volume average value determination unit, configured to determine the average value of the visitor volume in the preset period of the merchant according to the visitor volume in the preset period in the user access data of the merchant.

[0212] Optionally, the average increase rate determination unit is specifically configured to:

[0213] Determine the increase rate of the visitor volume when the merchant first shows an increase in the statistical period; and

[0214] Determine the average value of the increase rate of the visitor volume in the preset period of the merchant according to the increase rate of the visitor volume when the first increase occurs and the increase rate of the visitor volume after that increase rate.

[0215] Optionally, the visitor volume range determination unit is specifically configured to:

[0216] Determine the maximum value and the minimum value of the visitor volume in the preset period of the merchant during the statistical period according to the visitor volume in the preset period in the user access data of the merchant; wherein, the occurrence time of the maximum value is after the occurrence time of the minimum value, and the multiple of the maximum value to the average value of the visitor volume in the preset period is less than a preset multiple, and the minimum value has excluded the data when not in business; and

[0217] Determine the visitor volume range of the merchant during the statistical period according to the maximum value and the minimum value.

[0218] Optionally, the visitor volume average value determination unit is specifically configured to:

[0219] Determine the weight of each visitor volume in the preset period according to the chronological order of each visitor volume in the preset period of the merchant during the statistical period; and

[0220] Determine the average value of the visitor volume in the preset period of the merchant according to each visitor volume in the preset period and the corresponding weight.

[0221] Optionally, the calculation model setting module includes:

[0222] A first calculation model setting unit, configured to set the product of the average value of the visitor volume in the preset period, the visitor volume range, and the mention rate of the Internet celebrity keywords as the first calculation model for identifying Internet celebrity merchants according to the key calculation factors; and / or

[0223] A second calculation model setting unit, configured to set the product of the average value of the increase in the number of visitors in the preset period, the range of the number of visitors, and the mention rate of the Internet celebrity keywords as the second calculation model for identifying newly emerging Internet celebrity merchants according to the key calculation factors.

[0224] Optionally, the calculation result obtaining module includes:

[0225] A first Internet celebrity result obtaining unit, configured to calculate the product of the average value of the number of visitors in the preset period, the range of the number of visitors, and the mention rate of the Internet celebrity keywords for each merchant according to the first calculation model, and obtain the calculation result of each merchant as an Internet celebrity merchant; and / or

[0226] A first newly emerging Internet celebrity result obtaining unit, configured to calculate the product of the average value of the increase in the number of visitors in the preset period, the range of the number of visitors, and the mention rate of the Internet celebrity keywords for each merchant according to the second calculation model, and obtain the calculation result of each merchant as a newly emerging Internet celebrity merchant.

[0227] Optionally, the key calculation factors include: the mention rate of Internet celebrity keywords, the positive range of traffic, the negative range of traffic, the traffic growth trend, the average number of visitors in the preset period, and / or the quality weight, where the statistical period includes at least two preset periods.

[0228] Optionally, the data acquisition module includes:

[0229] An Internet celebrity keyword mention rate determination unit, configured to determine the number of comments including Internet celebrity keywords and not including Internet celebrity negative words according to the user comment data of the merchant, determine the total number of user comments, and determine the mention rate of the Internet celebrity keywords of the merchant according to the number of comments including Internet celebrity keywords and not including Internet celebrity negative words and the total number of user comments;

[0230] An extreme value determination unit, configured to determine the maximum value of the number of visitors in the preset period within the statistical period according to the user access data of the merchant, determine the minimum value of the number of visitors in the preset period that appears before the maximum value as the first minimum value, and determine the minimum value of the number of visitors in the preset period that appears after the maximum value as the second minimum value;

[0231] A range determination unit, configured to determine the positive range of traffic of the merchant according to the maximum value and the first minimum value, and use the difference between the maximum value and the second minimum value as the negative range of traffic of the merchant;

[0232] A traffic growth determination unit, configured to use the difference between the positive range of traffic and the negative range of traffic as the traffic growth trend of the merchant;

[0233] A visitor volume average determination unit, configured to determine the average value of the preset period visitor volume of the merchant according to the preset period visitor volume in the user access data of the merchant; and / or

[0234] A quality weight determination unit, configured to determine the quality weight of the merchant according to the comprehensive quality score and the number of comments of the merchant.

[0235] Optionally, the range determination unit includes:

[0236] An initial positive range determination subunit, configured to use the difference between the maximum value and the first minimum value as the initial positive range of the traffic of the merchant;

[0237] A comment statistics subunit, configured to count the number of comments containing Internet celebrity negative words in the user comment data of the merchant, and determine the total number of comments of the merchant in the statistical period;

[0238] A negative word proportion determination subunit, configured to use the ratio of the number of comments containing Internet celebrity negative words to the total number of comments as the proportion of Internet celebrity negative words corresponding to the merchant;

[0239] An average proportion determination subunit, configured to count the average value of the proportions of Internet celebrity negative words corresponding to all merchants; and

[0240] A positive range determination subunit, configured to perform a weight reduction process on the initial positive range of the traffic according to the proportion of Internet celebrity negative words corresponding to the merchant and the average value, to obtain the positive range of the traffic of the merchant.

[0241] Optionally, the quality weight determination unit is specifically configured to:

[0242] If the number of comments is greater than or equal to a preset comment threshold, use the comprehensive quality score of the merchant as the quality weight of the merchant;

[0243] If the number of comments is less than the preset comment threshold, use the product of the comprehensive quality score of the merchant and a preset coefficient as the quality weight of the merchant, where the preset coefficient is less than 1.

[0244] Optionally, the calculation model setting module includes:

[0245] A first model setting unit, configured to set the product of the average value of the preset period visitor volume, the traffic growth trend, the mention rate of Internet celebrity keywords, and the quality weight as a first calculation model for identifying Internet celebrity merchants according to the key calculation factors; and / or

[0246] The second model setting unit is used for the key calculation factor, and sets the product of the traffic growth trend, the Internet celebrity keyword mention rate and the quality weight as the second calculation model for identifying new Internet celebrity merchants.

[0247] Optionally, the calculation result obtaining module includes:

[0248] A second Internet celebrity result obtaining unit is used to calculate, for each of the merchants, the product of the average visitor volume in the preset period, the traffic growth trend, the Internet celebrity keyword mention rate and the quality weight according to the first calculation model, to obtain a calculation result of each merchant as an Internet celebrity merchant; and / or

[0249] The second new internet celebrity result obtaining unit is used to calculate, for each of the merchants, the product of the traffic growth trend, the internet celebrity keyword mention rate and the quality weight according to the second calculation model, to obtain the calculation result of each merchant as a new internet celebrity merchant.

[0250] Optionally, the Internet celebrity merchant determination module includes:

[0251] A first merchant determining unit, configured to determine merchants whose geographical locations are within a statistical area according to the geographical locations of the merchants;

[0252] A first sorting module is used to sort the merchants located in the statistical area according to the scores of the merchants located in the statistical area as Internet celebrity merchants from high to low; and

[0253] The Internet celebrity list generation module is used to determine that merchants that are ranked high and meet preset conditions are Internet celebrity merchants, and generate the Internet celebrity merchants into the Internet celebrity list within the statistical area.

[0254] Optionally, the Internet celebrity merchant determination module includes:

[0255] A second merchant determination module, configured to determine merchants whose geographical locations are within a statistical area according to the geographical locations of the merchants;

[0256] A second sorting module is used to sort the merchants located in the statistical area according to the scores of the merchants located in the statistical area as new Internet celebrity merchants from high to low;

[0257] A removal module is used to remove merchants that do not meet the conditions of new Internet celebrities from the merchants in the ranking; and

[0258] The module for generating a new Internet celebrity list is used to determine the merchants in the processed ranking that are ranked high and meet the preset conditions as new Internet celebrity merchants, and generate the new Internet celebrity merchants into the new Internet celebrity list in the statistical area.

[0259] Optionally, the merchants that do not meet the conditions of new Internet celebrities include one or more of brand chain stores, merchants with an average number of visitors per preset period greater than a preset value, and merchants on the Internet celebrity list.

[0260] Optionally, the statistical period of the Internet celebrity merchants is greater than that of the new Internet celebrity merchants.

[0261] The device for determining Internet celebrity merchants provided in the embodiments of the present application is used to implement the steps of the method for determining Internet celebrity merchants described in Embodiment 1 of the present application. For the specific implementation manners of the modules of the device, please refer to the corresponding steps, which will not be elaborated here.

[0262] The device for determining Internet celebrity merchants disclosed in the embodiments of the present application obtains user access data and user comment data of merchants within a statistical period through a data acquisition module, and obtains key calculation factors based on the user access data and the user comment data. A calculation model setting module sets a calculation model for identifying Internet celebrity merchants according to the key calculation factors. A calculation result obtaining module obtains a calculation result according to the calculation model. An Internet celebrity merchant determination module determines the merchant as an Internet celebrity merchant and / or a new Internet celebrity merchant according to the score ranking of the calculation result, realizing automatic identification of Internet celebrity merchants, no longer relying on manual identification, improving the identification efficiency, and determining whether a merchant is an Internet celebrity merchant based on the score ranking of each merchant, no longer relying on subjective human judgment, improving the accuracy of determining Internet celebrity merchants, and being able to identify new Internet celebrity merchants, reducing the lag of Internet celebrity merchant identification compared with manual judgment.

[0263] Correspondingly, the present application also discloses an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the method for determining Internet celebrity merchants as described in Embodiment 1 of the present application. The electronic device can be a PC, a mobile terminal, a personal digital assistant, a tablet computer, etc.

[0264] The present application also discloses a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the steps of the method for determining Internet celebrity merchants as described in Embodiment 1 of the present application.

[0265] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to describe the differences from other embodiments. The same or similar parts among the embodiments can be referred to each other. For the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, please refer to the partial description of the method embodiments.

[0266] The above has introduced in detail a method, device, electronic device and storage medium for determining Internet celebrity merchants provided by the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

[0267] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disc, etc., including several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

Claims

1. A method for determining an Internet celebrity merchant, characterized in that, Including: Obtain the user access data and user comment data of merchants within a statistical period, and obtain key calculation factors based on the user access data and the user comment data. The key calculation factors include: the mention rate of internet celebrity keywords, the increase rate of visitor volume in a preset period, the average value of the increase rate of visitor volume in a preset period, the range of visitor volume, and / or the average value of visitor volume in a preset period, where the statistical period includes at least two preset periods; Set a calculation model for identifying internet celebrity merchants according to the key calculation factors, including: setting the product of the average value of visitor volume in the preset period, the range of visitor volume, and the mention rate of internet celebrity keywords as the first calculation model for identifying internet celebrity merchants according to the key calculation factors; and / or setting the product of the average value of the increase rate of visitor volume in the preset period, the range of visitor volume, and the mention rate of internet celebrity keywords as the second calculation model for identifying newly emerging internet celebrity merchants according to the key calculation factors; Obtain a calculation result according to the calculation model, the user access data, and the user comment data, including: for each merchant, calculate the product of the average value of visitor volume in the preset period, the range of visitor volume, and the mention rate of internet celebrity keywords according to the first calculation model to obtain the calculation result of each merchant as an internet celebrity merchant; and / or for each merchant, calculate the product of the average value of the increase rate of visitor volume in the preset period, the range of visitor volume, and the mention rate of internet celebrity keywords according to the second calculation model to obtain the calculation result of each merchant as a newly emerging internet celebrity merchant; and Determine the merchant as an internet celebrity merchant and / or a newly emerging internet celebrity merchant according to the score ranking of the calculation result.

2. The method according to claim 1, characterized in that, Before the step of obtaining the key calculation factors according to the user access data and the user comment data, it further includes: Determine the merchants that meet the preliminary screening conditions according to the user access data and the user comment data, where the preliminary screening conditions include: the number of comments including internet celebrity keywords in the user comment data is greater than or equal to a quantity threshold, and the average value of visitor volume in the preset period in the user access data is greater than or equal to a visitor volume threshold.

3. The method according to claim 2, characterized in that, Before the step of determining the merchants that meet the preliminary screening conditions according to the user access data and the user comment data, it further includes: Filter out the access data with integrity determination cheating in the user access data; Use the access data including access to a preset page in the filtered user access data as valid user access data.

4. The method according to claim 1, characterized in that, The step of obtaining the key calculation factors according to the user access data and the user comment data includes: Determine the number of comments including internet celebrity keywords according to the user comment data of the merchant, determine the total number of user comments, and determine the mention rate of internet celebrity keywords of the merchant according to the number of comments including internet celebrity keywords and the total number of user comments; Determine the increase rate of visitor volume in the preset period of the merchant according to the visitor volume in the preset period and the visitor volume in the previous preset period of the preset period in the user access data of the merchant; Determine the average value of the preset-period visitor volume increase rate of the merchant according to the preset-period visitor volume increase rate of the merchant within the statistical period; Determine the range of the visitor volume of the merchant within the statistical period according to the preset-period visitor volume in the user access data of the merchant; and / or Determine the average value of the preset-period visitor volume of the merchant according to the preset-period visitor volume in the user access data of the merchant.

5. The method according to claim 4, characterized in that, The step of determining the average value of the preset-period visitor volume increase rate of the merchant according to the preset-period visitor volume increase rate of the merchant within the statistical period includes: Determine the visitor volume increase rate when the first growth increase occurs for the merchant within the statistical period; and Determine the average value of the preset-period visitor volume increase rate of the merchant according to the visitor volume increase rate when the first growth increase occurs and the visitor volume increase rates after that visitor volume increase rate.

6. The method according to claim 4, characterized in that, The step of determining the range of the visitor volume of the merchant within the statistical period according to the preset-period visitor volume in the user access data of the merchant includes: Determine the maximum value and the minimum value of the preset-period visitor volume of the merchant within the statistical period according to each preset-period visitor volume in the user access data of the merchant; wherein, the occurrence time of the maximum value is after the occurrence time of the minimum value, and the multiple of the maximum value to the average value of the preset-period visitor volume is less than or equal to the first preset multiple, and the minimum value has excluded the data when not in business; and Determine the range of the visitor volume of the merchant within the statistical period according to the maximum value and the minimum value.

7. The method according to claim 4, characterized in that, The step of determining the average value of the preset-period visitor volume of the merchant according to the preset-period visitor volume in the user access data of the merchant includes: Determine the weight of each preset-period visitor volume according to the chronological order of each preset-period visitor volume of the merchant within the statistical period; and Determine the average value of the preset-period visitor volume of the merchant according to each preset-period visitor volume and the corresponding weight.

8. The method according to claim 1, characterized in that, The key calculation factors include: the mention rate of internet celebrity keywords, the positive range of traffic, the negative range of traffic, the traffic growth trend, the average value of the preset-period visitor volume, and / or the quality weight, wherein the statistical period includes at least two preset periods.

9. The method according to claim 8, characterized in that, The step of obtaining the key calculation factors according to the user access data and the user comment data includes: Determine the number of comments that include internet celebrity keywords and do not include internet celebrity negative words according to the user comment data of the merchant, determine the total number of user comments, and determine the mention rate of the internet celebrity keywords of the merchant according to the number of comments that include internet celebrity keywords and do not include internet celebrity negative words and the total number of user comments; Determine the maximum value of the preset-period visitor volume within the statistical period according to the user access data of the merchant, determine the minimum value of the preset-period visitor volume that appears before the maximum value as the first minimum value, and determine the minimum value of the preset-period visitor volume that appears after the maximum value as the second minimum value; Determine the positive traffic range of the merchant according to the maximum value and the first minimum value, and use the difference between the maximum value and the second minimum value as the negative traffic range of the merchant; Use the difference between the positive traffic range and the negative traffic range as the traffic growth trend of the merchant; Determine the average value of the preset period visitor volume in the user access data of the merchant; and / or Determine the quality weight of the merchant according to the comprehensive quality score and the number of comments of the merchant.

10. The method according to claim 9, wherein The step of determining the positive traffic range of the merchant according to the maximum value and the first minimum value includes: Use the difference between the maximum value and the first minimum value as the initial positive traffic range of the merchant; Count the number of comments containing negative influencer words in the user comment data of the merchant, and determine the total number of comments of the merchant in the statistical period; Use the ratio of the number of comments containing negative influencer words to the total number of comments as the proportion of negative influencer words corresponding to the merchant; Count the average value of the proportions of negative influencer words corresponding to all merchants; and Perform a deweighting process on the initial positive traffic range according to the proportion of negative influencer words corresponding to the merchant and the average value to obtain the positive traffic range of the merchant.

11. The method according to claim 9, wherein The step of determining the quality weight of the merchant according to the comprehensive quality score and the number of comments of the merchant includes: If the number of comments is greater than or equal to the preset comment threshold, use the comprehensive quality score of the merchant as the quality weight of the merchant; If the number of comments is less than the preset comment threshold, use the product of the comprehensive quality score of the merchant and a preset coefficient as the quality weight of the merchant, where the preset coefficient is less than 1.

12. The method according to claim 9, wherein The step of setting a calculation model for identifying influencer merchants according to the key calculation factors includes: According to the key calculation factors, set the product of the average value of the preset period visitor volume, the traffic growth trend, the mention rate of influencer keywords, and the quality weight as the first calculation model for identifying influencer merchants; and / or According to the key calculation factors, set the product of the traffic growth trend, the mention rate of influencer keywords, and the quality weight as the second calculation model for identifying newly emerging influencer merchants.

13. The method according to claim 12, wherein The step of obtaining a calculation result according to the calculation model, the user access data, and the user comment data includes: For each merchant, calculate the product of the average value of the preset period visitor volume, the traffic growth trend, the mention rate of influencer keywords, and the quality weight according to the first calculation model to obtain the calculation result of each merchant as an influencer merchant; and / or For each merchant, calculate the product of the traffic growth trend, the mention rate of influencer keywords, and the quality weight according to the second calculation model to obtain the calculation result of each merchant as a newly emerging influencer merchant.

14. The method according to claim 1, wherein The step of determining that the merchant is an influencer merchant according to the score ranking of the calculation result includes: Determine the merchants whose geographical locations are within the statistical area according to the geographical location of the merchant; Sorting the merchants located in the statistical area according to the scores of the merchants located in the statistical area as Internet celebrity merchants from high to low; and Merchants that are ranked high and meet preset conditions are determined to be Internet celebrity merchants, and the Internet celebrity merchants are generated into an Internet celebrity list within the statistical area.

15. The method according to claim 1, wherein The step of determining the merchant as a new internet celebrity merchant according to the score ranking of the calculation results comprises: Determine merchants whose geographical locations are within the statistical area according to the geographical locations of the merchants; Sorting the merchants located in the statistical area according to the scores of the merchants located in the statistical area as new internet celebrity merchants from high to low; For the merchants in the ranking, those merchants that do not meet the criteria for new internet celebrities are eliminated; and For the merchants in the processed ranking, merchants that are ranked high and meet preset conditions are determined to be new Internet celebrity merchants, and the new Internet celebrity merchants are generated into a new Internet celebrity list in the statistical area.

16. The method according to claim 15, wherein The merchants that do not meet the conditions for becoming new Internet celebrities include one or more of brand chain stores, merchants whose average visitor volume in a preset period is greater than a preset value, and merchants on the Internet celebrity list.

17. The method according to claim 1, wherein The statistical period of the Internet celebrity merchants is greater than the statistical period of the new Internet celebrity merchants.

18. An apparatus for determining an internet celebrity merchant, wherein include: A data acquisition module, used to acquire user access data and user comment data of merchants within a statistical period, and obtain key calculation factors according to the user access data and the user comment data, wherein the key calculation factors include: the mention rate of Internet celebrity keywords, the increase in visitor volume in a preset period, the average value of the increase in visitor volume in a preset period, the extreme difference in visitor volume and / or the average value of visitor volume in a preset period, wherein the statistical period includes at least two preset periods; A calculation model setting module is used to set a calculation model for identifying Internet celebrity merchants according to the key calculation factors, specifically to set the product of the average visitor volume in the preset period, the extreme difference of the visitor volume and the Internet celebrity keyword mention rate as a first calculation model for identifying Internet celebrity merchants according to the key calculation factors; and / or, according to the key calculation factors, to set the product of the average visitor volume increase in the preset period, the extreme difference of the visitor volume and the Internet celebrity keyword mention rate as a second calculation model for identifying new Internet celebrity merchants; A calculation result obtaining module, used to obtain the calculation result according to the calculation model, the user access data and the user comment data, specifically used to calculate, for each of the merchants, the product of the average visitor volume in the preset period, the range of the visitor volume and the mention rate of the Internet celebrity keyword according to the first calculation model, to obtain the calculation result of each merchant as an Internet celebrity merchant; and / or for each of the merchants, the product of the average visitor volume increase in the preset period, the range of the visitor volume and the mention rate of the Internet celebrity keyword according to the second calculation model, to obtain the calculation result of each merchant as a newly promoted Internet celebrity merchant; and The Internet celebrity merchant determination module is used to determine whether the merchant is an Internet celebrity merchant and / or a new Internet celebrity merchant according to the score ranking of the calculation result.

19. The device according to claim 18, wherein, The device also includes: The merchant preliminary screening module is used to determine merchants that meet the preliminary screening conditions according to the user access data and user review data, where the preliminary screening conditions include: the number of reviews including internet celebrity keywords in the user review data is greater than or equal to a quantity threshold, and the average number of visitors in a preset period in the user access data is greater than or equal to a visitor volume threshold.

20. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, When the processor executes the computer program, it implements the method for determining internet celebrity merchants according to any one of claims 1 to 17.

21. A computer-readable storage medium, having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the steps of the method for determining internet celebrity merchants according to any one of claims 1 to 17.

Images