Item attention tracking system and method based on user behavior analysis

Abstract

The application discloses a kind of commodity attention tracking system and method based on user behavior analysis, it is related to computer data analysis technical field, obtain the browsing record of each network account in browsing record sequence, the time proportion of different commodity attribute introduction content that network account browses same commodity is taken as the browsing feature of network account, the average residence time of sharing link in browsing record sequence is calculated, the history record of target user sharing commodity is obtained, the network account of target user sending sharing link in history record is gathered to introduction content, obtain all the browsing record sequence of target contact person, the difference of browsing feature and average residence time are used to evaluate each browsing feature of target contact person, according to the proportion of each commodity attribute introduction content in the introduction content of the sharing commodity to be shared, contact is matched, the contact matched is sorted by average residence time, and the sequence of recommended sharing is obtained.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer data analysis, in particular to a product attention tracking system and method based on user behavior analysis. BACKGROUND

[0002] With the development of Internet technology, more and more product recommendation businesses are transferred online, and related business tasks are promoted by sending product links. Different network users accept product link information by viewing notification prompts in application software, and product links are also easier to share among network users, that is, product links can be secondarily spread among other network users without the management of the initial sharer. Such technology greatly improves the promotion efficiency of product information.

[0003] However, at the same time, due to the existence of link sharing without the knowledge of the initial sharer, the initial sharer is difficult to evaluate the sharing process of the link, which is not conducive to the initial sharer to evaluate the acceptance degree of the product by the viewer. The initial sharer is also difficult to make a judgment on the pertinence of information sharing. SUMMARY

[0004] The purpose of the present application is to provide a product attention tracking system and method based on user behavior analysis to solve the problems in the prior art.

[0005] To achieve the above purpose, the present application provides the following technical scheme: a product attention tracking method based on user behavior analysis, the method comprising:

[0006] Step S100: according to the product attribute of the product, the introduction content of the product is classified and collected, the introduction content corresponding to several products and merchants is collected to establish a product database, and the sharing link corresponding to each product in the product database is set;

[0007] Step S200: taking a user of the product database as a target user, the target user sends the sharing link to a network account through the network, the network account sends the sharing link to another network account, the propagation order of the same sharing link in several network accounts is obtained, the account that orders the product is taken as the last network account, and the network accounts are arranged into a browsing record sequence according to the propagation order;

[0008] Step S300: obtaining the browsing record of each network account in the browsing record sequence, recording the time used by the network account to browse the introduction content of different product attributes, taking the time proportion of the network account to browse the introduction content of different product attributes of the same product as the browsing feature of the network account, and comparing the difference between the browsing feature of the last network account in the target sequence and the target sequence;

[0009] Step S400: collect the propagation time of the sharing link in the browsing record sequence, obtain the length of the browsing record sequence, and calculate the average residence time of the sharing link in each browsing record sequence;

[0010] Step S500: obtain the history record of the target user sharing the goods, collect the network accounts of the target user sending the sharing link in the history record into the introduction content, take a contact in the sharing contact set of the target user as a target contact, obtain all browsing record sequences of the target contact, classify the browsing record sequences according to the browsing features, and evaluate the browsing features of the target contact according to the differences of the browsing features and the average residence time;

[0011] Step S600: the target user selects a kind of goods from the goods database as a to-be-shared good, matches the contacts according to the proportion of each good attribute introduction content in the introduction content of the to-be-shared good, sorts the matched contacts according to the average residence time, and obtains the recommended sharing sequence.

[0012] Further, step S200 includes:

[0013] Step S201: take a good in the goods database as a target good, and obtain the introduction content of the target good;

[0014] Step S202: take a sharing link shared by the target user as a target link, and record that the target link is shared from one account to another account as one propagation;

[0015] Step S203: arrange the network accounts viewing the target good according to the propagation order of the target link, record the account purchasing the target good as the last network account, and compose a target sequence with all the network accounts from the first account shared by the target user to the last network account.

[0016] Further, step S300 includes:

[0017] Step S301: obtain the i-th account Ui in the target sequence, obtain the total time ta of the account Ui browsing the introduction content of the target good in the target sequence, obtain the k-th introduction content in the introduction content of the target good, take the k-th good attribute as qk, obtain the time tk of the user Ui browsing the k-th introduction content, calculate the feature value aik of the account Ui browsing the k-th good attribute corresponding introduction content, and aik= tk / ta;

[0018] Step S302: combine the commodity attributes with the corresponding feature values to obtain the feature values corresponding to the kth numerical value to obtain the evaluation group (qk, aik), respectively acquire the account Ui reading all the feature values of the commodity attributes, and collect the evaluation groups corresponding to the respective feature values to obtain the user reading record list of the account Ui;

[0019] Step S303: collect the feature values of the target commodity corresponding to the same commodity attribute, calculate the average value of the feature values of the same commodity attribute, and integrate the respective commodity attributes and the corresponding average values into the reference state list to obtain the commodity attributes in the reference state list integrated into the reference attribute set R1;

[0020] Step S304: acquire the user reading record list of the last account in the target sequence, collect the commodity attributes in the user reading record list into the target attribute set R2, acquire the same commodity attributes as the comparison attributes from R1, acquire the average values corresponding to the comparison attributes from the reference state list, and integrate the comparison attributes and the corresponding average values into the comparison set. The arrangement order of the commodity attributes in the comparison set is the same as that in the target attribute set R2;

[0021] Step S305: calculate the difference value w of the target attribute set R2 and the comparison set, wherein q 1 p1 q 2 p1 q

[0022] The same sharing link is transmitted between the network accounts, the network accounts are sorted, the first network account in a sequence is the network account directly receiving the sharing link sent by the target user, and the last network account is the network account purchasing the link corresponding commodity;

[0023] The purpose of the sharing link is to find a suitable buyer. After the transaction is completed, the attribute of the commodity introduction information browsed by the buyer is marked, and the browsing record sequence is marked. The mark corresponding to the browsing record sequence is the commodity attribute browsed by the last network account and the corresponding time proportion;

[0024] Each network account in the browsing record sequence browses the commodity. By comparing the commodity attribute browsed by the last network account and the corresponding time proportion with the average value of the commodity attribute browsed by the network account in the sequence and the corresponding time proportion, the difference between the demand of the last network account and the average demand in the sequence is obtained;

[0025] The higher the difference degree is, the lower the targeting of the sharing process is, and the lower the difference degree is, the stronger the targeting of the sharing process is. The targeting of a browsing record sequence is measured by the commodity attribute, the corresponding time proportion and the difference value.

[0026] Further, the step S400 comprises:

[0027] Step S401: Linking the target received by an account to the time length of sharing the target link as the retention time, calculating the total length of the retention time in the target sequence, and recording the total length as T;

[0028] Step S402: Obtaining the user reading record list of all accounts in the target sequence, and counting the number of user reading record lists in all user reading record lists that are the same as the user reading record list of the account Ui, and recording the number as M;

[0029] Step S403: Calculate the retention index γ of the target sequence, γ=N×lg(M×T), wherein N represents the number of times of propagation of the target link in the target sequence, and lg represents the logarithmic function with 10 as the base;

[0030] The browsing features of the last network account in the browsing sequence are taken as the reference standard, and the number of times that such features appear in the browsing record sequence is searched. The more the number of times is, the more mediocre the attribute features of the commodity are. After the network accounts with the same needs browse for many times, someone is willing to place an order. When the number of times is small, the commodity is attractive to customers with certain needs;

[0031] N and T measure the distance of the browsing record sequence from two different angles. N represents the order of the browsing record sequence, and T represents the time span. Therefore, in terms of sharing and transaction efficiency of commodities, the smaller the retention index γ value is, the stronger the sharing link propagation efficiency is.

[0032] Further, the step S500 comprises:

[0033] Step S501: Obtain all transaction record sequences of the target contact, take the user reading record list of the last account in the target sequence as the target feature, obtain all transaction record sequences in which the user reading record list of the last account is the same as the target feature, and collect the transaction record sequences into a feature record set;

[0034] Step S502: Obtain the difference value and the retention index of each browsing record sequence in the feature record set, record the average value of the difference value as the first evaluation coefficient, and record the average value of the retention index as the second evaluation coefficient;

[0035] Step S503: taking the user reading record list of the last account of the target sequence as the feature label of the target sequence, and collecting the feature label, the first evaluation coefficient and the second evaluation coefficient to form an evaluation group;

[0036] Step S504: collecting the evaluation groups corresponding to all feature labels of the target contact to obtain an evaluation database of the target contact.

[0037] Further, step S600 includes:

[0038] Step S601: obtaining the product introduction content of the to-be-shared product, collecting all feature words of the product introduction content to form a set D0, and collecting the feature words corresponding to the e-th product attribute of the to-be-shared product to form a set De according to the product attributes;

[0039] Step S602: calculating the attribute proportion αe of the e-th product attribute, αe = num(De) / num(D0), wherein num is a function of obtaining the number of feature words in the set;

[0040] Step S603: collecting the product attributes of the to-be-shared product and the corresponding attribute proportions to form an attribute label;

[0041] Step S604: obtaining the evaluation group corresponding to the feature label same as the attribute label, and collecting all evaluation groups into a first to-be-shared set;

[0042] Step S605: setting a judgment threshold F, collecting the evaluation groups with the first evaluation coefficient less than F in the first to-be-shared set into a second to-be-shared set, and sorting the second to-be-shared set according to the order of the second evaluation coefficient from small to large to obtain a third sharing set;

[0043] Step S606: obtaining the account groups of the evaluation groups in the third sharing set in sequence to form a contact sequence, and pushing the contact sequence to the target user.

[0044] In order to better realize the above method, a product attention degree tracking system based on user behavior analysis is also proposed, and the system includes:

[0045] The commodity management module, the browsing record sequence management module, the difference comparison module, the retention time management module, the feature evaluation module and the recommendation sorting module, wherein the commodity management module is used for managing the commodity information and the correspondence between the sharing link of the commodity and the commodity, the browsing record sequence management module is used for obtaining the propagation record of the sharing link, and the network accounts are composed into a browsing record sequence according to the propagation order of the sharing link, the difference comparison module is used for comparing the difference between the last network account in the target sequence and the browsing feature of the target sequence, the retention time management module is used for calculating the average retention time of the sharing link in each browsing record sequence, the feature evaluation module is used for evaluating the browsing record sequence corresponding to the target contact, and the recommendation sorting module is used for analyzing the introduction content of the commodity, sorting the matched contacts, and obtaining the recommended sharing sequence.

[0046] Further, the browsing record sequence management module comprises an introduction content management unit, a propagation record management unit and a browsing record sequence management unit, wherein the introduction content management unit is used for managing the introduction content of the commodity, the propagation record management unit is used for managing the propagation record of the sharing link, and the browsing record sequence management unit is used for capturing the transaction record of the commodity to obtain the browsing record sequence.

[0047] Further, the difference comparison module comprises a feature value calculation unit, a user reading record management unit, a comparison management unit and a difference value calculation unit, wherein the feature value calculation unit is used for obtaining the browsing time of the introduction content corresponding to each commodity attribute, calculating the feature value of the corresponding type of introduction content, the user reading record management unit is used for collecting the evaluation groups corresponding to each feature value to obtain a user reading record list, the comparison management unit is used for selecting the average browsing proportion of the corresponding type from the target sequence according to the type of the introduction content browsed by the last account in the target sequence, and the difference value calculation unit is used for calculating the difference value between the target attribute set and the comparison set.

[0048] Further, the retention time management module comprises a time acquisition unit, a repetition detection unit and a retention index calculation unit, wherein the time acquisition unit is used for acquiring the retention time in any two network accounts, the repetition detection unit is used for detecting the repetition number of the user reading record list corresponding to the last network account in the target sequence, and the retention index calculation unit is used for calculating the retention index of the target sequence.

[0049] Further, the feature evaluation module comprises an evaluation coefficient management unit, an evaluation group management unit and an evaluation database management unit, wherein the evaluation coefficient management unit is used for acquiring the first evaluation coefficient and the second evaluation coefficient, the evaluation group management unit is used for collecting the feature label, the first evaluation coefficient and the second evaluation coefficient to form an evaluation group, and the evaluation database management unit is used for managing the evaluation database of the target contact.

[0050] Further, the recommendation sorting module comprises an attribute analysis unit, a feature matching unit, a threshold judgment unit and a sorting and pushing unit, wherein the attribute analysis unit is configured to analyze attribute proportions of various product attributes in product introduction content, the feature matching unit is configured to manage the first to-be-shared set, the threshold judgment unit is configured to manage the second to-be-shared set, and the sorting and pushing unit is configured to manage the third to-be-shared set and perform contact order pushing to the target user.

[0051] Compared with the prior art, the present application has the beneficial effects that: the propagation state of the sharing link of the product is captured, the propagation effect of the sharing link is measured by measuring the reading of the product introduction content by the network account after receiving the sharing link, the propagation effect of the product link is evaluated and analyzed under the condition of avoiding the acquisition of the personal privacy information of the network account as much as possible, the product promotion business data is enriched, and the decision on the product promotion is effectively fed back. BRIEF DESCRIPTION OF DRAWINGS

[0052] Figure 1 FIG. 1 is a structural schematic diagram of a product attention tracking system based on user behavior analysis according to the present application;

[0053] Figure 2 FIG. 2 is a flowchart of a product attention tracking method based on user behavior analysis according to the present application. DETAILED DESCRIPTION

[0054] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0055] Embodiment: As shown in FIGS. 1 and 2, the present application provides a technical solution, a product attention tracking method based on user behavior analysis: Figure 1 and Figure 2

[0056] Step S100: according to the product attributes of the product, the introduction content of the product is classified and collected, the introduction content corresponding to several products and merchants is collected to establish a product database, and the sharing link corresponding to each product in the product database is set;

[0057] ​Step S200: take a user of the commodity database as a target user, the target user sends a sharing link to a network account through a network, the network account sends the sharing link to another network account, obtain the propagation order of the same sharing link in several network accounts, take the account that orders the commodity as the last network account, arrange the network accounts in the propagation order into a browsing record sequence;

[0058] In an embodiment, the target user is a direct promoter or a seller of the commodity, and the network account is a network user in a role of a distributor or a customer participating in the sales.

[0059] Step S200 includes:

[0060] Step S201: take a commodity in the commodity database as a target commodity, and obtain introduction content of the target commodity;

[0061] Step S202: take a sharing link shared by the target user as a target link, and take sharing of the target link from one account to another account as one propagation;

[0062] Step S203: arrange the network accounts that view the target commodity according to the propagation order of the target link, take the account that purchases the target commodity as the last network account, and form a target sequence with all the network accounts from the first account shared by the target user to the last network account.

[0063] Step S300: obtain browsing records of each network account in the browsing record sequence, record the time used by the network account to browse introduction content of different commodity attributes, take the time proportion of the network account to browse the introduction content of the same commodity attribute of the target commodity as a browsing feature of the network account, and compare the difference between the browsing feature of the last network account in the target sequence and the target sequence;

[0064] Step S300 includes:

[0065] Step S301: obtain an i-th account Ui in the target sequence, obtain total time ta of the account Ui to browse the introduction content of the target commodity in the target sequence, obtain a k-th introduction content in the introduction content of the target commodity, take the k-th commodity attribute as qk, obtain time tk of the user Ui to browse the k-th introduction content, calculate a feature value αik of the account Ui to browse the introduction content corresponding to the k-th commodity attribute, and αik= tk / ta;

[0066] Step S302: combine the commodity attribute and the corresponding feature value to obtain an evaluation group (qk, αik) corresponding to the k-th numerical value, obtain the feature value of the account Ui to read all the commodity attributes respectively, and collect the evaluation groups corresponding to the feature values to obtain a user reading record list of the account Ui.

[0067] Step S303: The feature values of the target commodity corresponding to the same commodity attribute are collected, the average value of the same commodity attribute feature value is calculated, each commodity attribute and the corresponding average value are merged into the reference state list, and the commodity attributes in the reference state list are merged into the reference attribute set R1;

[0068] Step S304: The user reading record list of the last account in the target sequence is obtained, the commodity attributes in the user reading record list are collected into the target attribute set R2, the same commodity attributes as R2 are obtained from R1 as comparison attributes, the average values corresponding to the comparison attributes are obtained from the reference state list, and the comparison attributes and the corresponding average values are merged into the comparison set. The arrangement order of the commodity attributes in the comparison set is the same as that in the target attribute set R2.

[0069] Step S305: The difference value w between the target attribute set R2 and the comparison set is calculated, Wherein, q 1 p1 q p1 represents the average value corresponding to the p1th commodity attribute in the comparison set, q 2 p1 The feature value corresponding to the p1th commodity attribute in the target attribute set R2, and p2 represents the number of commodity attributes in the target attribute set R2.

[0070] Step S400: The propagation time of the sharing link in the browsing record sequence is collected, the length of the browsing record sequence is obtained, and the average residence time of the sharing link in each browsing record sequence is calculated.

[0071] Wherein, step S400 includes:

[0072] Step S401: The time length from when a certain account receives a target link to when the target link is shared out is recorded as the residence time, the total duration of the residence time in the target sequence is calculated, and the total duration is recorded as T.

[0073] Step S402: The user reading record list of all accounts in the target sequence is obtained, and the number of user reading record lists in all user reading record lists that are the same as the user reading record list of the account Ui is counted, and the number is recorded as M.

[0074] Step S403: The residence index γ of the target sequence is calculated, γ=N×lg(M×T), wherein N represents the number of times of propagation of the target link in the target sequence, and lg represents the logarithmic function with 10 as the base.

[0075] Step S500: Obtain the history record of the target user sharing the goods, collect the network accounts of the target user sending the sharing link in the history record into the introduction content, take a contact in the sharing contact set of the target user as a target contact, obtain all the browsing record sequences of the target contact, classify the browsing record sequences according to the browsing features, and evaluate the browsing features of the target contact according to the differences of the browsing features and the average dwell time;

[0076] Step S500 includes:

[0077] Step S501: Obtain all the transaction record sequences of the target contact, take the user reading record list of the last account in the target sequence as a target feature, obtain the transaction record sequences in which the user reading record list of the last account is the same as the target feature, and collect the transaction record sequences into a feature record set;

[0078] Step S502: Obtain the difference value and the dwell index of each browsing record sequence in the feature record set, take the average value of the difference value as a first evaluation coefficient, and take the average value of the dwell index as a second evaluation coefficient;

[0079] Step S503: Take the user reading record list of the last account in the target sequence as a feature label of the target sequence, and collect the feature label, the first evaluation coefficient and the second evaluation coefficient to form an evaluation group;

[0080] Step S504: Collect all the evaluation groups corresponding to the feature labels of the target contact to obtain an evaluation database of the target contact.

[0081] Step S600: The target user selects a kind of goods from the goods database as a to-be-shared good, matches the contacts according to the proportion of each goods attribute introduction content in the introduction content of the to-be-shared good, sorts the matched contacts according to the average dwell time, and obtains a recommended sharing sequence;

[0082] Step S601: Obtain the goods introduction content of the to-be-shared good, collect all the feature words of the goods introduction content into a set D0, collect the feature words according to the goods attributes, and take the set of the feature words corresponding to the e-th goods attribute of the to-be-shared good as De;

[0083] Step S602: Calculate the attribute proportion ae of the e-th goods attribute, ae=num(De) / num(D0), wherein num is a function of obtaining the number of feature words in the set;

[0084] Step S603: Collect the goods attributes of the to-be-shared good and the corresponding attribute proportions to form an attribute label;

[0085] Step S604: Obtain the evaluation groups corresponding to the feature tags same as the attribute tags, and merge all the evaluation groups into a first to-be-shared set;

[0086] One contact corresponds to multiple evaluation groups, and each evaluation group evaluates the sales management situation of the contact when the commodity has a certain feature. Through analysis of the introduction content of the newly added commodity, the contact meeting the feature of the newly added commodity is screened out, and the contact is sorted according to the propagation efficiency corresponding to the feature of the commodity;

[0087] Step S605: Set a judgment threshold F, and merge the evaluation groups with the first evaluation coefficient less than F in the first to-be-shared set into a second to-be-shared set. The second to-be-shared set is sorted according to the order of the second evaluation coefficient from small to large, and a third sharing set is obtained.

[0088] Step S606: Obtain the account groups of each evaluation group in the third sharing set in sequence to form a contact sequence, and push the contact sequence to the target user.

[0089] The product attention tracking system based on user behavior analysis includes a product management module, a browsing record sequence management module, a difference comparison module, a retention time management module, a feature evaluation module, and a recommendation sorting module.

[0090] The product management module is used to manage the product information and the correspondence between the sharing link of the product and the product.

[0091] The browsing record sequence management module is used to obtain the propagation record of the sharing link, and the network accounts are grouped into a browsing record sequence according to the propagation order of the sharing link. The browsing record sequence management module includes an introduction content management unit, a propagation record management unit, and a browsing record sequence management unit. The introduction content management unit is used to manage the introduction content of the product. The propagation record management unit is used to manage the propagation record of the sharing link. The browsing record sequence management unit is used to capture the transaction record of the product to obtain the browsing record sequence.

[0092] The difference comparison module is used to compare the difference between the last network account in the target sequence and the browsing feature of the target sequence. The difference comparison module includes a feature value calculation unit, a user reading record management unit, a comparison management unit, and a difference value calculation unit. The feature value calculation unit is used to obtain the browsing time of the introduction content corresponding to each product attribute, calculate the feature value of the corresponding type of introduction content, and collect the evaluation groups corresponding to each feature value to obtain a user reading record list. The comparison management unit is used to select the average browsing proportion of the corresponding type from the target sequence according to the type of the introduction content browsed by the last account in the target sequence. The difference value calculation unit is used to calculate the difference value between the target attribute set and the comparison set.

[0093] The retention time management module is configured to calculate the average retention time of the sharing links in each browsing record sequence, and the feature evaluation module is configured to evaluate the browsing record sequence corresponding to the target contact, wherein the retention time management module comprises a time collection unit, a repetition detection unit and a retention index calculation unit, the time collection unit is configured to collect the retention time of any two network accounts, the repetition detection unit is configured to detect the repetition number of the user reading record list corresponding to the last network account in the target sequence, and the retention index calculation unit is configured to calculate the retention index of the target sequence.

[0094] The feature evaluation module is configured to evaluate the browsing record sequence corresponding to the target contact, wherein the feature evaluation module comprises an evaluation coefficient management unit, an evaluation group management unit and an evaluation database management unit, the evaluation coefficient management unit is configured to collect the first evaluation coefficient and the second evaluation coefficient, the evaluation group management unit is configured to collect the feature label, the first evaluation coefficient and the second evaluation coefficient to form an evaluation group, and the evaluation database management unit is configured to manage the evaluation database of the target contact.

[0095] The recommendation sorting module is configured to analyze the introduction content of the goods, sort the matched contacts, and obtain the sequence of recommended sharing, wherein the recommendation sorting module comprises an attribute analysis unit, a feature matching unit, a threshold judgment unit and a sorting pushing unit, the attribute analysis unit is configured to analyze the attribute proportion of various goods attributes in the goods introduction content, the feature matching unit is configured to manage the first sharing set, the threshold judgment unit is configured to manage the second sharing set, and the sorting pushing unit is configured to manage the third sharing set and push the contact sequence to the target user.

[0096] It is apparent for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, but can be implemented in other concrete forms without departing from the spirit or essential characteristics of the present application. Therefore, the embodiments should be considered in all aspects as illustrative and not restrictive, and the scope of the present application is defined by the appended claims rather than the above description, and all changes falling within the meaning and range of the equivalent elements of the claims are intended to be embraced in the present application. Any reference signs in the claims should not be considered as limiting the claims involved.

Claims

1. A product attention tracking method based on user behavior analysis, characterized by: The method comprises the following steps: Step S100: Classify and aggregate the product descriptions based on the product attributes, aggregate the descriptions of several products and merchants to establish a product database, and set a sharing link corresponding to each product in the product database; Step S200: A user in the product database is used as the target user. The target user sends a sharing link to a certain online account via the network. The certain online account sends the sharing link to another online account. The order in which the same sharing link is propagated across the multiple online accounts is obtained. The account that placed the product order is used as the last online account. The online accounts are arranged into a browsing record sequence according to the propagation order. Step S300: Obtaining the browsing history of each network account in the browsing history sequence, recording the time the network account spent browsing the introduction content of different product attributes, and using the proportion of time the network account spent browsing the introduction content of different product attributes for the same product as the browsing characteristics of the network account. Comparing the differences in the browsing characteristics between the last network account in the target sequence and the target sequence; Step S400: collecting the propagation time of the shared links in the browsing record sequence, obtaining the length of the browsing record sequence, and calculating the average retention time of the shared links in each browsing record sequence; Step S500: Obtain the target user's product sharing history, aggregate the target user's network accounts that sent sharing links in the history into the introduction content, select a contact in the target user's sharing contact set as the target contact, obtain all browsing history sequences of the target contact, classify the browsing history sequences according to browsing characteristics, and evaluate the various browsing characteristics of the target contact based on the differences in browsing characteristics and average dwell time; Step S600: The target user selects a product from the product database as the product to be shared, matches contacts based on the proportion of each product attribute introduction content in the introduction content of the product to be shared, and sorts the matched contacts by average residence time to obtain a recommended sharing sequence.

2. The method for tracking product attention based on user behavior analysis according to claim 1, characterized in that: Step S200 includes: Step S201: select a product in the product database as a target product and obtain the introduction content of the target product; Step S202: a shared link shared by a target user is used as a target link, and sharing the target link from one account to another is recorded as one transmission; Step S203: Arrange the network accounts that viewed the target product according to the propagation order of the target link, record the account that purchased the target product as the last network account, and form a target sequence with all network accounts from the first account shared by the target user to the last network account.

3. The method for tracking product attention based on user behavior analysis according to claim 2, characterized in that: Step S300 includes: Step S301: Obtain the i-th account Ui in the target sequence, obtain the total time ta that account Ui browses the target product introduction content in the target sequence, obtain the k-th introduction content in the target product introduction content, record the k-th product attribute as qk, obtain the time that user Ui browses the k-th introduction content as tk, and calculate the characteristic value αik of the introduction content corresponding to the k-th product attribute browsed by account Ui, where αik = tk / ta; Step S302: Combining the product attributes with the corresponding feature values ​​to obtain the feature value corresponding to the k-th value to obtain the evaluation group (qk, αik), respectively obtain the feature values ​​of all product attributes read by account Ui, and collect the evaluation groups corresponding to each feature value to obtain the user reading record list of account Ui; Step S303: Collect the feature values ​​corresponding to the same product attribute of the target product, calculate the average value of the feature values ​​of the same product attribute, and import each product attribute and the corresponding average value into a reference state list. Obtain the product attributes in the reference state list and import them into the reference attribute set R1. Step S304: Obtain the user reading record list of the last account in the target sequence, aggregate the product attributes in the user reading record list into the target attribute set R2, obtain the product attributes identical to those in R2 from R1 as comparison attributes, obtain the average values ​​corresponding to the comparison attributes from the reference state list, aggregate the comparison attributes and the corresponding average values ​​into a comparison set, and arrange the product attributes in the comparison set in the same order as the product attributes in the target attribute set R2; Step S305: Calculate the difference w between the target attribute set R2 and the comparison set. Among them, q 1 p1 represents the average value of the attributes of the product in p1 in the comparison set, q 2 p1 The feature value corresponding to the p1th product attribute in the target attribute set R2, and p2 represents the number of product attributes in the target attribute set R2.

4. The method for tracking product attention based on user behavior analysis according to claim 3, characterized in that: Step S400 includes: Step S401: The time from when an account receives a target link to when it shares the target link is recorded as the retention time, and the total retention time in the target sequence is calculated and recorded as T; Step S402: Obtain user reading record lists of all accounts in the target sequence, count the number of user reading record lists that are identical to the user reading record list of account Ui, and record the number as M; Step S403: Calculate the retention index γ of the target sequence, γ=N×lg(M×T), where N represents the number of target link propagations in the target sequence, and lg represents a logarithmic function with base 10.

5. The method for tracking product attention based on user behavior analysis according to claim 4, characterized in that: Step S500 includes: Step S501: Obtain all transaction record sequences of the target contact, use the user reading record list of the last account in the target sequence as the target feature, obtain all transaction record sequences in all browsing record sequences whose user reading record list of the last account has the same target feature, and aggregate the transaction record sequences into a feature record set; Step S502: Obtain the difference value and retention index of each browsing record sequence in the feature record set, record the average value of the difference value as the first evaluation coefficient, and record the average value of the retention index as the second evaluation coefficient; Step S503: taking the user reading record list of the last account in the target sequence as the feature label of the target sequence, and combining the feature label, the first evaluation coefficient and the second evaluation coefficient to form an evaluation group; Step S504: Gather the evaluation groups corresponding to all feature tags of the target contact to obtain an evaluation database of the target contact.

6. The method for tracking product attention based on user behavior analysis according to claim 5, characterized in that: Step S600 includes: Step S601: Obtain the product description content of the product to be shared, group all the feature words in the product description content into a set D0, collect the feature words according to the product attributes, and record the set consisting of the feature words corresponding to the e-th product attribute of the product to be shared as De; Step S602: Calculate the attribute ratio αe of the e-th product attribute, αe=num(De) / num(D0), where num is a function for obtaining the number of set feature words; Step S603: Gather the attributes of each product to be shared and the corresponding attribute ratios to form an attribute label; Step S604: obtaining evaluation groups corresponding to the feature tags identical to the attribute tags, and merging all evaluation groups into a first set to be shared; Step S605: Setting a judgment threshold F, combining the evaluation groups in the first set to be shared whose first evaluation coefficient is less than F into the second set to be shared, and sorting the second set to be shared in ascending order of the second evaluation coefficient to obtain a third set to be shared; Step S606: sequentially obtain the accounts of each evaluation group in the third sharing set to form a contact sequence, and push the contact sequence to the target user.

7. A product attention tracking system based on user behavior analysis, configured to execute the product attention tracking method based on user behavior analysis according to any one of claims 1 to 6, characterized in that: The system includes: Product management module, browsing record sequence management module, difference comparison module, retention time management module, feature evaluation module and recommendation sorting module, among which, the product management module is used to manage product information and the corresponding relationship between the product sharing link and the product, the browsing record sequence management module is used to obtain the propagation record of the sharing link, and organize the network accounts into a browsing record sequence according to the propagation order of the sharing link, the difference comparison module is used to compare the difference in browsing features between the last network account in the target sequence and the target sequence, the retention time management module is used to calculate the average retention time of the sharing link in each browsing record sequence, the feature evaluation module is used to evaluate the browsing record sequence corresponding to the target contact, and the recommendation sorting module is used to analyze the introduction content of the product, sort the matched contacts, and obtain a recommended sharing sequence.

8. The product attention tracking system based on user behavior analysis according to claim 7, characterized in that: The browsing record sequence management module includes: an introduction content management unit, a dissemination record management unit, and a browsing record sequence management unit. The introduction content management unit is used to manage the introduction content of the product, the dissemination record management unit is used to manage the dissemination record of the sharing link, and the browsing record sequence management unit is used to capture the transaction record of the product and obtain the browsing record sequence; The difference comparison module includes: a characteristic value calculation unit, a user reading record management unit, a comparison management unit, and a difference value calculation unit. The characteristic value calculation unit is used to obtain the browsing time of the introduction content corresponding to each product attribute and calculate the characteristic value of the introduction content of the corresponding category. The user reading record management unit is used to collect the evaluation groups corresponding to each characteristic value to obtain a user reading record list. The comparison management unit is used to select the average browsing ratio of the corresponding category from the target sequence based on the category of the introduction content browsed by the last account in the target sequence. The difference value calculation unit is used to calculate the difference value between the target attribute set and the comparison set. The retention time management module includes: a time collection unit, a repetition detection unit and a retention index calculation unit. Among them, the time collection unit is used to collect the retention time in any two network accounts, the repetition detection unit is used to detect the number of repetitions of the user reading record list corresponding to the last network account in the target sequence, and the retention index calculation unit is used to calculate the retention index of the target sequence.

9. The product attention tracking system based on user behavior analysis according to claim 7, characterized in that: The feature evaluation module includes: an evaluation coefficient management unit, an evaluation group management unit and an evaluation database management unit, wherein the evaluation coefficient management unit is used to collect the first evaluation coefficient and the second evaluation coefficient, the evaluation group management unit is used to collect the feature label, the first evaluation coefficient and the second evaluation coefficient to form an evaluation group, and the evaluation database management unit is used to manage the evaluation database of the target contact.

10. The product attention tracking system based on user behavior analysis according to claim 7, characterized in that: The recommendation sorting module includes an attribute analysis unit, a feature matching unit, a threshold judgment unit and a sorting push unit, wherein the attribute analysis unit is used to analyze the attribute ratio of various product attributes in the product introduction content, the feature matching unit is used to manage the first set to be shared, the threshold judgment unit is used to manage the second set to be shared, and the sorting push unit is used to manage the third set to be shared and push contacts in order to the target user.

Images