Method and device for obtaining advertisement contact information, electronic device, and storage medium

Abstract

This application relates to the field of advertising and marketing technologies, and discloses a method for obtaining advertising contact information. The method includes: obtaining network behavior log data corresponding to multiple users respectively; obtaining a decision APP node and a conversion APP node corresponding to each network behavior log data respectively; sorting the decision APP nodes and the conversion APP nodes in chronological order of the occurrence time to obtain an APP decision path corresponding to each network behavior log data; obtaining a frequent APP item set according to each APP decision path; determining the decision APP nodes in the frequent APP item set as key contacts, and generating an APP strong association rule corresponding to the key contacts according to the frequent APP item set. The advertising contact information obtained in this way is more reliable, making the effect of formulating an advertising placement strategy according to the advertising contact information better, thereby being able to improve the return on investment of advertising and marketing. This application also discloses a device, an electronic device, and a storage medium for obtaining advertising contact information.

Description

Technical Field

[0001] The present application relates to the field of advertising and marketing technology, for example, to a method and device, electronic device, and storage medium for obtaining advertising contact information. Background Art

[0002] With the popularity of mobile terminal devices such as smartphones and tablets, APP (Application) clients have gradually become the main way for people to access the Internet. Advertisers are increasingly using these APPs as carriers to place advertisements in order to achieve the purpose of product promotion and increase revenue. Before conducting advertising marketing, advertisers usually need to conduct a series of market research. Through market research, the target groups and media for advertising are determined, so that advertising touchpoint information can be obtained. Advertising touchpoint information includes key touchpoints (media APPs for advertising) and the relationship between key touchpoints. This makes it easier to formulate advertising delivery strategies based on advertising touchpoint information.

[0003] In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in the related art:

[0004] Related technologies usually use traditional market research methods such as issuing questionnaires, reviewing industry reports, and interviewing experts to mine advertising touchpoint information. Since traditional market research methods are easily affected by the subjective thoughts of interviewers and participants and have low reliability, the effect of formulating advertising delivery strategies based on advertising touchpoint information is poor, resulting in a low return on investment in advertising marketing. Summary of the invention

[0005] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0006] The embodiments of the present disclosure provide a method and device, an electronic device, and a storage medium for obtaining advertising contact information, so as to improve the return on investment of advertising marketing.

[0007] In some embodiments, the method for obtaining advertisement contact information includes: obtaining network behavior log data corresponding to multiple users respectively, where the network behavior log data includes the occurrence time of user behaviors. Obtaining a decision APP node and a conversion APP node corresponding to each of the network behavior log data respectively. Sorting the decision APP node and the conversion APP node in chronological order of the occurrence time to obtain an APP decision path corresponding to each of the network behavior log data respectively. Obtaining a frequent APP item set according to each of the APP decision paths. Determining the decision APP nodes in the frequent APP item set as key contacts, and generating an APP strong association rule corresponding to the key contacts according to the frequent APP item set.

[0008] In some embodiments, the network behavior log data includes the name of the APP used by the user and APP text information; obtaining a decision APP node and a conversion APP node corresponding to each of the network behavior log data respectively includes: sorting out each of the APP text information according to a preset format to obtain a text data set. The text data set includes multiple pieces of text data, and the text data includes the name of the APP used by the user, a title text, and a body text. Performing entity recognition on each of the text data to obtain a first alternative brand name corresponding to each of the text data respectively. Performing disambiguation processing on each of the first alternative brand names to obtain a standard brand name corresponding to each of the brand names respectively. Determining a decision APP node and a conversion APP node according to each of the standard brand names and a preset target brand.

[0009] In some embodiments, the network behavior log data includes a user identification number ID, the occurrence time of user behaviors, the name of the APP used by the user, and a status identifier of the network behavior log data; determining a decision APP node and a conversion APP node according to each of the standard brand names and a preset target brand includes: determining a standard brand name identical to the preset target brand as a second alternative brand name. Screening out the APP information corresponding to the second alternative brand name from the network behavior log data. The APP information includes a user ID, the name of the APP used by the user, the occurrence time of user behaviors, and a status identifier of the network behavior log data. In the case where the second alternative brand name is included in the APP information or the text data corresponding to the APP information, determining the name of the APP used in the APP information as the target APP, and in the case where the status identifier of the network behavior log data corresponding to the target APP is a first preset type identifier, determining the target APP as the decision APP node; in the case where the status identifier of the network behavior log data corresponding to the target APP is a second preset type identifier, determining the target APP as the conversion APP node.

[0010] In some embodiments, obtaining frequent APP item sets according to each of the APP decision paths includes: obtaining the APP decision sets respectively corresponding to each of the APP decision paths, and determining the frequent APP item sets from each of the APP decision sets.

[0011] In some embodiments, obtaining the APP decision set corresponding to the APP decision path includes: traversing the APP decision path in the chronological order, and determining the occurrence time of the user behavior corresponding to the first transformed APP node in the APP decision path as the first time. Starting from the first transformed APP node, traversing in the direction opposite to the chronological order in turn, and determining the occurrence time of the user behavior corresponding to the traversed decision APP node as the second time. Respectively obtaining the time differences between the first time and each of the second times. When the time difference is less than a preset time threshold, adding the traversed decision APP node to the decision APP set; or, when the time difference is greater than or equal to the time threshold, performing a deduplication operation on the decision APP set. Removing the first transformed APP node and all nodes before the first transformed APP node from the APP decision path, and obtaining an alternative APP decision path. All nodes before the first transformed APP node are all nodes in the direction opposite to the chronological order starting from the first transformed APP node. Continuing to traverse the alternative APP decision path in the chronological order until there are no transformed APP nodes in the alternative APP decision path.

[0012] In some embodiments, determining the frequent APP item sets from each of the APP decision sets includes: performing the following operations on each APP decision set: performing a full permutation on the decision APP nodes in the APP decision set to generate multiple item sets corresponding to the APP decision set. Obtaining the support degrees respectively corresponding to each of the item sets, and determining the item sets corresponding to the support degrees greater than a first preset threshold as the frequent item sets.

[0013] In some embodiments, generating the APP strong association rules corresponding to the key touch points according to the frequent APP item sets includes: performing a full permutation on the decision APP nodes in the frequent item sets to generate multiple non-empty proper subsets, and generating alternative rules by using the frequent item sets and each of the non-empty proper subsets. Obtaining the confidence degrees respectively corresponding to each of the alternative rules, and determining the alternative rules with the confidence degrees greater than a second preset threshold as the APP strong association rules.

[0014] In some embodiments, the apparatus for obtaining advertisement contact information includes: a first obtaining module configured to obtain network behavior log data corresponding to multiple users respectively. The network behavior log data includes the occurrence time of user behaviors. A second obtaining module configured to obtain a decision APP node and a conversion APP node corresponding to each of the network behavior log data respectively. A sorting module configured to sort the decision APP node and the conversion APP node in chronological order of the occurrence time to obtain an APP decision path corresponding to each of the network behavior log data. A third obtaining module configured to obtain a frequent APP item set according to each of the APP decision paths. A determination module configured to determine the decision APP nodes in the frequent APP item set as key contacts, and generate an APP strong association rule corresponding to the key contacts according to the frequent APP item set.

[0015] In some embodiments, the electronic device includes a processor and a memory storing program instructions, and the processor is configured to execute the above method for obtaining advertisement contact information when running the program instructions.

[0016] In some embodiments, the storage medium stores program instructions, and the program instructions execute the above method for obtaining advertisement contact information when running.

[0017] The method, apparatus, electronic device, and storage medium for obtaining advertisement contact information provided by the embodiments of the present disclosure can achieve the following technical effects: By extracting the decision APP node and the conversion APP node from the network behavior log data corresponding to the user, and obtaining the APP decision path according to the decision APP node and the conversion APP node, a frequent APP item set can be obtained, so that key contacts and APP strong association rules corresponding to the key contacts can be obtained. Since the sample capacity of the network behavior log data is large, the timeliness is strong, and the authenticity is high, real and comprehensive consumer insights can be obtained faster, more accurately, and more efficiently. The advertisement contact information obtained in this way is more reliable, making the effect of formulating an advertisement placement strategy according to the advertisement contact information better, thereby improving the return on investment of advertisement marketing.

[0018] The above general description and the following description are only exemplary and explanatory, and are not used to limit this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] One or more embodiments are exemplarily illustrated by corresponding drawings. These exemplary illustrations and the drawings do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements. The drawings do not constitute a scale limitation, and among them:

[0020] Figure 1It is a schematic diagram of a method for obtaining advertisement contact information provided by an embodiment of the present disclosure;

[0021] Figure 2 It is a schematic diagram of another method for obtaining advertisement contact information provided by an embodiment of the present disclosure;

[0022] Figure 3 It is a schematic diagram of a method for obtaining a set of decision-making APPs provided by an embodiment of the present disclosure;

[0023] Figure 4 It is a schematic diagram of another method for obtaining advertisement contact information provided by an embodiment of the present disclosure;

[0024] Figure 5 It is a schematic diagram of a device for obtaining advertisement contact information provided by an embodiment of the present disclosure;

[0025] Figure 6 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0026] In order to be able to understand the features and technical content of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure will be described in detail below in conjunction with the accompanying drawings. The accompanying drawings are for reference and illustration only, and are not intended to limit the embodiments of the present disclosure. In the following technical description, for the sake of explanation, numerous details are provided to give a thorough understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other instances, well-known structures and devices may be shown in a simplified manner to simplify the drawings.

[0027] In the description of the embodiments of the present disclosure, the terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way may be interchanged under appropriate circumstances so as to implement the embodiments of the present disclosure described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion.

[0028] Unless otherwise specified, the term "plurality" means two or more.

[0029] In the embodiments of the present disclosure, the character " / " indicates that the objects before and after are in an "or" relationship. For example, A / B means: A or B.

[0030] The term "and / or" is an associative relationship describing an object, indicating that three relationships may exist. For example, A and / or B means: A or B, or, A and B these three relationships.

[0031] The term "corresponding" may refer to an association relationship or a binding relationship. That A corresponds to B means there is an association relationship or a binding relationship between A and B.

[0032] The technical solutions in the embodiments of the present invention can be applied to electronic devices such as computers, tablet computers, or servers.

[0033] In the embodiments of the present invention, the sample size of network behavior log data is large, the timeliness is strong, and the authenticity is high, which can obtain real and comprehensive consumer insights faster, more accurately, and more efficiently. By extracting decision APP nodes and conversion APP nodes from the network behavior log data corresponding to users through an electronic device, and obtaining APP decision paths according to the decision APP nodes and conversion APP nodes, frequent APP item sets can be obtained, and thus key touchpoints and APP strong association rules corresponding to the key touchpoints can be obtained. The advertising touchpoint information obtained in this way is not easily interfered by subjective human thoughts and has higher reliability. This makes the effect of formulating an advertising placement strategy based on the advertising touchpoint information better, thereby improving the return on investment of advertising marketing.

[0034] Combined Figure 1 As shown, the embodiments of the present disclosure provide a method for obtaining advertising touchpoint information, and the method includes:

[0035] Step S101, an electronic device obtains network behavior log data corresponding to multiple users respectively; the network behavior log data includes user IDs, the occurrence time of user behaviors, the names of APPs used by users, APP text information, and status identifiers of the network behavior log data. User behaviors include browsing, clicking, searching, downloading, purchasing, etc. within the APP. The APP text information includes the names of KOLs (Key Opinion Leaders), title texts, body texts, etc.

[0036] Step S102, the electronic device obtains decision APP nodes and conversion APP nodes corresponding to the respective network behavior log data.

[0037] Step S103, the electronic device sorts the decision APP nodes and conversion APP nodes in the chronological order of the occurrence time of user behaviors to obtain APP decision paths corresponding to the respective network behavior log data.

[0038] Step S104, the electronic device obtains frequent APP item sets according to the respective APP decision paths.

[0039] Step S105, the electronic device determines the decision APP nodes in the frequent APP item sets as key touchpoints, and generates APP strong association rules corresponding to the key touchpoints according to the frequent APP item sets.

[0040] By using the method for obtaining advertisement contact information provided in the embodiments of the present disclosure, by extracting the decision-making APP nodes and conversion APP nodes from the network behavior log data corresponding to the user, and obtaining the APP decision-making path according to the decision-making APP nodes and conversion APP nodes, frequent APP item sets can be obtained, so that key contacts and APP strong association rules corresponding to the key contacts can be obtained. Since the sample size of the network behavior log data is large, the timeliness is strong and the authenticity is high, real and comprehensive consumer insights can be obtained faster, more accurately and more efficiently. The advertisement contact information obtained in this way is more reliable, so that the effect of formulating an advertisement placement strategy according to the advertisement contact information is better, thereby improving the return on investment of advertisement marketing.

[0041] Optionally, the electronic device obtains the decision-making APP nodes and conversion APP nodes respectively corresponding to each network behavior log data, including: the electronic device sorts out each APP text information according to a preset format to obtain a text data set. The text data set includes multiple pieces of text data, and the text data includes the APP name used by the user, the title text and the body text. Entity recognition is performed on each piece of text data to obtain the first alternative brand names respectively corresponding to each piece of text data. Disambiguation processing is performed on each first alternative brand name to obtain the standard brand names respectively corresponding to each brand name. The decision-making APP nodes and conversion APP nodes are determined according to each standard brand name and a preset target brand. Among them, the preset format is the APP name used by the user, the title text and the body text.

[0042] In some embodiments, the electronic device sorts out each APP text information according to a preset format to obtain a text data set. The text data set includes multiple pieces of text data, and the text data includes the APP name used by the user, the title text and the body text. For example, the text data is: APP name: Xiaohongshu, title text: Title of the posted post, body text: Content of the posted post. The text data is: APP name: Douyin, title text: Title of the posted video, body text: empty.

[0043] Furthermore, the electronic device performs entity recognition on each piece of text data to obtain the first alternative brand names respectively corresponding to each piece of text data, including: the electronic device performs data cleaning on each piece of text data, and uses a pre-trained NER (Named Entity Recognition) algorithm model to perform entity recognition on the text data after data cleaning to obtain the first alternative brand names respectively corresponding to each piece of text data.

[0044] Further, the electronic device performs data cleaning on each text data, including: removing null values, stop words, illegal characters, etc. from each text data. By performing data cleaning on the text data, the quality of the text data can be improved, facilitating the user to obtain advertising touchpoint information. The advertising touchpoint information includes key touchpoints and the relationships between the key touchpoints.

[0045] Further, disambiguation processing is performed on each first alternative brand name to obtain the standard brand name corresponding to each brand name, including: matching the standard brand name corresponding to each first alternative brand name from a preset standard brand name table. The corresponding relationship between the first alternative brand name and the standard brand name is stored in the standard brand name table. In this way, by performing disambiguation processing on the first alternative brand name, in the case where the first alternative brand name is an English alias or other Chinese alias, the ambiguous brand name can be disambiguated and mapped to a unified standard brand name, avoiding repeated counting of the brand name, thus facilitating the user to obtain advertising touchpoint information.

[0046] Further, the electronic device determines the decision APP node and the conversion APP node according to each standard brand name and the preset target brand, including: the electronic device determines the standard brand name that is the same as the preset target brand as the second alternative brand name. The APP information corresponding to the second alternative brand name is screened out from the network behavior log data. The APP information includes the user ID, the APP name used by the user, the occurrence time of the user behavior, and the status identifier of the network behavior log data. In the case where the second alternative brand name is included in the APP information or the text data corresponding to the APP information, the APP name used by the user in the APP information is determined as the target APP, and in the case where the status identifier of the network behavior log data corresponding to the target APP is the first preset type identifier, the target APP is determined as the decision APP node; in the case where the status identifier of the network behavior log data corresponding to the target APP is the second preset type identifier, the target APP is determined as the conversion APP node. Among them, the first preset type identifier is "exposure", "click", or "search". The second preset type identifier is "purchase" or "download". Among them, the text data corresponding to the APP information is the text data corresponding to the APP name used by the user in the APP information.

[0047] Further, when the second alternative brand name is included in the APP information or the text data corresponding to the APP information, the APP name used by the user in the APP information is determined as the target APP, and when the status identifier of the network behavior log data corresponding to the target APP is the first preset type identifier, the target APP is determined as the decision APP node, including: determining as the target APP the APP name that includes the second alternative brand name in the APP information or the APP name that includes the second alternative brand name in the text data corresponding to the APP information. And when the status identifier of the network behavior log data corresponding to the target APP is the first preset type identifier, the target APP is determined as the decision APP node.

[0048] In some embodiments, the second alternative brand name is "NIO". When the APP name in the APP information includes "NIO" or the APP name that includes "NIO" in the text data corresponding to the APP information, the APP name is determined as the target APP. And when the status identifier of the network behavior log data corresponding to the target APP is "exposure", "click", or "search", the target APP is determined as the decision APP node.

[0049] Further, when the second alternative brand name is included in the APP information or the text data corresponding to the APP information, the APP name used by the user in the APP information is determined as the target APP. And when the status identifier of the network behavior log data corresponding to the target APP is the second preset type identifier, the target APP is determined as the conversion APP node, including: determining as the target APP the APP name that includes the second alternative brand name in the APP information or the APP name that includes the second alternative brand name in the text data corresponding to the APP information. And when the status identifier of the network behavior log data corresponding to the target APP is the second preset type identifier, the target APP is determined as the conversion APP node.

[0050] In some embodiments, the second alternative brand name is "Airbnb". When the APP name in the APP information includes "Airbnb" or the APP name that includes "Airbnb" in the text data corresponding to the APP information, the APP name is determined as the target APP. And when the status identifier of the network behavior log data corresponding to the target APP is "purchase" or "download", the target APP is determined as the conversion APP node.

[0051] Further, sort the decision APP nodes and the conversion APP nodes in chronological order according to the occurrence time of the user behavior to obtain the APP decision path corresponding to each network behavior log data.

[0052] In some embodiments, the decision-making APP nodes include Weibo, Xiaohongshu, Kuaishou, and Toutiao. The conversion APP nodes include JD.com and Taobao Mobile. The corresponding occurrence time of Weibo is D1, the corresponding occurrence time of Xiaohongshu is D2, the corresponding occurrence time of Kuaishou is D3, the corresponding occurrence time of Toutiao is D4, the corresponding occurrence time of JD.com is T1, and the corresponding occurrence time of Taobao Mobile is T2. Among them, the chronological order of the occurrence times is D1, D2, T1, D3, D4, T2. Then, the decision-making APP nodes and the conversion APP nodes are sorted in chronological order to obtain the APP decision path corresponding to the network behavior log data as "Weibo (D1) → Xiaohongshu (D2) → JD.com (T1) → Kuaishou (D3) → Toutiao (D4) → Taobao Mobile (T2)".

[0053] Further, the electronic device obtains frequent APP item sets according to each APP decision path, including: the electronic device obtains the APP decision sets corresponding to each APP decision path respectively, and determines the frequent APP item sets from each APP decision set.

[0054] Combined with Figure 2 As shown, an embodiment of the present disclosure provides a method for obtaining advertisement touchpoint information, and the method includes:

[0055] Step S201, the electronic device obtains network behavior log data corresponding to multiple users respectively; the network behavior log data includes a user identity identification number ID, the occurrence time of the user behavior, the name of the application software APP used by the user, APP text information, and a status identifier of the network behavior log data. The user behavior includes behaviors such as browsing, clicking, searching, downloading, and purchasing within the APP. The APP text information includes the name of the KOL (Key Opinion Leader), title text, body text, etc.

[0056] Step S202, the electronic device obtains the decision-making APP nodes and the conversion APP nodes corresponding to each network behavior log data respectively.

[0057] Step S203, the electronic device sorts the decision-making APP nodes and the conversion APP nodes in chronological order according to the occurrence time of the user behavior to obtain the APP decision path corresponding to each network behavior log data respectively.

[0058] Step S204, the electronic device obtains the APP decision sets corresponding to each APP decision path respectively.

[0059] Step S205, the electronic device determines the frequent APP item sets from each APP decision set.

[0060] In step S206, the electronic device determines the decision-making APP node in the frequent APP item set as the key contact point, and generates an APP strong association rule corresponding to the key contact point according to the frequent APP item set.

[0061] By using the method for obtaining advertisement contact point information provided in the embodiments of the present disclosure, by extracting the decision-making APP node and the conversion APP node from the network behavior log data corresponding to the user, and obtaining the APP decision-making path according to the decision-making APP node and the conversion APP node, a frequent APP item set can be obtained, so that a key contact point and an APP strong association rule corresponding to the key contact point can be obtained. Since the sample size of the network behavior log data is large, the timeliness is strong, and the authenticity is high, the true and comprehensive consumer insights can be obtained faster, more accurately, and more efficiently. The advertisement contact point information obtained in this way is more reliable, making the effect of formulating an advertisement placement strategy according to the advertisement contact point information better, thereby improving the return on investment of advertisement marketing.

[0062] Further, the electronic device obtains an APP decision-making set corresponding to the APP decision-making path, including: the electronic device traverses the APP decision-making path in the chronological order of the occurrence time of the user behavior, and determines the occurrence time of the user behavior corresponding to the first conversion APP node in the APP decision-making path as the first time. Starting from the first conversion APP node, traversing in the reverse direction of the chronological order in turn, and determining the occurrence time of the user behavior corresponding to the traversed decision-making APP node as the second time. Respectively obtain the time differences between the first time and each second time. In the case that the time difference is less than the preset time threshold, add the traversed decision-making APP node to the decision-making APP set. Or, in the case that the time difference is greater than or equal to the time threshold, perform a duplicate removal operation on the decision-making APP set. Remove the first conversion APP node and all nodes before the first conversion APP node from the APP decision-making path to obtain an alternative APP decision-making path. All nodes before the first conversion APP node are all nodes in the reverse direction of the chronological order starting from the first conversion APP node. Continue to traverse the alternative APP decision-making path in chronological order until there is no conversion APP node in the alternative APP decision-making path.

[0063] Further, when the time difference is greater than or equal to the time threshold, the electronic device performs a duplicate removal operation on the decision-making APP set, including: the electronic device determines whether there are duplicate decision-making APP nodes in the decision-making APP set, and in the case that there are duplicate decision-making APP nodes in the decision-making APP set, removes the duplicate decision-making APP nodes.

[0064] Optionally, the electronic device continues to traverse the alternative APP decision path in the chronological order of the occurrence time of the user behavior until there is no converted APP node in the alternative APP decision path, including: the electronic device traverses the alternative APP decision path in chronological order. When there is a converted APP node in the alternative APP decision path, the occurrence time of the user behavior corresponding to the first converted APP node in the alternative APP decision path is determined as the first time. Starting from the first converted APP node, traverse in the reverse direction of the chronological order, and determine the occurrence time of the user behavior corresponding to the traversed decision APP node as the second time. Respectively obtain the time differences between the first time and each second time. When the time difference is less than the preset time threshold, add the traversed decision APP node to the decision APP set. Or, when the time difference is greater than or equal to the time threshold, perform a deduplication operation on the decision APP set. Remove the first converted APP node and all nodes before the first converted APP node from the alternative APP decision path to obtain a new alternative APP decision path. All nodes before the first converted APP node are all nodes in the reverse direction of the chronological order starting from the first converted APP node.

[0065] Optionally, the electronic device continues to traverse the alternative APP decision path in chronological order until there is no converted APP node in the alternative APP decision path, including: the electronic device traverses the alternative APP decision path in chronological order and stops traversing when there is no converted APP node in the alternative APP decision path to obtain the decision APP set.

[0066] Combined Figure 3 As shown, an embodiment of the present disclosure provides a method for obtaining a decision APP set, and the method includes:

[0067] Step S301, the electronic device traverses the APP decision path in the chronological order of the occurrence time of the user behavior, and determines the occurrence time of the user behavior corresponding to the first converted APP node in the APP decision path as the first time.

[0068] Step S302, the electronic device starts from the first converted APP node and traverses in the reverse direction of the chronological order in turn, and determines the occurrence time of the user behavior corresponding to the traversed decision APP node as the second time.

[0069] Step S303, the electronic device respectively obtains the time differences between the first time and each second time.

[0070] Step S304, when the time difference is less than the preset time threshold, the electronic device adds the traversed decision APP node to the decision APP set.

[0071] Step S305, the electronic device removes the first converted APP node and all nodes before the first converted APP node from the APP decision path to obtain a new alternative APP decision path. All nodes before the first converted APP node are all nodes in the reverse direction of the time sequence starting from the first converted APP node.

[0072] Step S306, the electronic device traverses the new alternative APP decision path in chronological order to determine whether there is a converted APP node in the new alternative APP decision path; if there is a converted APP node in the new alternative APP decision path, step S301 is executed; or, if there is no converted APP node in the new alternative APP decision path, step S307 is executed.

[0073] Step S307, the electronic device stops traversing to obtain a decision APP set.

[0074] By using the method for obtaining a decision APP set provided in the embodiments of the present disclosure, by traversing the APP decision path in chronological order, the converted APP nodes in the APP decision path can be removed, and the decision APP nodes corresponding to the time differences less than the time threshold can be added to the decision APP set, so as to obtain the decision APP set, which is convenient for the user to obtain the frequent APP item set according to the decision APP set, so as to obtain the key contacts and the relationships between the key contacts, which is convenient for formulating advertising marketing strategies.

[0075] Further, the electronic device determines the frequent APP item set from each APP decision set, including: the electronic device performs the following operations on each APP decision set: performing a full permutation on the decision APP nodes in the APP decision set to generate multiple item sets corresponding to the APP decision set. Obtaining the support degrees corresponding to each item set, and determining the item sets corresponding to the support degrees greater than the first preset threshold as frequent item sets. Optionally, the first preset threshold is 0.8.

[0076] In some embodiments, as shown in Table 1, Table 1 is an example table of a decision APP set provided in the embodiments of the present disclosure.

[0077]

[0078]

[0079] Table 1

[0080] In Table 1, the decision APP set corresponding to serial number 1 includes JD.com, Xiaohongshu, and Weibo. The decision APP set corresponding to serial number 2 includes Kuaishou and Toutiao. The decision APP set corresponding to serial number N-1 includes Douyin, Kuaishou, and Xiaohongshu. The decision APP set corresponding to serial number N includes Douyin, Kuaishou, and Weibo.

[0081] In some embodiments, all decision-making APP nodes in each APP decision set include JD.com, Xiaohongshu, and Weibo. For example, the permutations of JD.com, Xiaohongshu, and Weibo to obtain item sets include [JD.com], [Xiaohongshu], [Weibo], [JD.com, Xiaohongshu], [JD.com, Weibo], [Xiaohongshu, Weibo], [JD.com, Xiaohongshu, Weibo].

[0082] Furthermore, obtaining the support degrees corresponding to each item set includes: by calculating to obtain the support degree corresponding to the item set. Among them, Support(I i ) is the support degree corresponding to the item set I i . n i is the number of decision-making APP sets that contain all decision-making APP nodes in the item set I i , and N is the total number of decision-making APP sets.

[0083] Furthermore, the first preset threshold is obtained by the following method: calculating minSupport = N * α to obtain the first preset threshold. Among them, minSupport is the first preset threshold. N is the total number of decision-making APP sets. α is a preset proportionality factor.

[0084] Optionally, the electronic device generates an APP strong association rule corresponding to the key contact according to the frequent APP item set, including: the electronic device performs a full permutation on the decision-making APP nodes in the frequent item set to generate multiple non-empty proper subsets. Using the frequent item set and each non-empty proper subset to generate alternative rules. Obtaining the confidence degrees corresponding to each alternative rule, and determining the alternative rules with confidence degrees greater than the second preset threshold as APP strong association rules. Optionally, the second preset threshold is 0.8. Among them, the magnitude of the confidence degree is used to characterize the strength of the synergistic effect between key contacts. For example,

[0085] In some embodiments, the frequent item set is [JD.com, Xiaohongshu, Weibo], and the decision-making APP nodes in the frequent item set: JD.com, Xiaohongshu, and Weibo are fully permuted to obtain non-empty proper subsets including: [JD.com], [Xiaohongshu], [Weibo], [JD.com, Xiaohongshu], [JD.com, Weibo], [Xiaohongshu, Weibo].

[0086] In some embodiments, the frequent item set i is [JD.com, Xiaohongshu, Weibo], and each non-empty proper subset s includes: [JD.com], [Xiaohongshu], [Weibo], [JD.com, Xiaohongshu], [JD.com, Weibo], [Xiaohongshu, Weibo]. Then, the alternative rules are generated using the frequent item set i and each non-empty proper subset s as (i - s) → s. For example: the alternative rules are JD.com → (Xiaohongshu, Weibo), Xiaohongshu → (JD.com, Weibo), Weibo → (JD.com, Xiaohongshu), (JD.com, Xiaohongshu) → (Weibo), (JD.com, Weibo) → (Xiaohongshu), or (Weibo, Xiaohongshu) → (JD.com), etc.

[0087] Further, obtaining the confidence corresponding to the alternative rule includes: by calculating to obtain the confidence corresponding to the alternative rule. Among them, Confidence((i - s) → s) is the confidence corresponding to the alternative rule (i - s) → s. Support(i) is the support corresponding to the frequent item set i, and Support(i - s) is the support corresponding to the non-empty proper subset (i - s).

[0088] In some embodiments, Confidence(JD.com → Xiaohongshu) = 0.9 means that there is a 90% probability that people who use JD.com will also use Xiaohongshu.

[0089] Further, after obtaining the confidence corresponding to each alternative rule, it further includes: obtaining the lift corresponding to each confidence, determining the confidence with the lift greater than the third preset threshold as the effective confidence, and determining the alternative rule corresponding to the effective confidence greater than the second preset threshold as the effective APP strong association rule. Since the APP strong association rule with a high confidence is not necessarily an effective association rule, screening the APP strong association rule through the lift can obtain an effective association rule.

[0090] Further, obtaining the lift corresponding to the confidence includes: by calculating to obtain the lift corresponding to the confidence. Among them, Lift((i - s) → s) is the lift. Confidence((i - s) → s) is the confidence corresponding to the alternative rule (i - s) → s. Support(s) is the support corresponding to the non-empty proper subset s.

[0091] In some embodiments, when Lift((i - s) → s) = 1, it indicates that the item set (i - s) and the item set (s) are independent and not related. When Lift((i - s) → s) ≤ 1, it indicates that the item set (i - s) and the item set (s) are negatively correlated. When Lift((i - s) → s) ≥ 1, it indicates that the item set (i - s) and the item set (s) are positively correlated.

[0092] Combined with Figure 4As shown in the figure, an embodiment of the present disclosure provides a method for obtaining advertisement contact information, and the method includes:

[0093] Step S401, an electronic device obtains network behavior log data corresponding to multiple users respectively; the network behavior log data includes a user identity identification number ID, the occurrence time of the user behavior, the name of the application software APP used by the user, APP text information, and a status identifier of the network behavior log data. The user behavior includes behaviors such as browsing, clicking, searching, downloading, and purchasing within the APP. The APP text information includes the name of the KOL (Key Opinion Leader), title text, body text, etc.

[0094] Step S402, the electronic device obtains a decision APP node and a conversion APP node corresponding to each network behavior log data respectively.

[0095] Step S403, the electronic device sorts the decision APP nodes and the conversion APP nodes in the chronological order of the occurrence time of the user behavior to obtain an APP decision path corresponding to each network behavior log data.

[0096] Step S404, the electronic device obtains a frequent APP item set according to each APP decision path.

[0097] Step S405, the electronic device determines the decision APP nodes in the frequent APP item set as key contacts, and performs a full permutation on the decision APP nodes in the frequent item set to generate multiple non-empty proper subsets.

[0098] Step S406, the electronic device generates alternative rules by using the frequent item set and each non-empty proper subset.

[0099] Step S407, the electronic device obtains the confidence corresponding to each alternative rule.

[0100] Step S408, the electronic device determines the alternative rules with a confidence greater than a second preset threshold as APP strong association rules.

[0101] By using the method for obtaining advertisement contact information provided by the embodiments of the present disclosure, through data mining from the network behavior log data corresponding to users by utilizing data capabilities, decision-making APP nodes and conversion APP nodes can be extracted, an APP decision-making path can be obtained according to the decision-making APP nodes and the conversion APP nodes, frequent APP item sets can be obtained, and thus key contacts and APP strong association rules corresponding to the key contacts can be obtained. Since the sample size of the network behavior log data is large, the timeliness is strong, and the authenticity is high, true and comprehensive consumer insights can be obtained faster, more accurately, and more efficiently. The reliability of the advertisement contact information obtained in this way is higher, the effect of formulating an advertisement placement strategy according to the advertisement contact information is better, and thus the return on investment of advertisement marketing can be improved.

[0102] Combined with Figure 5 As shown in the figure, the embodiments of the present disclosure provide a device for obtaining advertisement contact information, and the device includes: a first acquisition module 501, a second acquisition module 502, a sorting module 503, a third acquisition module 504, and a determination module 505. The first acquisition module 501 is configured to acquire network behavior log data corresponding to multiple users respectively, and send the network behavior log data to the second acquisition module. The network behavior log data includes a user identity identification number ID, the occurrence time of a user behavior, the name of an application software APP used by the user, APP text information, and a status identifier of the network behavior log data. The second acquisition module 502 is configured to receive the network behavior log data sent by the first acquisition module, acquire decision-making APP nodes and conversion APP nodes corresponding to the respective network behavior log data, and send the decision-making APP nodes and the conversion APP nodes to the sorting module. The sorting module 503 is configured to receive the decision-making APP nodes and the conversion APP nodes sent by the second acquisition module, sort the decision-making APP nodes and the conversion APP nodes in chronological order, obtain an APP decision-making path corresponding to each network behavior log data, and send the APP decision-making path to the third acquisition module. The third acquisition module 504 is configured to receive the APP decision-making path sent by the sorting module, acquire frequent APP item sets according to each APP decision-making path, and send the frequent APP item sets to the determination module.

[0103] The determination module 505 is configured to receive the frequent APP item sets sent by the third acquisition module, determine the decision-making APP nodes in the frequent APP item sets as key contacts, and generate APP strong association rules corresponding to the key contacts according to the frequent APP item sets.

[0104] Using the device for obtaining advertising contact information provided by the embodiments of the present disclosure, the first acquisition module acquires network behavior log data corresponding to multiple users respectively. The network behavior log data includes user identity identification number ID, the occurrence time of user behavior, the name of the application software APP used by the user, APP text information, and the status identification of the network behavior log data. The second acquisition module acquires the decision APP node and the conversion APP node corresponding to each network behavior log data respectively. The sorting module sorts the decision APP node and the conversion APP node in chronological order to obtain the APP decision path corresponding to each network behavior log data respectively. The third acquisition module acquires the frequent APP item set according to each APP decision path. The determination module determines the decision APP node in the frequent APP item set as the key contact point, and generates the APP strong association rule corresponding to the key contact point according to the frequent APP item set. By extracting the decision APP node and the conversion APP node from the network behavior log data corresponding to the user, and obtaining the APP decision path according to the decision APP node and the conversion APP node, the frequent APP item set can be obtained, so that the key contact point and the APP strong association rule corresponding to the key contact point can be obtained. Since the sample size of the network behavior log data is large, the timeliness is strong, and the authenticity is high, the real and comprehensive consumer insights can be obtained faster, more accurately, and more efficiently. The advertising contact information obtained in this way is more reliable, making the effect of formulating the advertising placement strategy according to the advertising contact information better, and thus improving the return on investment of advertising marketing.

[0105] Further, the second acquisition module is configured to acquire the decision APP node and the conversion APP node corresponding to each network behavior log data respectively in the following manner: organize each APP text information according to a preset format to obtain a text data set. The text data set includes multiple pieces of text data; the text data includes the name of the APP used by the user, the title text, and the body text. Perform entity recognition on each piece of text data to obtain the first alternative brand name corresponding to each piece of text data respectively. Perform disambiguation processing on each first alternative brand name to obtain the standard brand name corresponding to each brand name respectively. Determine the decision APP node and the conversion APP node according to each standard brand name and the preset target brand.

[0106] Further, decision APP nodes and conversion APP nodes are determined according to each standard brand name and a preset target brand: The standard brand name that is the same as the preset target brand is determined as the second alternative brand name, and the APP information corresponding to the second alternative brand name is filtered out from the network behavior log data. The APP information includes the user ID, the name of the APP used by the user, the occurrence time of the user behavior, and the status identifier of the network behavior log data. When the second alternative brand name is included in the APP information or the text data corresponding to the APP information, the name of the APP used by the user in the APP information is determined as the target APP. And when the status identifier of the network behavior log data corresponding to the target APP is the first preset type identifier, the target APP is determined as a decision APP node. When the status identifier of the network behavior log data corresponding to the target APP is the second preset type identifier, the target APP is determined as a conversion APP node.

[0107] Further, the third acquisition module is configured to obtain frequent APP item sets according to each APP decision path in the following manner: Obtain the APP decision sets corresponding to each APP decision path, and determine the frequent APP item sets from each APP decision set.

[0108] Further, obtaining the APP decision set corresponding to the APP decision path includes: Traversing the APP decision path in chronological order, and determining the occurrence time of the user behavior corresponding to the first conversion APP node in the APP decision path as the first time. Starting from the first conversion APP node, traverse in the reverse direction of the chronological order, and determine the occurrence time of the user behavior corresponding to the traversed decision APP node as the second time. Respectively obtain the time differences between the first time and each second time. When the time difference is less than the preset time threshold, add the traversed decision APP node to the decision APP set; or, when the time difference is greater than or equal to the time threshold, perform a duplicate removal operation on the decision APP set. Remove the first conversion APP node and all nodes before the first conversion APP node from the APP decision path to obtain an alternative APP decision path; all nodes before the first conversion APP node are all nodes in the reverse direction of the chronological order starting from the first conversion APP node. Continue to traverse the alternative APP decision path in chronological order until there is no conversion APP node in the alternative APP decision path.

[0109] Further, determining the frequent APP item sets from each APP decision set includes: Performing the following operations on each APP decision set: Performing a full permutation on the decision APP nodes in the APP decision set to generate multiple item sets corresponding to the APP decision set. Obtain the support degrees corresponding to each item set, and determine the item sets corresponding to the support degrees greater than the first preset threshold as the frequent item sets.

[0110] Further, the determination model is configured to generate the APP strong association rules corresponding to the key contacts according to the frequent APP item sets in the following manner: perform a full permutation on the decision APP nodes in the frequent item sets to generate multiple non-empty proper subsets. Generate alternative rules by using the frequent item sets and each non-empty proper subset. Obtain the confidence levels corresponding to the alternative rules respectively, and determine the alternative rules with the confidence levels greater than the second preset threshold as the APP strong association rules.

[0111] Combined with Figure 6 As shown in the figure, an embodiment of the present disclosure provides an electronic device, including a processor 600 and a memory 601. Optionally, the electronic device may further include a communication interface 602 and a bus 603. Among them, the processor 600, the communication interface 602, and the memory 601 can complete mutual communication through the bus 603. The communication interface 602 can be used for information transmission. The processor 600 can call the logical instructions in the memory 601 to execute the method for obtaining advertising contact information in the above embodiments.

[0112] By using the electronic device provided in the embodiment of the present disclosure, by extracting the decision APP nodes and the conversion APP nodes from the network behavior log data corresponding to the user, and obtaining the APP decision path according to the decision APP nodes and the conversion APP nodes, frequent APP item sets can be obtained, and thus key contacts and the APP strong association rules corresponding to the key contacts can be obtained. Since the sample capacity of the network behavior log data is large, the timeliness is strong, and the authenticity is high, real and comprehensive consumer insights can be obtained faster, more accurately, and more efficiently. The advertising contact information obtained in this way is more reliable, making the effect of formulating the advertising placement strategy according to the advertising contact information better, and thus improving the return on investment of advertising marketing.

[0113] Optionally, the electronic device includes a computer, a tablet computer, a server, etc.

[0114] In addition, when the logical instructions in the above-mentioned memory 601 are implemented in the form of software function units and sold or used as an independent product, they can be stored in a computer-readable storage medium.

[0115] The memory 601, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as the program instructions / modules corresponding to the methods in the embodiments of the present disclosure. The processor 600 executes the functional applications and data processing by running the program instructions / modules stored in the memory 601, that is, implements the method for obtaining advertising contact information in the above embodiments.

[0116] The memory 601 may include a program storage area and a data storage area. The program storage area may store an operating system and application programs required for at least one function. The data storage area may store data created according to the use of the terminal device and the like. In addition, the memory 601 may include a high-speed random access memory and may also include a non-volatile memory.

[0117] An embodiment of the present disclosure provides a storage medium storing program instructions that, when running, execute the above method for obtaining advertisement contact information.

[0118] An embodiment of the present disclosure provides a computer program product. The computer program product includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions that, when executed by a computer, cause the computer to execute the above method for obtaining advertisement contact information.

[0119] The above computer-readable storage medium may be a transient computer-readable storage medium or a non-transient computer-readable storage medium.

[0120] The technical solution of an embodiment of the present disclosure may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The foregoing storage medium may be a non-transient storage medium, including: various media that can store program codes such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, or may also be a transient storage medium.

[0121] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure, enabling those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, process, and other changes. Embodiments merely represent possible variations. Unless explicitly required, individual components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terms used in this application are only for describing embodiments and do not limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to also include the plural forms. Similarly, as used in this application, the term "and / or" refers to any and all possible combinations of one or more of the associated listed items. Additionally, when used in this application, the term "comprise" and its variants "comprises" and / or "comprising" etc. mean the presence of the stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groupings of these. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, or device comprising the element. Herein, each embodiment may focus on the differences from other embodiments, and the same or similar parts among the embodiments may be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method parts disclosed in the embodiments, the relevant parts may refer to the description of the method parts.

[0122] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner may depend on the specific application and design constraints of the technical solution. The technical personnel can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the embodiments of the present disclosure. The technical personnel can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0123] In the embodiments disclosed in this document, the disclosed methods, products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units can be merely a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Additionally, the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms. The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to implement this embodiment. Additionally, in the embodiments of the present disclosure, the various functional units can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0124] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the block can occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks can also occur in a different order than that disclosed in the description. Sometimes, there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. Each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for obtaining advertising contact information, characterized in that, Including: Obtaining network behavior log data corresponding to multiple users respectively; The network behavior log data includes the occurrence time of user behavior; Obtaining a decision APP node and a conversion APP node corresponding to each of the network behavior log data; the network behavior log data includes the name of the APP used by the user, APP text information, or the network behavior log data includes a user identification number ID, the name of the APP used by the user, and a status identifier of the network behavior log data; Sorting the decision APP node and the conversion APP node in chronological order of the occurrence time to obtain an APP decision path corresponding to each of the network behavior log data; Obtaining frequent APP item sets according to each of the APP decision paths; Determining the decision APP node in the frequent APP item set as a key contact point, and generating an APP strong association rule corresponding to the key contact point according to the frequent APP item set; Among them, obtaining frequent APP item sets according to each of the APP decision paths includes: Traversing the APP decision path in chronological order, determining the occurrence time of the user behavior corresponding to the first conversion APP node in the APP decision path as the first time; starting from the first conversion APP node, traversing in the reverse direction of the chronological order in turn, and determining the occurrence time of the user behavior corresponding to the traversed decision APP node as the second time; respectively obtaining the time differences between the first time and each of the second times; in the case where the time difference is less than a preset time threshold, adding the traversed decision APP node to the decision APP set; or, in the case where the time difference is greater than or equal to the time threshold, performing a duplicate removal operation on the decision APP set; removing the first conversion APP node and all nodes before the first conversion APP node from the APP decision path to obtain an alternative APP decision path; all nodes before the first conversion APP node are all nodes in the reverse direction of the chronological order starting from the first conversion APP node; continuing to traverse the alternative APP decision path in chronological order until there is no conversion APP node in the alternative APP decision path; Performing the following operations on each APP decision set: performing a full permutation on the decision APP nodes in the APP decision set to generate multiple item sets corresponding to the APP decision set; obtaining the support degrees corresponding to each of the item sets; and determining the item sets corresponding to the support degrees greater than a first preset threshold as frequent APP item sets.

2. The method according to claim 1, wherein The network behavior log data includes the name of the APP used by the user, APP text information; obtaining a decision APP node and a conversion APP node corresponding to each of the network behavior log data includes: Sorting out each of the APP text information according to a preset format to obtain a text data set; the text data set includes multiple pieces of text data; the text data includes the name of the APP used by the user, a title text, and a body text; Perform entity recognition on each piece of the text data to obtain the first alternative brand names respectively corresponding to each piece of the text data; Perform disambiguation processing on each of the first alternative brand names to obtain the standard brand names respectively corresponding to each of the brand names; Determine a decision APP node and a conversion APP node according to each of the standard brand names and a preset target brand.

3. The method according to claim 2, wherein The network behavior log data includes a user identity identification number ID, the occurrence time of a user behavior, the name of the APP used by the user, and a status identifier of the network behavior log data; Determining a decision APP node and a conversion APP node according to each of the standard brand names and a preset target brand includes: Determine the standard brand names that are the same as the preset target brand as the second alternative brand names; Screen out the APP information corresponding to the second alternative brand names from the network behavior log data; the APP information includes a user ID, the name of the APP used by the user, the occurrence time of the user behavior, and a status identifier of the network behavior log data; In the case where the second alternative brand name is included in the APP information or the text data corresponding to the APP information, determine the name of the APP used by the user in the APP information as the target APP, and in the case where the status identifier of the network behavior log data corresponding to the target APP is the first preset type identifier, determine the target APP as the decision APP node; in the case where the status identifier of the network behavior log data corresponding to the target APP is the second preset type identifier, determine the target APP as the conversion APP node.

4. The method according to claim 1, wherein Generating the APP strong association rules corresponding to the key touchpoints according to the frequent APP item sets includes: Perform a full permutation on the decision APP nodes in the frequent APP item sets to generate multiple non-empty proper subsets; Generate alternative rules by using the frequent APP item sets and each of the non-empty proper subsets; Obtain the confidence levels respectively corresponding to each of the alternative rules; Determine the alternative rules with confidence levels greater than a second preset threshold as the APP strong association rules.

5. The method according to any one of claims 1 to 4, characterized in that In the case where the time difference is greater than or equal to a time threshold, perform a duplicate removal operation on the decision APP set, including: Determine whether there are duplicate decision APP nodes in the decision APP set; In the case where there are duplicate decision APP nodes in the decision APP set, remove the duplicate decision APP nodes.

6. The method according to any one of claims 1 to 4, characterized in that, Continue to traverse the alternative APP decision paths in chronological order until there are no conversion APP nodes in the alternative APP decision paths, including: Traverse the alternative APP decision paths in chronological order; Stop traversing in the case where there are no conversion APP nodes in the alternative APP decision paths to obtain a decision APP set.

7. The method according to claim 4, characterized in that, After obtaining the confidence levels respectively corresponding to each of the alternative rules, it further includes: Obtain the lift degrees respectively corresponding to each of the confidence levels; Determine the confidence levels with lift degrees greater than a third preset threshold as valid confidence levels; Determine the alternative rules corresponding to the valid confidence levels greater than the second preset threshold as valid APP strong association rules.

8. A device for obtaining advertisement contact information, characterized in that, including: A first acquisition module configured to acquire network behavior log data respectively corresponding to multiple users; The network behavior log data includes the occurrence time of user behavior; A second acquisition module, configured to acquire a decision APP node and a conversion APP node respectively corresponding to each of the network behavior log data; the network behavior log data includes the name of the APP used by the user, APP text information, or the network behavior log data includes a user identification number ID, the name of the APP used by the user, and a status identifier of the network behavior log data; A sorting module, configured to sort the decision APP node and the conversion APP node in chronological order of the occurrence time to obtain an APP decision path respectively corresponding to each of the network behavior log data; A third acquisition module, configured to acquire a frequent APP item set according to each of the APP decision paths; A determination module, configured to determine the decision APP node in the frequent APP item set as a key contact point, and generate an APP strong association rule corresponding to the key contact point according to the frequent APP item set; Among them, acquiring a frequent APP item set according to each of the APP decision paths includes: Traversing the APP decision path in the chronological order, determining the occurrence time of the user behavior corresponding to the first conversion APP node in the APP decision path as the first time; starting from the first conversion APP node, traversing in the direction opposite to the chronological order in turn, and determining the occurrence time of the user behavior corresponding to the traversed decision APP node as the second time; respectively obtaining the time difference between the first time and each of the second times; in the case that the time difference is less than a preset time threshold, adding the traversed decision APP node to the decision APP set; or, in the case that the time difference is greater than or equal to the time threshold, performing a duplicate removal operation on the decision APP set; removing the first conversion APP node and all nodes before the first conversion APP node from the APP decision path to obtain an alternative APP decision path; all nodes before the first conversion APP node are all nodes in the direction opposite to the chronological order starting from the first conversion APP node; continuing to traverse the alternative APP decision path in the chronological order until there is no conversion APP node in the alternative APP decision path; Performing the following operations on each APP decision set: performing a full permutation on the decision APP nodes in the APP decision set to generate a plurality of item sets corresponding to the APP decision set; obtaining the support degree corresponding to each of the item sets; determining the item set corresponding to the support degree greater than a first preset threshold as a frequent APP item set.

9. An electronic device, comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to execute the method for obtaining advertisement contact point information according to any one of claims 1 to 7 when running the program instructions.

10. A storage medium stores program instructions, characterized in that, When running, the program instructions execute the method for obtaining advertisement contact point information according to any one of claims 1 to 7.

Images