CN111966948B - Information delivery method, device, equipment and storage medium - Google Patents
Information delivery method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN111966948B CN111966948B CN202011021719.5A CN202011021719A CN111966948B CN 111966948 B CN111966948 B CN 111966948B CN 202011021719 A CN202011021719 A CN 202011021719A CN 111966948 B CN111966948 B CN 111966948B
- Authority
- CN
- China
- Prior art keywords
- search
- website
- target
- websites
- search word
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure provides an information delivery method, relates to the technical field of Internet, in particular to the field of network popularization, and can be applied to scene recognition of user intention. The information delivery method comprises the steps of obtaining historical access data of a plurality of websites, and determining a target website set to be subjected to information delivery in the websites according to the historical access data; determining the weight of each intention search word in the intention search word set used for accessing the target website set according to the historical access data; screening users accessing at least one target website in the target website set according to the intention search word set and the weight to obtain a target user set; and delivering the information to users in the target user set. The disclosure also provides an information delivery device, equipment and a storage medium.
Description
Technical Field
The present disclosure relates to the field of internet technologies, in particular, to the field of network popularization, and more particularly, to an information delivery method, an information delivery device, and a storage medium.
Background
With the development of internet technology, information delivery becomes a main information flow marketing means. At present, the information delivery method mainly comprises information delivery based on intention words and information delivery based on crowd packages.
Information delivery based on intention words the target delivery crowd is delineated by setting intention words related to the business of the information to be delivered, which cannot adequately reflect the potential intention of the user. The method can reflect the potential intention of the user to a certain extent, but the target delivery crowd and the business are limited to one preset website.
Disclosure of Invention
In view of this, the present disclosure provides an information delivery method, apparatus, device, and storage medium.
The first aspect of the present disclosure provides an information delivery method, including:
acquiring historical access data of a plurality of websites, and determining a target website set to be subjected to information release in the websites according to the historical access data;
determining an intention search word set for accessing the target website set and weights of all intention search words in the intention search word set according to the historical access data;
Screening users accessing at least one target website in the target website set according to the intention search word set and the weight to obtain a target user set; and
and the information is put into users in the target user set.
A second aspect of the present disclosure provides an information delivery apparatus, including:
the target website determining module is configured to acquire historical access data of a plurality of websites and determine a target website set to be subjected to information release in the websites according to the historical access data;
an intent representation determination module configured to determine a set of intent search terms for accessing the set of target websites and weights for individual intent search terms in the set of intent search terms based on the historical access data;
the target user screening module is configured to search the word set and the weight according to the intention, and screen users accessing at least one target website in the target website set to obtain a target user set; and
and the information delivery module is configured to deliver the information to the users in the target user set.
A third aspect of the present disclosure provides an information delivery apparatus, including:
A memory storing program instructions; and
and a processor configured to execute the program instructions to perform the information delivery method provided in the first aspect of the present disclosure.
A fourth aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions that, when executed, are configured to implement the information delivery method provided by the first aspect of the present disclosure.
A fifth aspect of the present disclosure provides a computer program product comprising a computer program which, when executed by a processor, implements the above method.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent from the following description of embodiments thereof with reference to the accompanying drawings in which:
FIG. 1 schematically illustrates a system architecture to which an information delivery method according to an embodiment of the present disclosure is applied;
FIG. 2 schematically illustrates a flow chart of a method of information delivery according to an embodiment of the present disclosure;
FIG. 3 schematically illustrates a flow chart of a method of determining a set of target websites among a plurality of websites according to another embodiment of the present disclosure;
FIG. 4 schematically illustrates an implementation of the method of determining a set of target websites in the plurality of websites shown in FIG. 3;
FIG. 5 schematically illustrates a flow chart of a method of determining weights for intended search terms according to another embodiment of the present disclosure;
FIG. 6 schematically illustrates a flowchart of a method of screening target users for terms and weights according to intent in accordance with another embodiment of the present disclosure;
FIG. 7 schematically illustrates a block diagram of an information delivery device according to an embodiment of the disclosure;
fig. 8 schematically shows a block diagram of an information delivery device adapted to perform information delivery according to an embodiment of the present disclosure.
Detailed Description
Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is only exemplary and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the concepts of the present disclosure.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and/or the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be construed to have meanings consistent with the context of the present specification and should not be construed in an idealized or overly formal manner.
Where expressions like at least one of "A, B and C, etc. are used, the expressions should generally be interpreted in accordance with the meaning as commonly understood by those skilled in the art (e.g.," a system having at least one of A, B and C "shall include, but not be limited to, a system having a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).
When training is performed by using a training data set constructed by image data acquired by a road side sensor and a lamp color recognition neural network model is built, the recognition effect of the built neural network model is affected because yellow lamp data occupies less in the training data set. The embodiment of the disclosure provides an image data mining method for automatically screening image data lighted by a yellow lamp from image data acquired by a road side sensor so as to supplement a training data set, thereby improving the recognition effect of an established neural network model.
Fig. 1 schematically illustrates a system architecture to which an information delivery method according to an embodiment of the present disclosure is applied. As shown in fig. 1, a terminal device 101 communicates with a server 102 via a network 103. The terminal device 101 may be a variety of electronic devices that can be used for internet access including, but not limited to, personal computers, notebook computers, tablet computers, mobile phones, smart phones, personal digital assistants PDAs, wearable devices, etc. The server 102 collects various behavior data when the user accesses the internet, and mines the user's intention by analyzing the user behavior data to push a traffic information stream to the user according to the user's intention. The server 102 may be a stand-alone server or a cluster of a plurality of servers. The system architecture shown in fig. 1 is merely an example, and the information delivery method according to the embodiments of the present disclosure may be applied in any suitable scenario to achieve information delivery for an intended crowd.
Fig. 2 schematically illustrates a flow chart of an information delivery method 200 according to an embodiment of the disclosure. As shown in fig. 2, the information delivery method 200 includes the steps of:
in step S210, historical access data of a plurality of websites is acquired, and a target website set to be subjected to information delivery in the plurality of websites is determined according to the historical access data.
In step S220, a set of intent search words for accessing the set of target websites and weights for each of the intent search words in the set of intent search words are determined based on the historical access data.
In step S230, users accessing at least one target website in the target website set are filtered to obtain the target user set according to the intention search word set and the weight.
In step S240, the information is delivered to the users in the target user set.
In the information delivery process based on crowd-sourcing, information is fixedly delivered to a target website, the target website is closely related to information to be delivered in service, and the close relativity in service can be determined through industrial investigation before information delivery. The limitation of the crowd-sourced information delivery method is that, on the one hand, since the target object of such information delivery is limited to the crowd visiting the target website, it is possible to miss users who actually have an interest in the information to be delivered, but have visited another, business-like website without visiting the target website. On the other hand, in view of the cost of the prior investigation, it is impossible to acquire all the websites similar in business for information delivery before information delivery.
According to the embodiment of the disclosure, a target website to be subjected to information delivery is first expanded. Specifically, in step S210, historical access data of a plurality of websites is obtained, where the historical access data of the websites is used to record historical access behaviors of the user to the websites. For example, the historical access data records the time of the user access behavior, the website accessed by the user, the specific page of the website accessed by the user, the time of the user visiting the specific page, the time of leaving the page and other user access behavior tracks. Further, according to the historical access data, the residence time of the user on a specific webpage can be obtained, and information such as the number of times the user accesses a certain website or a certain specific webpage in a period of time can be obtained.
Historical access data for the website may be recorded on the user device. For example, when a user accesses the internet through a browser application installed on a personal computer or a handheld mobile device, the browser may record the user's access behavior in a search log accordingly. For example, in a search log, a search statement or the like used by a user, which is the website and time of the accessed website, the identity information of the user who performed the access, and the like are generally recorded. According to an embodiment, a search log may be utilized to obtain historical access data for a website. Embodiments of the present disclosure are not limited in this regard and various suitable methods may be employed to obtain historical access data for a website.
Next, at least one website which is similar in business to the first website to be subjected to information delivery is determined from a plurality of websites obtained according to the acquired historical access data, so as to expand the websites to be subjected to information delivery. Here, the first website to be subjected to information delivery may be a target website determined by an industry investigation before delivering information as described above, or may be a target website determined according to a significant correlation on a service attribute, or may be a target website targeted in an existing crowd-based information delivery application. The first web site may be determined by one skilled in the art according to the actual situation. According to an embodiment, the principle of augmenting the target web site is to find a web site that is similar in business to the first web site. Thus, by expanding the target website, information delivery can be expanded in business. If the user is interested in the business associated with the first web site, it is highly likely that other web sites that are similar in business to the first web site will be accessed even if the user does not access the first web site. Therefore, in the present embodiment, by expanding the target website, the information delivery party range can be remarkably expanded.
Next, after the target website to be subjected to information delivery is expanded into a target website set, it is necessary to make further determination of the intention of the user who accesses the website. This is because a user who accesses a set of target websites is likely to have accessed only one or a few target websites in the set of target websites by mistake, and in this case, the user cannot be considered to be interested in the business related to the set of target websites, and thus there is a possibility that information may be erroneously put in. In an embodiment of the present disclosure, in step S220 and in step S230, users accessing at least one target website in the target website set are further filtered by determining the set of intent search terms for accessing the target website set and the weight of each intent search term in the set of intent search terms according to the historical access data and according to the set of intent search terms and the weight of each intent search term in the set of intent search terms, thereby excluding users who have actually accessed only one or several target websites in the target website set by mistake, to avoid erroneous delivery of information. According to an embodiment, the target user set is obtained by further screening the users accessing at least one target website in the target website set, and in step S240, information delivery is performed only on the target user set.
According to the embodiment of the disclosure, the target website set is obtained by expanding the target websites to be subjected to information release, so that the coverage range of the information release is remarkably enlarged. Meanwhile, according to the intention search word set used for accessing the target website set and the weight of the intention search word, the actual intention of the user accessing at least one target website in the target website set is inferred to carry out information release, and accurate information release is ensured.
FIG. 3 schematically illustrates a flow chart of a method of determining a set of target websites among a plurality of websites according to another embodiment of the present disclosure. As shown in fig. 3, the method comprises the following steps:
in step S311, a set of search sentences for each of the plurality of websites is determined from the history access data.
In step S312, a first website to be subjected to information delivery is determined among a plurality of websites.
In step S313, a website having an intersection of the search term set and the search term set of the first website is determined as a candidate website among the plurality of websites.
In step S314, it is determined that, among the candidate websites, the candidate websites having the similarity of the search term set with the search term set of the first website greater than the preset second threshold are second websites.
In step S315, the first website and the second website are included in the target website set.
According to an embodiment, in step S311, the set of search sentences of the website refers to search sentences used when the user searches and accesses the website by searching. In this embodiment, the search term may be any form of expression. For example, the search term may be a sentence, a phrase, a word, or an expression containing characters, such as a plurality of phrases, a plurality of words, or the like, which are spaced apart from each other by spaces. The form of the search statement is not limited in the embodiments of the present disclosure. According to an embodiment, a search statement and a correspondence of the search statement to a website may be obtained through a search log. The identity information of the user accessing the website, the time the user accessed the website, the search sentences used by the user, and the website address of the accessed website can be obtained by means of existing search log extraction tools. Based on this information, the search term used by the user is included in the search term set. It will be readily appreciated that the same user may enter the same website or website page through different search terms, and different users may enter the same website or website page through the same or different search terms. These search terms should be contained in a collection of search terms corresponding to the web site being accessed. For example, according to the record of the search log, the user a accesses the IT technical website C through the search term "system software", and the user B accesses the IT technical website C through the search term "system fail to start", and both the search term "system software" and "system fail to start" are included in the search term set of the website C.
Next, in step S312, the method in the foregoing embodiment may be employed to determine the first website to be subjected to information delivery. For example, a preferred website determined according to the business attribute of the information to be put is taken as the first website. Or expanding the target website for information delivery based on the existing crowd-sourced information delivery application, and taking the target website aimed at in the existing crowd-sourced information delivery application as the first website.
Next, in step S313, websites that are candidate websites are determined among the plurality of websites, that is, websites that are similar in traffic to the first website are preliminarily screened. According to an embodiment, a search term set of each of a plurality of websites except for a first website is compared with a search term set of the first website, and if a certain search term of the search term set of the first website is included in the search term sets of websites (except for the first website), the website is determined as a candidate website. And comparing the search statement set of each website except the first website with the search statement set of the first website in turn, and finally excluding websites in which the search statement set and the search statement set of the first website have no intersection. For example, if the search term set of one website among the plurality of websites is { system failed to start, system software, computer black }, and the search term set of the first website is { system software, windows, windows10}, the website is determined as a candidate website because the "system software" in the search term set of the first website is included in the search term set of the website.
Next, in step S314, among the determined plurality of candidate websites, a website that is a second website is determined by calculating a similarity between the search term set of each candidate website and the search term set of the first website, that is, candidate websites that are similar in traffic to the first website are further screened. According to an embodiment, calculating the similarity between the set of search terms of each candidate website and the set of search terms of the first website includes extracting the set of search terms of the first website from the set of search terms of the first website according to the historical access data, extracting the set of search terms of each candidate website from the set of search terms of each candidate website in the candidate websites according to the historical access data, and counting the number of identical search terms included in the set of search terms of the first website and the set of search terms of each candidate website, respectively.
Extracting a set of search terms for the first web site from the set of search terms for the first web site based on the historical access data further includes the steps of segmenting and filtering. Specifically, according to an embodiment, each search sentence included in the search sentence set of the first website is subjected to segmentation processing to obtain at least one first search word, the at least one first search word is included in the search word set of the first website, statistics is performed on the number of times of accessing the first website through the at least one first search word according to historical access data, and the first search word with the number of times smaller than a preset third threshold value is deleted from the obtained search word set of the first website.
The segmentation processing of the search sentence refers to the segmentation of the search sentence into a plurality of search words in a single word unit by using a word segmentation tool. In general, in the multiple search words obtained by segmentation, some auxiliary words and punctuations which do not have actual meanings can be removed, and only words, such as nouns and verbs, which represent the actual meanings are reserved. For example, for the search statement "why cannot the system be started? The result of the segmentation process is that a set of search terms { system, why, not, started,? "why", "what" and "? "and only" system "," no "and" launch "are reserved as first search terms. However, in some embodiments, "system" and "launch" may also be reserved in the set of search terms as the first search term, which may be determined by the word segmentation tool used, and the disclosed embodiments do not limit the terms.
Then, on the basis of the search word set obtained through the segmentation processing, the user access amount of each search word in the search word set is screened. The user access amount in the embodiments of the present disclosure refers to the number of times that a user accessing a website accesses the website through a search term including the search term, and the user access amount may be counted according to historical access data. For example, if the search term set of the first website a is { system failed to start, system software, system failure, computer black }, the search term set after the segmentation process for the search term set includes the first search term "system". Next, obtaining an access behavior record of the user about the first website a according to the historical access data includes: user B accesses the main page of the first website a at time a via the search term "system fail start", user B accesses page A1 of the first website a via the search term "system fail" at time B, and user C accesses page A2 of the first website a via the search term "system software" at time C. Thus, in the time period from a to d, the user B accesses the first website a (the access to the second page of the first website a is also denoted as the access to the first website a) 3 times sequentially through the search sentence containing the first search word "system", so the counted number of user accesses for the search word "system" is 3 times. The more times the user accesses the first website through the search word, the higher the correlation between the search word and the service of the first website is, namely, the better the search word can reflect the service of the first website. In an embodiment of the present disclosure, a threshold value (third threshold value) related to the user access amount is preset, the counted number of times of accessing the first website through the search word is compared with the threshold value, the search word with the number of times smaller than the threshold value is deleted from the previously obtained search word set, and only the search word with the number of times greater than or equal to the threshold value is retained in the search word set. Through the screening based on the access amount of the user, the relevance of the search word and the service of the first website can be further improved.
Next, the steps of segmentation and filtering are performed as described in the above embodiments in the operation of extracting the search term set of each candidate website from the search term set of each candidate website, respectively, according to the history access data. Specifically, according to an embodiment, each search sentence included in the search sentence set of each candidate website is subjected to segmentation processing to obtain at least one second search word, the at least one second search word is included in the search word set of the candidate website, the number of times of visiting the greeting selected website through the at least one second search word is counted according to historical access data, and the second search word with the number of times smaller than a third threshold value is deleted from the obtained search word set of the candidate website. According to the embodiment, the search term set of each candidate website can be obtained by performing the above operation on the search term set of each candidate website. The step of segmenting and filtering the search term may refer to the operation performed on the search term set of the first website, which is not described herein.
By the above processing of the search term set of the first website and the search term set of each candidate website, the search term set of the first website and the search term set of each candidate website can be obtained, respectively. Next, for each candidate website, the number of the same search words in the search word set of the candidate website and the search word set of the first website are counted. According to an embodiment, a query approach may be employed. For example, a query may be made as to whether the set of search terms for the first website have the same search term for each search term in the set of search terms for the candidate website. According to an embodiment, the calculation may also be based on vectors. For example, the search terms in the search term set of the candidate website and the search terms in the search term set of the first website may be respectively ranked according to a certain ranking rule, and calculated according to a method for calculating the vector similarity between the ranked sets.
The similarity between the set of search terms for each candidate website and the set of search terms for the first website reflects the relevance of the two sets in terms of search term granularity, and the higher the similarity, the higher the relevance between the two sets. It is readily understood that the higher the correlation between the two sets, the more similar the search terms contained in the search terms in the description set, which indicates that the two websites are more similar in terms of business. Thus, a threshold value related to the set similarity can be preset. For example, in the case where the set similarity is obtained by counting the number of the same search words in the search word set of the candidate web site as the search word set of the first web site, a threshold value, such as a second threshold value, regarding the number of the same search words may be set. Comparing the counted number of the same search words with a second threshold value, and determining candidate websites with the number of the same search words larger than the second threshold value as second websites. And comparing the statistics made for each candidate website in turn, and screening candidate websites meeting the conditions from the statistics as second websites.
Next, in step S315, the first website and the at least one second website obtained by the screening are taken together as target websites, thereby expanding the target websites from the first website to a target website set of a plurality of websites including the first website and the at least one second website.
FIG. 4 schematically illustrates an implementation of the method of determining a set of target websites in the plurality of websites shown in FIG. 3. As shown in fig. 4, 5 websites, URL1, URL2, URL3, URL4, and URL5, respectively, are acquired according to the history access data. FIG. 4 also shows a set of search data for each web site determined from the historical access data. For example, the search statement set for URL1 is { A1, A2, A3, A4, A5}. First, a first website is determined according to service attributes, and URL1 is set as the first website closest to information to be put in service, and URL1 and a search statement set thereof are shown by rectangular boxes as shown in fig. 4. Candidate websites are then determined among websites URL2, URL3, URL4, and URL5. As shown in fig. 4, the search term set of the web site URL2 is { A1, A2, A6}, wherein the search terms A1 and A2 are also included in the search term set of the web site URL1, so that the search term set of the web site URL2 and the search term set of the web site URL1 have intersections { A1, A2}, thus determining the web site URL2 as a candidate web site. Similarly, the intersection between the set of search terms of web site URL3 and the set of search terms of web site URL1 is obtained as the set { A3, A4, A5}, and the intersection between the set of search terms of web site URL4 and the set of search terms of web site URL1 is obtained as the set { A5}, so that web site URL4 and URL5 are also determined as candidate web sites. The set of search terms for web site URL5 is { D1, D2, D3, D4, D5}, where none of the search terms are identical to the search terms of web site URL 1. Therefore, there is no intersection between the set of search terms of website URL5 and the set of search terms of website URL1, and thus Wang Zhang URL5 cannot be a candidate website. Thus, a candidate web site set including web sites URL2, URL3, and URL4 is further obtained. And extracting the search sentence sets of the websites to obtain the search word sets of the websites. As shown in fig. 4, the search word set of the first web site URL1 is { a11, a12, a21, a22, a32}, and the search word set of the second web site URL2 is { a11, a12, a61, a62, a63}, so the number of search words having the same structure between the first web site URL1 and the second web site URL2 is 2. Similarly, the number of search words having the same meaning as that of the first web site URL1 and the third web site URL3 is 3, and the number of search words having the same meaning as that of the first web site URL1 and the fourth web site URL4 is 1. If it is assumed that the second threshold value is preset to 2 in this example, the second web site URL2 is selected as the second web site. The final target web site set is a set composed of the first web site URL1 and the third web site URL3, as shown in fig. 4.
According to the embodiment of the disclosure, the target website which only comprises the first website is expanded to expand the information release range. Meanwhile, based on preliminary screening and further screening of the first website and other websites in the plurality of websites, the correlation of the expanded second website and the first website in service is ensured, so that the accuracy of information delivery is ensured.
Fig. 5 schematically illustrates a flow chart of a method of determining weights for intended search terms according to yet another embodiment of the present disclosure. As shown in fig. 5, the method comprises the following steps:
in step S521, a set of search sentences for the set of target websites is determined from the history access data.
In step S522, a set of search terms for the set of target websites is extracted from the set of search sentences for the set of target websites according to the history access data.
In step S523, the number of target websites in the set of target websites accessed by the search term is counted according to the history access data, and the counted number value is used as the weight of the search term.
In step S524, the search word having the weight of the obtained search word greater than the preset fourth threshold is determined as an intended search word for accessing the target website in the target website set, the intended search word is included in the intended search word set, and the weight of the obtained search word is taken as the weight of the intended search word.
According to an embodiment, in step S521, the set of search sentences for the set of target websites refers to search sentences used when the user searches and accesses any one of the set of target websites. The search term set may be obtained by referring to the previous method of obtaining a search term set for each of a plurality of websites. In addition, in the present embodiment, the target website set is composed of the first website and the second website obtained by screening, and therefore, the search term set for the target website set may be obtained by combining the search term set of the first website and the search term set of the second website obtained by screening.
Next, in step S522, extracting the set of search terms for the set of target websites from the set of search sentences for the set of target websites may include the steps of segmentation and filtering. According to an embodiment, the method specifically includes that each search sentence included in a search sentence set of a target website set is segmented to obtain at least one target search word, the at least one target search word is contained in the search word set of the target website set, statistics is carried out on the number of times of accessing a target website in the target website set through the at least one target search word according to historical access data, and the target search word with the number of times smaller than a preset third threshold value is deleted from the obtained search word set of the target website set. More specific operations may be performed by referring to the operation of extracting the search term set of the first website from the search term set of the first website according to the historical access data in the foregoing embodiments, which is not described herein. It should be noted that the set of search terms of the target web site set cannot be obtained by the union between the set of search terms of the first web site obtained previously and the set of search terms of the second web site obtained by screening. This is because, when the classified search terms are screened based on the user access amount, it is counted from the history access data how many times all target websites included in the target website set are accessed by the search term including the search term.
Next, in step S523, a weight of each search term is calculated on the search term set of the resulting target web site set. According to an embodiment, for each search term included in a set of search terms of a set of target websites, a count is made of a number of target websites in the set of target websites accessed by a search sentence containing the search term. For example, if the set of target websites includes 5 target websites, denoted as target websites A, B, C, D and E, respectively. For a certain search term in the search term set, such as the search term "system", the query history access data obtains the following behavior record, the user U1 accesses the target website a at time a through the search term "system cannot be started", the user U1 accesses the target website B through the search term "system failure" at time B, and the user U2 accesses the page A2 of the target website a and the target website E through the search term "system software" at time c. Then 3 websites in the set of target websites, namely target websites A, B and E, are accessed by the search term containing the search term "system", so the number of target websites accessed by the search term containing the search term "system" is noted as 3. It should be noted that in the statistics process, it is not necessary to distinguish between accesses by different users to different websites (e.g., user U1 accesses target website B and user U2 accesses target website E). And during the statistics process, the same target website accessed by different search sentences containing the search term (e.g., user U1 accesses target website A via "System cannot Start" and user U2 accesses page A2 of target website A via "System software") is not counted repeatedly. Thus, in this example, the maximum number counted is 5, i.e., the number of target websites included in the target website set.
The number of target websites in the target website set that can be accessed by the search term containing the search term indicates the business relationship between the search term and the target websites in the target website set. The more the number of target websites in the target website set that can be accessed by a search term, the better the search term can be shown to represent the business associated with each target website, i.e. the search term has obvious characteristics on the business of the target websites. In other words, if a user accesses target websites in a set of target websites through such search terms, it is explained that more when the user accesses the target websites, information about the traffic of the target websites can be delivered to the user because of representative traffic of the target websites. In this embodiment, the counted number value is used as the weight of the search term. For example, the weight of the search term "system" is determined to be "3".
Next, in step S524, after the weights of each search word in the search word set of the target website set are obtained by statistics, the intent search word and the weights of the intent search word of the target website in the target website set are determined using the search word and the determined search word weights. Specifically, a threshold (fourth threshold) related to the weight of the search term is preset, the search term with the weight smaller than or equal to the threshold is deleted, only the search term with the weight larger than the threshold is reserved and used as the intended search term of the target website, and the weight of the corresponding search term is used as the weight of the intended search term. This is to account for the fact that if the weight of a search term is too small, it is stated that only a small number of target websites in the set of target websites can be accessed by the search term, which is stated that the search term is not already well representative of the traffic of the target websites in the set of target websites. According to another embodiment of the present disclosure, after the number of target websites accessed through the search term including the search term is counted, the counted number value may be normalized, and the normalized number value may be used as a weight of the search term. The method mainly aims at the situation that a large number of target websites are included in the target website set, and the situation that the weights are too large and are difficult to store and calculate is avoided.
According to the embodiment of the disclosure, the search word which can better represent the target website service is selected by calculating the weights of the intention search word and the intention search word of the target website on the search word set of the target website set, and meanwhile, the representative relationship is quantified by utilizing the weight characteristics, so that the comparison of the access intention of the user is facilitated, and the information delivery is more accurately carried out.
FIG. 6 schematically illustrates a flowchart of a method of screening target users for terms and weights according to intent in accordance with another embodiment of the present disclosure. As shown in fig. 6, the screening process includes the steps of:
in step S641, search terms used by the user to access at least one target website in the set of target websites are obtained.
In step S642, among the search words used by the user, search words falling into the set of intended search words are determined as intended search words of the user.
In step S643, the weights of the intent search words of the user are determined from the weights of the individual intent search words in the intent search word set.
In step S644, a user intent score for the target web site collection is calculated based on the weight of the user intent search term.
In step S645, users whose intention scores are greater than a preset first threshold are included in the target user set.
The embodiment provides a process for determining a target user to be subjected to information delivery according to an intention search word of a target website and the weight of the intention search word. Specifically, in step S641, first, a search sentence used by the user to access at least one target website in the target website set is acquired, and then the used search sentence is subjected to a segmentation process to obtain at least one search term. In this embodiment, the operation of obtaining the search term from the search sentence used by the user may refer to the segmentation process of extracting the search term set of the first website from the search sentence set of the first website in the foregoing embodiment, which is not described herein. Next, in step S642 and step S643, it is determined whether the search words used by the user are intended search words of the target website, those search words that fall into the intended search word set are found, and these search words are taken as the intended search words of the user, while the corresponding weights are obtained. Next, in step S644, the weights of the user 'S intention search terms are added, and the sum of the weights is used as a score for the user' S intention to the target web site collection.
According to an embodiment, the higher the user's intent score, the more likely the user accesses the target websites in the set of target websites to be representative of the traffic of those target websites. Thus, a threshold (first threshold) related to the score of the score may be preset according to the delivery demand, and the delivery scale, i.e. the number of target people to which information delivery is to be made, may be determined by the threshold. Specifically, a first threshold value having a large value may be set, and a user whose intention score is larger than the first threshold value may be regarded as the target user. Therefore, users in the target user set can have higher intention scoring, and information delivery can be performed more accurately. In further embodiments, it is also possible to set a first threshold value having a smaller value and to set a user whose intention score is greater than the first threshold value as the target user. Therefore, more users can be contained in the target user set, not only can certain throwing accuracy be ensured, but also the information throwing range can be properly enlarged, and the method is suitable for occasions requiring high coverage rate of information throwing. In actual use, a suitable first threshold can be selected according to specific information delivery requirements or service requirements, so that the number of target users is adjusted, and information delivery with controllable coverage range and accuracy is performed. The information delivery method according to the embodiment of the disclosure can be widely applied to various information flow marketing.
Fig. 7 schematically shows a block diagram of an information delivery device 700 according to an embodiment of the disclosure. As shown in fig. 7, the information delivery apparatus 700 includes a target website determination module 710, an intent representation determination module 720, a target user screening module 730, and an information delivery module 740.
According to an embodiment, the target website determining module 710 is configured to obtain historical access data of a plurality of websites, and determine a target website set to be information released among the plurality of websites according to the historical access data. The intent representation determination module 720 is configured to determine a set of intent search terms for accessing the set of target websites and weights for individual intent search terms in the set of intent search terms based on the historical access data. The target user screening module 730 is configured to screen users accessing at least one target website in the set of target websites for a set of target users based on the intent search term set and the weights. The information delivery module 740 is configured to deliver information to users in the set of target users.
The specific operations of the above functional modules may be obtained by referring to the operation steps of the information delivery method 200 in the foregoing embodiments, which are not described herein.
Fig. 8 schematically shows a block diagram of an information delivery device 800 adapted to perform information delivery according to an embodiment of the present disclosure. The information delivery method according to the embodiment of the present disclosure may be performed using the information delivery apparatus shown in fig. 8.
As shown in fig. 8, an information delivery device 800 according to an embodiment of the present disclosure includes a processor 801 and a memory 802. The processor 801 may perform various suitable actions and processes in accordance with programs or instructions stored in the memory 802. The processor 801 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or an associated chipset and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), or the like. The processor 801 may also include on-board memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for performing the different actions of the method flows according to embodiments of the disclosure.
The processor 801 and the memory 802 are connected to each other by a bus. The processor 801 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the memory 802. It should be noted that the program may also be stored in one or more storage devices other than the memory 802. The processor 801 may also perform various operations of the method flows according to embodiments of the present disclosure by executing programs stored in the one or more storage devices.
According to an embodiment of the present disclosure, the information delivery device 800 may further comprise an input means 803 and an output means 804, the input means 803 and the output means 804 also being connected to the bus. Furthermore, the information delivery device 800 may further include one or more of the following: an input section including a keyboard, a mouse, etc.; an output section including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), etc., and a speaker, etc.; a storage section including a hard disk or the like; and a communication section including a network interface card such as a LAN card, a modem, and the like.
According to embodiments of the present disclosure, the method flow according to embodiments of the present disclosure may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable storage medium, the computer program comprising program code for performing the method shown in the flowcharts. In such embodiments, the computer program may be downloaded and installed from a network via a communication portion, and/or installed from a removable medium. The above-described functions defined in the system of the embodiments of the present disclosure are performed when the computer program is executed by the processor 801. The systems, devices, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.
The present disclosure also provides a computer-readable storage medium and a computer program product. The computer-readable storage medium may be embodied in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the apparatus/device/system. The computer readable storage medium carries one or more programs which, when executed by the processor 801, implement methods in accordance with embodiments of the present disclosure. The computer program product comprises a computer program which, when executed by a processor, can implement the method of any of the embodiments described above.
According to embodiments of the present disclosure, the computer-readable storage medium may be a computer-non-volatile computer-readable storage medium, which may include, for example, but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Those skilled in the art will appreciate that the features recited in the various embodiments of the disclosure and/or in the claims may be combined in various combinations and/or combinations, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, the features recited in the various embodiments of the present disclosure and/or the claims may be variously combined and/or combined without departing from the spirit and teachings of the present disclosure. All such combinations and/or combinations fall within the scope of the present disclosure.
The embodiments of the present disclosure are described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the embodiments cannot be used advantageously in combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be made by those skilled in the art without departing from the scope of the disclosure, and such alternatives and modifications are intended to fall within the scope of the disclosure.
Claims (14)
1. An information delivery method, comprising:
acquiring historical access data of a plurality of websites, and determining a target website set to be subjected to information release in the websites according to the historical access data;
determining a search statement set for the target website set according to the historical access data;
extracting a search word set of the target website set from the search statement set of the target website set according to the historical access data;
counting the number of target websites in the target website set accessed by the search word according to the historical access data, and taking the counted number value as the weight of the search word;
Determining the search word with the weight of the obtained search word being greater than a preset fourth threshold as an intention search word of a target website in the target website set, including the intention search word in the intention search word set, and taking the weight of the obtained search word as the weight of the intention search word;
acquiring search words used by a user to access at least one target website in the target website set;
determining search words falling into the intent search word set from search words used by the user as intent search words of the user;
determining the weight of the intention search word of the user according to the weight of each intention search word in the intention search word set;
calculating intention scoring of the user to the target website set according to the weight of the intention search word of the user;
the users with the intention scores larger than a preset first threshold value are contained in a target user set; and
and the information is put into users in the target user set.
2. The method of claim 1, wherein the determining a set of target websites from the historical access data for which information is to be posted among the plurality of websites comprises:
Determining a set of search terms for each of the plurality of websites based on the historical access data;
determining a first website to be subjected to information release in the plurality of websites;
determining websites, which have intersections with the search statement set of the first website, from the plurality of websites as candidate websites;
determining candidate websites, of which the similarity between the search sentence set and the search sentence set of the first website is greater than a preset second threshold, from the candidate websites as second websites;
the first website and the second website are included in the set of target websites.
3. The method of claim 2, wherein the determining, among the candidate websites, candidate websites having a similarity of a set of search sentences to a set of search sentences of the first website greater than a preset second threshold as second websites comprises:
extracting a search word set of a first website from the search statement set of the first website according to the historical access data;
extracting a search word set of each candidate website from a search statement set of each candidate website in the candidate websites according to the historical access data;
Counting the number of the same search words included in the search word set of the first website and the search word set of each candidate website respectively;
and determining the candidate website as a second website under the condition that the number of the same search words is larger than a preset second threshold value.
4. The method of claim 3, wherein the extracting the set of search terms for the first website from the set of search sentences for the first website according to the historical access data comprises:
performing segmentation processing on each search sentence included in the search sentence set of the first website to obtain at least one first search word;
including the at least one first search term in a set of search terms for the first website; and
counting the times of accessing the first website through the at least one first search word according to the historical access data, and deleting the first search word with the times smaller than a preset third threshold from the obtained search word set of the first website.
5. The method of claim 4, wherein the extracting the set of search terms for each of the candidate websites from the set of search terms for each of the candidate websites, respectively, based on the historical access data comprises:
Performing segmentation processing on each search sentence included in the search sentence set of each candidate website to obtain at least one second search word;
including the at least one second search term in a set of search terms for the candidate website; and
and counting the times of accessing the candidate websites through the at least one second search word according to the historical access data, and deleting the second search word with the times smaller than the third threshold from the obtained search word set of the candidate websites.
6. The method of claim 2, wherein a first website to be served with information is determined among the plurality of websites according to a business attribute of the information to be served.
7. The method of claim 1, wherein the extracting the set of search terms for the set of target websites from the set of search sentences for the set of target websites based on the historical access data comprises:
performing segmentation processing on each search sentence included in the search sentence set of the target website set to obtain at least one target search word;
the at least one target search word is contained in a search word set of the target website set; and
Counting the times of accessing the target websites in the target website set through the at least one target search word according to the historical access data, and deleting the target search word with the times smaller than a preset third threshold value from the obtained search word set of the target website set.
8. The method of claim 1, wherein the obtaining search terms used by the user to access at least one target website of the set of target websites comprises:
acquiring search sentences used by the user for accessing at least one target website in the target website set; and
and carrying out segmentation processing on the search sentence to obtain at least one search word.
9. The method of claim 8, wherein the calculating the user's intent score for the set of target websites based on the weight of the user's intent search terms comprises:
and adding weights of the intention search words of the users, and scoring the intention of the users on the target website set by taking the sum of the added weights as a score.
10. The method of claim 1, wherein after counting the number of target websites in the set of target websites accessed by the search term based on the historical access data, further comprising:
And carrying out normalization processing on the counted number value, and taking the normalized number value as the weight of the search word.
11. The method of claim 1, wherein the historical access data comprises a search log including a website and time of the accessed website, a user performing the access, and search terms used by the user.
12. An information delivery apparatus comprising:
the target website determining module is configured to acquire historical access data of a plurality of websites and determine a target website set to be subjected to information release in the websites according to the historical access data;
an intent representation determination module configured to determine a set of intent search terms for accessing the set of target websites and weights for individual intent search terms in the set of intent search terms based on the historical access data;
the target user screening module is configured to search the word set and the weight according to the intention, and screen users accessing at least one target website in the target website set to obtain a target user set; and
an information delivery module configured to deliver the information to users in the set of target users,
Wherein the determining, according to the historical access data, the set of intent search words for accessing the set of target websites and the weights of the intent search words in the set of intent search words comprises: determining a search statement set for the target website set according to the historical access data; extracting a search word set of the target website set from the search statement set of the target website set according to the historical access data; counting the number of target websites in the target website set accessed by the search word according to the historical access data, and taking the counted number value as the weight of the search word; determining the search word with the weight of the obtained search word being greater than a preset fourth threshold as an intention search word of a target website in the target website set, including the intention search word in the intention search word set, and taking the weight of the obtained search word as the weight of the intention search word;
wherein the searching the word set and the weight according to the intention, and filtering the user accessing at least one target website in the target website set to obtain a target user set includes: acquiring search words used by the user to access at least one target website in the target website set; determining search words falling into the intent search word set from search words used by the user as intent search words of the user; determining the weight of the intention search word of the user according to the weight of each intention search word in the intention search word set; calculating intention scoring of the user to the target website set according to the weight of the intention search word of the user; and including the user whose intention score is greater than a preset first threshold in the target user set.
13. An information delivery apparatus comprising:
a memory storing program instructions; and
a processor configured to execute the program instructions to perform the information delivery method of any one of claims 1 to 11.
14. A computer readable storage medium storing computer executable instructions which, when executed, are adapted to carry out the information delivery method of any one of claims 1 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011021719.5A CN111966948B (en) | 2020-09-25 | 2020-09-25 | Information delivery method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011021719.5A CN111966948B (en) | 2020-09-25 | 2020-09-25 | Information delivery method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111966948A CN111966948A (en) | 2020-11-20 |
| CN111966948B true CN111966948B (en) | 2023-08-01 |
Family
ID=73387402
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011021719.5A Active CN111966948B (en) | 2020-09-25 | 2020-09-25 | Information delivery method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111966948B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113569135B (en) * | 2021-06-30 | 2024-03-29 | 深圳市东信时代信息技术有限公司 | Recommendation method, device, computer equipment and storage medium based on user portrait |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20010092922A (en) * | 2000-03-27 | 2001-10-27 | 이현구 | Method for Searching Similar Websites |
| CN102567494A (en) * | 2011-12-22 | 2012-07-11 | 北京亿赞普网络技术有限公司 | Website classification method and device |
| CN102663054A (en) * | 2012-03-29 | 2012-09-12 | 奇智软件（北京）有限公司 | Method and device for determining weight of website |
| CN103745380A (en) * | 2013-12-24 | 2014-04-23 | 亿赞普(北京)科技有限公司 | Advertisement delivery method and apparatus |
| WO2017024884A1 (en) * | 2015-08-07 | 2017-02-16 | 广州神马移动信息科技有限公司 | Search intention identification method and device |
| CN106959971A (en) * | 2016-01-12 | 2017-07-18 | 阿里巴巴集团控股有限公司 | The processing method and processing device of user behavior data |
| CN109801103A (en) * | 2019-01-14 | 2019-05-24 | 海南英赛德信息系统有限公司 | Information distribution method and device, storage medium and electronic equipment |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100161385A1 (en) * | 2008-12-19 | 2010-06-24 | Nxn Tech, Llc | Method and System for Content Based Demographics Prediction for Websites |
| US9576251B2 (en) * | 2009-11-13 | 2017-02-21 | Hewlett Packard Enterprise Development Lp | Method and system for processing web activity data |
-
2020
- 2020-09-25 CN CN202011021719.5A patent/CN111966948B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20010092922A (en) * | 2000-03-27 | 2001-10-27 | 이현구 | Method for Searching Similar Websites |
| CN102567494A (en) * | 2011-12-22 | 2012-07-11 | 北京亿赞普网络技术有限公司 | Website classification method and device |
| CN102663054A (en) * | 2012-03-29 | 2012-09-12 | 奇智软件（北京）有限公司 | Method and device for determining weight of website |
| CN103745380A (en) * | 2013-12-24 | 2014-04-23 | 亿赞普(北京)科技有限公司 | Advertisement delivery method and apparatus |
| WO2017024884A1 (en) * | 2015-08-07 | 2017-02-16 | 广州神马移动信息科技有限公司 | Search intention identification method and device |
| CN106959971A (en) * | 2016-01-12 | 2017-07-18 | 阿里巴巴集团控股有限公司 | The processing method and processing device of user behavior data |
| CN109801103A (en) * | 2019-01-14 | 2019-05-24 | 海南英赛德信息系统有限公司 | Information distribution method and device, storage medium and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 面向个性化站点的用户检索意图建模方法;张瑞芳;郭克华;;计算机工程与应用(06);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111966948A (en) | 2020-11-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106649818B (en) | Application search intention identification method and device, application search method and server | |
| CN108509482B (en) | Question classification method and device, computer equipment and storage medium | |
| CN110083688B (en) | Search result recall method, device, server and storage medium | |
| CN108319627B (en) | Keyword extraction method and keyword extraction device | |
| CN111814770B (en) | Content keyword extraction method of news video, terminal device and medium | |
| CN107862022B (en) | Culture resource recommendation system | |
| CN106445963B (en) | Advertisement index keyword automatic generation method and device of APP platform | |
| US10528662B2 (en) | Automated discovery using textual analysis | |
| CN108446295B (en) | Information retrieval method, information retrieval device, computer equipment and storage medium | |
| CN111708909B (en) | Video tag adding method and device, electronic equipment and computer readable storage medium | |
| CN111259271A (en) | Comment information display method and device, electronic equipment and computer readable medium | |
| CN105302807B (en) | Method and device for acquiring information category | |
| CN112740202A (en) | Performing image search using content tags | |
| CN110569419A (en) | question-answering system optimization method and device, computer equipment and storage medium | |
| CN113626704A (en) | Method, device and equipment for recommending information based on word2vec model | |
| CN112818200A (en) | Data crawling and event analyzing method and system based on static website | |
| CN111966948B (en) | Information delivery method, device, equipment and storage medium | |
| CN105786858A (en) | Information search system and method | |
| CN113961810A (en) | News pushing method and device, computer equipment and storage medium | |
| CN107665442B (en) | Method and device for acquiring target user | |
| TW201421267A (en) | Searching system and method | |
| CN105955988B (en) | Information searching method and device | |
| CN106919603B (en) | Method and device for calculating word segmentation weight in query word mode | |
| CN112749258A (en) | Data searching method and device, electronic equipment and storage medium | |
| CN110188339B (en) | Scenic spot evaluation method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |