CN106445963B - Advertisement index keyword automatic generation method and device of APP platform - Google Patents

Advertisement index keyword automatic generation method and device of APP platform Download PDF

Info

Publication number
CN106445963B
CN106445963B CN201510488047.1A CN201510488047A CN106445963B CN 106445963 B CN106445963 B CN 106445963B CN 201510488047 A CN201510488047 A CN 201510488047A CN 106445963 B CN106445963 B CN 106445963B
Authority
CN
China
Prior art keywords
app
search
advertisement
topic
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
Application number
CN201510488047.1A
Other languages
Chinese (zh)
Other versions
CN106445963A (en
Inventor
王振凯
曹国栋
唐竞胜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Qihoo Technology Co Ltd
Original Assignee
Beijing Qihoo Technology Co Ltd
Qizhi Software Beijing Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Qihoo Technology Co Ltd, Qizhi Software Beijing Co Ltd filed Critical Beijing Qihoo Technology Co Ltd
Priority to CN201510488047.1A priority Critical patent/CN106445963B/en
Publication of CN106445963A publication Critical patent/CN106445963A/en
Application granted granted Critical
Publication of CN106445963B publication Critical patent/CN106445963B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/335—Filtering based on additional data, e.g. user or group profiles
    • G06F16/337—Profile generation, learning or modification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/31—Indexing; Data structures therefor; Storage structures
    • G06F16/313—Selection or weighting of terms for indexing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0277—Online advertisement

Abstract

The invention discloses an automatic generation method and device for advertisement index keywords of an APP platform, and relates to the technical field of search. The method comprises the following steps: calculating the theme distribution of each APP aiming at the description information of each APP; calculating the topic distribution of each search word according to the click relation between each search word and each APP in the search history record; calculating topic similarity between topic distribution of the search terms and topic distribution of an advertisement APP (application) aiming at each search term; if the topic similarity is larger than a topic threshold value, taking the search word as a keyword of the advertisement APP; and constructing advertisement index keywords corresponding to the advertisement APP according to the corresponding relation between the keywords and the advertisement APP. The method and the device can automatically select the advertisement index key words for the advertisement APP of the APP provider, reduce the selection process of the APP provider on the advertisement index key words, improve the user experience of the application platform and improve the income of the APP platform.

Description

Advertisement index keyword automatic generation method and device of APP platform
Technical Field
The invention relates to the technical field of search, in particular to an automatic generation method and device of advertisement index keywords of an APP platform.
Background
With the development of the smart mobile terminal, more and more users download various APPs (applications) to use in the smart mobile terminal. Based on the situation, the APP platform comes along, and the user can access the APP platform through the intelligent mobile terminal, for example, the APP distribution application installed in the intelligent mobile terminal is used for accessing the APP platform, so that various APPs can be downloaded from the platform. Among them, APP distributes applications such as various cell phone assistants.
In the APP platform, in order to enable APP owners with promotion needs, such as APP providers, APPs of the APP owners can be displayed in front of APP search pages, and the APP owners can purchase bid words for the APPs to serve as advertisement index keywords.
However, bid terms purchased by APP providers may not match with APPs themselves, so that when a search engine of an application platform performs retrieval according to a search term input by a user, information of APPs with low relevance to the search term may be returned, which results in that when the user searches for an APP required by the user, more operations, such as page turning, need to be performed, which affects efficiency of obtaining the APP required by the user. Further, for APP providers, since they need to select various bid terms by themselves, the operation is cumbersome.
Disclosure of Invention
In view of the above problems, the present invention is proposed to provide an apparatus for automatically generating advertisement index keywords of an APP platform and a corresponding method for automatically generating advertisement index keywords of an APP platform that overcome or at least partially solve the above problems.
According to one aspect of the invention, an automatic generation method of advertisement index keywords of an APP platform is provided, which comprises the following steps:
calculating the theme distribution of each APP aiming at the description information of each APP;
calculating the topic distribution of each search word according to the click relation between each search word and each APP in the search history record;
calculating topic similarity between topic distribution of the search terms and topic distribution of an advertisement APP (application) aiming at each search term;
if the topic similarity is larger than a topic threshold value, taking the search word as a keyword of the advertisement APP;
and constructing advertisement index keywords corresponding to the advertisement APP according to the corresponding relation between the keywords and the advertisement APP.
Preferably, before calculating, for each search term, a topic similarity between the topic distribution of the search term and the topic distribution of the advertisement APP, the method further includes:
judging whether the search quantity of the search word is larger than a search quantity threshold value or not;
and if the search quantity of the search terms is larger than the search quantity threshold value, calculating the topic similarity between the topic distribution of the search terms and the topic distribution of the advertisement APP aiming at each search term.
Preferably, the calculating the topic distribution of each APP according to the description information of each APP includes:
and calculating the topic distribution of each APP according to the topic model of the potential Dirichlet allocation aiming at the description information of each APP.
Preferably, before constructing an advertisement index keyword corresponding to the advertisement APP according to the correspondence between the keyword and the advertisement APP, the method further includes:
and extracting keywords corresponding to the advertisement APP directly from the name and/or the label of the advertisement APP.
Preferably, before constructing an advertisement index keyword corresponding to the advertisement APP according to the correspondence between the keyword and the advertisement APP, the method further includes:
calculating the text similarity between the search word and the name of the advertisement APP for each search word in the search downloading record;
and if the text similarity is greater than a text similarity threshold, acquiring the search word as a keyword.
Preferably, before constructing an advertisement index keyword corresponding to the advertisement APP according to the correspondence between the keyword and the advertisement APP, the method further includes:
for each search word in the search downloading record of the search history record, judging whether the independent access downloading frequency of the search word is greater than an independent access threshold value or not, and whether the category of the search word and the category of the advertisement APP belong to the same category or not;
and if the independent access downloading times of the search words are larger than an independent access threshold value, and the categories of the search words and the categories of the advertisement APP belong to the same category, taking the search words as key words.
Preferably, before constructing an advertisement index keyword corresponding to the advertisement APP according to the correspondence between the keyword and the advertisement APP, the method further includes:
for the APPs under each first class, the description information of each APP under each first class is utilized, and each APP is divided into a second class under the corresponding first class by adopting a classifier;
for each search word, calculating a secondary category corresponding to the search word according to a click relation between the search word and each APP in the search history record and a secondary category to which each APP belongs at the first stage;
and acquiring search words corresponding to the secondary category according to the secondary category of the advertisement APP to serve as the keywords.
According to another aspect of the present invention, there is provided an apparatus for automatically generating advertisement index keywords of an APP platform, including:
the APP theme distribution calculation module is suitable for calculating the theme distribution of each APP aiming at the description information of each APP;
the search word topic distribution calculation module is suitable for calculating topic distribution of each search word according to the click relation between each search word and each APP in the search history record;
the topic similarity search word extraction module is suitable for calculating topic similarity between topic distribution of the search words and topic distribution of the advertisement APP aiming at each search word;
the first keyword adding module is suitable for taking the search word as a keyword of the advertisement APP if the topic similarity is larger than a topic threshold;
and the advertisement index keyword building module is suitable for building the advertisement index keyword corresponding to the advertisement APP according to the corresponding relation between the keyword and the advertisement APP.
Preferably, before the topic similarity search term extraction module, the method further comprises:
the search quantity judging module is suitable for judging whether the search quantity of the search word is larger than a search quantity threshold value or not; and if the search quantity of the search terms is larger than the search quantity threshold value, entering a topic similar search term extraction module.
Preferably, the APP topic distribution calculation module comprises:
and the potential dirichlet allocation topic model calculation module is suitable for calculating topic distribution of each APP according to the potential dirichlet allocation topic model aiming at the description information of each APP.
Preferably, before the advertisement index keyword construction module, the method further comprises:
and the direct extraction module is suitable for directly extracting the keywords corresponding to the advertisement APP from the name and/or the label of the advertisement APP.
Preferably, before the advertisement index keyword construction module, the method further comprises:
the text search word acquisition module is suitable for calculating the text similarity between the search word and the name of the advertisement APP for each search word in the search downloading record;
and the second keyword adding module is suitable for acquiring the search word as the keyword if the text similarity is greater than a text similarity threshold.
Preferably, before the advertisement index keyword construction module, the method further comprises:
the independent access search word extraction module is suitable for judging whether the independent access downloading times of the search words are larger than an independent access threshold value and whether the categories of the search words and the categories of the advertisement APP belong to the same category or not for each search word in the search downloading records of the search history record;
and the third key word adding module is suitable for taking the search word as a key word if the independent access downloading frequency of the search word is greater than an independent access threshold value and the category of the search word and the category of the advertisement APP belong to the same category.
Preferably, before the advertisement index keyword construction module, the method further comprises:
the APP category subdivision module is suitable for dividing each APP into a second category under the corresponding first category by using the description information of each APP under the first category and a classifier for the APPs under each first category;
the search word classification module is suitable for calculating a secondary category corresponding to a search word according to the click relation between the search word and each APP in the search history record and the secondary category to which each APP belongs in the primary category;
and the category search word extraction module is suitable for acquiring search words corresponding to the secondary category according to the secondary category where the advertisement APP is located and using the search words as keywords.
According to the method and the device for automatically generating the advertisement index key words of the APP platform, for the advertisement APPs which need to be popularized by the APP provider, in the APP platform, the articles of the APP (including the advertisement APPs) are utilized to calculate the topic distribution of the APP, and the click relation between the search words and the APP is utilized to calculate the topic distribution of the search words, so that for the advertisement APPs, the topic similarity between the advertisement APPs and the search words can be calculated, the keyword of which the topic similarity is greater than the topic threshold value is taken as the advertisement APP, and the keyword can be taken as the advertisement index key word of the advertisement APP when the index is constructed, thereby solving the problems that the APP provider needs to select the advertisement index key word through complicated operation and the advertisement APP appears in the search results with low relevance with the search words input by the user due to the fact that the selected advertisement index key word is improper, the method has the advantages that the advertisement index key words can be automatically selected for the advertisement APP of the APP provider, the selection process of the APP provider for the advertisement index key words is reduced, the advertisement APP is prevented from appearing in the search results with low relevancy to the search words input by the user, user experience of an application platform is improved, the APP with similar subjects can be provided for the search words input by the user, and the beneficial effect of the retrieval width is improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flowchart illustrating an automatic advertisement index keyword generation method of an APP platform according to an embodiment of the present invention;
FIG. 1A shows a presentation example of an advertisement APP according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating an automatic advertisement index keyword generation method of an APP platform according to an embodiment of the present invention;
FIG. 3 shows a block diagram of an apparatus for automatically generating advertisement index keywords of an APP platform according to an embodiment of the present invention;
fig. 4 shows a block diagram of an apparatus for automatically generating advertisement index keywords of an APP platform according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Referring to fig. 1, a flowchart of an automatic advertisement index keyword generation method of an APP platform according to an embodiment of the present invention is shown, where the method specifically includes the following steps:
step 101, calculating the theme distribution of each APP aiming at the description information of each APP;
the embodiment of the invention is applied to the APP platform, and the APP supplier can upload the APP in the account registered by the APP platform. Of course, the supplier can designate the APP as the advertisement APP in the account, and pay certain value data for the APP, and then the APP platform can know that the APP is the advertisement APP.
In the embodiment of the invention, when the topic distribution of each APP is calculated, the article sample is the description information of each advertisement APP and non-advertisement APP. The description information can be understood as detailed introduction information of the APP.
Based on the description information of each APP, the topic model can be used for analysis, and the topic distribution of each APP is calculated. The calculated topic distribution of the APP comprises the topic distribution of the advertisement APP. The topic distribution can be understood as the topic distribution of an article, for example, for article 1, the probability of topic 1 is 0.6, the probability of topic 2 is 0.3, and a topic vector (0.6, 0.4) is obtained, so that the topic distribution of article 1 can be understood.
102, calculating the theme distribution of each search word according to the click relation between each search word and each APP in the search history record;
during the search process of the user, the user may click to check detailed information of the APP in a search result page without downloading, or may click to download the APP, so that a series of click relations for search terms are formed. In the embodiment of the present invention, the click relationship may only include a click relationship between the search term and the viewed APP, or may only include a click relationship between the search term and each downloaded APP, and of course, the click relationship may also include a click relationship between the search term and the viewed APP, and a click relationship between the search term and each downloaded APP.
In the embodiment of the present invention, the topic distribution of each search term may be calculated according to the click relationship between the search term and each APP and the topic distribution of each APP in step 101. That is, according to the click relationship between the search term and each APP, the click distribution of a search term to each APP is counted, for example, the click APP1 proportion of the search term 1 is 0.8, the click APP2 proportion is 0.2, then the click distribution of the search term 1 is APP2(0.8,0.2), and the two items correspond to APP1 and APP2 in sequence.
For example, if the search term 1 clicks APP1 by 0.8, clicks APP2 by 0.2, APP1 by (0.6, 0.4), APP2 by (0.7, 0.3), the topic distribution of the search term may be ((0.6+.07) × 0.8, (0.4+0.3) × 0.2); wherein, each item of the theme distribution respectively corresponds to a theme 1 and a theme 2.
103, calculating the topic similarity between the topic distribution of the search terms and the topic distribution of the advertisement APP aiming at each search term; if the topic similarity is greater than the topic threshold, entering step 103;
in the embodiment of the present invention, for the advertisement APP, a vector of its topic distribution may be extracted from step 101, and then for each search term, a vector of its topic distribution may be extracted. Since both are vectors, the similarity between the two vectors can be calculated.
In the embodiment of the present invention, for the similarity between the topic distribution of the search term and the topic distribution of the APP, KL distance and/or JS distance calculation may be employed. Wherein, KL distance is Kullback-Leibler divergence, also called relative entropy, and for two probability distributions P and Q of a discrete random variable, their KL divergence is defined as: d (P | | Q) ═ Σ P (i) log (P (i)/Q (i)) … … formula (1).
Wherein, when log is calculated, 2 is taken as a base.
And for the JS distance Jensen-Shannon divergence which is an optimization scheme of the KL distance, the formula is as follows:
Figure GDA0001796085620000071
wherein
Figure GDA0001796085620000081
Wherein D is calculated by formula (1).
The JSD value is between 0 and 1. Larger indicates more consistent distribution of the two topics and higher similarity.
The topic distribution of the search terms and the topic distribution of the advertisement APP correspond to P and Q respectively.
Of course, other distances may also be used to calculate the topic similarity between the topic distribution of the search term and the topic distribution of the advertisement APP, such as a cosine distance.
Preferably, the cosine distance and the JS distance are adopted at the same time, and then the two distances are averaged or subjected to weight addition calculation. Thus, the calculated similarity is more accurate.
In the embodiment of the present invention, a theme threshold may be preset according to the actual test, and step 104 is performed if the theme similarity is greater than the theme threshold.
Step 104, using the search word as a keyword of the advertisement APP;
for a search term with topic similarity to an advertisement APP greater than a topic threshold, the search term may be added to a keyword set of the advertisement APP.
And 105, constructing advertisement index keywords corresponding to the advertisement APP according to the corresponding relation between the keywords and the advertisement APP.
In the embodiment of the invention, the APP platform can be provided with two sets of indexes, one set of indexes constructed aiming at the common APP, and the other set of indexes constructed aiming at the advertisement APP. When the index is constructed for the advertisement APP, the keyword sets of the advertisement APPs obtained in the step 101-104 are used to construct the index, and the keywords in the keyword sets are constructed as the advertisement index keywords in the index.
Of course, in practical applications, for different advertisement APPs having the same advertisement index keyword, the advertisement APPs may be arranged in the index list after the advertisement index keyword.
And for the APP platform, after receiving the search terms input by the user, searching in the indexes for the common APP and the indexes for the advertisement APPs respectively, and displaying each advertisement APP searched in the indexes for the advertisement APPs in the first search result in a sequence in front in the first search result.
In the embodiment of the invention, for the index, the index is marked as the advertisement APP through the advertisement identification in the application platform, and then when the APP is retrieved, if the APP has the advertisement identification, the APP can be displayed in advance. The advertisement is identified as "promotion" or "referral". In addition, various advertisement marks can be set in the embodiment of the invention, and different advertisement marks have different display weights. For example, the display weight of "promotion" is high, and the display weight of "recommendation" is lower than that of "promotion". As shown in fig. 1A, the words "promote" and "recommend" are identified as the advertisement APP, and then advance financing and favorable network financing are the advertisement APP. And searching the keyword of "financing" to show the advertisement app.
In summary, the method and apparatus for automatically generating advertisement index keywords of the APP platform are, for advertisement APPs that need to be promoted by APP providers, in the APP platform, the article of each APP (including advertisement APP) is used for calculating the topic distribution of each APP, the click relation between the search word and the APP is used for calculating the topic distribution of each search word, thus, for the advertisement APP, the topic similarity between the advertisement APP and the search word can be calculated, the keyword of the advertisement APP with the topic similarity larger than the topic threshold value is used as the topic similarity, so that the keyword can be used as an advertisement index keyword of the advertisement APP when building the index, thereby solving the problem that APP suppliers need to select advertisement index keywords through complicated operations, and the problem that the advertisement APP appears in the search result with low relevance with the search word input by the user due to the fact that the selected advertisement index key words are inappropriate. The embodiment of the invention can automatically select the advertisement index key words for the advertisement APP of the APP supplier, reduce the selection process of the APP supplier to the advertisement index key words, avoid the advertisement APP from appearing in the search results with low correlation degree with the search words input by the user, and improve the user experience of the application platform.
Moreover, aiming at the search of the search engine according to the text correlation with the search word in the prior art, the method and the device can provide APP with similar subjects for the search word input by the user, and improve the search width.
Referring to fig. 2, a flowchart of an automatic advertisement index keyword generation method of an APP platform according to an embodiment of the present invention is shown, where the method specifically includes the following steps:
step 201, calculating topic distribution of each APP according to a potential Dirichlet allocation topic model aiming at the description information of each APP;
in the embodiment of the present invention, since the description information of the APP can be understood as an article in practice, the topic model may be an LDA (Latent Dirichlet Allocation topic) model, and LDA is a document topic generation model. The generative model is a process in which each word of an article is considered to be obtained by "selecting a topic with a certain probability and selecting a word from the topic with a certain probability". Then, if we want to generate a document, the probability of each word in it occurring is:
Figure GDA0001796085620000101
therefore, in the embodiment of the present invention, each article may be analyzed through the LDA model to obtain the topic distribution corresponding to each description information, that is, the probability distribution of each topic, for example, the probability of the topic 1 is 0.6, the probability of the topic 2 is 0.3, and a vector (0.6, 0.4) is obtained. Then, according to the corresponding relation between the description information and the APP, the theme distribution of the APP can be obtained.
Of course, in the embodiment of the present invention, other topic models may also be used to calculate the APP topic distribution, and the present invention does not limit this.
Step 202, calculating the theme distribution of each search word according to the click relation between each search word and each APP in the search history record;
step 203, judging whether the search quantity of the search word is larger than a search quantity threshold value; if the search volume of the search word is larger than the search volume threshold, entering step 204;
in practical application, some search terms are small in search quantity and some search terms are large in search quantity, and for the APP to be popularized, the search terms with large search quantity are easier to be retrieved, so that the corresponding APPs are easier to popularize, and therefore the popularization efficiency of the advertisement APPs of the APP platform is improved. Therefore, the present invention counts the search volume of each search term in the search history, and presets a search volume threshold, and only if the search volume is greater than the search volume threshold, the process proceeds to step 205.
Step 204, calculating the topic similarity between the topic distribution of the search terms and the topic distribution of the advertisement APP aiming at each search term; if the topic similarity is greater than the topic threshold, go to step 205;
step 205, using the search word as a keyword of the advertisement APP;
preferably, before constructing an advertisement index keyword corresponding to the advertisement APP according to the correspondence between the keyword and the advertisement APP, the method further includes:
step A11, extracting keywords corresponding to the advertisement APP directly from the name and/or label of the advertisement APP.
In the embodiment of the invention, characters/words and the like can be directly extracted from the text information related to the advertisement APP to be used as the keywords of the advertisement APP.
Specifically, step a11 includes:
and a substep A111, performing word segmentation operation on the name of the advertisement APP, and taking the word segmentation result as a class keyword.
In the embodiment of the invention, the identity information of the advertisement APP comprises a name, such as "travel by taking", then the invention can directly perform word segmentation operation on the name, and after the word segmentation of "travel by taking", the word segmentation result is "travel by taking" and "travel", so that the "travel by taking" and "travel" can be used as keywords of the advertisement APP "travel by taking".
And/or substep A112, convert the name of the advertisement APP into the spelling bunch and/or carry on the word segmentation result that the word segmentation gets to convert into the spelling bunch by the said name, regard said spelling bunch as the key word;
for the name of the advertisement APP, the name can be directly converted into pinyin such as 'xiechenglvxing', or the word segmentation result can be converted into pinyin, and if the pinyin carrying the word is 'xiecheng', the pinyin can be used as the keyword of the advertisement APP.
And/or substep a113, using the tag words of the advertisement APP as keywords.
For a preset tag word of an advertisement APP, a tag word with manual operation like "travel with travel" APP: "travel", "train ticket", "travel strategy", "air ticket", "trip", "hotel", these tag words may be used as keywords.
Preferably, before constructing an advertisement index keyword corresponding to the advertisement APP according to the correspondence between the keyword and the advertisement APP, the method further includes:
step B11, calculating the text similarity between the search word and the name of the advertisement APP for each search word in the search download record;
in practical application, a user inputs a search word in a terminal for searching, the user may click to download an APP or may not download the APP, and then the application platform may record the search downloading situation of each search word, for example, user a searches "financing", downloads APP1 in a search result page, and user B searches "financing", may download APP2 in the search result page, and may obtain the search downloading record of each search word through the record of the search downloading behavior of a large number of users.
In a specific implementation, the search download record is stored in the application platform in the form of a search download log.
And step B12, if the text similarity is greater than the text similarity threshold, acquiring the search word as the keyword.
The embodiment of the invention can extract each used search word from the search download log and calculate the text similarity between the search word and the name of the advertisement APP. Such as calculating the cosine distance between the search word text and the advertisement APP name text.
The embodiment of the invention can set a text similarity threshold aiming at the text similarity, and if the text similarity is greater than the text similarity threshold, the search word is obtained as the keyword of the advertisement APP. And if the text similarity is smaller than a text similarity threshold, ignoring the word.
Preferably, before constructing an advertisement index keyword corresponding to the advertisement APP according to the correspondence between the keyword and the advertisement APP, the method further includes:
step B21, for each search word in the search download record of the search history record, judging whether the independent access download times of the search word is larger than an independent access threshold value, and whether the category of the search word and the category of the advertisement APP belong to the same category;
and step B22, if the independent access downloading times of the search words are larger than an independent access threshold value, and the categories of the search words and the categories of the advertisement APP belong to the same category, taking the search words as keywords.
For a search word in the search download log, multiple users may download APPs in the search result of the search word displayed by the terminal, and the terminal having the same IP downloads multiple APPs or the same APP downloads multiple times. In order to reduce the influence of the terminal of the same IP on the download weight of the search terms, the embodiment of the present invention counts the number of times of independent access download of each search term, that is, UV (uniform viewer) download, that is, even if the terminal of the same IP downloads for multiple times, the number of times of UV download is counted only once. Then, for a search term, counting how many IP terminals download APP by using the search result of the search term.
Then, an independent access threshold value for the number of times of UV downloading is set in the embodiment of the present invention, if it is determined that the number of times of UV downloading of the search word is greater than the independent access threshold value, it may be determined whether the category of the search word and the category of the advertisement APP belong to the same category, and if the category of the search word and the category of the advertisement APP at this time belong to the same category, the search word is used as a keyword of the advertisement APP. For a search word, the independent access downloading frequency is smaller than or equal to the independent access threshold, the category of the search word and the category of the advertisement APP do not belong to the same category, and the search word can be ignored.
Of course, the advertisement APP in the embodiment of the present invention may be classified as a general APP. Search terms may also be classified as such. The present invention is not limited to this specific classification procedure. The following steps can of course be taken to classify APP and search terms:
substep B211, for the APPs in each primary category, using the description information of each APP in the primary category and adopting a classifier to divide each APP into secondary categories in the corresponding primary category;
various categories are preset in the application platform, and the categories are started from primary categories, such as game categories and sports categories. In fact, for an APP under a first class, the APP can be classified more finely according to the description information of the APP. In practical application, the description information can be classified by using a Bayesian classifier, and each APP under the first-level category is classified under each second-level category.
And a substep B212, for each search word, calculating a secondary category corresponding to the search word according to the click relation between the search word and each APP in the search history record and the secondary category to which each APP belongs at the first stage.
During the search process of the user, the user may click to check detailed information of the APP in a search result page without downloading, or may click to download the APP. According to the embodiment of the invention, each search word can be classified under the corresponding secondary category by combining the secondary category APP in the sub-step B211 according to the click relation between the search word and each APP. Of course the advertising APP also participates in the classification process.
For example, if the ratio of the number of times that the search word 1 clicks the APP in the secondary category 1 is greater than the ratio threshold, the search word is classified under the secondary category 1.
The above-mentioned click relation between the search term and each APP may be a relation between the search term and each APP click check, a relation between the search term and each APP click download, or a total relation between the search term and each APP click check and click download.
Preferably, before constructing an advertisement index keyword corresponding to the advertisement APP according to the correspondence between the keyword and the advertisement APP, the method further includes:
step C11, for the APPs under each first class, using the description information of each APP under each first class and adopting a classifier to divide each APP into a second class under the corresponding first class;
step C12, for each search word, calculating a secondary category corresponding to the search word according to the click relation between the search word and each APP in the search history record and the secondary category to which each APP belongs at the first level;
steps C11-C12 are similar to the previous substeps B211-B212. Because the ratio of the times of clicking the APP in the secondary category 1 by the similar search word 1 is greater than the ratio threshold, the search word is classified under the secondary category 1, and the click ratio of the search word is very small under a certain secondary category, that is, the probability that the search word is the secondary category is small, so that the search word can be removed from the secondary category.
After the search word is associated with the secondary category, the search word with a low probability corresponding to the secondary category is deleted, and the remaining search words of the secondary category are generated into a word package and then applied in step C13.
And step C13, acquiring search terms corresponding to the secondary category according to the secondary category where the advertisement APP is located, and using the search terms as keywords.
For the advertisement APPs, since the secondary category where each APP is located is calculated in step C11, the secondary category of the advertisement APP is also determined, and the word package of the keyword of the secondary category is determined in step C12, then the word in the word package may be used as the keyword of the advertisement APP.
In the embodiment of the present invention, for an APP, the foregoing various ways of extracting keywords may be combined arbitrarily, and the present invention does not limit this.
In the embodiment of the present invention, for the keywords obtained by combining the aforementioned various keyword obtaining manners, normalization may be performed first in step 205, and the same keywords are combined to obtain the simplest keyword set.
Of course, for the above-mentioned various ways of calculating keywords by using search history, the use of search history between each two ways may be independent and not affect each other.
And step 206, constructing advertisement index keywords corresponding to the advertisement APP according to the corresponding relation between the keywords and the advertisement APP.
In the embodiment of the invention, the APP platform can be provided with two sets of indexes, one set of indexes constructed aiming at the common APP, and the other set of indexes constructed aiming at the advertisement APP. When the index is constructed for the advertisement APPs, the index is constructed by using the keyword sets of the advertisement APPs obtained in step 201 and 205, and the keywords in the keyword sets are constructed as the advertisement index keywords in the index.
In summary, the method and apparatus for automatically generating advertisement index keywords of the APP platform are, for advertisement APPs that need to be promoted by APP providers, in the APP platform, the article of each APP (including advertisement APP) is used for calculating the topic distribution of each APP, the click relation between the search word and the APP is used for calculating the topic distribution of each search word, thus, for the advertisement APP, the topic similarity between the advertisement APP and the search word can be calculated, the keyword of the advertisement APP with the topic similarity larger than the topic threshold value is used as the topic similarity, so that the keyword can be used as an advertisement index keyword of the advertisement APP when building the index, thereby solving the problem that APP suppliers need to select advertisement index keywords through complicated operations, and the problem that the advertisement APP appears in the search result with low relevance with the search word input by the user due to the fact that the selected advertisement index key words are inappropriate. The embodiment of the invention can automatically select the advertisement index key words for the advertisement APP of the APP supplier, reduce the selection process of the APP supplier to the advertisement index key words, avoid the advertisement APP from appearing in the search results with low correlation degree with the search words input by the user, and improve the user experience of the application platform.
Moreover, aiming at the search of the search engine according to the text correlation with the search word in the prior art, the method and the device can provide APP with similar subjects for the search word input by the user, and improve the search width.
Furthermore, the embodiment of the invention can further improve the width of the advertisement APP word packet by combining with various acquisition modes of the keywords of the advertisement APP, so that the popularization range of the advertisement APP in the retrieval process is wider.
Finally, the above mode can improve the recall rate of the advertisement APP and the income of the APP platform.
Referring to fig. 3, a structural diagram of an apparatus for automatically generating advertisement index keywords of an APP platform according to an embodiment of the present invention is shown, where the structure may specifically include the following modules:
the APP topic distribution calculation module 301 is adapted to calculate topic distribution of each APP for the description information of each APP;
the search term topic distribution calculation module 302 is adapted to calculate topic distribution of each search term according to the click relation between each search term and each APP in the search history record;
the topic similarity search term extraction module 303 is adapted to calculate, for each search term, a topic similarity between topic distribution of the search term and topic distribution of the advertisement APP;
a keyword adding module 304, adapted to take the search term as a keyword of the advertisement APP if the topic similarity is greater than a topic threshold;
an advertisement index keyword construction module 305, adapted to construct an advertisement index keyword corresponding to the advertisement APP according to the correspondence between the keyword and the advertisement APP.
Referring to fig. 4, a structural diagram of an apparatus for automatically generating advertisement index keywords of an APP platform according to an embodiment of the present invention is shown, where the structure may specifically include the following modules:
the APP topic distribution calculation module 401 is adapted to calculate topic distribution of each APP for the description information of each APP, and specifically includes:
the potential dirichlet allocation topic model calculation module 4011 is adapted to calculate topic distribution of each APP according to the potential dirichlet allocation topic model for the description information of each APP.
The search term topic distribution calculation module 402 is adapted to calculate topic distribution of each search term according to the click relation between each search term and each APP in the search history record;
a search quantity judging module 403, adapted to judge whether the search quantity of the search word is greater than a search quantity threshold; if the search volume of the search term is greater than the search volume threshold, the topic similarity search term extraction module 404 is entered.
A topic similarity search term extraction module 404, adapted to calculate, for each search term, a topic similarity between a topic distribution of the search term and a topic distribution of an advertisement APP;
a keyword adding module 405 adapted to take the search term as a keyword of the advertisement APP if the topic similarity is greater than a topic threshold;
and an advertisement index keyword construction module 406, adapted to construct an advertisement index keyword corresponding to the advertisement APP according to the corresponding relationship between the keyword and the advertisement APP.
Preferably, before the advertisement index keyword construction module, the method further comprises:
and the direct extraction module is suitable for directly extracting the keywords corresponding to the advertisement APP from the name and/or the label of the advertisement APP.
Preferably, before the advertisement index keyword construction module, the method further comprises:
the text search word acquisition module is suitable for calculating the text similarity between the search word and the name of the advertisement APP for each search word in the search downloading record;
and the second keyword adding module is suitable for acquiring the search word as the keyword if the text similarity is greater than a text similarity threshold.
Preferably, before the advertisement index keyword construction module, the method further comprises:
the independent access search word extraction module is suitable for judging whether the independent access downloading times of the search words are larger than an independent access threshold value and whether the categories of the search words and the categories of the advertisement APP belong to the same category or not for each search word in the search downloading records of the search history record;
and the third key word adding module is suitable for taking the search word as a key word if the independent access downloading frequency of the search word is greater than an independent access threshold value and the category of the search word and the category of the advertisement APP belong to the same category.
Preferably, before the advertisement index keyword construction module, the method further comprises:
the APP category subdivision module is suitable for dividing each APP into a second category under the corresponding first category by using the description information of each APP under the first category and a classifier for the APPs under each first category;
the search word classification module is suitable for calculating a secondary category corresponding to a search word according to the click relation between the search word and each APP in the search history record and the secondary category to which each APP belongs in the primary category;
and the category search word extraction module is suitable for acquiring search words corresponding to the secondary category according to the secondary category where the advertisement APP is located and using the search words as keywords.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general-purpose systems may also be used with the present invention based on the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, for any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement embodiments in accordance with the inventionAdvertisement index key of APP platform Automatic generation of wordsSome or all of the functions of some or all of the components in the device. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

Claims (12)

1. An automatic generation method of advertisement index keywords of an APP platform comprises the following steps:
calculating the theme distribution of each APP aiming at the description information of each APP;
calculating the topic distribution of each search word according to the click relation between each search word and each APP in the search history record;
calculating topic similarity between topic distribution of the search terms and topic distribution of an advertisement APP (application) aiming at each search term;
if the topic similarity is larger than a topic threshold value, taking the search word as a keyword of the advertisement APP;
constructing advertisement index keywords corresponding to the advertisement APP according to the corresponding relation between the keywords and the advertisement APP;
wherein, before constructing the advertisement index keyword corresponding to the advertisement APP according to the corresponding relationship between the keyword and the advertisement APP, the method further comprises:
for each search word in the search downloading record of the search history record, judging whether the independent access downloading frequency of the search word is greater than an independent access threshold value or not, and whether the category of the search word and the category of the advertisement APP belong to the same category or not;
and if the independent access downloading times of the search words are larger than an independent access threshold value, and the categories of the search words and the categories of the advertisement APP belong to the same category, taking the search words as key words.
2. The method of claim 1, further comprising, before calculating, for each search term, a topic similarity between the topic distribution of the search term and the topic distribution of advertisement APP:
judging whether the search quantity of the search word is larger than a search quantity threshold value or not;
and if the search quantity of the search terms is larger than the search quantity threshold value, calculating the topic similarity between the topic distribution of the search terms and the topic distribution of the advertisement APP aiming at each search term.
3. The method of claim 1, wherein the calculating the topic distribution of each APP according to the description information of each APP comprises:
and calculating the topic distribution of each APP according to the topic model of the potential Dirichlet allocation aiming at the description information of each APP.
4. The method of claim 1, before constructing an advertisement index keyword corresponding to an advertisement APP according to a correspondence between the keyword and the advertisement APP, further comprising:
and extracting keywords corresponding to the advertisement APP directly from the name and/or the label of the advertisement APP.
5. The method of claim 1, before constructing an advertisement index keyword corresponding to an advertisement APP according to a correspondence between the keyword and the advertisement APP, further comprising:
calculating the text similarity between the search word and the name of the advertisement APP for each search word in the search downloading record;
and if the text similarity is greater than a text similarity threshold, acquiring the search word as a keyword.
6. The method of claim 1, before constructing an advertisement index keyword corresponding to an advertisement APP according to a correspondence between the keyword and the advertisement APP, further comprising:
for the APPs under each first class, the description information of each APP under each first class is utilized, and each APP is divided into a second class under the corresponding first class by adopting a classifier;
for each search word, calculating a secondary category corresponding to the search word according to a click relation between the search word and each APP in the search history record and a secondary category to which each APP belongs at the first stage;
and acquiring search words corresponding to the secondary category according to the secondary category of the advertisement APP to serve as the keywords.
7. An advertisement index keyword automatic generation device of an APP platform comprises:
the APP theme distribution calculation module is suitable for calculating the theme distribution of each APP aiming at the description information of each APP;
the search word topic distribution calculation module is suitable for calculating topic distribution of each search word according to the click relation between each search word and each APP in the search history record;
the topic similarity search word extraction module is suitable for calculating topic similarity between topic distribution of the search words and topic distribution of the advertisement APP aiming at each search word;
the first keyword adding module is suitable for taking the search word as a keyword of the advertisement APP if the topic similarity is larger than a topic threshold;
the advertisement index keyword building module is suitable for building an advertisement index keyword corresponding to the advertisement APP according to the corresponding relation between the keyword and the advertisement APP;
before the advertisement index keyword building module, the method further comprises:
the independent access search word extraction module is suitable for judging whether the independent access downloading times of the search words are larger than an independent access threshold value and whether the categories of the search words and the categories of the advertisement APP belong to the same category or not for each search word in the search downloading records of the search history record;
and the third key word adding module is suitable for taking the search word as a key word if the independent access downloading frequency of the search word is greater than an independent access threshold value and the category of the search word and the category of the advertisement APP belong to the same category.
8. The apparatus of claim 7, wherein before the topic similarity search term extraction module, further comprising:
the search quantity judging module is suitable for judging whether the search quantity of the search word is larger than a search quantity threshold value or not; and if the search quantity of the search terms is larger than the search quantity threshold value, entering a topic similar search term extraction module.
9. The apparatus of claim 7, wherein the APP topic distribution computation module comprises:
and the potential dirichlet allocation topic model calculation module is suitable for calculating topic distribution of each APP according to the potential dirichlet allocation topic model aiming at the description information of each APP.
10. The apparatus of claim 7, wherein prior to the advertisement index keyword construction module, further comprising:
and the direct extraction module is suitable for directly extracting the keywords corresponding to the advertisement APP from the name and/or the label of the advertisement APP.
11. The apparatus of claim 7, wherein prior to the advertisement index keyword construction module, further comprising:
the text search word acquisition module is suitable for calculating the text similarity between the search word and the name of the advertisement APP for each search word in the search downloading record;
and the second keyword adding module is suitable for acquiring the search word as the keyword if the text similarity is greater than a text similarity threshold.
12. The apparatus of claim 7, wherein prior to the advertisement index keyword construction module, further comprising:
the APP category subdivision module is suitable for dividing each APP into a second category under the corresponding first category by using the description information of each APP under the first category and a classifier for the APPs under each first category;
the search word classification module is suitable for calculating a secondary category corresponding to a search word according to the click relation between the search word and each APP in the search history record and the secondary category to which each APP belongs in the primary category;
and the category search word extraction module is suitable for acquiring search words corresponding to the secondary category according to the secondary category where the advertisement APP is located and using the search words as keywords.
CN201510488047.1A 2015-08-10 2015-08-10 Advertisement index keyword automatic generation method and device of APP platform Active CN106445963B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510488047.1A CN106445963B (en) 2015-08-10 2015-08-10 Advertisement index keyword automatic generation method and device of APP platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510488047.1A CN106445963B (en) 2015-08-10 2015-08-10 Advertisement index keyword automatic generation method and device of APP platform

Publications (2)

Publication Number Publication Date
CN106445963A CN106445963A (en) 2017-02-22
CN106445963B true CN106445963B (en) 2021-11-23

Family

ID=58093726

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510488047.1A Active CN106445963B (en) 2015-08-10 2015-08-10 Advertisement index keyword automatic generation method and device of APP platform

Country Status (1)

Country Link
CN (1) CN106445963B (en)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106909688B (en) * 2017-03-07 2020-10-16 阿里巴巴（中国）有限公司 Method and device for recommending search terms based on input search terms
CN107220374B (en) * 2017-06-20 2020-11-27 创新先进技术有限公司 Searching method, client, server and searching device
CN107861753B (en) * 2017-06-26 2020-12-11 平安普惠企业管理有限公司 APP generation index, retrieval method and system and readable storage medium
CN108304453B (en) * 2017-12-18 2021-07-06 北京奇艺世纪科技有限公司 Method and device for determining video related search terms
CN108304457A (en) * 2017-12-22 2018-07-20 努比亚技术有限公司 A kind of application mask method, server and computer readable storage medium
CN110083774B (en) * 2019-05-10 2023-11-03 腾讯科技（深圳）有限公司 Method and device for determining application recommendation list, computer equipment and storage medium
CN112132601B (en) * 2019-06-25 2023-07-25 百度在线网络技术（北京）有限公司 Advertisement title rewriting method, apparatus and storage medium
CN110597987A (en) * 2019-08-21 2019-12-20 微梦创科网络科技（中国）有限公司 Search recommendation method and device
CN111475729B (en) * 2020-04-07 2023-07-25 腾讯科技（深圳）有限公司 Search content recommendation method and device
CN111858684A (en) * 2020-07-03 2020-10-30 京华信息科技股份有限公司 Method and system for improving retrieval accuracy based on user checking and recording

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102708115A (en) * 2004-08-09 2012-10-03 亚马逊技术股份有限公司 Method and system for identifying keywords for use in placing keyword-targeted advertisements
CN104133877A (en) * 2014-07-25 2014-11-05 百度在线网络技术（北京）有限公司 Software label generation method and device
CN104424279A (en) * 2013-08-30 2015-03-18 腾讯科技（深圳）有限公司 Text relevance calculating method and device

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8176067B1 (en) * 2010-02-24 2012-05-08 A9.Com, Inc. Fixed phrase detection for search

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102708115A (en) * 2004-08-09 2012-10-03 亚马逊技术股份有限公司 Method and system for identifying keywords for use in placing keyword-targeted advertisements
CN104424279A (en) * 2013-08-30 2015-03-18 腾讯科技（深圳）有限公司 Text relevance calculating method and device
CN104133877A (en) * 2014-07-25 2014-11-05 百度在线网络技术（北京）有限公司 Software label generation method and device

Also Published As

Publication number Publication date
CN106445963A (en) 2017-02-22

Similar Documents

Publication Publication Date Title
CN106445963B (en) Advertisement index keyword automatic generation method and device of APP platform
CN106649818B (en) Application search intention identification method and device, application search method and server
CN109325179B (en) Content promotion method and device
US11176142B2 (en) Method of data query based on evaluation and device
CN106919575B (en) Application program searching method and device
CN103577416B (en) Expanding query method and system
US20160267189A1 (en) Method for performing network search at a browser side and a browser
CN105912669B (en) Method and device for complementing search terms and establishing individual interest model
CN107862022B (en) Culture resource recommendation system
CN102929939B (en) The offer method and device of customized information
CN104391999B (en) Information recommendation method and device
KR101491627B1 (en) Quantification method, apparatus and system of reviews for mobile application evaluation
CN111797239B (en) Application program classification method and device and terminal equipment
CN110008397B (en) Recommendation model training method and device
CN103577432A (en) Method and system for searching commodity information
CN108269122B (en) Advertisement similarity processing method and device
CN108319376B (en) Input association recommendation method and device for optimizing commercial word promotion
CN107977445B (en) Application program recommendation method and device
CN110825977A (en) Data recommendation method and related equipment
CN106919588A (en) A kind of application program search system and method
CN108229999B (en) Method and device for evaluating competitive products
CN102364467A (en) Network search method and system
CN111159563A (en) Method, device and equipment for determining user interest point information and storage medium
CN110765760A (en) Legal case distribution method and device, storage medium and server
CN103745380A (en) Advertisement delivery method and apparatus

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20240115

Address after: 100088 room 112, block D, 28 new street, new street, Xicheng District, Beijing (Desheng Park)

Patentee after: BEIJING QIHOO TECHNOLOGY Co.,Ltd.

Address before: 100088 room 112, block D, 28 new street, new street, Xicheng District, Beijing (Desheng Park)

Patentee before: BEIJING QIHOO TECHNOLOGY Co.,Ltd.

Patentee before: Qizhi software (Beijing) Co.,Ltd.