CN111782913A - Method and device for determining brand intention words - Google Patents
Method and device for determining brand intention words Download PDFInfo
- Publication number
- CN111782913A CN111782913A CN201910804575.1A CN201910804575A CN111782913A CN 111782913 A CN111782913 A CN 111782913A CN 201910804575 A CN201910804575 A CN 201910804575A CN 111782913 A CN111782913 A CN 111782913A
- Authority
- CN
- China
- Prior art keywords
- brand
- word
- preset
- search
- target search
- 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.)
- Pending
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
- G06F16/90—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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/374—Thesaurus
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application discloses a method and a device for determining brand intention words. The method comprises the following steps: acquiring search behavior information of a user, wherein the search behavior information comprises search words and brand information of articles for which click behaviors of search results of the search words are aimed; taking brand information of an article for which a click behavior of a search result of a search word is aimed as brand information associated with the search word, and counting click data of the brand information associated with a target search word based on the search behavior information; performing correlation analysis on the target search word and a preset brand word in a preset brand word library in response to the fact that click data of brand information related to the target search word meets a preset click heat condition; and in response to determining that the correlation between the target search word and the preset brand words in the preset brand word bank meets the preset correlation condition, determining the target search word as a brand intention word associated with the preset brand words. The method realizes accurate mining and expansion of the brand intention words.
Description
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to the technical field of data processing, and particularly relates to a method and a device for determining brand intention words.
Background
With the development of internet technology, more and more users complete transactions through the internet. The processing of transactions in the network platform greatly facilitates the life of people, for example, the e-commerce platform provides convenient and fast network shopping service for users. In order to screen out information of interest to a user from a large amount of data, it is necessary to accurately locate the user's needs.
In the e-commerce platform, a user may query for items of interest by searching for keywords. The E-commerce platform background can analyze the intention of the user and recall the corresponding search result. The E-commerce platform can build a corresponding intention word library based on the user intentions represented by different search keywords and configure corresponding intention word labels for the commodities. For example, a library of brand intent words may be constructed to configure brand labels for the goods. When the search keywords of the user hit words in the brand intention thesaurus, the commodities with corresponding brand labels are returned as search results.
The behavior of the user sending out the search keyword has strong randomness, so that the brand name cannot be accurately described, the search keyword of the user is different from the pre-stored brand name, and the article information of the brand expected to be inquired by the user cannot be accurately recalled at this time.
Disclosure of Invention
Embodiments of the present disclosure propose methods, apparatuses, electronic devices, and computer-readable media for determining brand intention words.
In a first aspect, embodiments of the present disclosure provide a method for determining brand intention words, comprising: acquiring search behavior information of a user, wherein the search behavior information comprises search words and brand information of articles for which click behaviors of search results of the search words are aimed; taking brand information of an article for which a click behavior of a search result of a search word is aimed as brand information associated with the search word, and counting click data of the brand information associated with a target search word based on the search behavior information; performing correlation analysis on the target search word and a preset brand word in a preset brand word library in response to the fact that click data of brand information related to the target search word meets a preset click heat condition; and in response to determining that the correlation between the target search word and the preset brand words in the preset brand word bank meets the preset correlation condition, determining the target search word as a brand intention word associated with the preset brand words.
In some embodiments, the performing the correlation analysis on the target search term and the preset brand term in the preset brand thesaurus includes: judging whether the target search word is a subsequence of a preset brand word in a preset brand word bank; the determining, in response to determining that the correlation between the target search term and the preset brand term in the preset brand thesaurus satisfies the preset correlation condition, the target search term as a brand intention term associated with the preset brand term includes: and in response to determining that the target search word is a subsequence of the preset brand words in the preset brand word bank, determining the target search word as a brand intention word associated with the preset brand word.
In some embodiments, the counting click data of brand information associated with the target search term based on the search behavior information includes: counting the click ratio of each brand information related to the target search term based on the search behavior information; the preset click heat condition includes: the click ratio of the brand information corresponding to at least one brand associated with the target search term exceeds a preset threshold value.
In some embodiments, the performing the correlation analysis on the target search term and the preset brand term in the preset brand thesaurus includes: taking the brand word corresponding to the brand information of which the clicking proportion exceeds a preset threshold value in the brand information associated with the target search word as a preset brand word to be matched; and performing correlation analysis on the target search word and the preset brand word to be matched.
In some embodiments, the above method further comprises: carrying out normalization preprocessing on search terms and brand information in the search behavior information; the click data of the brand information associated with the target search term based on the search behavior information statistics comprises the following steps: and counting click data of the brand information associated with the target search term based on the preprocessed search term and the brand information associated with the preprocessed search term.
In some embodiments, the above method further comprises: and in response to the fact that the received search request contains a brand intention word associated with the preset brand word, searching the searched article in an article library corresponding to the preset brand word, wherein the brand of the article in the article library corresponding to the preset brand word is the brand identified by the preset brand word.
In a second aspect, an embodiment of the present disclosure provides an apparatus for determining a brand intention word, including: an acquisition unit configured to acquire search behavior information of a user, the search behavior information including a search word and brand information of an article to which a click behavior of a search result of the search word is directed; a counting unit configured to count click data of brand information associated with a target search term based on search behavior information, with brand information of an article to which a click behavior of a search result of the search term is directed as the brand information associated with the search term; the analysis unit is configured to perform correlation analysis on the target search word and preset brand words in a preset brand word library in response to determining that click data of brand information associated with the target search word meets a preset click heat condition; the determining unit is configured to determine the target search word as a brand intention word associated with a preset brand word in response to determining that the correlation between the target search word and the preset brand word in the preset brand word bank meets a preset correlation condition.
In some embodiments, the analyzing unit is configured to perform correlation analysis on the target search word and a preset brand word in a preset brand word bank as follows: judging whether the target search word is a subsequence of a preset brand word in a preset brand word bank; the above determination unit is further configured to: and in response to determining that the target search word is a subsequence of the preset brand words in the preset brand word bank, determining the target search word as a brand intention word associated with the preset brand word.
In some embodiments, the statistical unit is configured to count click data of brand information associated with the target search term as follows: counting the click ratio of each brand information related to the target search term based on the search behavior information; the preset click heat condition includes: the click ratio of the brand information corresponding to at least one brand associated with the target search term exceeds a preset threshold value.
In some embodiments, the analyzing unit is further configured to perform correlation analysis on the target search word and a preset brand word in a preset brand word bank as follows: taking the brand word corresponding to the brand information of which the clicking proportion exceeds a preset threshold value in the brand information associated with the target search word as a preset brand word to be matched; and performing correlation analysis on the target search word and the preset brand word to be matched.
In some embodiments, the above apparatus further comprises: the preprocessing unit is configured to perform normalization preprocessing on the search terms and the brand information in the search behavior information; the statistic unit is further configured to count click data of brand information associated with the target search term based on the preprocessed search term and the brand information associated with the preprocessed search term.
In some embodiments, the above apparatus further comprises: the searching unit is configured to search the searched articles in the article library corresponding to the preset brand words in response to the received searching request including the brand intention words related to the preset brand words, wherein the brands of the articles in the article library corresponding to the preset brand words are the brands identified by the preset brand words.
In a third aspect, an embodiment of the present disclosure provides an electronic device, including: one or more processors; a storage device for storing one or more programs which, when executed by one or more processors, cause the one or more processors to implement the method for determining brand intent words as provided in the first aspect.
In a fourth aspect, an embodiment of the disclosure provides a computer-readable medium on which a computer program is stored, wherein the program, when executed by a processor, implements the method for determining brand intention words provided by the first aspect.
The method and apparatus for determining a brand intention word, an electronic device, and a computer-readable medium according to the above embodiments of the present disclosure, by obtaining search behavior information of a user, the search behavior information including a search word and brand information of an article to which a click behavior of a search result of the search word is directed, then taking the brand information of the article to which the click behavior of the search result of the search word is directed as brand information associated with the search word, counting click data of the brand information associated with a target search word based on the search behavior information, and then in response to determining that the click data of the brand information associated with the target search word satisfies a preset click heat condition, performing correlation analysis on the target search word and a preset brand word in a preset brand word bank, and then in response to determining that the correlation of the target search word and the preset brand word in the preset brand word bank satisfies a preset correlation condition, the target search word is determined to be the brand intention word associated with the preset brand word, so that accurate mining and expansion of the brand intention word are achieved, and accurate analysis of the search intention of the user related to the brand can be facilitated.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture diagram in which embodiments of the present disclosure may be applied;
FIG. 2 is a flow diagram of one embodiment of a method for determining brand intention words according to the present disclosure;
FIG. 3 is a flow diagram of another embodiment of a method for determining brand intention words according to the present disclosure;
FIG. 4 is a schematic diagram of an embodiment of an apparatus for determining brand intent words of the present disclosure;
FIG. 5 is a schematic block diagram of a computer system suitable for use in implementing an electronic device of an embodiment of the present disclosure.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
FIG. 1 illustrates an exemplary system architecture 100 to which the method for determining brand intent words or the apparatus for determining brand intent words of the present application may be applied.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. The network may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user 110 may use the terminal devices 101, 102, 103 to interact with the server 105 over the network 104 to receive or send messages or the like. Various life service applications, such as a browser application, a search application, an e-commerce application, an audio/video playing application, a social platform application, and the like, may be installed on the terminal devices 101, 102, and 103.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting internet access including, but not limited to, desktop computers, smart phones, tablet computers, smart watches, notebook computers, laptop portable computers, e-book readers, and the like.
The server 105 may be a server that provides various types of life services, such as a backend server of an e-commerce platform. The server 105 may receive the search request sent by the terminal apparatuses 101, 102, 103, and parse the user's intention based on the search request, search for content matching the user's intention in the database, and return the searched content to the terminal apparatuses 101, 102, 103 through the network 104.
The terminal devices 101, 102, and 103 may be software. When the terminal apparatuses 101, 102, 103 are software, they can be installed in the electronic apparatuses listed above. It may be implemented as multiple pieces of software or software modules (e.g., multiple pieces of software or software modules to provide distributed services) or as a single piece of software or software module. And is not particularly limited herein.
The server 105 may be hardware or software. When the server 105 is hardware, it may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When the server 105 is software, it may be implemented as multiple pieces of software or software modules (e.g., multiple pieces of software or software modules used to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.
The method for determining the brand intention word provided by the embodiment of the application can be executed by the server 105, and accordingly, the device for determining the brand intention word can be arranged in the server 105.
It should be understood that the number of terminal devices, networks, servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, servers, as desired for implementation.
With continued reference to FIG. 2, a flow 200 of one embodiment of a method for determining brand intent words in accordance with the present application is shown. The method for determining the brand intention words comprises the following steps of:
In the present embodiment, an executing subject (e.g., a server shown in fig. 1) of the method for determining brand intention words may collect search behavior information of a large number of users. Here, the search behavior information includes a search word and brand information of an article to which a click behavior of a search result of the search word is directed.
The execution main body can match with the item information in the database and provide the search result based on the search word after responding to the received search request sent by the user. Here, the search term may be an entity term extracted from a query expression of the user, or the search term of the user may be directly used as the search term. The article information is attribute information of the article, such as descriptive information of the article's identification, function, brand, category, size, and the like. The search results may typically contain item information for a plurality of items. When the user clicks the item information in the search result, the execution main body may record the user's click behavior and the item to which the user's click behavior is directed, and may also obtain brand information of the item to which the user's click behavior is directed.
For example, when the user searches for "hua is a mobile phone," the search result provided by the background includes "hua is a" brand mobile phone, "apple" brand mobile phone, "millet" brand mobile phone, and so on. If the user clicks the mobile phone with the brand of 'Hua is' and the mobile phone with the brand of 'millet' in the search result, the user click can be recorded, and the brand of 'Hua is' and 'millet' of the clicked mobile phone can be recorded.
The search behavior information obtained by the execution main body may include search behavior information of a plurality of users, or may include search behavior information of one user at different times. In practice, all search behavior information in the platform may be collected and stored in the database over a period of time without differentiation between users. When determining the brand intention word, the execution subject may extract the search behavior information of the user from the database.
Optionally, after the search behavior information is obtained in step 201, normalization processing may be performed on the search terms and the brand information in the search behavior information, specifically, the search terms and the brand information may be converted into a standard text format, so that the formats of the search terms and the brand information are unified, the text formats of the search terms and the brand information in the search behavior information corresponding to different search records are unified, and specifically, the search terms and the brand information may be unified by case, full angle/half angle, traditional Chinese characters/simplified Chinese characters, and the like.
And after normalization preprocessing, performing subsequent operation of counting click data of brand information associated with the target search term based on the preprocessed search term and the brand information associated with the preprocessed search term.
Statistics of click data of brand information associated with the target search term may then be performed based on the obtained search behavior information. Any search word in the acquired search behavior information can be taken as a target search word for statistics, or each search word in the acquired search behavior information can be taken as a target search word for statistics.
The number of clicks of each brand information associated with the target search term may be counted as click data, respectively. In practice, the number of times different brands of items in the search results are clicked when searching with the target search term may be counted. For example, for the target search term "Mate mobile phone," the search result may include hua be Mate series mobile phone, hua be glory series mobile phone, apple mobile phone, samsung mobile phone, and so on, and the number of times that the user clicks each brand mobile phone in the search result may be counted as a statistical result of click data of each brand information associated with the target search term.
Alternatively, the click rate of each brand information associated with the target search term may be counted based on the search behavior information. That is, after counting the number of clicks of each brand information associated with the target search term, calculating the proportion of the number of clicks of each brand information in the number of clicks of all brand information associated with the target search term. For example, in the example where the target search term is "Mate mobile phone", the click ratios corresponding to the brand information are respectively: mate 75% in bloom, glory 10% in bloom, apple 5%, Samsung 5%, and others 5%. The click rate may represent a degree of association between the target search term and each brand information.
Optionally, the search behavior information may further include a time of clicking on each brand of item in the search result. When the click data is counted, the click data in a preset time period may be counted, for example, the click data in the last month may be counted, or the click data in different time periods of the day may be counted.
It may be determined whether the click data of the brand information associated with the target search term obtained in step 202 meets a preset click heat condition. Here, if the counted number of clicks of each brand information associated with the target search term in step 202 is the number of clicks, the preset click popularity condition may include that the number of clicks is greater than the preset number of times, accordingly; or, if the step 202 statistically obtains the click ratio of each brand information associated with the target search term, the preset click popularity condition includes: the click ratio of the brand information corresponding to at least one brand associated with the target search term exceeds a preset threshold value.
When the click data of the brand information associated with the target search term meets a preset click heat condition, it can be determined that the target search term contains a stronger brand search intention. At this time, correlation analysis can be performed on the target search word and the preset brand words in the preset brand word bank.
The preset brand lexicon contains preset brand words of the brand to which the item belongs, wherein each brand may have a plurality of preset brand words, for example, the brand words "adidas" and "adidas" of sports apparel are two different preset brand words of the same brand. When the correlation analysis operation is performed, the target search word and each preset brand word in the preset brand word library can be subjected to correlation analysis respectively. The correlation analysis method can specifically adopt a method for calculating text similarity, and the text similarity of the two methods is used for representing the correlation; or whether the target search word is included in the preset brand word or not can be directly compared, if the target search word is included in the preset brand word, the target search word and the preset brand word have strong correlation, and if the target search word is not included in the preset brand word, the target search word and the preset brand word have weak correlation.
In some alternative implementations, the predetermined brand thesaurus includes a plurality of brand words of predetermined brands. If the click data counted in step 202 is the click ratio of each brand information associated with the target search term, under the condition that it is determined that the click ratio of the brand information corresponding to at least one brand associated with the target search term exceeds the preset threshold, a brand word corresponding to the brand information of which the click ratio exceeds the preset threshold in the brand information associated with the target search term may be taken as a preset brand word to be matched, and then correlation analysis is performed on the target search term and the preset brand word to be matched.
Specifically, if the click ratio of a brand word in all brand words corresponding to the brand information associated with the target search word exceeds a preset threshold, the association between the target search word and the brand word may be considered to be strong, and the brand word may be matched with the intention of the user who performs the search based on the target search word. At this time, the brand word can be used as a preset brand word to be matched, and the correlation between the target search word and the preset brand word to be matched is further analyzed based on methods such as text similarity calculation.
As an example, the target search word is "Kors", and in the click data based on the item search result provided by the target search word, the click ratio for the "michelson" brand accounts for 80%, and assuming that the preset threshold value is 70%, it may be determined that the "michelson" brand is a preset brand word to be matched, and then correlation analysis is performed on the target search word "Kors" and the preset brand word "michelson (michelson)" to be matched.
By taking the brand word corresponding to the brand information with the click ratio exceeding the preset threshold value as the preset brand word to be matched, the range of the brand word subjected to correlation analysis with the target search word can be effectively reduced, and therefore the brand intention word can be quickly determined.
If the correlation between the target search word and the preset brand word in the preset brand word bank meets a preset correlation condition, for example, the text similarity between the target search word and the preset brand word exceeds a preset similarity threshold, the target search word may be determined to be a brand intention word of the preset brand word whose correlation meets the preset correlation condition.
The brand intention word of the preset brand word is a word representing the intention of acquiring the information of the article under the brand corresponding to the preset brand word. For example, in the above example, if the correlation between the target search term "Kors" and the preset brand word "Michael Kors" satisfies the preset correlation condition, the target search term "Kors" is determined to be the brand intention word of the preset brand word "Michael Kors". Indicating that the target search term "Kors" has the intent to obtain information for "Michael Kors" branded items.
In the embodiment, the target search term of which the correlation with the preset brand term meets the preset correlation condition is determined as the brand intention term of the preset brand term, so that accurate mining and expansion of the brand intention term are realized. The brand intention words and the corresponding preset brand words can be stored in a corresponding database in a correlated mode, or corresponding entries are newly added in the brand intention dictionary.
Optionally, the target search word and the preset brand word in the preset brand word bank may be subjected to correlation analysis in the following manner: and judging whether the target search word is a subsequence of the preset brand words in the preset brand word bank. Each single word in the target search word and the preset brand word can be used as an element in the sequence, and whether each single word in the target search word sequentially appears in the preset brand word or not can be judged. If the target search word is a subsequence of a preset brand word in a preset brand word bank, determining that the correlation between the target search word and the preset brand word meets the preset correlation condition, and determining the target search word as a brand intention word associated with the preset brand word.
Here, the sub-sequences comprise sub-strings. As an example, if the target search term "Kors" is a substring of "Michael Kors" and the target search term "mk" is a subsequence of the preset brand term "Michael Kors", then both the target search terms "Kors" and "mk" may be determined as brand intention terms associated with the preset brand term "Michael Kors".
Whether the target search word is a subsequence of the preset brand word or not is analyzed, so that the correlation between the target search word and the preset brand word can be determined more accurately and quickly, and the accuracy and the recognition efficiency of recognizing the brand intention word of the preset brand word are improved.
With continued reference to FIG. 3, another embodiment of the disclosed method for determining brand intent words is shown. As shown in FIG. 3, a flow 300 of the method for determining brand intention words of the present embodiment includes the following steps:
And 304, in response to determining that the correlation between the target search word and the preset brand words in the preset brand word bank meets a preset correlation condition, determining the target search word as a brand intention word associated with the preset brand words.
In this embodiment, after receiving the search request, the search request may be analyzed to determine whether a brand intention word associated with a preset brand word is included. Specifically, whether a word in the search request exists in the brand intention word dictionary or not can be searched, and if yes, a brand corresponding to the searched brand intention word is used as an intention brand of a user sending the search request. The item requested to search may then be looked up in an item repository corresponding to the user's intended brand. The brand to which the article in the article library corresponding to the preset brand word belongs is a brand identified by the preset brand word.
As an example, if "mk" is determined as a brand intention word associated with "Michael Kors" in steps 301 to 304 and the association relationship between the two is stored in a brand intention word dictionary in the form of a vocabulary entry, when a search request with "mk" as a search word is received in step 305, the corresponding brand word "Michael Kors" may be found in the brand intention word dictionary, and commodity information may be searched in a commodity information base of a brand corresponding to the brand word "Michael Kors". The product information base of the brand corresponding to the brand word "Michael Kors" includes information on the product of which the brand belongs to "Michael Kors".
When a search request containing a brand intention word associated with a preset brand word is received, the search intention of the user related to the brand is quickly determined, and then corresponding item information can be quickly searched in an item library associated with the preset brand word, so that the speed of responding to the search request of the user is increased, and meanwhile, the accuracy of a returned search result can be improved.
With further reference to fig. 4, as an implementation of the methods shown in the above-mentioned figures, the present application provides an embodiment of an apparatus for determining a brand intention word, which corresponds to the method embodiments shown in fig. 2 and 3, and which is particularly applicable to various electronic devices.
As shown in fig. 4, the apparatus 400 for determining a brand intention word of the present embodiment includes: an acquisition unit 401, a statistical unit 502, an analysis unit 503, and a determination unit 504. The obtaining unit 401 is configured to obtain search behavior information of a user, where the search behavior information includes a search word and brand information of an article for which a click behavior of a search result of the search word is directed; the counting unit 402 is configured to count click data of brand information associated with a target search term based on search behavior information, with brand information of an article for which a click behavior of a search result of the search term is directed as the brand information associated with the search term; the analysis unit 403 is configured to perform correlation analysis on the target search word and a preset brand word in a preset brand word library in response to determining that click data of brand information associated with the target search word satisfies a preset click heat condition; the determining unit 404 is configured to determine the target search word as a brand intention word associated with a preset brand word in response to determining that the correlation of the target search word with the preset brand word in the preset brand word bank satisfies a preset correlation condition.
In some embodiments, the analyzing unit 403 is configured to perform correlation analysis on the target search word and a preset brand word in a preset brand word bank as follows: judging whether the target search word is a subsequence of a preset brand word in a preset brand word bank; the above-mentioned determining unit 404 is further configured to: and in response to determining that the target search word is a subsequence of the preset brand words in the preset brand word bank, determining the target search word as a brand intention word associated with the preset brand word.
In some embodiments, the statistical unit is configured to count click data of brand information associated with the target search term as follows: counting the click ratio of each brand information related to the target search term based on the search behavior information; the preset click heat condition includes: the click ratio of the brand information corresponding to at least one brand associated with the target search term exceeds a preset threshold value.
In some embodiments, the analyzing unit 403 is further configured to perform correlation analysis on the target search word and a preset brand word in a preset brand word bank as follows: taking the brand word corresponding to the brand information of which the clicking proportion exceeds a preset threshold value in the brand information associated with the target search word as a preset brand word to be matched; and performing correlation analysis on the target search word and the preset brand word to be matched.
In some embodiments, the apparatus 400 further comprises: the preprocessing unit is configured to perform normalization preprocessing on the search terms and the brand information in the search behavior information;
the statistic unit 402 is further configured to count click data of brand information associated with the target search term based on the preprocessed search term and the brand information associated with the preprocessed search term.
In some embodiments, the apparatus 400 further comprises: the searching unit is configured to search the searched articles in the article library corresponding to the preset brand words in response to the received searching request including the brand intention words related to the preset brand words, wherein the brands of the articles in the article library corresponding to the preset brand words are the brands identified by the preset brand words.
It should be understood that the elements recited in apparatus 400 correspond to various steps in the methods described with reference to fig. 2 and 3. Thus, the operations and features described above for the method are equally applicable to the apparatus 400 and the units included therein, and are not described in detail here.
The apparatus 400 for determining a brand intention word according to the above embodiment of the present application obtains search behavior information of a user, the search behavior information including a search word and brand information of an article to which a click behavior of a search result of the search word is directed, then takes the brand information of the article to which the click behavior of the search result of the search word is directed as brand information associated with the search word, counts click data of brand information associated with a target search word based on the search behavior information, then performs correlation analysis on the target search word and a preset brand word in a preset brand lexicon in response to determining that the click data of the brand information associated with the target search word satisfies a preset click popularity condition, then determines the target search word as the brand intention word associated with the preset brand word in response to determining that the correlation of the target search word and the preset brand word in the preset brand lexicon satisfies the preset correlation condition, accurate mining and expansion of brand intention words are achieved.
Referring now to FIG. 5, a schematic diagram of an electronic device (e.g., the server of FIG. 1) 500 suitable for use in implementing embodiments of the present disclosure is shown. The electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 5, electronic device 500 may include a processing means (e.g., central processing unit, graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM 502, and the RAM503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
Generally, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, and the like; a storage device 508 including, for example, a hard disk; and a communication device 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 5 illustrates an electronic device 500 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 5 may represent one device or may represent multiple devices as desired.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 509, or installed from the storage means 508, or installed from the ROM 502. The computer program, when executed by the processing device 501, performs the above-described functions defined in the methods of embodiments of the present disclosure. It should be noted that the computer readable medium described in the embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, 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), an optical fiber, 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 embodiments of the 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. In embodiments of the present disclosure, however, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring search behavior information of a user, wherein the search behavior information comprises search words and brand information of articles for which click behaviors of search results of the search words are aimed; taking brand information of an article for which a click behavior of a search result of a search word is aimed as brand information associated with the search word, and counting click data of the brand information associated with a target search word based on the search behavior information; performing correlation analysis on the target search word and a preset brand word in a preset brand word library in response to the fact that click data of brand information related to the target search word meets a preset click heat condition; and in response to determining that the correlation between the target search word and the preset brand words in the preset brand word bank meets the preset correlation condition, determining the target search word as a brand intention word associated with the preset brand words.
Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart 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 application. 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 and/or flowchart illustration, and combinations of blocks in the block diagrams and/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.
The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes an acquisition unit, a statistical unit, an analysis unit, and a determination unit. Here, the names of these units do not constitute a limitation to the unit itself in some cases, and for example, the acquisition unit may also be described as a "unit that acquires search behavior information of a user".
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (12)
1. A method for determining brand intent words, comprising:
acquiring search behavior information of a user, wherein the search behavior information comprises search terms and brand information of an article for which click behaviors of search results of the search terms are specific;
taking brand information of an article for which the click behavior of the search result of the search word is aimed as brand information associated with the search word, and counting click data of the brand information associated with the target search word based on the search behavior information;
performing correlation analysis on the target search word and a preset brand word in a preset brand word library in response to the fact that click data of brand information related to the target search word meet a preset click heat condition;
in response to determining that the correlation between the target search word and a preset brand word in the preset brand word bank meets a preset correlation condition, determining the target search word as a brand intention word associated with the preset brand word.
2. The method of claim 1, wherein the performing a correlation analysis between the target search term and a preset brand term in a preset brand term library comprises:
judging whether the target search word is a subsequence of a preset brand word in the preset brand word bank;
the determining the target search word as a brand intention word associated with a preset brand word in response to determining that the correlation between the target search word and the preset brand word in the preset brand word bank meets a preset correlation condition includes:
in response to determining that the target search word is a subsequence of preset brand words in the preset brand lexicon, determining the target search word as a brand intention word associated with the preset brand words.
3. The method of claim 1, wherein the counting click data of brand information associated with target search terms based on the search behavior information comprises:
counting the click ratio of each brand information associated with the target search term based on the search behavior information;
the preset click heat condition comprises the following steps: the click ratio of the brand information corresponding to at least one brand associated with the target search term exceeds a preset threshold value.
4. The method of claim 3, wherein the performing a correlation analysis between the target search term and a preset brand term in a preset brand term library comprises:
taking the brand word corresponding to the brand information of which the clicking proportion exceeds a preset threshold value in the brand information associated with the target search word as a preset brand word to be matched; and performing correlation analysis on the target search word and the preset brand word to be matched.
5. The method of claim 1, wherein the method further comprises:
carrying out normalization preprocessing on the search terms in the search behavior information and the brand information;
the counting of click data of brand information associated with target search terms based on the search behavior information includes:
and counting click data of the brand information associated with the target search term based on the preprocessed search term and the brand information associated with the preprocessed search term.
6. The method of any of claims 1-5, wherein the method further comprises:
in response to the fact that the received search request contains a brand intention word associated with a preset brand word, searching for the searched article in an article library corresponding to the preset brand word, wherein a brand to which the article in the article library corresponding to the preset brand word belongs is a brand identified by the preset brand word.
7. An apparatus for determining brand intent words, comprising:
an acquisition unit configured to acquire search behavior information of a user, the search behavior information including a search word and brand information of an article to which a click behavior of a search result of the search word is directed;
a counting unit configured to count click data of brand information associated with a target search term based on search behavior information, with brand information of an article to which a click behavior of a search result of the search term is directed as the brand information associated with the search term;
the analysis unit is configured to perform correlation analysis on the target search word and preset brand words in a preset brand word bank in response to determining that click data of brand information associated with the target search word meets a preset click heat condition;
the determining unit is configured to determine the target search word as a brand intention word associated with a preset brand word in response to determining that the correlation between the target search word and the preset brand word in the preset brand word bank meets a preset correlation condition.
8. The method of claim 7, wherein the analysis unit is configured to perform correlation analysis on the target search word and a preset brand word in a preset brand lexicon as follows:
judging whether the target search word is a subsequence of a preset brand word in the preset brand word bank;
the determining unit is further configured to:
in response to determining that the target search word is a subsequence of preset brand words in the preset brand lexicon, determining the target search word as a brand intention word associated with the preset brand words.
9. The apparatus according to claim 7, wherein the statistical unit is configured to count click data of brand information associated with the target search term as follows:
counting the click ratio of each brand information associated with the target search term based on the search behavior information;
the preset click heat condition comprises the following steps: the click ratio of the brand information corresponding to at least one brand associated with the target search term exceeds a preset threshold value.
10. The apparatus of claim 9, wherein the analysis unit is further configured to perform correlation analysis on the target search word and a preset brand word in a preset brand lexicon as follows:
taking the brand word corresponding to the brand information of which the clicking proportion exceeds a preset threshold value in the brand information associated with the target search word as a preset brand word to be matched; and performing correlation analysis on the target search word and the preset brand word to be matched.
11. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-6.
12. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910804575.1A CN111782913A (en) | 2019-08-28 | 2019-08-28 | Method and device for determining brand intention words |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910804575.1A CN111782913A (en) | 2019-08-28 | 2019-08-28 | Method and device for determining brand intention words |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111782913A true CN111782913A (en) | 2020-10-16 |
Family
ID=72755123
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910804575.1A Pending CN111782913A (en) | 2019-08-28 | 2019-08-28 | Method and device for determining brand intention words |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111782913A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112883266A (en) * | 2021-02-18 | 2021-06-01 | 深圳市欢太科技有限公司 | Search method, search device, storage medium and electronic equipment |
| CN113407666A (en) * | 2021-05-28 | 2021-09-17 | 北京达佳互联信息技术有限公司 | Target crowd search intention identification method and device, electronic equipment and medium |
| CN115599768A (en) * | 2022-10-19 | 2023-01-13 | 深圳市灵智数字科技有限公司（Cn） | Association word library construction method, association word recommendation method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679119A (en) * | 2017-09-19 | 2018-02-09 | 北京京东尚科信息技术有限公司 | The method and apparatus for generating brand derivative words |
| CN107870984A (en) * | 2017-10-11 | 2018-04-03 | 北京京东尚科信息技术有限公司 | The method and apparatus for identifying the intention of search term |
| CN107908615A (en) * | 2017-10-17 | 2018-04-13 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus for obtaining search term corresponding goods classification |
-
2019
- 2019-08-28 CN CN201910804575.1A patent/CN111782913A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679119A (en) * | 2017-09-19 | 2018-02-09 | 北京京东尚科信息技术有限公司 | The method and apparatus for generating brand derivative words |
| CN107870984A (en) * | 2017-10-11 | 2018-04-03 | 北京京东尚科信息技术有限公司 | The method and apparatus for identifying the intention of search term |
| CN107908615A (en) * | 2017-10-17 | 2018-04-13 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus for obtaining search term corresponding goods classification |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112883266A (en) * | 2021-02-18 | 2021-06-01 | 深圳市欢太科技有限公司 | Search method, search device, storage medium and electronic equipment |
| CN113407666A (en) * | 2021-05-28 | 2021-09-17 | 北京达佳互联信息技术有限公司 | Target crowd search intention identification method and device, electronic equipment and medium |
| CN113407666B (en) * | 2021-05-28 | 2023-12-19 | 北京达佳互联信息技术有限公司 | Target crowd search intention recognition method and device, electronic equipment and medium |
| CN115599768A (en) * | 2022-10-19 | 2023-01-13 | 深圳市灵智数字科技有限公司（Cn） | Association word library construction method, association word recommendation method and device |
| CN115599768B (en) * | 2022-10-19 | 2023-06-09 | 深圳市灵智数字科技有限公司 | Association word library construction method, association word recommendation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11252245B2 (en) | Information pushing method and device | |
| CN107679211B (en) | Method and device for pushing information | |
| US10289957B2 (en) | Method and system for entity linking | |
| CN109145280A (en) | The method and apparatus of information push | |
| CN108572990B (en) | Information pushing method and device | |
| CN110069698B (en) | Information pushing method and device | |
| CN105574089B (en) | Knowledge graph generation method and device, and object comparison method and device | |
| CN107832338B (en) | Method and system for recognizing core product words | |
| JP2023533475A (en) | Artificial intelligence for keyword recommendation | |
| CN111782913A (en) | Method and device for determining brand intention words | |
| US11423096B2 (en) | Method and apparatus for outputting information | |
| CN111401974A (en) | Information sending method, information sending device, electronic equipment and computer readable medium | |
| CN112287206A (en) | Information processing method and device and electronic equipment | |
| CN110737824B (en) | Content query method and device | |
| KR20190031536A (en) | Application Information Triggering | |
| TWI528186B (en) | System and method for posting messages by audio signals | |
| CN110895587B (en) | Method and device for determining target user | |
| CN111415183A (en) | Method and apparatus for processing access requests | |
| CN111488386B (en) | Data query method and device | |
| CN110633405A (en) | Method and device for pushing information | |
| CN116910102A (en) | Enterprise query method and device based on user feedback and electronic equipment | |
| CN110796505B (en) | Business object recommendation method and device | |
| WO2022222660A1 (en) | Object display method and apparatus, electronic device, and computer readable storage medium | |
| CN111339124B (en) | Method, apparatus, electronic device and computer readable medium for displaying data | |
| CN111475722B (en) | Method and apparatus for transmitting information |
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 |