CN110674401B - Method and device for determining sequence of search items and electronic equipment - Google Patents
Method and device for determining sequence of search items and electronic equipment Download PDFInfo
- Publication number
- CN110674401B CN110674401B CN201910888019.7A CN201910888019A CN110674401B CN 110674401 B CN110674401 B CN 110674401B CN 201910888019 A CN201910888019 A CN 201910888019A CN 110674401 B CN110674401 B CN 110674401B
- Authority
- CN
- China
- Prior art keywords
- search
- determining
- term
- items
- terms
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present disclosure discloses a method of determining an order of search terms, comprising: determining a first search term corresponding to the search term; determining a visual feature vector for the first search term; clustering the first search item according to the visual feature vector of the first search item to obtain a clustering result; determining a first category according to the clustering result, wherein the first category comprises M search items in the first search items, M is a positive integer and is greater than a first threshold; updating click rates of the M search terms; and determining the display sequence of the first search item according to the click rate of the first search item. The embodiment of the disclosure provides a method and a device for determining the sequence of search terms, and the display sequence of the search terms with visual relevance can be adjusted for the search terms corresponding to the search terms, so that the accuracy of search results is improved, and better user experience is brought.
Description
Technical Field
The present disclosure relates to the field of information processing, and in particular, to a method and an apparatus for determining an order of search items, an electronic device, and a computer-readable storage medium.
Background
With the coming of the information age, how to accurately acquire required information from vast information ocean is a main problem to be solved in the field of search.
A common method in the existing search-related method is to crawl relevant data from each data source in a network for a search term and form corresponding search items, then calculate scores of the search items according to click rates of the search items corresponding to the search term in unit time, and determine a display sequence of the search items according to the scores, so as to display the search item with the highest degree of association or the most accurate degree of association with the search term in the front column.
For some search terms, which themselves have visual relevance (including but not limited to color and/or shape), for example, for the search term "jewelry", one would likely associate gold, silver, emerald, etc., and for the search term "computer", one would likely associate a rectangle. Accordingly, among the search terms corresponding to these search terms, the search term having the above-described visual relevance may be more relevant to the search term, but in the related art, the above-described relevance is not considered when determining the display order of the search terms.
Disclosure of Invention
In view of the foregoing drawbacks, embodiments of the present disclosure provide a method, an apparatus, an electronic device, and a computer-readable storage medium for determining an order of search terms, which can adjust a display order of search terms having visual relevance among the search terms corresponding to the search terms, improve accuracy of search results, and bring better user experience.
In a first aspect, an embodiment of the present disclosure provides a method for determining an order of search terms, including: determining a first search term corresponding to the search term; determining a visual feature vector for the first search term; clustering the first search item according to the visual feature vector of the first search item to obtain a clustering result; determining a first category according to the clustering result, wherein the first category comprises M search items in the first search items, M is a positive integer and is greater than a first threshold; updating click rates of the M search terms; and determining the display sequence of the first search item according to the click rate of the first search item.
In a second aspect, an embodiment of the present disclosure provides an apparatus for determining an order of search terms, including: the determining module is used for determining a first search item corresponding to the search word; the determining module is further configured to determine a visual feature vector of the first search term; the clustering module is used for clustering the first search item according to the visual feature vector of the first search item to obtain a clustering result; the determining module is further configured to determine a first category according to the clustering result, where the first category includes M search terms of the first search terms, M is a positive integer and M is greater than a first threshold; the updating module is used for updating the click rate of the M search items; the determining module is further configured to determine a display order of the first search term according to the click rate of the first search term.
In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a memory for storing computer readable instructions; and one or more processors coupled with the memory for executing the computer readable instructions, such that the processors when executed implement the method of determining an order of search terms of any of the preceding first aspects.
In a fourth aspect, the present disclosure provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, which when executed by a computer, cause the computer to perform the method of determining an order of search items according to any one of the first aspect.
The present disclosure discloses a method, an apparatus, an electronic device, and a computer-readable storage medium for determining an order of search items. Wherein the method of determining an order of search terms comprises: determining a first search term corresponding to the search term; determining a visual feature vector for the first search term; clustering the first search item according to the visual feature vector of the first search item to obtain a clustering result; determining a first category according to the clustering result, wherein the first category comprises M search items in the first search items, M is a positive integer and is greater than a first threshold; updating click rates of the M search terms; and determining the display sequence of the first search item according to the click rate of the first search item. The embodiment of the disclosure provides a method and a device for determining the sequence of search terms, and the display sequence of the search terms with visual relevance can be adjusted for the search terms corresponding to the search terms, so that the accuracy of search results is improved, and better user experience is brought.
The foregoing is a summary of the present disclosure, and for the purposes of promoting a clear understanding of the technical means of the present disclosure, the present disclosure may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale.
FIG. 1 is a flow diagram of an embodiment of a method for determining an order of search terms provided by an embodiment of the present disclosure;
FIG. 2 is a schematic structural diagram of an embodiment of an apparatus for determining an order of search terms according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an electronic device provided according to an embodiment of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
Before describing the embodiments of the present disclosure, a brief introduction of some prior art in the search area is provided for a better understanding of the embodiments of the present disclosure. As described in the background and understood by those skilled in the art, when a user searches through a search engine, a search word is typically input on an interface displayed by the search engine, and then the search engine displays a search term corresponding to the search word to the user according to a certain display order, wherein a process of inputting the search word to obtain the search term of the search word may be referred to as query (sometimes, the search word may also be referred to as query and simply denoted as q), and a search term corresponding to the search word may also be referred to as doc of the search word, wherein the search term of the search word may be determined by means of a crawler technology, an indexing technology, a relevance calculation technology, and the like, and for the above related technologies, various existing or future technologies may be adopted and are not expanded here. In the prior art, during a search performed by a user through a search engine, the search engine or other computing device records various search data of the user through a log file or the like, for example, records search data (including, for example, the number of searches, the search frequency) of the user on one or more search terms and/or click data (including, for example, the number of clicks, the number of presentations, and/or the display sequence of clicked search terms) of the user on search terms of the search terms, and the like. In order to display a search term more related or accurate to a search term in the front, scores of the search terms are calculated according to the click rate of the search term corresponding to the search term in a unit time (including, for example, the last year, the last month, etc.) that can be arbitrarily set, and then the display order of the search terms is adjusted according to the scores.
The method for determining the order of the search items provided by this embodiment may be performed by an apparatus for determining the order of the search items, which may be implemented as software, may be implemented as hardware, or may be implemented as a combination of software and hardware, for example, the search includes a computer device, so that the method for determining the order of the search items provided by this disclosure is performed by the computer device, as will be understood by those skilled in the art, the computer device may include various types, for example, a server, and as an example, the method for determining the order of the search items provided by this disclosure may be performed by one server, and the method for determining the order of the search items provided by this disclosure may be performed by cooperation of multiple servers.
Fig. 1 is a flowchart of an embodiment of a method for determining an order of search terms according to an embodiment of the present disclosure, which may be performed by the apparatus for determining an order of search terms described above.
As shown in fig. 1, a method of determining an order of search items according to an embodiment of the present disclosure includes the steps of:
step S101, determining a first search item corresponding to a search word;
in step S101, the device for determining the sequence of search terms determines a first search term corresponding to a search term, as understood by those skilled in the art, when a user searches through a search engine, the search term may be input, and then the search engine, in response to the input of the user, will call up and display the first search term corresponding to the search term to the user, where the process may be referred to as query, and sometimes may also be referred to as query, where the first search term corresponding to the search term may be obtained by applying a calculation method, such as a relevancy calculation method, after crawling, indexing, and storing and maintaining network data in a specific form, and obtained by filtering based on preset conditions, such as crawling, indexing, and storing and maintaining network data in a specific form, and obtaining P search terms corresponding to the search term by applying a calculation method, such as a relevancy calculation method, and the like For example, the P search terms may be used as the first search term, and Q search terms with the highest click rate among the P search terms may also be used as the first search term, where the related existing or future crawling, indexing, storing, maintaining, and/or relevance calculating techniques may all be applied to the embodiment of the present disclosure, and the embodiment of the present disclosure is not limited thereto. It is worth noting that the means for determining the order of search terms in the present disclosure may be a computer device separate from the search engine, or the search engine itself.
S102, determining a visual feature vector of the first search item;
in step S102, the means for determining the order of search terms determines a visual feature vector for the first search term. In an alternative embodiment, a corresponding table of tag information and visual feature vector may be stored, and then the visual feature vector of the first search term may be determined according to the corresponding table, as described in the background of the present disclosure and understood by those skilled in the art, tag information may be determined for a search term through an indexing technique, so as to determine a search term corresponding to a search word based on the tag information and a relevancy algorithm, and therefore the first search term corresponds to the tag information, then in step S102, the visual feature vector corresponding to the tag information of the first search term may be searched according to the corresponding table of the tag information and the visual feature vector, and the corresponding visual feature vector is used as the visual feature vector of the first search term. In yet another alternative embodiment, the visual feature vector of the first search term may be extracted through a neural network, and optionally, the first search term comprises a video item and/or an image item, then the visual feature of the video item and/or the image item may be extracted directly through the neural network; optionally, the content of the first search item includes a video item and/or an image item, for example, the link corresponding to the first search item includes news, and an image is included in the news, so that a visual feature of the image can be extracted through the neural network as a visual feature of the first search item.
As will be appreciated by those skilled in the art, the visual feature vector in the embodiments of the present disclosure includes a vector of preset dimensions for describing visual features including, but not limited to, color features and/or shape features. For example, in the above embodiment of extracting the visual feature vector of the first search item through a neural network, the image corresponding to the first search item may be input to the neural network, and then the visual feature of the image corresponding to the first search item is output through the operation of the convolutional layer, the nonlinear layer, and/or the pooling layer of the neural network, and further the video corresponding to the first search item may be input to the neural network, the image frame of the video is extracted according to a preset algorithm, and after some processing such as column merging and weighting, the visual feature of the video corresponding to the first search item is output through the operation of the convolutional layer, the nonlinear layer, and/or the pooling layer of the neural network, and a common neural network for extracting the visual feature vector of the first search item includes, for example, an imageNet network, it can extract 128-dimensional data feature vectors based on the input image or video, and of course, other neural networks are also included, such as RCNN, LeNet, AlexNet, VGGNet, etc., which is not limited by the embodiment of the present disclosure.
Step S103, clustering the first search item according to the visual feature vector of the first search item to obtain a clustering result;
in step S103, the means for determining the order of search terms clusters the first search term determined in step S102 according to the visual feature vector of the first search term. For a search term, the first search term corresponding to the search term may include a plurality of search terms, and in step S102, the plurality of search terms in the first search term are represented by respective visual feature vectors, so in step S103, a clustering algorithm may be applied based on the visual feature vectors of the plurality of search terms to obtain a clustering result, and since the clustering algorithm performs clustering based on the visual feature vectors, the search terms clustered in the obtained clustering result are considered to have the same or similar visual features.
Optionally, the first search term is clustered according to the visual feature vector of the first search term through a gaussian (mixture) density algorithm, or the first search term is clustered according to the visual feature vector of the first search term through a K-means (K-means) algorithm.
Step S104, determining a first category according to the clustering result, wherein the first category comprises M search items in the first search items, M is a positive integer and is greater than a first threshold value.
In step S104, the means for determining the order of the search items determines a first category according to the clustering result of step S103, wherein the number M of the search items included in the first category is greater than a first threshold, that is, M of the first search items in the clustering result are grouped into the first category, and M is greater than the first threshold, and the first threshold may be preset. The clustering result is obtained, for example, by a gaussian (mixed) density algorithm, a cluster in which the number of search items whose distance from a cluster core is smaller than a preset value reaches the first threshold value in the clustering result may be regarded as the first category, and a cluster in which the number of search items in the clustering result reaches the first threshold value may be regarded as the first category, for example, by a K-means algorithm, according to the obtained clustering result. It will be understood by those skilled in the art that the clustering result may include one cluster, and then the one cluster may be taken as the first category; the clustering result may further include a plurality of clusters, and each of the plurality of clusters may be respectively used as the first category.
Step S105, updating click rates of the M search terms;
in step S105, the means for determining the order of search items updates the click rates of the M search items determined in step S104. As mentioned above, since the clustering algorithm is applied based on the visual feature vector of the first search term to obtain the clustering result, the search terms clustered in the clustering result are considered to have the same or similar visual features, that is, the M search terms in the first category have visual features, and the M search terms may better describe, explain, and/or correspond to the search terms, the click rates of the M search terms may be updated in step S105, and the display order thereof may be adjusted, so as to improve the accuracy of the search result.
As will be appreciated by those skilled in the art, the click-through rate of a search term, which is generally expressed by a CTR, is generally understood to be the ratio of the sum of the number of times the search term is clicked on per unit of time to the sum of the number of times the search term is presented, e.g., for the M search termsiThe click rate of the ith search item in the M search items is represented, a value of i is 1 to M, and the unit time may be preset, for example, from the first day to the last day of the last month. Of course, based on different click models, the way of counting the sum of the number of times the search term is clicked and the sum of the number of times the search term is displayed may be different, and the obtained click rate value may also be different.
In an alternative embodiment, step S105: updating click-through rates for the M search terms, including: determining N search items with the highest click rate in the M search items, wherein N is a positive integer; and updating the click rate of the M search items according to the similarity between the M search items and the N search items and the click rate of the N search items. Since the M search terms are search terms corresponding to the search term in step S101, and it can be clarified through steps S103 and S104 that the M search terms have the same or similar visual features, the M search terms are considered to be more related to the search term, further, N search terms with the highest click rate are determined from the M search terms, and since the N search terms are not only more related to the search term but also have a higher click rate, the N search terms can be considered to have higher quality with respect to the search term, therefore, the click rate of the M search terms can be adjusted according to the N search terms in order to improve the click rate of all or part of the M search terms. For example, in the above alternative embodiment, the click rate of the M search terms may be adjusted according to the similarity between the M search terms and the N search terms, and if the search term of the M search terms is more similar to the N search terms, which means that the quality of the search term is higher, the click rate may be appropriately increased.
Optionally, updating the click-through rates of the M search terms according to the similarities between the M search terms and the N search terms and the click-through rates of the N search terms, including: updating the click rate of the M search terms according to a click rate update formula, wherein the click rate update formula comprises:
wherein, CTRjThe click rate of a search item j in the M search items is represented, the value range of j is 1 to M, and CTRiFor the click rate of search item i of the N search items, SIMijIs the similarity between search term i and search term j.
Optionally, the similarity SIM between search item i and search item jijIs based on the search term iA visual feature vector, and the visual feature vector of search term j. For example, the search item i and the search item j have visual feature vectors with the same dimension, ratios of the visual feature vectors of the dimensions of the search item i to the visual feature vectors of the dimensions of the search item j may be calculated, and the ratios are summed and then divided by the dimensions to obtain the similarity SIMijOf course, the similarity between two search terms may also be calculated based on the visual feature vectors of the two search terms in other manners, which is not limited by the present disclosure.
According to the click rate updating formula, for a search item j in the M search items, the similarity between the search item j and each search item in the N search items can be calculated, the product of the similarity and the click rate of each search item in the N corresponding search items is calculated, and the ratio between the value obtained by summing the N products and the value obtained by summing the click rates of the N search items is used as the click rate of the search item j. In this way, the click rate of the search item with the later click rate among the M search items can be increased, and since it can be clarified through steps S103 and S104 that the M search items have the same or similar visual features, it is considered that the M search items are more related to the search term, and then through step S105, the click rate of all or part of the M search items can be updated to adjust the display order thereof.
And step S106, determining the display sequence of the first search item according to the click rate of the first search item.
In step S106, the means for determining the order of search items determines the display order of the first search item according to the click rates of the M search items and the click rates of the search items other than the M search items in the first search item updated in step S105.
Optionally, step S106: determining a display order of the first search term according to the click rate of the first search term, including: determining the first search term according to the click rate of the first search termThe score of the search item is positively correlated with the click rate of the first search item; determining the display order of the first search term according to a score of the first search term. As described in the background, a common manner of determining includes calculating a score according to a click rate of the search term, and determining a display order of the search term according to the score. In the present embodiment, for example, for the search item i in the first search items, the click through rate is CTRiCorresponding Score ofi＝f(CTRi) That is, Score of search term iiIs the click-through rate CTR for the search term iiFunction of, ScoreiAnd CTRiPositive correlation, i.e. the higher the click rate of the search term i, the Score of the search term iiThe higher the score of the search term i, the more forward the display order of the search term i is with respect to all search terms under the search term.
It should be noted that the specific algorithm for calculating the scores and/or the display orders of the search terms based on the click-through rates of the search terms in the embodiments of the present disclosure is not limited, and any existing and future methods for determining the display orders of the search terms based on the click-through rates can be applied to the embodiments of the present disclosure.
The embodiment of the disclosure provides a method and a device for determining the sequence of search terms, and the like, for the search terms corresponding to the search terms, the search terms with visual relevance can be adjusted, the accuracy of search results is improved, and better user experience is brought.
Fig. 2 is a schematic structural diagram of an embodiment of an apparatus 200 for determining an order of search terms according to an embodiment of the present disclosure, and as shown in fig. 2, the apparatus 200 for determining an order of search terms includes a determining module 201, a clustering module 202, and an updating module 203.
The determining module 201 is configured to determine a first search term corresponding to a search term;
the determining module 201 is further configured to determine a visual feature vector of the first search term;
the clustering module 202 is configured to cluster the first search item according to the visual feature vector of the first search item to obtain a clustering result;
the determining module 201 is further configured to determine a first category according to the clustering result, where the first category includes M search terms in the first search terms, M is a positive integer and M is greater than a first threshold;
the updating module 203 is configured to update click rates of the M search terms;
the determining module 201 is further configured to determine a display order of the first search term according to the click rate of the first search term.
The apparatus shown in fig. 2 can perform the method of the embodiment shown in fig. 1, and reference may be made to the related description of the embodiment shown in fig. 1 for a part of this embodiment that is not described in detail. The implementation process and technical effect of the technical solution refer to the description in the embodiment shown in fig. 1, and are not described herein again.
Referring now to FIG. 3, a block diagram of an electronic device 300 suitable for use in implementing embodiments of the present disclosure is shown. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 3 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. 3, the electronic device 300 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 301 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data necessary for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus or a communication line 304. An input/output (I/O) interface 305 is also connected to bus or communication line 304.
Generally, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touch pad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage devices 308 including, for example, magnetic tape, hard disk, etc.; and a communication device 309. The communication means 309 may allow the electronic device 300 to communicate wirelessly or by wire with other devices to exchange data. While fig. 3 illustrates an electronic device 300 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.
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 through the communication means 309, or installed from the storage means 308, or installed from the ROM 302. The computer program, when executed by the processing device 301, performs the above-described functions defined in the methods of the embodiments of the present disclosure.
It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may include, 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 the present 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 contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either 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 perform the method of determining an order of search items in the above embodiments.
Computer program code for carrying out operations for aspects 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 disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams 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 disclosure may be implemented by software or hardware. Where the name of an element does not in some cases constitute a limitation on the element itself.
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on 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 accordance with one or more embodiments of the present disclosure, there is provided a method of determining an order of search terms, including: determining a first search term corresponding to the search term; determining a visual feature vector for the first search term; clustering the first search item according to the visual feature vector of the first search item to obtain a clustering result; determining a first category according to the clustering result, wherein the first category comprises M search items in the first search items, M is a positive integer and is greater than a first threshold; updating click rates of the M search terms; and determining the display sequence of the first search item according to the click rate of the first search item.
Further, determining a visual feature vector for the first search term comprises: extracting the visual feature vector of the first search term through a neural network.
Further, the first search term includes a video item and/or an image item.
Further, clustering the first search term according to the visual feature vector of the first search term includes: clustering the first search term according to the visual feature vector of the first search term through a Gaussian density algorithm or a K-means algorithm.
Further, updating the click-through rates of the M search terms includes: determining N search items with the highest click rate in the M search items, wherein N is a positive integer; and updating the click rate of the M search items according to the similarity between the M search items and the N search items and the click rate of the N search items.
Further, updating the click rate of the M search terms according to the similarity between the M search terms and the N search terms and the click rate of the N search terms, including: updating the click rate of the M search terms according to a click rate update formula, wherein the click rate update formula comprises:
wherein, CTRjThe click rate of a search item j in the M search items is represented, the value range of j is 1 to M, and CTRiFor the click rate of search item i of the N search items, SIMijIs the similarity between search term i and search term j.
Further, the similarity SIM between the search item i and the search item jijIs determined from the visual feature vector of search term i and the visual feature vector of search term j.
Further, determining the display order of the first search term according to the click rate of the first search term includes: determining the score of the first search item according to the click rate of the first search item, wherein the score of the first search item is positively correlated with the click rate of the first search item; determining the display order of the first search term according to a score of the first search term.
In accordance with one or more embodiments of the present disclosure, there is provided an apparatus for determining an order of search items, including: the determining module is used for determining a first search item corresponding to the search word; the determining module is further configured to determine a visual feature vector of the first search term; the clustering module is used for clustering the first search item according to the visual feature vector of the first search item to obtain a clustering result; the determining module is further configured to determine a first category according to the clustering result, where the first category includes M search terms of the first search terms, M is a positive integer and M is greater than a first threshold; the updating module is used for updating the click rate of the M search items; the determining module is further configured to determine a display order of the first search term according to the click rate of the first search term.
Further, the determining module is further configured to: extracting the visual feature vector of the first search term through a neural network.
Further, the first search term includes a video item and/or an image item.
Further, the clustering module is further configured to: clustering the first search term according to the visual feature vector of the first search term through a Gaussian density algorithm or a K-means algorithm.
Further, the update module is further configured to: determining N search items with the highest click rate in the M search items, wherein N is a positive integer; and updating the click rate of the M search items according to the similarity between the M search items and the N search items and the click rate of the N search items.
Further, the update module is further configured to: updating the click rate of the M search terms according to a click rate update formula, wherein the click rate update formula comprises:
wherein, CTRjThe click rate of a search item j in the M search items is represented, the value range of j is 1 to M, and CTRiFor the click rate of search item i of the N search items, SIMijIs the similarity between search term i and search term j.
Further, the similarity SIM between the search item i and the search item jijIs according to the visual characteristics of the search term iA feature vector, and the visual feature vector of search term j.
Further, the determining module is further configured to: determining the score of the first search item according to the click rate of the first search item, wherein the score of the first search item is positively correlated with the click rate of the first search item; determining the display order of the first search term according to a score of the first search term.
According to one or more embodiments of the present disclosure, there is provided an electronic device including: a memory for storing computer readable instructions; and one or more processors coupled with the memory for executing the computer readable instructions, such that the processors when executed implement the method of determining an order of search terms of any of the preceding first aspects.
According to one or more embodiments of the present disclosure, there is provided a non-transitory computer readable storage medium characterized in that it stores computer instructions which, when executed by a computer, cause the computer to perform the method of determining the order of search items of any of the preceding first aspects.
The foregoing description is only exemplary of the preferred embodiments of the disclosure 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 disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.
Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
Claims (10)
1. A method of determining an order of search terms, comprising:
determining a first search term corresponding to the search term;
determining a visual feature vector for the first search term;
clustering the first search item according to the visual feature vector of the first search item to obtain a clustering result;
determining a first category according to the clustering result, wherein the first category comprises M search items in the first search items, M is a positive integer and is greater than a first threshold;
updating click-through rates for the M search terms, including:
determining N search items with the highest click rate in the M search items, wherein N is a positive integer;
updating the click rate of the M search items according to the similarity between the M search items and the N search items and the click rate of the N search items;
and determining the display sequence of the first search item according to the click rate of the first search item.
2. The method of determining an order of search terms of claim 1, wherein determining a visual feature vector for the first search term comprises:
extracting the visual feature vector of the first search term through a neural network.
3. The method of determining an order of search terms of claim 2, wherein the first search term comprises a video term and/or an image term.
4. The method of determining an order of search terms of claim 1, wherein clustering the first search term according to the visual feature vector of the first search term comprises:
clustering the first search term according to the visual feature vector of the first search term through a Gaussian density algorithm or a K-means algorithm.
5. The method of claim 1, wherein updating the click-through rates of the M search terms according to the similarities of the M search terms and the N search terms and the click-through rates of the N search terms comprises:
updating the click rate of the M search terms according to a click rate update formula, wherein the click rate update formula comprises:
wherein, CTRjThe click rate of a search item j in the M search items is represented, the value range of j is 1 to M, and CTRiFor the click rate of search item i of the N search items, SIMijIs the similarity between search term i and search term j.
6. The method of determining an order of search terms of claim 5, wherein the similarity between search term i and search term jSIM cardijIs determined from the visual feature vector of search term i and the visual feature vector of search term j.
7. The method of determining an order of search terms of claim 1, wherein determining an order of display of the first search term according to a click-through rate of the first search term comprises:
determining the score of the first search item according to the click rate of the first search item, wherein the score of the first search item is positively correlated with the click rate of the first search item;
determining the display order of the first search term according to a score of the first search term.
8. An apparatus for determining an order of search terms, comprising:
the determining module is used for determining a first search item corresponding to the search word;
the determining module is further configured to determine a visual feature vector of the first search term;
the clustering module is used for clustering the first search item according to the visual feature vector of the first search item to obtain a clustering result;
the determining module is further configured to determine a first category according to the clustering result, where the first category includes M search terms of the first search terms, M is a positive integer and M is greater than a first threshold;
an update module for updating click-through rates of the M search terms, comprising:
determining N search items with the highest click rate in the M search items, wherein N is a positive integer;
updating the click rate of the M search items according to the similarity between the M search items and the N search items and the click rate of the N search items;
the determining module is further configured to determine a display order of the first search term according to the click rate of the first search term.
9. An electronic device, comprising:
a memory for storing computer readable instructions; and
a processor for executing the computer readable instructions such that the processor when executed implements a method of determining an order of search terms according to any of claims 1-7.
10. A non-transitory computer readable storage medium storing computer readable instructions which, when executed by a computer, cause the computer to perform the method of determining an order of search terms of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910888019.7A CN110674401B (en) | 2019-09-19 | 2019-09-19 | Method and device for determining sequence of search items and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910888019.7A CN110674401B (en) | 2019-09-19 | 2019-09-19 | Method and device for determining sequence of search items and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110674401A CN110674401A (en) | 2020-01-10 |
| CN110674401B true CN110674401B (en) | 2022-04-15 |
Family
ID=69078372
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910888019.7A Active CN110674401B (en) | 2019-09-19 | 2019-09-19 | Method and device for determining sequence of search items and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110674401B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009030972A1 (en) * | 2007-09-06 | 2009-03-12 | Chin San Sathya Wong | Method and system of generating and presenting search results |
| CN101583949A (en) * | 2007-01-05 | 2009-11-18 | 雅虎公司 | Clustered search processing |
| CN102810117A (en) * | 2012-06-29 | 2012-12-05 | 北京百度网讯科技有限公司 | Method and equipment for supplying search result |
| CN103399951A (en) * | 2013-08-19 | 2013-11-20 | 山东大学 | Semi-supervised image reordering method with self-feedback characteristic based on heterogeneous diagram |
| CN104239566A (en) * | 2014-09-28 | 2014-12-24 | 小米科技有限责任公司 | Method and device for searching videos |
| CN104598611A (en) * | 2015-01-29 | 2015-05-06 | 百度在线网络技术（北京）有限公司 | Method and system for sequencing search entries |
| CN106886553A (en) * | 2016-12-27 | 2017-06-23 | 浙江宇视科技有限公司 | A kind of image search method and server |
| CN106971004A (en) * | 2017-04-26 | 2017-07-21 | 百度在线网络技术（北京）有限公司 | Search result provides method and device |
| CN109086394A (en) * | 2018-07-27 | 2018-12-25 | 天津字节跳动科技有限公司 | Search ordering method, device, computer equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110040740A1 (en) * | 2009-08-15 | 2011-02-17 | Alex Nugent | Search engine utilizing flow networks |
-
2019
- 2019-09-19 CN CN201910888019.7A patent/CN110674401B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101583949A (en) * | 2007-01-05 | 2009-11-18 | 雅虎公司 | Clustered search processing |
| WO2009030972A1 (en) * | 2007-09-06 | 2009-03-12 | Chin San Sathya Wong | Method and system of generating and presenting search results |
| CN102810117A (en) * | 2012-06-29 | 2012-12-05 | 北京百度网讯科技有限公司 | Method and equipment for supplying search result |
| CN103399951A (en) * | 2013-08-19 | 2013-11-20 | 山东大学 | Semi-supervised image reordering method with self-feedback characteristic based on heterogeneous diagram |
| CN104239566A (en) * | 2014-09-28 | 2014-12-24 | 小米科技有限责任公司 | Method and device for searching videos |
| CN104598611A (en) * | 2015-01-29 | 2015-05-06 | 百度在线网络技术（北京）有限公司 | Method and system for sequencing search entries |
| CN106886553A (en) * | 2016-12-27 | 2017-06-23 | 浙江宇视科技有限公司 | A kind of image search method and server |
| CN106971004A (en) * | 2017-04-26 | 2017-07-21 | 百度在线网络技术（北京）有限公司 | Search result provides method and device |
| CN109086394A (en) * | 2018-07-27 | 2018-12-25 | 天津字节跳动科技有限公司 | Search ordering method, device, computer equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 基于视觉特征的图像检索重排序;陈畅怀等;《信息技术》;20121231;第1-7页 * |
| 聚类技术在图像检索中的应用;鲍健鹏等;《福建电脑》;20070630;第61-62页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110674401A (en) | 2020-01-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110704751B (en) | Data processing method and device, electronic equipment and storage medium | |
| CN110634047B (en) | Method and device for recommending house resources, electronic equipment and storage medium | |
| WO2020156389A1 (en) | Information pushing method and device | |
| CN111414498A (en) | Multimedia information recommendation method and device and electronic equipment | |
| CN111368185A (en) | Data display method and device, storage medium and electronic equipment | |
| CN110413742B (en) | Resume information duplication checking method, device, equipment and storage medium | |
| CN113986933A (en) | Materialized view creating method and device, storage medium and electronic equipment | |
| CN110674400B (en) | Sorting method, sorting device, electronic equipment and computer-readable storage medium | |
| CN112819512B (en) | Text processing method, device, equipment and medium | |
| CN111444356A (en) | Search-based recommendation method and device | |
| CN113407814B (en) | Text searching method and device, readable medium and electronic equipment | |
| US20240168605A1 (en) | Text input method and apparatus, and electronic device and storage medium | |
| WO2022233311A1 (en) | Display method and apparatus, and electronic device | |
| CN111078849A (en) | Method and apparatus for outputting information | |
| CN110674399B (en) | Method and apparatus for determining order of search items | |
| CN114445754A (en) | Video processing method and device, readable medium and electronic equipment | |
| CN110598102A (en) | Method, apparatus, electronic device, and computer-readable storage medium for determining an order of search items | |
| CN110674401B (en) | Method and device for determining sequence of search items and electronic equipment | |
| CN111382365A (en) | Method and apparatus for outputting information | |
| CN113221572B (en) | Information processing method, device, equipment and medium | |
| US20210271720A1 (en) | Method and apparatus for sending information | |
| CN111782895B (en) | Retrieval processing method and device, readable medium and electronic equipment | |
| CN110598133A (en) | Method, apparatus, electronic device, and computer-readable storage medium for determining an order of search items | |
| CN112148751B (en) | Method and device for querying data | |
| CN113255812A (en) | Video frame detection method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |