CN110930208B - Object searching method and device - Google Patents

Object searching method and device Download PDF

Info

Publication number
CN110930208B
CN110930208B CN201811094922.8A CN201811094922A CN110930208B CN 110930208 B CN110930208 B CN 110930208B CN 201811094922 A CN201811094922 A CN 201811094922A CN 110930208 B CN110930208 B CN 110930208B
Authority
CN
China
Prior art keywords
language
search
search results
version
searching
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201811094922.8A
Other languages
Chinese (zh)
Other versions
CN110930208A (en
Inventor
王金刚
陈博兴
骆卫华
司罗
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alibaba Group Holding Ltd
Original Assignee
Alibaba Group Holding Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Alibaba Group Holding Ltd filed Critical Alibaba Group Holding Ltd
Priority to CN201811094922.8A priority Critical patent/CN110930208B/en
Publication of CN110930208A publication Critical patent/CN110930208A/en
Application granted granted Critical
Publication of CN110930208B publication Critical patent/CN110930208B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/06Buying, selling or leasing transactions
    • G06Q30/0601Electronic shopping [e-shopping]
    • G06Q30/0641Shopping interfaces
    • G06Q30/0643Graphical representation of items or shoppers

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Machine Translation (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

The invention discloses an object searching method and device. Wherein the method comprises the following steps: receiving a search object input in a first language; converting the search object from the first language to a second language; searching the search object in the second language to obtain a search result in the second language; converting the search results of the second language into a multi-version first language to obtain the search results of the multi-version first language; reordering the multi-version first language search results based on at least the historical operation log of the multi-version first language search results to obtain reordered search results; and displaying the reordered search results. The method solves the technical problems of low translation accuracy and poor user experience in the translation process of the foreign language searching method in the related technology.

Description

Object searching method and device
Technical Field
The present invention relates to the field of object searching, and in particular, to an object searching method and apparatus.
Background
With the development of electronic commerce, the current electronic commerce platform is more and more internationalized, and when a foreign language website is established, chinese commodity information is usually accurately translated into a target foreign language for display. Because of the large regionalism of languages, the languages are various and the language habits are various. Moreover, the existing manual translation has high cost and low efficiency, and is difficult to meet the commodity display requirement of high-speed updating. In particular, when performing translation, there are times when a chinese commodity may translate into multiple foreign language versions, but for users in different regions there may be unacceptable versions in more than ten translations. For example, "Orange Juice" of Chinese, may be converted into English translations of "Orange Juice", "Orange Square", "Tang", etc.; for another example, for the chinese commodity title "female long dress", the english translations that may be converted into are "word's long dress", "word's long address", "word's long-length address", and so on. The versions accepted by users in different areas are different, so that unacceptable versions exist in the translations, and when the unacceptable versions are displayed to the users, the accuracy of the translations is reduced, and the use experience of the users is obviously reduced.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The embodiment of the invention provides an object searching method and device, which at least solve the technical problems of low translation accuracy and poor user experience in the translation process of a foreign language searching method in the related technology.
According to an aspect of an embodiment of the present invention, there is provided an object searching method including: receiving a search object input in a first language; converting the search object from the first language to a second language; searching the search object in the second language to obtain a search result in the second language; converting the search results of the second language into the first language of multiple versions to obtain the search results of the first language of multiple versions; reordering the multi-version first language search results based on at least the historical operation log of the multi-version first language search results to obtain reordered search results; and displaying the reordered search results.
According to another aspect of the embodiment of the present invention, there is also provided an object searching method, including: receiving a search sentence, wherein the language type of the search sentence is a first language; converting the language type of the search sentence into a multi-version second language, and obtaining a search result corresponding to the multi-version second language, wherein the language type of the search result is the second language; and reordering the search results corresponding to the multi-version second language based on the historical operation log of the search results to obtain ordered search results.
According to another aspect of the embodiment of the present invention, there is also provided an object searching method, including: receiving a search sentence, wherein the language type of the search sentence is a first language; converting the language type of the search statement into a second language, and acquiring a search result corresponding to the search statement based on the conversion result, wherein the language type of the search result is the second language; converting the language type of the search result into a multi-version first language; and reordering the multi-version first language search results based on the historical operation log of the multi-version first language search results to obtain ordered search results.
According to another aspect of the embodiment of the present invention, there is also provided an object searching method, including: receiving a search request, wherein the search request carries a search object input in a first language; responding to the search request, and searching after the search object is converted from the first language into the second language, so as to obtain a search result; after the search results in the second language are converted into the multi-version first language, the multi-version first language search results are reordered based on the historical operation log of the multi-version first language search results, and the ordered search results are displayed.
According to another aspect of the embodiment of the present invention, there is also provided an object searching apparatus including: a receiving module for receiving a search object input in a first language; a first conversion module for converting the search object from the first language to a second language; the searching module is used for searching the searching object in the second language to obtain a searching result in the second language; the second conversion module is used for converting the search results in the second language into the first language with multiple versions to obtain the search results in the first language with multiple versions; the sorting module is used for reordering the search results of the multiple versions of the first language at least based on the historical operation log of the search results of the multiple versions of the first language to obtain reordered search results; and the display module is used for displaying the reordered search results.
According to another aspect of the embodiment of the present invention, there is also provided a storage medium including a stored program, where the program, when executed, controls a device in which the storage medium is located to perform any one of the object searching methods described above.
According to another aspect of the embodiment of the present invention, there is further provided a processor, configured to execute a program, where the program executes any one of the above object searching methods.
In the embodiment of the invention, a search object input in a first language is received; converting the search object from the first language to a second language; searching the search object in the second language to obtain a search result in the second language; converting the search results in the second language into the multi-version first language to obtain multi-version first language search results; reordering the multi-version first language search results based on at least the historical operation log of the multi-version first language search results to obtain reordered search results; the method for displaying the reordered search results achieves the aim of determining the most suitable translation version of a user aiming at the historical language habit of the user by ordering the search results corresponding to the first language of a plurality of different versions of the search results of the second language and ordering according to the historical operation log of the search results, thereby realizing the technical effects of improving the translation accuracy and the user experience in the search process, and further solving the technical problems of low translation accuracy and poor user experience in the translation process of the foreign language search method in the related art.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:
FIG. 1 is a block diagram of the hardware architecture of a computer terminal (or mobile device) for implementing a data processing method;
fig. 2 is a schematic diagram of an object searching method according to embodiment 1 of the present invention;
FIG. 3 is a flowchart of another object searching method according to embodiment 1 of the present invention;
FIG. 4 is a flowchart of another object searching method according to embodiment 1 of the present invention;
FIG. 5 is a schematic diagram of the structure of an encoder-decoder translation model according to embodiment 1 of the present invention;
FIG. 6 is a flowchart of a commodity title translation method according to embodiment 1 of the present invention;
fig. 7 is a flowchart of an object searching method according to embodiment 2 of the present invention;
fig. 8 is a flowchart of an object searching method according to embodiment 3 of the present invention;
fig. 9 is a flowchart of an object searching method according to embodiment 4 of the present invention;
fig. 10 is a schematic structural view of an object searching apparatus according to embodiment 5 of the present invention;
Fig. 11 is a block diagram of a computer terminal according to embodiment 6 of the present application.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
In accordance with an embodiment of the present invention, there is also provided a method embodiment of an object searching method, it being noted that the steps shown in the flowchart of the figures may be performed in a computer system, such as a set of computer executable instructions, and, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in an order other than that shown or described herein.
The method embodiment provided in the first embodiment of the present application may be executed in a mobile terminal, a computer terminal or a similar computing device. Fig. 1 shows a block diagram of a hardware structure of a computer terminal (or mobile device) for implementing an object search method. As shown in fig. 1, the computer terminal 10 (or mobile device 10) may include one or more (shown as 102a, 102b, … …,102 n) processors 102 (the processors 102 may include, but are not limited to, a microprocessor MCU, a programmable logic device FPGA, etc. processing means), a memory 104 for storing data. In addition, the method may further include: a transmission module, a display, an input/output interface (I/O interface), a Universal Serial Bus (USB) port (which may be included as one of the ports of the I/O interface), a network interface, a power supply, and/or a camera. It will be appreciated by those of ordinary skill in the art that the configuration shown in fig. 1 is merely illustrative and is not intended to limit the configuration of the electronic device described above. For example, the computer terminal 10 may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
It should be noted that the one or more processors 102 and/or other data processing circuits described above may be referred to generally herein as "data processing circuits. The data processing circuit may be embodied in whole or in part in software, hardware, firmware, or any other combination. Furthermore, the data processing circuitry may be a single stand-alone processing module, or incorporated, in whole or in part, into any of the other elements in the computer terminal 10 (or mobile device). As referred to in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of the path of the variable resistor termination to interface).
The memory 104 may be used to store software programs and modules of application software, such as program instructions/data storage devices corresponding to the object searching method in the embodiment of the present invention, and the processor 102 executes the software programs and modules stored in the memory 104, thereby executing various functional applications and data processing, that is, implementing the object searching method of the application program. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission module is used for receiving or transmitting data through a network. The specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission module includes a network adapter (Network Interface Controller, NIC) that can connect to other network devices through the base station to communicate with the internet. In one example, the transmission module may be a Radio Frequency (RF) module, which is used to communicate with the internet wirelessly.
The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with a user interface of the computer terminal 10 (or mobile device).
The hardware block diagram shown in fig. 1 may be used not only as an exemplary block diagram of the computer terminal 10 (or mobile device) described above, but also as an exemplary block diagram of the server described above, and in an alternative embodiment, the computer terminal 10 (or mobile device) shown in fig. 1 described above is used as an embodiment (e.g., a transmitting end, a receiving end, etc.). The computer terminal 10 (or mobile device) may be connected or electronically connected to one or more servers (e.g., security server, resource server, game server, etc.) via a data network connection. In alternative embodiments, the computer terminal 10 (or mobile device) described above may be any mobile computing device or the like. The data network connection may be a local area network connection, a wide area network connection, an internet connection, or other type of data network connection. The computer terminal 10 (or mobile device) may execute to connect to a network service executed by a server (e.g., a security server) or a set of servers. Web servers are web-based user services such as social networks, cloud resources, email, online payment, or other online applications.
Electronic commerce (e.g. electronic commerce) is a common transaction mode, along with the development of electronic commerce and internet, an electronic commerce platform is also gradually internationalized, and a domestic electronic commerce platform needs to develop cross-border services, firstly, a foreign language (such as english, russian and spanish) website needs to be built, and chinese commodity information (title and detail page) is accurately translated into a target language for display. The usual translation mode is manual translation, which translates the information of the Chinese commodity to be displayed into the information of the target language in advance, and then pops up the prestored information translated into the target language for the user to review when the user clicks the query. But the number and content of the commodities are frequently updated in the face of the electronic commerce website, and the manual translation is far from meeting the requirement. The manual translation mode is low in updating speed, the ultrahigh updating frequency on the e-commerce platform is difficult to keep up, and the cost of manual translation is too high.
With the development and research of artificial intelligence, machine translation technology based on neural networks has greatly developed, and in the fields of news and the like, a neural network translation model is close to the level of human translation. The machine translation technology is used for completing translation of commodity titles, so that a great deal of labor cost can be saved, and the efficiency is incomparable with that of manual translation. When overseas users search for goods using a local language (hereinafter, described in detail by using english as an example), since the goods index library of the background of the e-commerce website is constructed based on chinese, firstly, the english query (query instruction) of the user needs to be translated into the chinese query instruction for searching, and the searched goods list is returned and the goods information of the english version is displayed. For the same Chinese commodity title, because of the changes of semantics (synonyms/polysemous words/hyponyms), word orders, tenses and the like, various different English translation versions may exist, how to select the most accurate translation for display, and the user experience and the final success transformation of the website are related. The neural network machine translation generates multi-version translations for the same original text through beam search (beam search), and reorders and selects the best version of the multi-version translations for final display according to information such as a language model.
In the above-described operating environment, the present application provides an object searching method as shown in fig. 2. Fig. 2 is a schematic diagram of an object searching method according to embodiment 1 of the present invention, and as shown in fig. 2, the object searching method provided in the embodiment of the present application may be implemented by the following method steps:
step S202, a search object input in a first language is received.
As an alternative embodiment, the main implementation body of the above steps is a search tool, and the search tool may be a search website specially used for searching, or may be a search tool used in an e-commerce platform or other websites, so that a user can quickly find goods or contents related to a search object.
As an alternative embodiment, the search object may be a keyword input in the first language, and the keyword may be a kind, an attribute, a size, a name, and the like of the target object.
As an alternative embodiment, the above-mentioned keywords are input in the first language, and text information, such as a category, an attribute, a size name, etc., indicating that the user wishes to obtain the target object expressed in the first language is described.
As an alternative embodiment, the first language may be any kind of language, for example, english, french, german, etc.
Step S204, converting the search object from the first language to the second language.
As an alternative embodiment, the main implementation body of the above steps is a search tool, and the search tool may be a search website specially used for searching, or may be a search tool used in an e-commerce platform or other websites, so that a user can quickly find goods or contents related to a search object.
As an alternative embodiment, the search tool generally uses a second language as a basic language, for example, a chinese e-commerce platform, where the basic language is generally chinese, and when searching in a first language in a foreign language website of the e-commerce platform, a search object input in the first language is translated into chinese, and then searching is performed according to the chinese search object to obtain chinese information of a related target object, and then the chinese information of the target object is translated into corresponding first language information.
As an alternative embodiment, the above-mentioned conversion of the search object from the first language to the second language facilitates searching of websites in the second language as a basis. The search tool is a search tool in a second language based language.
Step S206, searching the second language searching object to obtain the second language searching result.
As an alternative embodiment, the step searches in the second language for the search object in the second language as the search tool in the second language as the basic language, so as to obtain the search result in the second language.
As an alternative embodiment, the search results include a plurality of objects in a second language, and the search results may be ranked according to a plurality of different ranking criteria. The search results ranked by different ranking criteria may be different or the same, and the ranking criteria may be default or user-selected.
As an optional embodiment, the user selection ranking criterion may be selected by a user, where the user selects a ranking rule in a first language, the ranking rule in the first language corresponds to a ranking rule in a second language, and when the first ranking rule in the first language is selected, the ranking rule in the second language is triggered, and ranking is performed according to the ranking rule in the second language.
Step S208, converting the search result in the second language into the first language with multiple versions to obtain the search result in the first language with multiple versions.
As an alternative embodiment, the second language search results may not be acceptable to the user using the first language, and thus the second language search results may be converted to the first language search results before the second language search results are presented.
In the process of converting the search results in the second language into the search results in the first language, one search result in the second language may translate a plurality of search results in the first language, for example, "Orange Juice" in Chinese, and "Orange Juice", "Orange square", "Tang" may be converted into English translations; for another example, for the chinese commodity title "female long dress", the english translations that may be converted into are "word's long dress", "word's long address", "word's long-length address", and so on.
As an alternative embodiment, the first language may be any language other than the second language, but the language may vary somewhat according to the time and space differences of propagation, for example, english is the most widely used language in the world, but english is also classified into various kinds, mainly into american english and english, and other, for example, indian english, etc., and descriptions of the same thing are also different from subclasses of languages. Therefore, the translation of the search result most suitable for the user needs to be selected and displayed to the user, so that the experience of the user is improved.
Step S210, based on at least the historical operation log of the multi-version first language search results, reordering the multi-version first language search results to obtain reordered search results.
As an alternative embodiment, the ranking criteria for the search results may need to be determined before the translation of the search results that are most appropriate to the user is presented to the user.
As an alternative embodiment, the reordering of the search results may be based on a variety of factors, for example, may be based on a historical operation log of the search results, because the historical operation log of the search results may display some of the search records generated before the search object to some extent, and the search records may reflect the general search characteristics of the search object to some extent, so that the reordering of the search results based on the historical operation log of the search results may effectively improve the accuracy of the search to some extent.
Step S212, displaying the reordered search results.
As an alternative embodiment, after each translation result of each search result is ranked according to the history operation log, the ranked search result may be displayed to the user, or the translation result with the top ranking may be selected and displayed to the user. That is, the search results are all optimal translation results sequenced according to the historical operation log, so that the translation accuracy and the user experience can be effectively improved.
In the embodiment of the invention, a search object input in a first language is received; converting the search object from the first language to a second language; searching the search object in the second language to obtain a search result in the second language; converting the search results of the second language into a multi-version first language, and reordering the search results of the multi-version first language at least based on the historical operation log of the search results of the multi-version first language to obtain reordered search results; the method for displaying the reordered search results achieves the aim of determining the most suitable translation version of the user according to the historical language habit of the user by ordering the multi-version first languages converted from the second language and ordering according to the historical operation log of the search results, thereby realizing the technical effects of improving the translation accuracy and the user experience degree in the search process, and further solving the technical problems of low translation accuracy and poor user experience in the translation process of the foreign language search method in the related technology.
As an alternative embodiment, the historical operation log includes at least one of: browsing records of browsing the search results, clicking records of clicking the search results, and purchasing records of purchasing the search results.
As an alternative embodiment, the browsing record for browsing the search results can describe the browsing intention, the searching range and the like of the user in the search tool, and can reflect the requirements of the user to a certain extent. For example, after a user searches for "men's pants" and browses most of them as jeans, the user may be considered to need to find jeans.
As an alternative embodiment, the click record of clicking on the search result can illustrate the understanding intention of the user in the search tool, the interested content range and the like, and can reflect the interest of the user to a certain extent. For example, when the user frequently clicks "mobile phone", the user is considered to have a greater interest in purchasing mobile phones.
As an alternative embodiment, the above purchase record for purchasing the search result may illustrate the purchase intention of the user in the search tool, the purchased commodity range, etc., and may reflect the purchase requirement of the user to some extent. For example, after purchasing a plurality of "candies," the user considers that there is a certain purchase demand for the candies.
As an alternative embodiment, the browse recording includes at least: the number of times of browsing, the duration of browsing; the click record includes: the number of clicks; the purchase record includes: number of purchases.
As an optional embodiment, the above browsing record for browsing the search result may be embodied by the number of browsing times and the browsing duration; the above-mentioned click record for clicking the search result can be embodied by the number of clicks; the above-mentioned purchase record for purchasing the search result may be embodied by the number of purchases or the number of purchases.
As an alternative embodiment, further comprising: a historical log of operations for a geographic area is obtained.
It should be noted that, when the history log is obtained, the ranking of the search results is also different because the history log in different ranges is obtained. For example, for a historical operating log that is in a country range, the ranked search results will be relatively broad due to the broad range; for another example, for a historical log of operations in a regional geographic area below a country range, the ranked search results may be relatively centralized relative to the country range. Thus, if the selected historical oplog is relative to a smaller geographic area, the search results, while relatively few, will be relatively accurate.
The history operation log comprises position information, namely, the geographical area of the user is defined, the language habit and the category of the user can be more accurately determined, and the accuracy of sequencing a plurality of different translation versions is effectively improved.
As an alternative embodiment, fig. 3 is a flowchart of another object searching method according to embodiment 1 of the present invention, and as shown in fig. 3, the obtaining a history operation log for a geographical area includes:
step S302, determining the expression form of the input search object in the first language;
step S304, determining a geographic area corresponding to the expression form;
step S306, a history operation log in the geographic area is obtained.
As an alternative embodiment, the form of the search object in the first language determined and input may be specific terms, logic, etc. of the search object, for example, although different english countries represent the same object, different idioms may be adopted, and the different idioms may directly represent the language types and the terms of the use regions to some extent. By means of the special words and expressions, the geographical area corresponding to the expression can be determined.
As an alternative embodiment, the geographic area corresponding to the determined expression form may be a geographic area corresponding to the expression form of the search object, where the geographic area corresponding to the expression form of the search object may be a geographic area corresponding to the expression form of the search object, and the geographic areas corresponding to different expression forms may overlap.
As an optional embodiment, the obtaining of the history operation log in the geographical area may be the history operation log of the user in the geographical area, and combining the geographical area where the user is located with the history operation log may effectively increase the accuracy rate of sorting the translation results of different versions.
As an alternative embodiment, converting the search results in the second language into the multi-version first language, obtaining the search results in the multi-version first language includes: and converting the search results in the second language into the first language in multiple versions by adopting a beam search method to obtain the search results in the first language in multiple versions.
As an alternative embodiment, when the second language is converted into the first language with multiple versions, the method can use the beam searching method herein or train multiple translation systems to generate the second language, and the method adopting the beam searching converts the searching result of the second language into the first language with multiple versions to obtain the searching result of the first language with multiple versions, so that the searching efficiency and the searching accuracy can be effectively improved.
As an alternative embodiment, fig. 4 is a flowchart of another object searching method according to embodiment 1 of the present invention, and as shown in fig. 4, the object searching method further includes:
step S402, evaluating the search results of the first language with multiple versions by adopting a translation model to obtain evaluation results;
step S404, pre-ordering the search results of the multi-version first language according to the evaluation results.
As an alternative embodiment, the translating the first language into the second language or the translating the second language into the first language uses a translation model, where the translation model may be a neural network deep learning model, and has a certain false-positive rate, so that evaluation and scoring are performed on the search result translated by the translation model.
For example, training a reverse english-to-intermediate translation model with the same training data scores the current forward translation results, e.g., target-to-Source.
For another example, the translations in the training corpus are reverse-trained into a translation model, and then the positive-order translation model data results are scored, e.g., right-to-Left scoring.
As an alternative embodiment, the translation model is adopted to evaluate the search results of the multiple versions of the first language to obtain evaluation results, and then the search results of the multiple versions of the first language are pre-ordered according to the evaluation results. The evaluation result is added with additional information such as searching, clicking and bargaining of the user as new characteristics, and supervised learning is carried out, so that the translation result is closer to a user searching object, and user experience can be effectively improved.
As an optional embodiment, the object searching method further includes: receiving an operation performed on the displayed search results; recording an operation log according to the operation; and updating the historical operation log by adopting the recorded operation log.
The new operation log is fused into the historical operation log to influence the next translation operation, so that a closed loop is formed, virtuous circle is generated, the translation generated by the trade name translation module is provided for a user, click feedback of the user can be used for optimizing the translation module, and the whole link can be continuously and iteratively optimized.
An alternative mode of the present embodiment will be described in detail below.
The device of the embodiment mainly comprises 4 modules, namely a query (search object) translation module, a commodity name translation module, a user log mining module and a multi-version translation reordering module. Several of the modules described above are described in detail below.
A query translation module: the method mainly realizes the translation from English query to Chinese of the user, because all the existing commodity resources of the E-commerce website are Chinese, including foreground display information such as product names, introduction details, user evaluation and the like and indexes used for searching in the background, a set of English index engineering quantity is built again, the maintenance cost is high, and the common practice is to translate the user query into Chinese and search on a Chinese index library. Because the query length is typically short (3-5 words), the query translation module is implemented using statistical machine translation methods, such as a moses SMT system.
Commodity title translation module: fig. 5 is a schematic diagram of the encoder-decoder translation model according to embodiment 1 of the present invention, and fig. 6 is a flowchart of the commodity title translation method according to embodiment 1 of the present invention, wherein the translated chinese query is used to retrieve the relevant commodity list on the index base, as the commodity name is chinese, which is not directly presented to the user and needs to be converted into chinese by the commodity title translation module, as shown in fig. 5 and 6. The trade name translation module uses a neural network translation method based on an encoder-decoder architecture, such as RNN, transducer, etc.
And a user log mining module: after the translated Chinese commodity list is returned to the user, the user browses, clicks the commodity of interest and enters a commodity detail page, and the names of the non-interested commodity or the commodity with the problem translation are skipped, so that the click log of the user can be used as supervised learning data for optimizing commodity name translation. In the method, a triplet format is used for storing user browsing, clicking and purchasing logs, < query, product translation, view# >, < query, product translation, click# >, < query, product translation, and purchase > wherein query represents user search query, product translation represents commodity English translation, view# represents user browsing times, click# represents times when the translation is clicked by a user, and purchase of the commodity by the user is represented.
Multi-version translation reordering module: as shown in fig. 5, the trade name translation uses a neural network translation system, and the translation process is a decoding process, and by setting different beam sizes (beam sizes), a method of beam search (beam search) can be used to generate translations of multiple versions. Because the bundle search is not a global optimal algorithm, in addition to scoring each version of translation by the model itself, all translation candidates typically need to be reordered by a reordering module to select the most accurate translation for presentation to the user in the current scenario. The reordering method may use a rank learning (rank) method, such as RankSVM, lamdaMart. The method takes the mined user log as a characteristic to be added into sequencing learning. The four steps form a closed loop, the translation generated by the trade name translation module is provided for a user, click feedback of the user can be used for optimizing the translation module, and the whole link is continuously and iteratively optimized.
Example 2
In accordance with an embodiment of the present invention, there is also provided another method embodiment of an object searching method, it being noted that the steps shown in the flowchart of the figures may be performed in a computer system, such as a set of computer executable instructions, and, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in an order other than that shown or described herein.
It should be noted that, the method embodiment provided in embodiment 2 of the present application may be executed in the computer terminal 10 (or the mobile device 10) shown in fig. 1 or similar computing device.
As an alternative embodiment, similar to the evaluation of the search result in the multi-version first language by using the translation model, when the first language is converted into the second language, the conversion of the first language into the multi-version second language may be considered, then the evaluation is performed on the search object in the multi-version second language by using the corresponding translation model, the search object to be searched is selected from the search objects in the multi-version second language based on the evaluation result, and then the search is performed according to the selected search object, so as to obtain the search result. Namely, in the embodiment of the invention, the accuracy of one translation is considered when converting the first language into the second language; the accuracy of one translation is also considered when the second language is translated into the first language, and the accuracy of the translation is considered for a plurality of times, so that the accuracy of search results displayed to a user can be improved to a certain extent.
Fig. 7 is a flowchart of an object searching method according to embodiment 2 of the present invention, and as shown in fig. 7, the object searching method provided in the embodiment of the present application may be implemented by the following method steps:
In step S702, a search sentence is received, where the language type of the search sentence is a first language.
As an alternative embodiment, the search term may include a keyword input in the first language, where the keyword may be a kind, an attribute, a size, a name, and the like of the target object. The keywords are input in the first language, and text information, such as a category, an attribute, a size name, and the like, of the target object that the user wishes to obtain in the first language is described.
In step S704, the language type of the search sentence is converted into a multi-version second language, and a search result corresponding to the multi-version second language is obtained, wherein the language type of the search result is the second language.
As an alternative embodiment, the search tool generally uses a second language as a basic language, for example, a chinese e-commerce platform, where the basic language is generally chinese, and when searching in a first language in a foreign language website of the e-commerce platform, a search sentence input in the first language is first converted into chinese, then searching is performed according to the chinese search sentence, so as to obtain chinese information of a related target object, and then the chinese information of the target object is converted into corresponding first language information.
As an alternative embodiment, the above-mentioned conversion of the search statement from the first language to the second language facilitates searching of websites in the second language as a basis. The search tool is a search tool in a second language based language.
Step S706, based on the history operation log of the search results, the search results corresponding to the second language of the multiple versions are reordered to obtain ordered search results.
As an alternative embodiment, the ranking criteria for the search results may need to be determined before the plurality of objects contained in the search results are reordered as described above.
As an alternative embodiment, the reordering of the search results corresponding to the second language with multiple versions may be based on a plurality of factors, for example, may be based on a history log of the search results, because the history log of the search results may display some search records generated before the search object to a certain extent, and the search records may reflect general search features of the search object to a certain extent, so that the reordering of the search results based on the history log of the search results may effectively improve the accuracy of the search to a certain extent.
Example 3
In accordance with an embodiment of the present invention, there is also provided another method embodiment of an object searching method, it being noted that the steps shown in the flowchart of the figures may be performed in a computer system, such as a set of computer executable instructions, and, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in an order other than that shown or described herein.
It should be noted that, the method embodiment provided in embodiment 3 of the present application may be executed in the computer terminal 10 (or the mobile device 10) shown in fig. 1 or similar computing device. Fig. 8 is a flowchart of an object searching method according to embodiment 3 of the present invention, and as shown in fig. 8, the object searching method provided in the embodiment of the present application may be implemented by the following method steps:
step S802, a search sentence is received, wherein the language type of the search sentence is a first language.
As an alternative embodiment, the search term may include a keyword input in the first language, where the keyword may be a kind, an attribute, a size, a name, and the like of the target object. The keywords are input in the first language, and text information, such as a category, an attribute, a size name, and the like, of the target object that the user wishes to obtain in the first language is described.
In step S804, the language type of the search sentence is converted into the second language, and the search result corresponding to the search sentence is obtained based on the conversion result, wherein the language type of the search result is the second language.
As an alternative embodiment, the search tool generally uses a second language as a basic language, for example, a chinese e-commerce platform, where the basic language is generally chinese, and when searching in a first language in a foreign language website of the e-commerce platform, a search sentence input in the first language is first converted into chinese, then searching is performed according to the chinese search sentence, so as to obtain chinese information of a related target object, and then the chinese information of the target object is converted into corresponding first language information.
As an alternative embodiment, the above-mentioned conversion of the search statement from the first language to the second language facilitates searching of websites in the second language as a basis. The search tool is a search tool in a second language based language.
In step S806, the language type of the search result is converted into the multi-version first language.
As an alternative embodiment, the language type of the converted search result is the first language or other languages other than the second language, in this embodiment, the converted search result is converted into the first language corresponding to the first language, because the general user will use the good language to search when searching. This can ensure search efficiency. The language type of the search result can be preset. Thereby ensuring the user experience.
Step S808, based on the historical operation log of the multi-version first language search results, reordering the multi-version first language search results to obtain ordered search results.
As an alternative embodiment, the determination of the ranking criteria for the search results may be required before the above-described reordering of the search results for the multiple versions of the first language.
Example 4
In accordance with an embodiment of the present invention, there is also provided another method embodiment of an object searching method, it being noted that the steps shown in the flowchart of the figures may be performed in a computer system, such as a set of computer executable instructions, and, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in an order other than that shown or described herein.
It should be noted that, the method embodiment provided in embodiment 4 of the present application may be executed in the computer terminal 10 (or the mobile device 10) shown in fig. 1 or similar computing device. Fig. 9 is a flowchart of an object searching method according to embodiment 4 of the present invention, and as shown in fig. 9, the object searching method provided in the embodiment of the present application may be implemented by the following method steps:
In step S902, a search request is received, where the search request carries a search object input in a first language.
The main execution body of the steps is a search tool, and the search tool can be a search website specially used for searching, or can be a search tool used in an electronic commerce platform or other websites, and is used for a user to quickly find commodities or contents related to a search object.
As an optional embodiment, the search request carries a search object input in the first language. The search object may be a keyword input in the first language, which may be a kind, an attribute, a size, a name, etc. of the target object. The keywords are input in the first language, and text information, such as a category, an attribute, a size name, and the like, of the target object that the user wishes to obtain in the first language is described.
As an alternative embodiment, the first language may be any kind of language, for example, english, french, german, etc.
As an alternative embodiment, the search tool generally uses a second language as a basic language, for example, a chinese e-commerce platform, where the basic language is generally chinese, and when searching in a first language in a foreign language website of the e-commerce platform, a search object input in the first language is first converted into chinese, then searching is performed according to the chinese search object to obtain chinese information of a related target object, and then the chinese information of the target object is converted into corresponding first language information.
Step S904, responding to the search request, and searching after the search object is converted from the first language into the second language, thereby obtaining the search result.
As an alternative embodiment, the step searches in the second language for the search object in the second language as the search tool in the second language as the basic language, so as to obtain the search result in the second language.
As an alternative embodiment, the search results include a plurality of objects in a second language, and the search results may be ranked according to a plurality of different ranking criteria. The search results ranked by different ranking criteria may be different or the same, and the ranking criteria may be default or user-selected.
As an optional embodiment, the user selection ranking criterion may be selected by a user, where the user selects a ranking rule in a first language, the ranking rule in the first language corresponds to a ranking rule in a second language, and when the first ranking rule in the first language is selected, the ranking rule in the second language is triggered, and ranking is performed according to the ranking rule in the second language.
As an alternative embodiment, the first language may be any language other than the second language, but the language may vary somewhat according to the time and space differences of propagation, for example, english is the most widely used language in the world, but english is also classified into various kinds, mainly into american english and english, and other, for example, indian english, etc., and descriptions of the same thing are also different from subclasses of languages. Therefore, the translation of the search result most suitable for the user needs to be selected and displayed to the user, so that the experience of the user is improved.
Step S906, after converting the second language search result into the multi-version first language, re-ranking the multi-version first language search result based on the historical operation log of the multi-version first language search result, and displaying the ranked search result.
Before the translation of the search results most suitable for the user is presented to the user, the ranking criteria of the search results need to be determined.
As an alternative embodiment, reordering the multi-version search results in the first language based on the historical operating log of the multi-version search results in the first language includes: receiving an input geographic area; and reordering the multi-version first language search results based on the historical operation log corresponding to the geographic region.
As an alternative embodiment, the geographic area for receiving input refers to a geographic area corresponding to the expression form of the search object, where the geographic area corresponding to the expression form of the search object may be a geographic area corresponding to a different expression form, and the geographic area corresponding to the different expression form may overlap.
As an optional embodiment, the search results are reordered based on the historical operation logs corresponding to the geographic area, and the historical operation logs in the geographic area are the historical operation logs of the user in the geographic area, so that the accuracy rate of ordering the translation results of different versions can be effectively increased by combining the geographic area where the user is with the historical operation logs.
As an optional embodiment, the object searching method further includes: receiving an operation performed on the displayed search results; and recording an operation log for the received operation.
As an alternative embodiment, the new operation log is fused into the historical operation log, so that the next translation operation is affected, a closed loop is formed, a virtuous circle is generated, the translation generated by the trade name translation module is provided for the user, click feedback of the user can be used for optimizing the translation module, and the whole link is continuously and iteratively optimized.
It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present invention is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present invention. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present invention.
From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus the necessary general hardware platform, but of course also by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method of the various embodiments of the present invention.
Example 5
According to an embodiment of the present invention, there is also provided an embodiment of an apparatus for implementing the object searching method of embodiment 1, and fig. 10 is a schematic structural diagram of an object searching apparatus according to embodiment 5 of the present invention, as shown in fig. 10, the apparatus including: a receiving module 1001, a first converting module 1002, a searching module 1003, a second converting module 1004, a sorting module 1005 and a displaying module 1006. The device will be described in detail below.
A receiving module 1001 for receiving a search object input in a first language; a first conversion module 1002, coupled to the receiving module 1001, for converting the search object from a first language to a second language; the search module 1003 is connected to the first conversion module 1002, and is configured to search for a search object in a second language, to obtain a search result in the second language; the second conversion module 1004 is connected to the search module 1003, and is configured to convert the search result in the second language into a multi-version first language, so as to obtain a multi-version first language search result; the sorting module 1005 is connected to the second conversion module 1004, and is configured to reorder the search results in the multiple versions of the first language based at least on the historical operation log of the search results in the multiple versions of the first language, to obtain reordered search results; the display module 1006 is connected to the ranking module 1005, and is configured to display the ranked search results.
Here, it should be noted that the receiving module 1001, the first converting module 1002, the searching module 1003, the second converting module 1004, the sorting module 1005 and the displaying module 1006 correspond to the steps S202 to S212 in the embodiment 1, and the two modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure of the embodiment 1. It should be noted that the above-described module may be operated as a part of the apparatus in the computer terminal 10 provided in embodiment 1.
Example 6
Embodiments of the present invention may provide a computer terminal, which may be any one of a group of computer terminals. Alternatively, in the present embodiment, the above-described computer terminal may be replaced with a terminal device such as a mobile terminal.
Alternatively, in this embodiment, the above-mentioned computer terminal may be located in at least one network device among a plurality of network devices of the computer network.
In this embodiment, the above-mentioned computer terminal may execute the program code of the following steps in the object search method of the application program: receiving a search object input in a first language; converting the search object from the first language to a second language; searching the search object in the second language to obtain a search result in the second language; converting the search results of the second language into a multi-version first language to obtain the search results of the multi-version first language; reordering the multi-version first language search results based on at least the historical operation log of the multi-version first language search results to obtain reordered search results; and displaying the ordered search results.
Alternatively, fig. 11 is a block diagram of a computer terminal according to embodiment 6 of the present application, and as shown in fig. 11, the computer terminal 110 may include: one or more (only one is shown) processors 112, memory 114, and a peripheral interface 116.
The memory may be used to store software programs and modules, such as program instructions/modules corresponding to the security vulnerability detection method and device in the embodiments of the present invention, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-mentioned method for detecting a system vulnerability attack. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include memory remotely located with respect to the processor, which may be connected to the terminal 100 through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The processor may call the information and the application program stored in the memory through the transmission device to perform the following steps: receiving a search object input in a first language; converting the search object from the first language to a second language; searching the search object in the second language to obtain a search result in the second language; converting the search results of the second language into a multi-version first language to obtain the search results of the multi-version first language; reordering the multi-version first language search results based on at least the historical operation log of the multi-version first language search results to obtain reordered search results; and displaying the reordered search results.
Optionally, the above processor may further execute program code for: the historical operation log of search results includes at least one of: browsing records of browsing the search results, clicking records of clicking the search results, and purchasing records of purchasing the search results.
Optionally, the above processor may further execute program code for: the browse records include at least: the number of times of browsing, the duration of browsing; the click record includes: the number of clicks; the purchase record includes: number of purchases.
Optionally, the above processor may further execute program code for: further comprises: a historical log of operations for a geographic area is obtained.
Optionally, the above processor may further execute program code for: acquiring a historical operation log for a geographic area includes: determining a representation of the input search object in the first language; determining a geographic area corresponding to the expression form; a historical log of operations within a geographic region is obtained.
Optionally, the above processor may further execute program code for: converting the search results in the second language into the multi-version first language, the obtaining the search results in the multi-version first language comprising: and converting the search results in the second language into the first language in multiple versions by adopting a beam search method to obtain the search results in the first language in multiple versions.
Optionally, the above processor may further execute program code for: further comprises: evaluating the search results of the multi-version first language by adopting a translation model to obtain evaluation results; and pre-ordering the search results of the multi-version first language according to the evaluation results.
Optionally, the above processor may further execute program code for: further comprises: receiving an operation performed on the displayed search results; recording an operation log according to the operation; and updating the historical operation log by adopting the recorded operation log.
Optionally, the above processor may further execute program code for: another object searching method includes: receiving a search sentence, wherein the language type of the search sentence is a first language; converting the language type of the search sentence into a multi-version second language, and obtaining a search result corresponding to the multi-version second language, wherein the language type of the search result is the second language; and reordering the search results corresponding to the multi-version second language based on the historical operation log of the search results to obtain the ordered search results.
Optionally, the above processor may further execute program code for: another object searching method includes: receiving a search sentence, wherein the language type of the search sentence is a first language; converting the language type of the search statement into a second language, and acquiring a search result corresponding to the search statement based on the conversion result, wherein the language type of the search result is the second language; converting the language type of the search result into a multi-version first language; and reordering the search results of the multiple versions of the first language based on the historical operation log of the search results of the multiple versions of the first language to obtain the ordered search results.
Optionally, the above processor may further execute program code for: another object searching method includes: receiving a search request, wherein the search request carries a search object input in a first language; responding to the search request, converting the search object from the first language into the second language, and searching to obtain a search result; after the search results of the second language are converted into the first language of the multiple versions, the search results of the first language of the multiple versions are reordered based on the historical operation log of the search results of the first language of the multiple versions, and the ordered search results are displayed.
Optionally, the above processor may further execute program code for: reordering the multi-version search results in the first language based on the historical log of operations on the multi-version search results in the first language comprises: receiving an input geographic area; and reordering the search results of the multi-version first language based on the historical operation log corresponding to the geographic region.
Optionally, the above processor may further execute program code for: further comprises: receiving an operation performed on the displayed search results; and recording an operation log for the received operation.
The embodiment of the invention provides a scheme of an object searching method. Receiving a search object input in a first language; converting the search object from the first language to a second language; searching the search object in the second language to obtain a search result in the second language; converting the search results of the second language into a multi-version first language to obtain the search results of the multi-version first language; reordering the multi-version first language search results based on at least the historical operation log of the multi-version first language search results to obtain reordered search results; the method for displaying the reordered search results includes the steps of sorting the first languages of various different versions translated from the search results of the second language and sorting according to the historical operation log of the search results, so that the purpose of determining the most suitable translation version of a user according to the historical language habit of the user is achieved, the technical effects of improving the translation accuracy and the user experience in the search process are achieved, and the technical problems that in the foreign language search method in the related technology, the translation accuracy is low and the user experience is poor are solved.
It will be appreciated by those skilled in the art that the configuration shown in fig. 11 is only illustrative, and the computer terminal may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a palm-phone computer, a mobile internet device (Mobile Internet Devices, MID), a PAD, etc. Fig. 11 is not limited to the structure of the electronic device. For example, the computer terminal 110 may also include more or fewer components (e.g., network interfaces, display devices, etc.) than shown in fig. 11, or have a different configuration than shown in fig. 11.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program for instructing a terminal device to execute in association with hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: flash disk, read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), magnetic or optical disk, and the like.
Example 7
The embodiment of the invention also provides a storage medium. Alternatively, in this embodiment, the storage medium may be used to store the program code executed by the object searching method provided in the first embodiment.
Alternatively, in this embodiment, the storage medium may be located in any one of the computer terminals in the computer terminal group in the computer network, or in any one of the mobile terminals in the mobile terminal group.
Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: receiving a search object input in a first language; converting the search object from the first language to a second language; searching the search object in the second language to obtain a search result in the second language; converting the search results of the second language into a multi-version first language to obtain the search results of the multi-version first language; reordering the multi-version first language search results based on at least the historical operation log of the multi-version first language search results to obtain reordered search results; and displaying the reordered search results.
Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: the historical operation log includes at least one of: browsing records of browsing the search results, clicking records of clicking the search results, and purchasing records of purchasing the search results.
Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: the browse records include at least: the number of times of browsing, the duration of browsing; the click record includes: the number of clicks; the purchase record includes: number of purchases.
Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: further comprises: a historical log of operations for a geographic area is obtained.
Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: acquiring a historical operation log for a geographic area includes: determining a representation of the input search object in the first language; determining a geographic area corresponding to the expression form; a historical log of operations within a geographic region is obtained.
Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: converting the search results in the second language into the multi-version first language, the obtaining the search results in the multi-version first language comprising: and converting the search results in the second language into the first language in multiple versions by adopting a beam search method to obtain the search results in the first language in multiple versions.
Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: further comprises: evaluating the search results of the multi-version first language by adopting a translation model to obtain evaluation results; and pre-ordering the search results of the multi-version first language according to the evaluation results.
Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: further comprises: receiving an operation performed on the displayed search results; recording an operation log according to the operation; and updating the historical operation log by adopting the recorded operation log.
Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: another object searching method includes: receiving a search sentence, wherein the language type of the search sentence is a first language; converting the language type of the search sentence into a multi-version second language, and obtaining a search result corresponding to the multi-version second language, wherein the language type of the search result is the second language; and reordering the search results corresponding to the multi-version second language based on the historical operation log of the search results to obtain the ordered search results.
Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: another object searching method includes: receiving a search sentence, wherein the language type of the search sentence is a first language; converting the language type of the search statement into a second language, and acquiring a search result corresponding to the search statement based on the conversion result, wherein the language type of the search result is the second language; converting the language type of the search result into a multi-version first language; and reordering the search results of the multiple versions of the first language based on the historical operation log of the search results of the multiple versions of the first language to obtain the ordered search results.
Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: another object searching method includes: receiving a search request, wherein the search request carries a search object input in a first language; responding to the search request, converting the search object from the first language into the second language, and searching to obtain a search result; after the search results of the second language are converted into the first language of the multiple versions, the search results of the first language of the multiple versions are reordered based on the historical operation log of the search results of the first language of the multiple versions, and the ordered search results are displayed.
Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: reordering the multi-version search results in the first language based on the historical log of operations on the multi-version search results in the first language comprises: receiving an input geographic area; and reordering the search results of the multi-version first language based on the historical operation log corresponding to the geographic region.
Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: further comprises: receiving an operation performed on the displayed search results; and recording an operation log for the received operation.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
In the foregoing embodiments of the present invention, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed technology content may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and are merely a logical functional division, and there may be other manners of dividing the apparatus in actual implementation, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention.

Claims (16)

1. An object searching method, comprising:
receiving a search object input in a first language;
converting the search object from the first language to a second language;
searching the search object in the second language to obtain a search result in the second language;
converting the search results of the second language into the first language of multiple versions to obtain the search results of the first language of multiple versions;
reordering the multi-version first language search results based on at least the historical operation log of the multi-version first language search results to obtain reordered search results;
and displaying the reordered search results.
2. The method of claim 1, wherein the historical oplog comprises at least one of:
browsing records of browsing the search results, clicking records of clicking the search results, and purchasing records of purchasing the search results.
3. The method of claim 2, wherein the navigation record comprises at least: the number of times of browsing, the duration of browsing; the click record includes: the number of clicks; the purchase record includes: number of purchases.
4. The method of claim 2, further comprising:
a historical log of operations for a geographic area is obtained.
5. The method of claim 4, wherein obtaining a historical operation log for a geographic area comprises:
determining a representation of the input search object in the first language;
determining a geographic area corresponding to the expression form;
and acquiring a historical operation log in the geographic area.
6. The method of claim 1, wherein converting the search results in the second language into the multi-version first language, resulting in the multi-version first language search results comprises:
and converting the search results in the second language into the search results in the first language in multiple versions by adopting a beam search method to obtain the search results in the first language in multiple versions.
7. The method of claim 1, further comprising:
evaluating the search results of the multi-version first language by adopting a translation model to obtain evaluation results;
And pre-ordering the search results of the multi-version first language according to the evaluation results.
8. The method of any of claims 1 to 7, further comprising:
receiving an operation performed on the displayed search results;
recording an operation log according to the operation;
and updating the historical operation log by adopting the recorded operation log.
9. An object searching method, comprising:
receiving a search sentence, wherein the language type of the search sentence is a first language;
converting the language type of the search sentence into a multi-version second language, and obtaining a search result corresponding to the multi-version second language, wherein the language type of the search result is the second language;
and reordering the search results corresponding to the multi-version second language based on the historical operation log of the search results to obtain ordered search results.
10. An object searching method, comprising:
receiving a search sentence, wherein the language type of the search sentence is a first language;
converting the language type of the search statement into a second language, and acquiring a search result corresponding to the search statement based on the conversion result, wherein the language type of the search result is the second language;
Converting the language type of the search result into a multi-version first language;
and reordering the multi-version first language search results based on the historical operation log of the multi-version first language search results to obtain ordered search results.
11. An object searching method, comprising:
receiving a search request, wherein the search request carries a search object input in a first language;
responding to the search request, and searching after the search object is converted from the first language into the second language, so as to obtain a search result;
after the second language search results are converted into the multi-version first language search results, the multi-version first language search results are reordered based on the historical operation log of the multi-version first language search results, and the ordered search results are displayed.
12. The method of claim 11, wherein reordering the multi-version first language search results based on a historical operating log of the multi-version first language search results comprises:
receiving an input geographic area;
and reordering the search results of the multi-version first language based on the historical operation log corresponding to the geographic area.
13. The method of claim 11, further comprising:
receiving an operation performed on the displayed search results;
and recording an operation log for the received operation.
14. An object searching apparatus comprising:
a receiving module for receiving a search object input in a first language;
a first conversion module for converting the search object from the first language to a second language;
the searching module is used for searching the searching object in the second language to obtain a searching result in the second language;
the second conversion module is used for converting the search results in the second language into the first language with multiple versions to obtain the search results in the first language with multiple versions;
the sorting module is used for reordering the search results of the multiple versions of the first language at least based on the historical operation log of the search results of the multiple versions of the first language to obtain reordered search results;
and the display module is used for displaying the reordered search results.
15. A storage medium comprising a stored program, wherein the program, when run, controls a device in which the storage medium is located to perform the object search method of any one of claims 1 to 13.
16. A processor for running a program, wherein the program runs on performing the object search method of any one of claims 1 to 13.
CN201811094922.8A 2018-09-19 2018-09-19 Object searching method and device Active CN110930208B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811094922.8A CN110930208B (en) 2018-09-19 2018-09-19 Object searching method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811094922.8A CN110930208B (en) 2018-09-19 2018-09-19 Object searching method and device

Publications (2)

Publication Number Publication Date
CN110930208A CN110930208A (en) 2020-03-27
CN110930208B true CN110930208B (en) 2023-05-05

Family

ID=69855926

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811094922.8A Active CN110930208B (en) 2018-09-19 2018-09-19 Object searching method and device

Country Status (1)

Country Link
CN (1) CN110930208B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1728134A (en) * 2004-07-30 2006-02-01 国际商业机器公司 Multi-language network information search method and system based on supertext
JP2010072909A (en) * 2008-09-18 2010-04-02 Nippon Telegr & Teleph Corp <Ntt> Document search device, document search method, and document search program
WO2012116561A1 (en) * 2011-03-02 2012-09-07 北京百度网讯科技有限公司 Web page ranking method and system in cross-language search
CN103049474A (en) * 2011-10-25 2013-04-17 微软公司 Search query and document-related data translation
US8577910B1 (en) * 2009-05-15 2013-11-05 Google Inc. Selecting relevant languages for query translation
CN105320706A (en) * 2014-08-05 2016-02-10 阿里巴巴集团控股有限公司 Processing method and device of search result
CN105760531A (en) * 2016-03-03 2016-07-13 华南师范大学 Multilingual search engine method and system
CN108304412A (en) * 2017-01-13 2018-07-20 北京搜狗科技发展有限公司 A kind of cross-language search method and apparatus, a kind of device for cross-language search

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8645289B2 (en) * 2010-12-16 2014-02-04 Microsoft Corporation Structured cross-lingual relevance feedback for enhancing search results
US8918308B2 (en) * 2012-07-06 2014-12-23 International Business Machines Corporation Providing multi-lingual searching of mono-lingual content
US8914395B2 (en) * 2013-01-03 2014-12-16 Uptodate, Inc. Database query translation system

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1728134A (en) * 2004-07-30 2006-02-01 国际商业机器公司 Multi-language network information search method and system based on supertext
JP2010072909A (en) * 2008-09-18 2010-04-02 Nippon Telegr & Teleph Corp <Ntt> Document search device, document search method, and document search program
US8577910B1 (en) * 2009-05-15 2013-11-05 Google Inc. Selecting relevant languages for query translation
WO2012116561A1 (en) * 2011-03-02 2012-09-07 北京百度网讯科技有限公司 Web page ranking method and system in cross-language search
CN103049474A (en) * 2011-10-25 2013-04-17 微软公司 Search query and document-related data translation
CN105320706A (en) * 2014-08-05 2016-02-10 阿里巴巴集团控股有限公司 Processing method and device of search result
CN105760531A (en) * 2016-03-03 2016-07-13 华南师范大学 Multilingual search engine method and system
CN108304412A (en) * 2017-01-13 2018-07-20 北京搜狗科技发展有限公司 A kind of cross-language search method and apparatus, a kind of device for cross-language search

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王末等."地学数据共享网用户Web行为预测及数据推荐方法".《地球信息科学学报》.2017,第19卷(第5期),第595-604页. *

Also Published As

Publication number Publication date
CN110930208A (en) 2020-03-27

Similar Documents

Publication Publication Date Title
US10552548B2 (en) Methods for automatic generation of parallel corpora
US8583685B2 (en) Determination of category information using multiple stages
CN103970857A (en) Recommended content determining system and method
US20150254714A1 (en) Systems and methods for keyword suggestion
KR20170018832A (en) Search based on combining user relationship data
US9953061B2 (en) Similarity engine for facilitating re-creation of an application collection of a source computing device on a destination computing device
US20160012124A1 (en) Methods for automatic query translation
US9990442B2 (en) Method for determining relevant search results
US10795938B2 (en) Spell checker
KR101647087B1 (en) Server and method for goods providing based on natural language processing
US11556969B2 (en) Method for performing sequence labelling on queries
US11748429B2 (en) Indexing native application data
KR20220026255A (en) Recommendation System for Health Supplement by Using Big Data
CN110930208B (en) Object searching method and device
US11256703B1 (en) Systems and methods for determining long term relevance with query chains
CN115618126A (en) Search processing method, system, computer readable storage medium and computer device
CN112148988B (en) Method, apparatus, device and storage medium for generating information
CN112749316A (en) Translation quality determination method and device, storage medium and processor
CN112559732A (en) Text processing method, device and system
CN111831130A (en) Input content recommendation method, terminal device and storage medium
CN111737550B (en) Search result processing method and device, storage medium and processor
CN111523952B (en) Information extraction method and device, storage medium and processor
Arreguin WEB CRAWLING AND COMMUNITY REVIEW TO PREVENT MISLEADING LINKS
CN112446222A (en) Translation optimization method and device and processor
US20180253739A1 (en) Automated Endorsement Prompting

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
REG Reference to a national code

Ref country code: HK

Ref legal event code: DE

Ref document number: 40026856

Country of ref document: HK

GR01 Patent grant
GR01 Patent grant