CN111782958A

CN111782958A - Recommendation word determining method and device, electronic device and storage medium

Info

Publication number: CN111782958A
Application number: CN202010691285.3A
Authority: CN
Inventors: 李俊良
Original assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd; Shenzhen Huantai Technology Co Ltd
Current assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd; Shenzhen Huantai Technology Co Ltd
Priority date: 2020-07-17
Filing date: 2020-07-17
Publication date: 2020-10-16

Abstract

The application relates to a method, a device, an electronic device and a storage medium for determining recommended words, wherein the method comprises the following steps: when a query instruction input by a user is detected, acquiring query words contained in the query instruction; acquiring a data source and determining a data set related to a query word in the data source; generating a query data set according to the data set; and determining the recommended words according to the inverted arrangement of the query words and the query data set. According to the method for determining the recommended word, the more accurate recommended word can be determined without collecting the click signal of the user, and the recommended word recommending efficiency of the user during query is improved.

Description

Recommendation word determining method and device, electronic device and storage medium

Technical Field

The invention belongs to the technical field of computers, and particularly relates to a method and a device for determining recommended words, an electronic device and a storage medium.

Background

Whether searching is carried out in a search engine or keyword searching is carried out in various types of application software, when a user inputs a query word, the search engine or various types of application software can determine a recommended word or a recommended word list according to the query word input by the user, and the user can select the content needing to be searched in the recommended word list and then enter a display interface of the selected content. Therefore, the page to be searched can be found without inputting complete search content by the user, and convenience is brought to the search operation of the user.

However, the existing recommended word is generally determined by mining the historical click condition of the search query word, and then determining the word with relatively high rank as the recommended word by matching with the mining of the synonym and the near-synonym of the query word input by the user. According to the method, a large amount of data accumulation and long-time click signal collection are needed to return accurate recommended words.

Disclosure of Invention

The application provides a recommended word determining method, a recommended word determining device, an electronic device and a storage medium, which are used for solving the technical problem that the current recommended word determining method needs a large amount of data and a long-time click signal collection to return a relatively accurate recommended word.

A first aspect of the present application provides a method for determining a recommended word, where the method includes:

when a query instruction input by a user is detected, acquiring a query word contained in the query instruction;

acquiring a data source and determining a data set related to the query word in the data source;

generating a query data set according to the data set;

and determining recommendation words according to the query words and the query data set in an inverted manner.

A second aspect of the present application provides a recommended word determining apparatus, including:

the first acquisition module is used for acquiring query words contained in a query instruction when the query instruction input by a user is detected;

the second acquisition module is used for acquiring a data source and determining a data set related to the query word in the data source;

the generating module is used for generating a query data set according to the data set;

and the determining module is used for determining recommendation words according to the query words and the query data set in an inverted manner.

A third aspect of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the steps in the method for determining a recommended word provided in the first aspect when executing the computer program.

A fourth aspect of the present application provides a storage medium on which a computer program is stored, the computer program, when being executed by a processor, implementing the steps in the recommended word determination method provided by the first aspect.

As can be seen from the foregoing embodiments of the present application, a method for determining a recommended word provided by the present application includes: when a query instruction input by a user is detected, acquiring query words contained in the query instruction; acquiring a data source and determining a data set related to a query word in the data source; generating a query data set according to the data set; and determining the recommended words according to the inverted arrangement of the query words and the query data set. According to the method for determining the recommended word, the more accurate recommended word can be determined without collecting the click signal of the user, and the recommended word recommending efficiency of the user during query is improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.

Fig. 1 is a block diagram of a terminal provided in the present application;

fig. 2 is a schematic flow chart of a recommended word determination method provided in the present application;

fig. 3 is a schematic structural diagram of a recommended word determining apparatus provided in the present application;

fig. 4 is a block diagram of an electronic device provided in the present application.

Detailed Description

In order to make the objects, features and advantages of the present application more obvious and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Fig. 1 shows a block diagram of a terminal, and the method for determining a recommended word provided by the present application may be applied to the terminal 10 shown in fig. 1, where the terminal 10 may be, but is not limited to: the normal operation needs to be maintained by depending on a battery, and the smart phone, the tablet personal computer, the telephone watch and the like with a display screen and a data interaction function are provided.

As shown in fig. 1, the terminal 10 includes a memory 101, a memory controller 102, a processor 103 (which may be plural, only one of which is shown), a data input component 104, and a display 105. These components communicate with each other via one or more communication buses/signal lines 106.

It will be appreciated that the configuration shown in fig. 1 is merely illustrative and is not intended to limit the configuration of the terminal 10, and that the terminal 10 may include more or fewer components than shown in fig. 1 or may have a different configuration than shown in fig. 1. The components shown in fig. 1 may be implemented in hardware, software, or a combination thereof.

The memory 101 may be used to store software programs and modules, such as instructions and modules corresponding to the method and apparatus for determining recommended words in the present application, and the processor 103 executes various functional applications and data processing by operating the software programs and modules stored in the memory 101, that is, the operation of the method and apparatus for determining recommended words is realized.

Memory 101 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 instances, the memory 101 may further include memory located remotely from the processor 103, which may be connected to the 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 data input component 104 may be implemented by a touch display screen together with the display 105, or may be implemented by a separate display 105 in cooperation with a keyboard input or a voice recognition input.

Based on the terminal 10, in order to solve the problem that a large amount of data and several types of data and a long-time click signal collection are required to return a relatively accurate recommended word when a search is performed in a search engine or an application program in the terminal, the present application provides a recommended word determining method, which is a flowchart of the recommended word determining method provided by the present application, as shown in fig. 2, and the method includes the following steps:

step 201, when a query instruction input by a user is detected, acquiring a query word contained in the query instruction;

it will be appreciated that when a user performs a search using a search engine or application, the keyword to be searched is entered. The current search engine or application program can generate corresponding recommended words after detecting the query words input by the user, and the user can select the recommended words meeting the query requirements of the user from the recommended words, so that the query process can be accelerated. A general search engine is provided with a search instruction or an icon, when a user clicks the search instruction or the icon, the fact that the user inputs a query instruction can be judged according to the search instruction or the icon, and recommended words are further generated and displayed for the user; or the user can be judged to input the query instruction by detecting that the user inputs the content in the search bar, the user does not need to click the search instruction or the icon, and the recommended word is generated and displayed for the user directly according to the query word input by the user in the search bar. The user inputs the query words in the search bar of the search engine or the application program through various input methods, or the user can recognize the voice of the user according to a voice recognition component arranged by the search engine or the application program and translate the voice data of the user into character data. The query word input by the user can be a Chinese field, pinyin of a Chinese character or characters in other languages.

Step 202, acquiring a data source and determining a data set related to the query word in the data source;

in the embodiment of the present application, when the search engine or the application is in an offline state, the data source may be a history data source stored in the memory, and the history data source may be basic data of the search engine or the application at installation and configuration, or data that is input and searched for by a user history. The data source may also include data that a web crawler crawls according to query terms entered by a user while a search engine or application is online. After the data are acquired, because the data amount of the data source is huge, some data which are definitely not related to the input query word can be excluded according to a preset exclusion method. For example, when the input query word is a Chinese word, the foreign language data in the data source can be deleted, and only the data of the Chinese or Chinese pinyin is reserved. The remaining data can be determined as a data set related to the query word, and the data can be a recommended word corresponding to the query word input by the user.

Step 203, generating a query data set according to the data set;

in this embodiment of the present application, since query terms input by a user are not all input according to a standard input method, for example, the user wants to search "shenzhen", and the input query terms may be "deep", "SZ", "shenzhen", or "shenzh", etc., before matching with the query terms, data in a data set related to the query terms need to be further processed, and different expression forms of the data in the data set are mined and generated, so as to generate a query data set. The query data set contains different possible input forms for each data in the data set that is related to the query term.

And 204, determining recommendation words in an inverted manner according to the query words and the query data set.

In the embodiment of the application, after the query data set is determined, the query data matched with the query terms are determined in the query data set according to the query terms. Continuing to explain by taking the above example as an example, when the query word input by the user is "SZ", searching is performed in the query data set to determine whether query data matched with the query word exists, and after determining that query data matched with the query word "SZ" exists, inverted confirmation is performed according to the query data "SZ", so that the recommended word "shenzhen" is determined.

As can be seen from the above description, the method for determining a recommended word provided in the embodiment of the present application includes:

when a query instruction input by a user is detected, acquiring query words contained in the query instruction; acquiring a data source and determining a data set related to a query word in the data source; generating a query data set according to the data set; and determining the recommended words according to the inverted arrangement of the query words and the query data set. According to the method for determining the recommended word, the more accurate recommended word can be determined without collecting the click signal of the user, and the recommended word recommending efficiency of the user during query is improved.

Further, generating a query data set from the data set related to the query term includes:

performing pinyin conversion on fields in the data set to obtain pinyin and full pinyin of the first letter of the field;

prefixing the first pinyin and the full pinyin to obtain a first query data set;

and n-gram processing is carried out on the fields in the data set to obtain a second query data set, wherein the query data set comprises a first query data set and a second query data set.

In the embodiment of the application, in a Chinese search engine or an application program, the general recommended words are Chinese fields. The data sets related to the query terms are mostly Chinese field data sets. Here, an application program for selling air tickets or train tickets is taken as an example, and in the application program, a search box is generally used for searching cities and station information such as airports and train stations. For example, the Chinese field of the city name of each large city of each country and each Chinese field information of each airport station and railway station are preset in the database of the application program. And after the preset data are acquired, performing pinyin conversion on the fields to obtain the pinyin of the first letter and the full pinyin of the fields. For example, the city field "Changsha" can obtain the pinyin of the first letter "CS", "CS" and the total pinyin of "CHANGSHA" and "CHANGSHA" after pinyin conversion. Then, the obtained initial pinyin and the full pinyin are prefixed, specifically, for example, "C" and "CS" are obtained by prefixing "CS" data, and data such as "C", "ch", "cha", "chan", "changs", "changsh" and "changsha" can be obtained by prefixing "changsha". Thus, the data obtained by performing pinyin conversion and prefixing on all fields in the data set related to the query word is determined as the first query data set.

In addition, the city field is n-gram processed. N-Gram (also sometimes referred to as N-Gram) is a very important concept in Natural Language processing, and one role of N-Gram is to evaluate the degree of difference between two strings, usually in Natural Language Processing (NLP). The specific processing steps of the n-gram are described below. For example, n-gram processing is carried out on a city name field 'ziqihaar', and when n is 1, the n-gram obtains results of 'qiqi', 'qihaar' and 'er'; when n is 2, n-grams yield results of "ziqi", "zihaha", "haar"; when n is 3, n-grams yield "zizaha" and "zizall"; when n is 4, the n-gram gives a result of "ziqihal". In this way, the data obtained by n-gram processing all the fields in the data set related to the query word is the second query data set. The first query data set and the second query data set are query data sets used for matching query words.

Further, it will be appreciated that in applications that sell airline or train tickets, there is also a class of important fields, namely the site field, which may or may not coincide with the city name field. For example, the site name of "Shenzhen" coincides with the city name field, while the site name field of "Shenzhen north" does not coincide with the city name field. Therefore, in the present application, it is also necessary to perform pinyin conversion on the site field, and then perform prefixing on the first pinyin and the full pinyin obtained by the pinyin conversion, so as to obtain a third query data set. And performing n-gram processing on the site field to obtain a fourth query data set. The specific steps of pinyin conversion, prefixing and n-gram processing are the same as the steps of processing the city name field, and are not described again. And the obtained third query data set and the fourth query data set both belong to the query data set. Therefore, more data which can be matched is provided, and the matching result with the query word is more accurate.

Further, determining recommendation words in an inverted manner according to the query words and the query data set, including:

generating a search tree according to the first query data set and the second query data set;

and determining the recommended words according to the inverted arrangement of the query word search tree.

The search tree, i.e., trie tree, is a variation of the hash tree that can be used to count, sort, and store a large number of strings, as well as text word frequency statistics in search engine systems. In the embodiment of the application, the data in the query data set are generated into the search tree according to a certain rule, and a tree-like relation is formed among the query data in the search tree. And comparing the query word with the search tree so as to determine the recommended word by reverse deduction. The method can reduce the query time by utilizing the public prefix of the character string, and furthest reduce the character string comparison of Wuwei, thereby obtaining higher query efficiency.

Further, determining the recommended word in an inverted manner according to the query word query data set comprises:

generating a hash table according to the first query data set and the second query data set;

and determining the recommended word according to the inverted arrangement of the query word and the hash table.

The hash table, also called hash table, is a data structure directly accessed according to key values, that is, records are accessed by mapping key values to a position in the table, so as to speed up the search. In the embodiment of the application, the query data set is generated into the hash table, and when a user inputs a query word, the corresponding data in the hash table is determined according to the query word and the mapping function, so that quick search is completed. And then the recommendation words can be determined in an inverted manner.

In the two searching modes, the algorithm for searching the hash table is low in complexity and high in searching speed, but the occupied memory is large, the fixed-length hash can be used, and the memory space is further saved. The search tree search can facilitate the prefix search, save the conversion time and occupy less memory, but the algorithm complexity is higher. Based on the advantages and disadvantages, the user can determine the searching mode according to the requirement.

Further, after determining the recommended word in an inverted manner according to the query word and the query data set, the method further includes:

sorting the recommended words;

and displaying the recommended words according to the sorting order.

In the embodiment of the application, there are often more than one determined recommended word, for example, when a user inputs an "SZ" query word, the output recommended word may be recommended words such as "shenzhen", "shenzhen north", and the like. The keywords can be sorted according to a set sequence, and the sorting principle can be set by a user according to own habits or determined according to historical click data of the user. The determination may also be made based on the relevance of the recommended word to the query word. After the recommended words are sorted according to the set order, the recommended words can be displayed according to the sorted order, so that the user can quickly determine the recommended words.

Further, acquiring a data source and determining a data set related to the query term in the data source includes:

backing up data in the data table;

formatting the backed-up data according to a preset format;

and determining a set of data in a preset area in the formatted data as a data set related to the query word.

In the embodiment of the present application, it can be understood that the data in the data table may be data that is carried by a search engine or an application program when the search engine or the application program is loaded, may also be historical data input or clicked by a user, and may also be related data that is crawled from a network by a web crawler. The process of backing up and formatting the data in the data table may be completed before the user inputs a query word, or may be completed after responding to a query instruction input by the user. The recommendation words can be returned more quickly after the user inputs the query instruction. The formatting of the backup data may be to perform the data in the backup data table according to a preset format, so as to facilitate uniform processing of data with a certain homogeneous attribute. For example, in the application program for selling air tickets or train tickets in the above example, after data is formatted and processed, the city name data may be placed in the same column, and then the column of data is directly processed in a unified manner, so that all the city name data can be processed. In addition, when there is misaligned data, a field may be additionally added to be filled up.

Further, the method further comprises:

responding to the clicking operation of the user on the recommended word, and acquiring the recommended word clicked by the user;

and matching the recommended words clicked by the user with the query words and storing the matched recommended words and the query words in a memory.

In the embodiment of the application, after the recommended words are determined and displayed according to a certain sequence. The user clicks the displayed recommended word according to the own requirement, the processor can acquire the click data of the user at the moment, and the click data is matched with the acquired query word input by the user, and even the user searching habit data is generated. The data is stored in a memory for determining the recommended words more quickly when a subsequent user searches.

As shown in fig. 3, a schematic structural diagram of a recommended word determining apparatus provided in the present application includes:

a first obtaining module 301, configured to obtain a query term included in a query instruction when the query instruction input by a user is detected;

a second obtaining module 302, configured to obtain a data source and determine a data set related to a query term in the data source;

a generating module 303, configured to generate a query data set according to the data set;

and the determining module 304 is configured to determine the recommended word in an inverted manner according to the query word and the query data set.

It can be understood that the functions of the modules of the apparatus for determining a recommended word provided in the embodiment of the present application are the same as the contents of the steps in the method for determining a recommended word provided in the embodiment of fig. 2, and are not described again here.

A third aspect of the present application provides an electronic apparatus that can be used to implement the recommended word determination method in the foregoing embodiments. As shown in fig. 4, the electronic device mainly includes:

memory 401, processor 402, bus 403, and computer programs stored on memory 401 and executable on processor 402, memory 401 and processor 402 being connected via bus 403. The processor 402, when executing the computer program, implements the recommended word determination method in the foregoing embodiments. Wherein the number of processors may be one or more.

The Memory 401 may be a high-speed Random Access Memory (RAM) Memory or a non-volatile Memory (non-volatile Memory), such as a disk Memory. The memory 401 is used for storing executable program code and the processor 402 is coupled to the memory 401.

A fourth aspect of the present application provides a storage medium, which may be a memory. The storage medium has stored thereon a computer program that, when executed by a processor, performs the steps of the method for determining a recommended word provided by the first aspect. Further, the computer-readable storage medium may be various media that can store program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a RAM, a magnetic disk, or an optical disk.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of modules is merely a logical division, and an actual implementation may have another division, for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. Modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present application may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware, and also can be implemented in the form of software functional modules.

The integrated modules, if implemented in the form of software functional modules and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a readable storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method of the embodiments of the present application. And the aforementioned readable storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

It should be noted that, for the sake of simplicity, the above-mentioned method embodiments are described as a series of acts or combinations, but those skilled in the art should understand that the present application is not limited by the described order of acts, as some steps may be performed in other orders or simultaneously according to the present application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In view of the above description of the method, apparatus, storage medium and terminal for determining a recommended word provided by the present application, those skilled in the art will recognize that changes may be made in the specific implementation and application scope according to the concepts of the embodiments of the present application.

Claims

1. A method for determining a recommended word, the method comprising:

generating a query data set according to the data set;

2. The method according to claim 1, wherein the generating a query data set from the data set comprises:

and performing n-gram processing on the field to obtain a second query data set, wherein the query data set comprises the first query data set and the second query data set.

3. The method for determining recommended word according to claim 2, wherein the determining recommended word in reverse arrangement according to the query word and the query data set comprises:

and determining a recommended word according to the inverted arrangement of the query word and the search tree.

4. The method for determining recommended word according to claim 2, wherein the determining recommended word in reverse arrangement according to the query word and the query data set comprises:

generating a hash table according to the first query data set and the second query number set;

and determining a recommended word according to the inverted arrangement of the query word and the hash table.

5. The method according to claim 1, wherein after determining the recommended word in reverse according to the query word and the query data set, the method further comprises:

sorting the recommended words;

and displaying the recommended words according to the sorting order.

6. The method for determining recommended word according to claim 1, wherein the obtaining a data source and determining a data set related to the query word in the data source comprises:

backing up data in the data table;

formatting the backed-up data according to a preset format;

7. The method according to claim 6, characterized in that the method further comprises:

8. A recommended word determining apparatus, characterized in that the apparatus comprises:

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable by the processor, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.

10. A storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, performs the steps of the method of any one of claims 1 to 7.