WO2022134355A1

WO2022134355A1 - Keyword prompt-based search method and apparatus, and electronic device and storage medium

Info

Publication number: WO2022134355A1
Application number: PCT/CN2021/083827
Authority: WO
Inventors: 付桂振
Original assignee: 平安科技（深圳）有限公司
Priority date: 2020-12-25
Filing date: 2021-03-30
Publication date: 2022-06-30
Also published as: CN112667775A

Abstract

A keyword prompt-based search method, a keyword prompt-based search apparatus, a device, and a storage medium, which relate to semantic parsing technology. The method comprises: acquiring an input word of a user, and performing similar word matching on the input word, so as to obtain a similar word set (S1); performing error prompting on the input word by using the similar word set, so as to obtain a search word (S2); monitoring a user instruction of the user, and when the user instruction is a search instruction, performing a search by using the search word (S3); when the user instruction is an input instruction, performing associated word matching on the search word, so as to obtain an associated word set (S4); performing subject screening on the associated word set, so as to obtain a subject word set with the same subject as the search word (S5); and prompting the user by using the subject word set, so as to obtain a search phrase, and performing a search by using the search phrase (S6). The problem of the efficiency and the accuracy being not high during a keyword-based search can be solved.

Description

Retrieval method, device, electronic device and storage medium based on keyword hints

This application claims the priority of the Chinese patent application filed on December 25, 2020, with the application number CN202011564401.1, and the invention title is "Keyword Hint-based Retrieval Method, Device, Electronic Device and Storage Medium", The entire contents of which are incorporated herein by reference.

technical field

The present application relates to the technical field of semantic parsing, and in particular, to a retrieval method, apparatus, electronic device, and computer-readable storage medium based on keyword hints.

Background technique

Data retrieval is a function that people attach great importance to in daily life, such as work and study. There is a large amount of data in the Internet, and how to accurately and efficiently query the data required by users has become the focus of people's attention.

The inventor realizes that the existing methods for improving the accuracy and efficiency of data retrieval are mostly the prefix matching method based on Tire tree, which uses the words input by the user to match the pre-key words from the preset keyword database to realize the retrieval prompt for the user. , to assist the user to complete the retrieval, but the matching requirements for words in this method are too high. When there are typos in the words, the user cannot be accurately prompted, thereby reducing the retrieval efficiency and retrieval accuracy.

SUMMARY OF THE INVENTION

A retrieval method based on keyword hints, comprising:

Obtain the input word of the user, and perform similar word matching on the input word to obtain a similar word set;

Using the similar word set to give an error prompt to the input word to obtain a search word;

Monitor the user instruction of the user, and when the user instruction is a retrieval instruction, use the retrieval word to perform retrieval;

When the user instruction is an input instruction, perform associated word matching on the search term to obtain an associated word set;

Perform theme screening on the associated word set to obtain a theme word set with the same theme as the search term;

The user is prompted by using the subject word set to obtain a search phrase, and the search phrase is used for retrieval.

A retrieval device based on keyword hints, the device includes:

A similar word matching module is used to obtain the input word of the user, and perform similar word matching on the input word to obtain a similar word set;

An error prompting module, used for using the similar word set to give an error prompt to the input word to obtain a search term;

The first retrieval module is used for monitoring the user instruction of the user, and when the user instruction is a retrieval instruction, the retrieval word is used for retrieval;

an associated word matching module, configured to perform associated word matching on the search term when the user instruction is an input command to obtain an associated word set;

a subject heading screening module, used for subject screening the associated word set to obtain a subject heading set with the same subject as the search term;

The second retrieval module is used for prompting the user by using the subject word set, obtaining a retrieval phrase, and using the retrieval phrase for retrieval.

An electronic device comprising:

a memory that stores at least one instruction; and

A processor that executes the instructions stored in the memory to achieve the following steps:

A computer-readable storage medium having at least one instruction stored in the computer-readable storage medium, the at least one instruction being executed by a processor in an electronic device to implement the following steps:

The present application can solve the problem of low efficiency and accuracy when searching based on keywords.

Description of drawings

1 is a schematic flowchart of a retrieval method based on keyword hints provided by an embodiment of the present application;

2 is a functional block diagram of a retrieval device based on keyword hints provided by an embodiment of the present application;

FIG. 3 is a schematic structural diagram of an electronic device implementing the keyword-hinting-based retrieval method according to an embodiment of the present application.

The realization, functional characteristics and advantages of the purpose of the present application will be further described with reference to the accompanying drawings in conjunction with the embodiments.

Detailed ways

It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

The embodiment of the present application provides a retrieval method based on keyword hints. The execution subject of the keyword hint-based retrieval method includes, but is not limited to, at least one of the electronic devices that can be configured to execute the method provided by the embodiments of the present application, such as a server and a terminal. In other words, the retrieval method based on keyword hints may be executed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.

Referring to FIG. 1 , a schematic flowchart of a retrieval method based on keyword hints provided by an embodiment of the present application is shown. In this embodiment, the retrieval method based on keyword hints includes:

S1. Acquire a user's input word, and perform similar word matching on the input word to obtain a similar word set.

In the embodiment of the present application, the input word of the user may be any word or phrase, for example, the keyword "Internet of Things" input by the user when querying Internet of Things related documents; the key word input by the user when querying information about diabetes related to diabetes The word "diabetes".

In detail, performing similar word matching on the input word to obtain a similar word set, including:

Analyzing the input word to obtain the input pronunciation and input glyph of each word in the input word;

Acquiring a preset standard character library, wherein the standard character library includes a plurality of standard characters and standard fonts and standard pronunciations corresponding to each standard character;

Screen out the first standard word with the same sound as the input word from the standard word library;

Screen out the second standard word that is the same as the input font from the standard font library;

The first standard word and the second standard word are assembled into a similar word set of the input word.

In the embodiment of the present application, a natural language processing model with a character parsing function is used to parse the input word, and the input word pronunciation and input glyph of each word in the input word are obtained, wherein the natural language processing model includes but is not limited to Forward Convolutional Neural Network Model and Recurrent Convolutional Neural Network Model.

In detail, the standard word library can be stored in a database in advance, and the standard word library can be obtained from the database for storing the standard word library by using a java statement with a data calling function. The standard character library includes a plurality of standard characters and standard fonts and standard pronunciations corresponding to each standard character.

In the embodiment of the present application, the screening of the first standard word with the same sound as the input word from the standard word library includes:

Calculate successively the similarity of the standard word pronunciation of each standard word in the described standard word library and the described input word pronunciation;

The standard word corresponding to the standard word sound whose distance value is smaller than the preset distance threshold is selected from the standard word library as the first standard word.

In detail, calculating the similarity between the standard pronunciation of each standard word in the standard word library and the input pronunciation in turn includes:

Utilize the following similarity algorithm to calculate the similarity between the standard pronunciation of each standard word in the standard word library and the input pronunciation:

Sim=Pearson(R, S)

Wherein, R is the standard word sound of any standard word in the standard word library, S is the input word sound, Pearson is the similarity calculation, and Sim is the similarity between R and S.

Specifically, the step of filtering out the second standard word with the same shape as the input font from the standard font library is consistent with the step of filtering out the first standard word with the same sound as the input word from the standard font library, I won't go into details here.

S2. Use the similar word set to give an error prompt to the input word to obtain a search word.

In the embodiment of the present application, the use of the similar word set to give an error prompt to the input word to obtain a search word includes:

calculating the word popularity of each similar character in the similar character set;

Arrange each similar word in the similar word set in descending order of the word popularity to obtain a similar word list;

An error prompt is given to the user according to the sequence of the similar word list, and the search words returned by the user are obtained.

In detail, the calculating the word popularity of each similar word in the similar word set includes:

The following heat algorithm is used to calculate the word heat of each similar word in the similar word set:

Among them, tf _m is the word popularity of the m-th similar word, n is the total number of times the m-th similar word appears in the pre-built retrieval database, k is the total number of texts in the retrieval database, and α is the pre-built retrieval database. set weight coefficient.

Specifically, the pre-built retrieval library includes any database that stores documents or data. For example, if a user searches for data in Baidu Library, Baidu Library is the search library.

Further, the word popularity may indicate the frequency of word occurrences. The higher the word popularity, the more likely the similar words corresponding to the word popularity are correct words. Therefore, in this embodiment of the present application, the word popularity is ranked from high to high. Arrange each similar character in the similar character set in a small order to obtain a similar character list, and give an error prompt to the user according to the sequence of the similar character list.

In the embodiment of the present application, using similar word sets to prompt errors for input words to obtain search words can reduce the probability of incorrectly inputting search words, reduce the possibility of users retrieving erroneous content, and help improve retrieval accuracy.

S3. Monitor the user instruction of the user, and when the user instruction is a retrieval instruction, use the retrieval word to perform retrieval.

In this embodiment of the present application, the user instruction includes a retrieval instruction and an input instruction. Wherein, the retrieval instruction refers to a computer instruction to perform retrieval, for example, after obtaining a retrieval term, execute retrieval instruction to directly use the retrieval term to perform retrieval; the input instruction refers to a computer instruction to continue writing the input term, for example, when After obtaining the search term, the user wishes to continue to write the input term instead of directly using the search term for retrieval.

In detail, the embodiment of the present application uses the ASM enhanced bytecode filter to intercept and obtain user instructions in the network. The ASM enhanced bytecode filter is a code analysis tool based on the Java bytecode level, using The section code filter intercepts user instructions, which can improve the success rate of user instruction interception.

In this embodiment of the present application, when the user instruction is a retrieval instruction, the retrieval using the retrieval term includes:

performing word coding on the search term to obtain a search code;

Check the retrieval environment;

Utilize a compiler corresponding to the retrieval environment to compile the retrieval code into retrieval sentences;

Execute the retrieval statement to retrieve.

In detail, performing word coding on the retrieval term to obtain retrieval coding, including:

encoding and converting each character in the character set to obtain character encoding;

The character codes are combined to obtain a retrieval code.

In detail, the embodiment of the present application uses a preset encoder to encode and convert each character in the character set, and the encoder includes but is not limited to an ASCII (American Standard Code for Information Interchange, American Standard Code for Information Interchange) encoder. .

The combining the character codes specifically refers to: combining the character codes corresponding to each character in the search term according to the order of the characters in the search term to obtain the character codes. For example, if there is a search term "ice cream", in which the character code of "ice" is ab, the character code of "ice" is ef, and the character code of "rain" is cd, according to the three characters in the search term "ice cream" The character codes corresponding to each word are sequentially combined to obtain the search code "abefcd" of the search word "ice cream".

In the embodiment of the present application, the retrieval environment is determined by the storage environment where the retrieval content is located. For example, when the retrieval content is stored in a java database, the storage environment is the java environment, that is, the retrieval environment is the java environment.

Using a compiler corresponding to the retrieval environment to compile the retrieval code into a retrieval sentence can improve the usability of the retrieval sentence and ensure the success rate of retrieval.

S4. When the user instruction is an input instruction, perform associated word matching on the search term to obtain an associated word set.

In the embodiment of the present application, when the user instruction is an input instruction, the associated word matching is performed on the search term to obtain an associated word set, including:

performing word vector transformation on the search term to obtain a search vector;

Calculate the distance value between the retrieval vector and the standard vector corresponding to each standard word in the preset standard thesaurus;

The standard words corresponding to the standard vectors whose distance values are smaller than the preset distance threshold are collected as a related word set.

In detail, the embodiment of the present application uses a preset word vector transformation model to perform word vector transformation on the search term to obtain a retrieval vector. Wherein, the word vector transformation model includes but is not limited to CRF model (Conditional Random Fields Model, conditional random field model), HMM model (Hidden Markov Model, hidden Markov model). Using the word vector transformation model to transform the search words into word vectors can improve the efficiency of transforming the search words into search vectors.

Specifically, the calculating the distance value between the retrieval vector and the standard vector corresponding to each standard word in the preset standard thesaurus includes:

Use the following distance algorithm to calculate the distance between the retrieval vector and the standard vector corresponding to each standard word in the preset standard thesaurus:

Wherein, S(X, Y _m ) is the distance value, X is the retrieval vector, and Y _m is the mth standard word in the standard vocabulary.

In this embodiment of the present application, the standard words corresponding to the standard vectors whose distance values are less than the preset distance threshold are collected as a set of related words, wherein the related words in the set of related words can be stored in a blockchain node. Improve the efficiency of obtaining related words.

In the embodiment of the present application, the related words are matched on the search terms to obtain a set of related words, and words related to the search terms can be screened from the standard thesaurus, which is beneficial to improve the retrieval efficiency.

S5. Perform subject filtering on the associated word set to obtain a subject word set with the same subject as the search term.

In the embodiment of the present application, the subject selection is performed on the associated word set to obtain a subject word set with the same subject as the search terms, including:

extracting the search subject of the search term;

extracting the associated word subject of each associated word in the associated word set;

Calculate the degree of matching between the retrieval topic and the associated word topics of each associated word in the associated word set;

The associated vocabulary set with the matching degree greater than the preset matching threshold is regarded as the subject vocabulary set.

In detail, the embodiment of the present application uses a pre-trained convolutional neural network to extract the retrieval topic of the search term and the associated word topic of each associated word in the associated word set, where the retrieval topic refers to the category of the retrieval term, and the associated word The subject refers to the category of the related word. For example, when the search term or the related word is "ice cream", the search subject of the search term or the related word subject of the related word is food.

Specifically, calculating the matching degree between the retrieval topic and the associated word topics of each associated word in the associated word set includes:

Use the following matching algorithm to calculate the matching degree between the retrieval topic and the associated word topics of each associated word in the associated word set:

d(A, B) ² = ‖AB‖ ²

Wherein, d(A, B) ² is the matching degree, A is the retrieval topic, and B is the associated word topic of any associated word in the associated word set.

S6. Prompt the user by using the subject word set to obtain a search phrase, and use the search phrase to perform retrieval.

In the embodiment of the present application, the use of the subject word set to prompt the user to obtain a search phrase includes:

Get the retrieval records of multiple users in the background;

Calculate the word popularity of each subject heading in the subject heading set according to the retrieval record;

Sort the words in the subject vocabulary set in descending order of the word popularity to obtain a subject vocabulary list;

Prompt the user according to the order of the subject word list, and obtain the feedback words from the user;

The feedback word and the search word set are the search word group.

Specifically, the retrieval records of multiple users in the background include retrieval traces of multiple users stored in the background, such as retrieval time, retrieval content, and the like.

In detail, the step of using the subject word set to prompt the user to obtain a search phrase is consistent with the step of using the similar word set to give an error prompt to the input word and obtaining the search word in step S2, which is not described here. Do repeat. The step of using the search phrase to search is the same as the step of using the search word to search in step S3, and will not be repeated here.

In this embodiment of the present application, the retrieval records of multiple users in the background can be used to analyze and obtain the word popularity of each theme word in the theme theme set. The words in the thesaurus are sorted in descending order of word popularity and prompted to the user, which is beneficial to improve the efficiency of retrieval.

In the embodiment of the present application, by performing similar word matching on the input words of the user, and using the matched similar word set to give an error prompt to the input words, the search words are obtained, which can reduce the probability of incorrectly inputting the search words and reduce the possibility of the user retrieving wrong content. , which is beneficial to improve the accuracy of retrieval; when the user command is an input command, the related words are matched for the search term, and the matched related word set is subject to subject screening to obtain the subject word set with the same subject as the search term, using the subject word set Prompting the user is beneficial to reduce the time for the user to input keywords and improve the retrieval efficiency. Therefore, the retrieval method based on keyword hints proposed in this application can solve the problem of low efficiency and accuracy in keyword-based retrieval.

As shown in FIG. 2 , it is a functional block diagram of a retrieval device based on keyword hinting provided by an embodiment of the present application.

The retrieval apparatus 100 based on keyword hinting described in this application can be installed in an electronic device. According to the implemented functions, the keyword prompt-based retrieval device 100 may include a similar word matching module 101 , an error prompt module 102 , a first retrieval module 103 , a related word matching module 104 , a subject word screening module 105 and a second retrieval module 106 . The modules described in this application may also be referred to as units, which refer to a series of computer program segments that can be executed by the processor of an electronic device and can perform fixed functions, and are stored in the memory of the electronic device.

In this embodiment, the functions of each module/unit are as follows:

The similar word matching module 101 is used for acquiring the input words of the user, and performing similar word matching on the input words to obtain a similar word set.

In detail, the similar word matching module 101 is specifically used for:

Sim=Pearson(R, S)

The error prompting module 102 is configured to use the similar word set to give an error prompt to the input word to obtain a search word.

In the embodiment of the present application, the error prompt module 102 is specifically used for:

The first retrieval module 103 is configured to monitor the user instruction of the user, and when the user instruction is a retrieval instruction, use the retrieval word to perform retrieval.

In the embodiment of the present application, the first retrieval module 103 is specifically used for:

performing word coding on the search term to obtain a search code;

Check the retrieval environment;

Execute the retrieval statement to retrieve.

The character codes are combined to obtain a retrieval code.

The combining the character codes specifically refers to: combining the character codes corresponding to each character in the search term according to the sequence of the characters in the search term to obtain the character codes. For example, if there is a search term "ice cream", in which the character code of "ice" is ab, the character code of "ice" is ef, and the character code of "rain" is cd, according to the three characters in the search term "ice cream" The character codes corresponding to each word are sequentially combined to obtain the search code "abefcd" of the search word "ice cream".

The associated word matching module 104 is configured to perform associated word matching on the search term when the user instruction is an input instruction to obtain a associated word set.

In this embodiment of the present application, the associated word matching module 104 is specifically used for:

In detail, the embodiment of the present application uses a preset word vector transformation model to perform word vector transformation on the search term to obtain a retrieval vector. Wherein, the word vector conversion model includes but is not limited to CRF model (Conditional Random Fields Model, conditional random field model), HMM model (Hidden Markov Model, Hidden Markov Model). Using the word vector transformation model to perform word vector transformation on the retrieval words can improve the efficiency of converting the retrieval words into retrieval vectors.

In the embodiment of the present application, the related words are matched on the search terms to obtain a set of related words, and words related to the search terms can be screened out from the standard thesaurus, which is beneficial to improve the retrieval efficiency.

The subject word screening module 105 is configured to perform subject screening on the associated word set to obtain a theme word set with the same subject as the search terms.

In the embodiment of the present application, the subject heading screening module 105 is specifically used for:

extracting the search subject of the search term;

d(A, B) ² = ‖AB‖ ²

The second retrieval module 106 is configured to use the subject word set to prompt the user, obtain a retrieval phrase, and use the retrieval phrase to perform retrieval.

In this embodiment of the present application, the second retrieval module 106 is specifically configured to:

Get the retrieval records of multiple users in the background;

The feedback word and the search word set are the search word group.

In detail, the step of using the subject word set to prompt the user to obtain the search phrase is consistent with the step of error prompting module 102 using the similar word set to prompt the input word to obtain the search word, here I won't go into details. The step of using the search phrase to perform retrieval is the same as the step of the first retrieval module 103 to perform the retrieval using the search phrase, and will not be repeated here.

In the embodiment of the present application, by performing similar word matching on the input words of the user, and using the matched similar word set to give an error prompt to the input words, the search words are obtained, which can reduce the probability of incorrectly inputting the search words and reduce the possibility of the user retrieving wrong content. , which is beneficial to improve the accuracy of retrieval; when the user command is an input command, the related words are matched for the search term, and the matched related word set is subject to subject screening to obtain the subject word set with the same subject as the search term, using the subject word set Prompting the user is beneficial to reduce the time for the user to input keywords and improve the retrieval efficiency. Therefore, the retrieval device based on keyword hints proposed in this application can solve the problem of low efficiency and accuracy in keyword-based retrieval.

As shown in FIG. 3 , it is a schematic structural diagram of an electronic device implementing a retrieval method based on keyword hints provided by an embodiment of the present application.

The electronic device 1 may include a processor 10, a memory 11 and a bus, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a keyword-hinting-based retrieval program 12.

Wherein, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, magnetic disk, CD etc. The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a mobile hard disk of the electronic device 1 . In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a pluggable mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital) equipped on the electronic device 1. , SD) card, flash memory card (Flash Card), etc. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software installed in the electronic device 1 and various data, such as the code of the retrieval program 12 based on keyword hints, etc., but also can be used to temporarily store data that has been output or will be output.

In some embodiments, the processor 10 may be composed of integrated circuits, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits packaged with the same function or different functions, including one or more integrated circuits. Central Processing Unit (CPU), microprocessor, digital processing chip, graphics processor and combination of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and by running or executing the programs or modules stored in the memory 11 (for example, based on Keyword hint retrieval program, etc.), and call the data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

The bus may be a peripheral component interconnect (PCI for short) bus or an extended industry standard architecture (Extended industry standard architecture, EISA for short) bus or the like. The bus can be divided into address bus, data bus, control bus and so on. The bus is configured to implement connection communication between the memory 11 and at least one processor 10 and the like.

FIG. 3 only shows an electronic device with components. Those skilled in the art can understand that the structure shown in FIG. 3 does not constitute a limitation on the electronic device 1, and may include fewer or more components than those shown in the figure. components, or a combination of certain components, or a different arrangement of components.

For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) for powering the various components, preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that the power management The device implements functions such as charge management, discharge management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and any other components. The electronic device 1 may further include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

Further, the electronic device 1 may also include a network interface, optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used in the electronic device 1 Establish a communication connection with other electronic devices.

Optionally, the electronic device 1 may further include a user interface, and the user interface may be a display (Display), an input unit (eg, a keyboard (Keyboard)), optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, and the like. The display may also be appropriately called a display screen or a display unit, which is used for displaying information processed in the electronic device 1 and for displaying a visualized user interface.

It should be understood that the embodiments are only used for illustration, and are not limited by this structure in the scope of the patent application.

The retrieval program 12 based on keyword hints stored in the memory 11 of the electronic device 1 is a combination of multiple instructions, and when running in the processor 10, can realize:

Specifically, for the specific implementation method of the above-mentioned instruction by the processor 10, reference may be made to the description of the relevant steps in the corresponding embodiment of FIG. 1, and details are not described herein.

Further, if the modules/units integrated in the electronic device 1 are implemented in the form of software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. The computer-readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM, Read-Only). Memory).

The present application also provides a computer-readable storage medium. The computer-readable storage medium may be volatile or non-volatile. The readable storage medium stores a computer program, and the computer program is stored in the When executed by the processor of the electronic device, it can achieve:

In the several embodiments provided in this application, it should be understood that the disclosed apparatus, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the modules is only a logical function division, and there may be other division manners in actual implementation.

The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

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

It will be apparent to those skilled in the art that the present application is not limited to the details of the above-described exemplary embodiments, but that the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

Accordingly, the embodiments are to be regarded in all respects as illustrative and not restrictive, and the scope of the application is to be defined by the appended claims rather than the foregoing description, which is therefore intended to fall within the scope of the claims. All changes within the meaning and scope of the equivalents of , are included in this application. Any reference signs in the claims shall not be construed as limiting the involved claim.

The blockchain referred to in this application is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain, essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block. The blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

Furthermore, it is clear that the word "comprising" does not exclude other units or steps and the singular does not exclude the plural. Several units or means recited in the system claims can also be realized by one unit or means by means of software or hardware. Second-class terms are used to denote names and do not denote any particular order.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit them. Although the present application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present application can be Modifications or equivalent substitutions can be made without departing from the spirit and scope of the technical solutions of the present application.

Claims

A retrieval method based on keyword hints, wherein the method comprises:

Obtain the input word of the user, and perform similar word matching on the input word to obtain a similar word set;

Using the similar word set to give an error prompt to the input word to obtain a search word;

Monitor the user instruction of the user, and when the user instruction is a retrieval instruction, use the retrieval word to perform retrieval;

When the user instruction is an input instruction, perform associated word matching on the search term to obtain an associated word set;

Perform theme screening on the associated word set to obtain a theme word set with the same theme as the search term;

The user is prompted by using the subject word set to obtain a search phrase, and the search phrase is used for retrieval.
The retrieval method based on keyword hints as claimed in claim 1, wherein the filtering out the first standard word with the same sound as the input word from the standard word library comprises:

Calculate successively the similarity of the standard word pronunciation of each standard word in the described standard word library and the described input word pronunciation;

The standard word corresponding to the standard word sound whose distance value is smaller than the preset distance threshold is selected from the standard word library as the first standard word.
The retrieval method based on keyword hints as claimed in claim 1, wherein the use of the similar word set to perform error hints on the input words to obtain retrieval words, comprising:

calculating the word popularity of each similar character in the similar character set;

Arrange each similar word in the similar word set in descending order of the word popularity to obtain a similar word list;

An error prompt is given to the user according to the sequence of the similar word list, and the search words returned by the user are obtained.
The retrieval method based on keyword hints according to claim 1, wherein the retrieval by using the retrieval words comprises:

performing word coding on the search term to obtain a search code;

Check the retrieval environment;

Utilize a compiler corresponding to the retrieval environment to compile the retrieval code into retrieval sentences;

Execute the retrieval statement to retrieve.
The retrieval method based on keyword hints as claimed in claim 4, wherein, performing word coding on the retrieval term to obtain retrieval coding, comprising:

encoding and converting each character in the character set to obtain character encoding;

The character codes are combined to obtain a retrieval code.
The retrieval method based on keyword hints according to any one of claims 1 to 5, wherein, performing related word matching on the search terms to obtain a related word set, comprising:

performing word vector transformation on the search term to obtain a search vector;

Calculate the distance value between the retrieval vector and the standard vector corresponding to each standard word in the preset standard thesaurus;

The standard words corresponding to the standard vectors whose distance values are smaller than the preset distance threshold are collected as a related word set.
The keyword-hinting-based retrieval method according to any one of claims 1 to 5, wherein the subject selection of the associated word set to obtain a subject word set with the same subject as the search terms, comprising:

extracting the search subject of the search term;

extracting the associated word subject of each associated word in the associated word set;

Calculate the degree of matching between the retrieval topic and the associated word topics of each associated word in the associated word set;

The associated vocabulary set with the matching degree greater than the preset matching threshold is regarded as the subject vocabulary set.
A retrieval device based on keyword hints, wherein the device includes:

A similar word matching module is used to obtain the input word of the user, and perform similar word matching on the input word to obtain a similar word set;

An error prompting module, used for using the similar word set to give an error prompt to the input word to obtain a search term;

The first retrieval module is used for monitoring the user instruction of the user, and when the user instruction is a retrieval instruction, the retrieval word is used for retrieval;

an associated word matching module, configured to perform associated word matching on the search term when the user instruction is an input command to obtain an associated word set;

a subject heading screening module, used for subject screening the associated word set to obtain a subject heading set with the same subject as the search term;

The second retrieval module is used for prompting the user by using the subject word set, obtaining a retrieval phrase, and using the retrieval phrase for retrieval.
An electronic device, wherein the electronic device comprises:

at least one processor; and,

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of:

Obtain the input word of the user, and perform similar word matching on the input word to obtain a similar word set;

Using the similar word set to give an error prompt to the input word to obtain a search word;

Monitoring the user's user instruction, when the user instruction is a retrieval instruction, use the retrieval word to perform retrieval;

When the user instruction is an input instruction, perform associated word matching on the search term to obtain an associated word set;

Perform theme screening on the associated word set to obtain a theme word set with the same theme as the search term;

The user is prompted by using the subject word set to obtain a search phrase, and the search phrase is used for retrieval.
The electronic device according to claim 9, wherein the filtering out the first standard word with the same sound as the input word from the standard word library comprises:

Calculate successively the similarity of the standard word pronunciation of each standard word in the described standard word library and the described input word pronunciation;

The standard word corresponding to the standard word sound whose distance value is smaller than the preset distance threshold is selected from the standard word library as the first standard word.
The electronic device according to claim 9, wherein the using the similar word set to perform an error prompt on the input word to obtain a search word, comprising:

calculating the word popularity of each similar character in the similar character set;

Arrange each similar word in the similar word set in descending order of the word popularity to obtain a similar word list;

An error prompt is given to the user according to the sequence of the similar word list, and the search words returned by the user are obtained.
The electronic device according to claim 9, wherein the retrieval using the retrieval term comprises:

performing word coding on the search term to obtain a search code;

Check the retrieval environment;

Utilize a compiler corresponding to the retrieval environment to compile the retrieval code into retrieval sentences;

Execute the retrieval statement to retrieve.
The electronic device according to claim 12 , wherein, performing word coding on the search term to obtain the search code, comprising:

encoding and converting each character in the character set to obtain character encoding;

The character codes are combined to obtain a retrieval code.
The electronic device according to any one of claims 9 to 13, wherein, performing related word matching on the search term to obtain a related word set, comprising:

performing word vector transformation on the search term to obtain a search vector;

Calculate the distance value between the retrieval vector and the standard vector corresponding to each standard word in the preset standard thesaurus;

The standard words corresponding to the standard vectors whose distance values are smaller than the preset distance threshold are collected as a related word set.
The electronic device according to any one of claims 9 to 13, wherein the subject selection is performed on the associated word set to obtain a subject word set with the same subject as the search terms, including:

extracting the search subject of the search term;

extracting the associated word subject of each associated word in the associated word set;

Calculate the degree of matching between the retrieval topic and the associated word topics of each associated word in the associated word set;

The associated vocabulary set with the matching degree greater than the preset matching threshold is regarded as the subject vocabulary set.
A computer-readable storage medium storing a computer program, wherein the computer program implements the following steps when executed by a processor:

Obtain the input word of the user, and perform similar word matching on the input word to obtain a similar word set;

Using the similar word set to give an error prompt to the input word to obtain a search word;

Monitor the user instruction of the user, and when the user instruction is a retrieval instruction, use the retrieval word to perform retrieval;

When the user instruction is an input instruction, perform associated word matching on the search term to obtain an associated word set;

Perform theme screening on the associated word set to obtain a theme word set with the same theme as the search term;

The user is prompted by the subject word set to obtain a search phrase, and the search phrase is used for retrieval.
The computer-readable storage medium of claim 16, wherein the filtering out the first standard word with the same sound as the input word from the standard word library comprises:

Calculate successively the similarity of the standard word pronunciation of each standard word in the described standard word library and the described input word pronunciation;

The standard word corresponding to the standard word sound whose distance value is smaller than the preset distance threshold is selected from the standard word library as the first standard word.
The computer-readable storage medium according to claim 16, wherein the using the similar word set to perform an error prompt on the input word to obtain a search word, comprising:

calculating the word popularity of each similar character in the similar character set;

Arrange each similar word in the similar word set in descending order of the word popularity to obtain a similar word list;

An error prompt is given to the user according to the sequence of the similar word list, and the search words returned by the user are obtained.
The computer-readable storage medium of claim 16, wherein the searching using the search terms comprises:

performing word coding on the search term to obtain a search code;

Check the retrieval environment;

Utilize a compiler corresponding to the retrieval environment to compile the retrieval code into retrieval sentences;

Execute the retrieval statement to retrieve.
The computer-readable storage medium according to claim 19, wherein, performing word coding on the search term to obtain the search code, comprising:

encoding and converting each character in the character set to obtain character encoding;

The character codes are combined to obtain a retrieval code.