Information query method, device, computer equipment and storage medium

By filtering homophone phrases to match the phrases of the target element type, the problem of excessive redundant information in the existing information query system is solved, and query efficiency and accuracy are improved.

CN113987127BActive Publication Date: 2024-11-12RUN TECH CO LTD BEIJING
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111292635.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-11-03
Publication Date
2024-11-12
Estimated Expiration
2041-11-03

AI Technical Summary

Technical Problem

The existing information query system has too much redundant information during fuzzy queries, and cannot obtain query results for specific elements, resulting in inefficient query.

Method used

By obtaining the initial query phrases entered by the user, determining their homophone phrases, and filtering out the phrases to be queried that match the actual element phrases based on the target feature type selected by the user, and conducting information queries to obtain accurate query results.

Benefits of technology

It effectively reduces the redundant information of query results, improves the accuracy and efficiency of information query, and ensures query results for specific elements.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113987127B_ABST
    Figure CN113987127B_ABST
Patent Text Reader

Abstract

The present invention discloses an information query method, device, computer equipment and storage medium. The information query method comprises: obtaining an initial query phrase input by a user, and obtaining a target element type selected by the user; determining at least two homophone phrases of the initial query phrase; determining a target element phrase library according to the target element type; screening at least two homophone phrases according to actual element phrases in the target element phrase library to obtain a phrase to be queried; performing information query according to the phrase to be queried to obtain a query result. The embodiment of the present invention improves query efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of computer technology, and in particular to an information query method, apparatus, computer equipment and storage medium. Background Art

[0002] Information query includes precise query and fuzzy query. When only the pronunciation of the text is determined, fuzzy query can be used.

[0003] Most of the known application management systems support fuzzy query, that is, all characters or words that have the same pronunciation as the query content are searched out.

[0004] However, these fuzzy queries are mostly indiscriminate queries, and the query results contain too much redundant information, making it impossible to obtain information query results for specific elements. Summary of the invention

[0005] The embodiments of the present invention provide an information query method, an apparatus, a computer device and a storage medium to improve information query efficiency.

[0006] In a first aspect, an embodiment of the present invention provides an information query method, the method comprising:

[0007] Obtaining the initial query phrase input by the user and obtaining the target element type selected by the user;

[0008] determining at least two homophones of the initial query phrase;

[0009] According to the target element type, determine the target element phrase library;

[0010] According to the actual element phrases in the target element phrase library, at least two homophone phrases are screened to obtain a phrase to be queried;

[0011] Information query is performed according to the phrase to be queried to obtain query results.

[0012] In a second aspect, an embodiment of the present invention further provides an information query device, the device comprising:

[0013] The phrase and type acquisition module is used to acquire the initial query phrase input by the user and acquire the target element type selected by the user;

[0014] A homophone phrase acquisition module, used to determine at least two homophone phrases of an initial query phrase;

[0015] An element phrase library determination module is used to determine a target element phrase library according to a target element type;

[0016] A module for determining a phrase to be queried is used to screen at least two homophone phrases according to actual element phrases in the target element phrase library to obtain a phrase to be queried;

[0017] The query result acquisition module is used to perform information query according to the query phrase to obtain the query result.

[0018] In a third aspect, an embodiment of the present invention further provides a computer device, the computer device comprising:

[0019] one or more processors;

[0020] A storage device for storing one or more programs;

[0021] When one or more programs are executed by one or more processors, the one or more processors implement the information query method provided by the embodiment of the present invention.

[0022] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the information query method provided by the embodiment of the present invention.

[0023] The present invention obtains an initial query phrase input by a user, determines homophones of the initial query phrase, determines a target element phrase library by obtaining the target element type selected by the user, and screens homophones of the initial query phrase according to actual element phrases in the target element phrase library to obtain a phrase to be queried, wherein the phrase to be queried is a phrase identical to the actual element phrase and meets specific element requirements, and obtains a query result according to the phrase to be queried, thereby solving the problem that there is too much redundant information in the query result and information query results for specific elements cannot be obtained, thereby achieving the effect of improving information query efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A flowchart of an information query method provided in Embodiment 1 of the present invention;

[0025] Figure 2 A flowchart of an information query method provided in Embodiment 2 of the present invention;

[0026] Figure 3 A flowchart of a name query method provided in Embodiment 2 of the present invention;

[0027] Figure 4 is a schematic diagram of the structure of an information query device provided by Embodiment 3 of the present invention;

[0028] Figure 5 A schematic diagram of the structure of a computer device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0029] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0030] Embodiment 1

[0031] Figure 1 This is a flowchart of an information query method provided in Embodiment 1 of the present invention. This embodiment is applicable to the case of fuzzy query of information. The method can be executed by an information query device, which can be implemented in software and / or hardware. The device can be configured in a computer device. The method specifically includes:

[0032] Step 110: Obtain the initial query phrase input by the user, and obtain the target element type selected by the user.

[0033] Among them, the initial query phrase is the phrase input by the user in the corresponding input area of ​​the query window, that is, the phrase input by the user to be searched, and the initial query phrase only needs to be a text with the same pronunciation as the phrase to be searched, without distinguishing the specific text. The target element type is the element type of the initial query phrase selected by the user. Exemplarily, the target element type can be a name type, an organization type, or an address type. Specifically, a query content input box, an element type selection box, and a query button can be set in the information query window, wherein the query content input box is used to obtain the initial query phrase, the element type selection box is used to obtain the target element type, and the query button is used to determine the execution of the next step. When the user enters the content to be searched in the query content input box, the computer device obtains the content entered by the user as the initial query phrase. When the user selects through the drop-down menu of the element type selection box, the computer device obtains the element type selected by the user as the target element type. After the user clicks the query button, the computer device confirms to enter the next step. Exemplarily, the query content input box can be associated with the element type selection box. After the computer obtains the two pieces of information, the user clicks the query button to proceed to the next step, otherwise the user is prompted to complete the information, for example, a pop-up window is displayed for text prompts.

[0034] Step 120: Determine at least two homophone phrases of the initial query phrase.

[0035] A homophone phrase is a phrase composed of characters with the same pinyin as the characters in the initial query phrase, and the characters in different phrases in the homophone phrase have at least one character with a different glyph. After obtaining the initial query phrase, the characters in the initial query phrase are translated into the pinyin corresponding to each character, and the characters corresponding to each pinyin are obtained in the pinyin dictionary database according to the pinyin, and the characters corresponding to each pinyin are stored in a set to form a homophone set. The characters are extracted from each homophone set in turn and combined to obtain homophone phrases, and the number of homophone phrases is greater than or equal to 2. Among them, the pinyin dictionary database is a database containing the mapping relationship between pinyin and characters, and all homophone characters corresponding to it can be found according to the pinyin.

[0036] In an optional embodiment, determining at least two homophones of the initial query phrase includes: if the target element type is an institution type or an address type, determining the homophones of each character in the initial query phrase respectively; and combining each homophone to obtain at least two homophones.

[0037] The target element type is an institution or address, that is, the initial query phrase is an institution name or an address name. Each character in the institution name or the address name has no special features. After obtaining the initial query phrase, each character in the initial query phrase is translated into pinyin in turn, and the characters corresponding to the pinyin are obtained in the pinyin dictionary database. All the obtained characters are stored in the homophone set corresponding to the characters in the initial query phrase, that is, the homophones of each character in the initial query phrase are determined respectively. One character is extracted from each homophone set corresponding to each character in the initial query phrase, and the homophones are combined to obtain a homophone phrase. Different characters in each homophone set are traversed one by one to obtain all homophone phrases. The number of homophone phrases is greater than or equal to 2.

[0038] By combining the homophones of each character in the respectively obtained initial query phrases of the institution type or address type, all homophone phrases can be obtained, thereby reducing omissions and improving the comprehensiveness of homophone phrases.

[0039] Step 130: Determine the target element phrase library according to the target element type.

[0040] The target element phrase database is a phrase database corresponding to the target element type, and is used to screen homophone phrases corresponding to the initial query phrase according to the target element type. According to the target element type selected by the user, the phrase database corresponding to the target element type is determined as the target element phrase database.

[0041] In an optional embodiment, determining the target element phrase library according to the target element type includes: matching the target element type with the association between the candidate element type and the candidate element phrase library, and using the candidate element phrase library matching the target element type as the target element phrase library.

[0042] The candidate element type is all element types. Specifically, the candidate element type may include name type, organization type and address type. It should be noted that the candidate element type may be set according to actual needs, for example, it may also be an article title type or a product name type. The candidate element phrase library is a corresponding phrase database established in advance according to the candidate element type. Specifically, the initial phrase corresponding to the candidate element type is obtained from public web page information through web crawler technology as the initial data of the candidate element phrase library. After obtaining the data provided by the user, the text information in the data is obtained, and the phrase corresponding to the candidate element type in the text information is obtained through natural language processing (NLP) technology. The obtained phrase is added to the candidate element phrase library corresponding to the candidate element type, and the candidate element phrase library is updated. It should be noted that after the phrase corresponding to the candidate element type is obtained through NLP technology, the obtained phrase can be manually screened to improve the accuracy of the established candidate element phrase library. Each candidate element type corresponds to a candidate element phrase database, for example, the name type corresponds to the name phrase database; the organization type corresponds to the organization phrase database; and the address type corresponds to the address phrase database.

[0043] After obtaining the target feature type, match the candidate feature type that is the same as the target feature type, match the candidate feature phrase library associated with the target feature type according to the association relationship between the candidate feature type and the candidate feature phrase library, and use the matched candidate feature phrase library as the target feature phrase library.

[0044] By matching the target element type with the association between the candidate element type and the candidate element phrase library, the target element phrase library corresponding to the target element type can be quickly and accurately obtained.

[0045] Step 140: Screen at least two homonymous phrases according to the actual element phrases in the target element phrase library to obtain a phrase to be searched.

[0046] The actual element phrase is a phrase stored in the target element phrase library, and is used to screen homophone phrases. The phrase to be queried is a homophone phrase screened according to the target element phrase library. Specifically, the homophone phrase is compared word by word with the actual element phrase in the target element phrase library, and homophone phrases including words different from the actual element phrase in the target element phrase library are eliminated, that is, phrases in the homophone phrase that are all the same as the actual element phrase words are screened out, and the screened phrases are the phrases to be queried.

[0047] Step 150: perform information search based on the phrase to be searched to obtain search results.

[0048] Query the information corresponding to the phrase to be queried in the user database and display it in the query results. Specifically, the user database can be a database for a specific business.

[0049] In the technical solution of this embodiment, by obtaining the initial query phrase input by the user, determining the homophonic phrases of the initial query phrase, determining the target element phrase library according to the target element type selected by the user, screening the homophonic phrases of the initial query phrase according to the actual element phrases in the target element phrase library to obtain the phrase to be queried, the phrase to be queried is the phrase that is the same as the actual element phrase, meets specific element requirements, and obtaining the query result according to the phrase to be queried solves the problem that there is too much redundant information in the query result and it is impossible to obtain the information query result for specific elements, achieving the effect of improving the information query efficiency.

[0050] Embodiment 2

[0051] Figure 2 It is a flowchart of an information query method provided by Embodiment 2 of the present invention. The technical solution of this embodiment is further refined on the basis of the above technical solution. Specifically, determining at least two homophonic phrases of the initial query phrase is refined as: if the target element type is a name type, extract the surname character to be queried from the initial query phrase; determine the homophonic surnames for the surname character to be queried, and determine the other homophonic characters for the characters other than the surname character to be queried in the initial query phrase; screen the homophonic surnames using the surname library to obtain the remaining homophonic surnames; combine the remaining homophonic surnames and the other homophonic characters to obtain at least two homophonic phrases. The method includes:

[0052] Step 210, obtain the initial query phrase input by the user and obtain the target element type selected by the user.

[0053] Step 220, if the target element type is a name type, extract the surname character to be queried from the initial query phrase.

[0054] When the target element type is a name type, the initial query phrase is a name type phrase, that is, the initial query phrase is a name. The surname character to be queried is the character representing the surname in the initial query phrase. The surnames in a name are some specific characters. For example, the surnames corresponding to the pinyin "wang" are characters such as "王, 汪, and 望", and do not include characters such as "网, 往, and 忘". There is no such restriction on the other characters other than the surname in a name. According to this feature of the name type initial query phrase, extract the surname character to be queried in the initial query phrase. Specifically, according to the input habit of names in Chinese, that is, the surname is in front and the given name is behind, it can be preset that when the target element type is a name type, the character in front of the initial query phrase is the surname character. Extracting the surname character from the initial query phrase can screen the surname character and reduce the workload of screening homophonic phrases subsequently.

[0055] In an optional embodiment, extracting the surname character to be queried from the initial query phrase includes: taking the first character in the initial query phrase as the surname character to be queried.

[0056] In Chinese, most surnames are single characters, that is, the first character in the name. In addition, there are a few surnames that are compound surnames, that is, two characters, for example, Ouyang, Zhuge, Nalan, etc., but the first character of the compound surname is also a fixed character. Therefore, the first character in the initial query phrase is used as the surname character to be queried.

[0057] Using the first character in the initial query phrase as the surname to be queried can simplify the extraction steps of the surname to be queried, has simple logic and is easy to implement, and improves the efficiency of extracting the surname to be queried.

[0058] Step 230: determine homophones for the surname to be queried, and determine other homophones for other characters in the initial query phrase except the surname to be queried.

[0059] A homophone surname is a character with the same pinyin as the surname to be queried. The surname to be queried is translated into its corresponding pinyin, and the homophone of the surname to be queried is obtained from the pinyin dictionary database to be determined as the homophone surname. After the homophone surname is determined, the homophones of other characters are obtained in turn from the pinyin dictionary database to be determined as other homophones.

[0060] Step 240: Use the surname database to filter homophones of surnames to obtain remaining homophones of surnames.

[0061] The surname database is a database containing the first characters of all single and double surnames, and is used to screen characters that meet the surname requirements. The remaining homophone surname characters are the characters that meet the surname requirements among the homophone surname characters. Specifically, the homophone surname characters are compared with the characters in the surname database, and the characters that do not exist in the surname database are eliminated to obtain the remaining homophone surname characters.

[0062] Optionally, a pinyin surname database may be pre-established, that is, a mapping relationship between pinyin and characters may be established in the pre-established surname database, and homophone surname characters of the surname to be queried may be directly determined in the pinyin surname database after step 220, and the homophone surname characters of the surname to be queried obtained at this time are the remaining homophone surname characters obtained in step 240. It should be noted that the homophones of other characters in the initial query phrase except the surname to be queried are still determined according to step 230, and the pinyin surname database is only applicable to determining homophone surname characters of surname characters.

[0063] Step 250: Combine the remaining homophone surname characters and other homophone characters to obtain at least two homophone phrases.

[0064] Combine the different characters in the remaining homophonic surname characters with the different characters in other homophonic characters to obtain homophonic phrases, and the number of homophonic phrases is greater than or equal to 2.

[0065] Step 260: Determine the target element phrase library according to the target element type.

[0066] Step 270: Screen at least two homophonic phrases according to the actual element phrases in the target element phrase library to obtain the phrases to be queried.

[0067] Step 280: Query information according to the phrases to be queried to obtain the query result.

[0068] Figure 3 It is a flowchart of a name query method provided by an embodiment of the present invention. Figure 3 The scenario in is to query the information corresponding to the name homophonic with "Wang Xiaoming" in the comprehensive query business system. The specific implementation steps of the information query method are as follows:

[0069] Step 310: The comprehensive query business system obtains the user input. The user inputs the initial query phrase "Wang Xiaoming" in the query content input box of the comprehensive query business system and selects the query type as name. The comprehensive query business system obtains the initial query phrase "Wang Xiaoming" and determines that the target query type is the name category.

[0070] Step 320: Obtain all homophonic characters according to the pinyin dictionary database. The comprehensive query business system translates the character "Wang" into its pinyin "wang", obtains all homophonic characters according to the pinyin in the dictionary database, and stores them in the first set; and sequentially obtains the homophonic words of the characters "Xiao" and "Ming" and stores them in the second set and the third set. Exemplarily, the first set is {Wang, Wang, Wang, Wang, Wang...}, the second set is {Xiao, Xiao, Xiao...}, and the third set is {Ming, Ming, Ming...}.

[0071] Step 330: Is it a surname category? Determine whether the query type selected by the user is a surname category. If so, go to step 340. If not, go to step 350.

[0072] Step 340: Surname screening. Compare the first set with the surname database to obtain the surname set, and compare the first set {Wang, Wang, Wang, Wang, Wang...} with the surname database to obtain the surname set {Wang, Wang, Wang...}.

[0073] Step 350: Obtain homophonic phrases. Combine the characters in each set in different ways to obtain the homophonic phrase set. For example, {Wang Xiaoming, Wang Xiaoming, Wang Xiaoming... Wang Xiaoming, Wang Xiaoming, Wang Xiaoming... Wang Xiaoming, Wang Xiaoming... Wang Xiaoming...}.

[0074] Step 360: Filter the target element phrase library. Determine the target element phrase library as a name phrase library according to the target element type, compare the homophone phrase with the name phrase library to obtain the phrase to be queried, and store the phrase to be queried in a set of phrases to be queried, for example, the set of phrases to be queried is {Wang Xiaoming, Wang Xiaoming, Wang Xiaoming, Wang Xiaoming, Wang Xiaoming...}.

[0075] Step 370: Display the query results. According to the query phrase, the comprehensive information of Wang Xiaoming, Wang Xiaoming, Wang Xiaoming, Wang Xiaoming, Wang Xiaoming, etc. is searched in the business database of the comprehensive query business system and displayed in the query result area.

[0076] The technical solution of this embodiment, when the target element type is a name, uses the surname library to filter out surname homophones in the name, and then combines them with homophones of other characters to obtain homophonetic phrases, which can reduce the workload of later screening of homophonetic phrases, improve the query speed, and quickly obtain query results.

[0077] Embodiment 3

[0078] Figure 4 The figure shows a schematic diagram of the structure of an information query device provided by the third embodiment of the present invention. The third embodiment is a corresponding device for implementing the information query method provided by the above embodiments of the present invention. The device can be implemented in software and / or hardware and can generally be integrated in a computer device. The information query device includes:

[0079] The phrase and type acquisition module 410 is used to acquire the initial query phrase input by the user and acquire the target element type selected by the user;

[0080] A homophone phrase acquisition module 420, for determining at least two homophone phrases of an initial query phrase;

[0081] The element phrase library determination module 430 is used to determine the target element phrase library according to the target element type;

[0082] The to-be-queried phrase determination module 440 is used to screen at least two homophone phrases according to the actual element phrases in the target element phrase library to obtain the to-be-queried phrase;

[0083] The query result acquisition module 450 is used to perform information query according to the query phrase to obtain the query result.

[0084] The technical solution of this embodiment obtains the initial query phrase input by the user, determines the homonymous phrases of the initial query phrase, determines the target element phrase library by obtaining the target element type selected by the user, and filters the homonymous phrases of the initial query phrase according to the actual element phrases in the target element phrase library to obtain the phrase to be queried, the phrase to be queried is the same as the actual element phrase and meets the specific element requirements, and obtains the query result according to the phrase to be queried, which solves the problem that there is too much redundant information in the query result and the information query result for the specific element cannot be obtained, thereby achieving the effect of improving the efficiency of information query.

[0085] Optionally, the homophone phrase acquisition module 420 includes:

[0086] A surname extraction unit, used for extracting the surname to be queried from the initial query phrase if the target element type is a name type;

[0087] A name homophone determination unit, used to determine homophones for the surname to be queried, and to determine other homophones for other characters in the initial query phrase except the surname to be queried;

[0088] A surname screening unit, used to screen homophone surnames using the surname library to obtain remaining homophone surnames;

[0089] The homophone name acquisition unit is used to combine the remaining homophone surname characters and other homophone characters to obtain at least two homophone phrases.

[0090] Optionally, extracting the surname to be queried from the initial query phrase is specifically used for: taking the first character in the initial query phrase as the surname to be queried.

[0091] Optionally, the homophone phrase acquisition module 420 further includes:

[0092] Each homophone acquisition unit is used to determine the homophone of each character in the initial query phrase if the target element type is an institution type or an address type;

[0093] The homophone combination unit is used to combine homophones to obtain at least two homophone phrases.

[0094] Optionally, the element phrase library determination module 430 includes:

[0095] The target element phrase library determination unit is used to match the target element type with the association relationship between the candidate element type and the candidate element phrase library, and use the candidate element phrase library matching the target element type as the target element phrase library.

[0096] The above-mentioned device can execute the information query method provided by the embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the information query method.

[0097] Embodiment 4

[0098] Figure 5 A schematic diagram of the structure of a computer device provided in Embodiment 4 of the present invention is shown in FIG. Figure 5 As shown, the computer device includes a processor 510, a memory 520, an input device 530, and an output device 540; the number of processors 510 in the computer device can be one or more. Figure 5 A processor 510 is taken as an example; the processor 510, memory 520, input device 530 and output device 540 in the computer device can be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0099] The memory 520, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the information query method in the embodiment of the present invention (for example, the phrase and type acquisition module 410, the homophone phrase acquisition module 420, the element phrase library determination module 430, the to-be-queried phrase determination module 440 and the query result acquisition module 450). The processor 510 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 520, that is, realizes the above-mentioned information query method.

[0100] The memory 520 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 520 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 520 may further include a memory remotely arranged relative to the processor 510, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0101] The input device 530 may be used to receive input character information and generate key signal input related to user settings and function control of the computer device. The output device 540 may include a display device such as a display screen.

[0102] Embodiment 5

[0103] Embodiment 5 of the present invention further provides a storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute an information query method when executed by a computer processor, the method comprising:

[0104] Obtaining the initial query phrase input by the user and obtaining the target element type selected by the user;

[0105] determining at least two homophones of the initial query phrase;

[0106] According to the target element type, determine the target element phrase library;

[0107] According to the actual element phrases in the target element phrase library, at least two homophone phrases are screened to obtain a phrase to be queried;

[0108] Information query is performed according to the phrase to be queried to obtain query results.

[0109] Of course, the computer executable instructions of a storage medium containing computer executable instructions provided by an embodiment of the present invention are not limited to the operations of the method described above, and can also execute related operations in the information query method provided by any embodiment of the present invention.

[0110] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (FLASH), a hard disk or an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0111] It is worth noting that in the embodiment of the above-mentioned search device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0112] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. An information query method, characterized in that: include: Obtain the initial query phrase input by the user and obtain the target element type selected by the user; determining at least two homophones of the initial query phrase; Determining a target element phrase library according to the target element type; According to the actual element phrases in the target element phrase library, at least two homophone phrases are screened to obtain a phrase to be queried; Information query is performed according to the phrase to be queried to obtain query results.

2. The method according to claim 1, characterized in that Determining at least two homophone phrases of the initial query phrase includes: If the target element type is name type, extract the surname to be queried from the initial query phrase; Determine homophones for the surname to be queried, and determine other homophones for other characters in the initial query phrase except the surname to be queried; Using the surname database to screen homophone surname characters, and obtaining the remaining homophone surname characters; The remaining homophone surname characters and other homophone characters are combined to obtain at least two homophone phrases.

3. The method according to claim 2, characterized in that Extract the surname to be searched from the initial query phrase, including: The first character in the initial query phrase is used as the surname character to be queried.

4. The method according to claim 1, characterized in that Determining at least two homophone phrases of the initial query phrase includes: If the target element type is an institution type or an address type, then the homophones of the characters in the initial query phrase are determined respectively; The homophones are combined to obtain the at least two homophone phrases.

5. The method according to claim 1, characterized in that According to the target element type, determining the target element phrase library includes: The target element type is matched with the association relationship between the candidate element type and the candidate element phrase library, and the candidate element phrase library matching the target element type is used as the target element phrase library.

6. An information query device, characterized in that: include: The phrase and type acquisition module is used to acquire the initial query phrase input by the user and acquire the target element type selected by the user; A homophone phrase acquisition module, used to determine at least two homophone phrases of the initial query phrase; An element phrase library determination module, used to determine a target element phrase library according to the target element type; A to-be-queried phrase determination module is used to screen at least two homophone phrases according to actual element phrases in the target element phrase library to obtain the to-be-queried phrase; The query result acquisition module is used to perform information query according to the phrase to be queried to obtain the query result.

7. The device according to claim 6, characterized in that The homophone phrase acquisition module comprises: A surname extraction unit, configured to extract the surname to be queried from the initial query phrase if the target element type is a name type; A name homophone determination unit, used to determine homophones for the surname to be queried, and to determine other homophones for other characters in the initial query phrase except the surname to be queried; A surname screening unit, used to screen homophone surnames using the surname library to obtain remaining homophone surnames; The homophone name acquisition unit is used to combine the remaining homophone surname characters and other homophone characters to obtain at least two homophone phrases.

8. The device according to claim 6, characterized in that The homophone phrase acquisition module includes: Each homophone acquisition unit is used to determine the homophone of each character in the initial query phrase if the target element type is an institution type or an address type; The homophone combining unit is used to combine the homophones to obtain the at least two homophone phrases.

9. A computer device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the information query method as described in any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the information query method as described in any one of claims 1 to 5 is implemented.