Search method and device

Abstract

The present application provides a search method and device. The method includes: receiving a search term input by a user; parsing the search term to obtain multiple parsed terms; determining the return result corresponding to each parsed term based on the multiple parsed terms and a term database, wherein the term database includes: a general term database, a historical selection database, and an abnormal term database, wherein the historical selection database includes terms previously selected by the user, and the abnormal term database includes terms that do not exist in the general term database and the historical selection database; and outputting the return results corresponding to the multiple parsed terms. This can avoid the problem of unsatisfactory search results when the search term cannot accurately describe the content that the user wants to search for.

Description

Technical Field

[0001] The present application relates to the field of search, and in particular to a search method and device. Background Art

[0002] When users need to check information, they can enter search terms in the search tool, and the search tool can search based on the search terms and then present the search results for the user to view. However, the search terms entered by the user may not accurately describe what the user really wants to search for. In this case, the search results presented are not what the user wants, and the user experience is not good. Summary of the invention

[0003] The embodiments of the present application provide a search method and device for solving the problem that search results are not ideal when the search terms cannot accurately describe the content that the user wants to search for.

[0004] In a first aspect, the present application provides a search method, comprising: receiving a search term input by a user; parsing the search term to obtain a plurality of parsed terms; determining a return result corresponding to each parsed term based on the plurality of parsed terms and a term database, the term database comprising: a general term database, a historical selection database and an abnormal term database, the historical selection database including terms previously selected by the user, the abnormal term database including terms that do not exist in the general term database and the historical selection database; and outputting the return results corresponding to the plurality of parsed terms.

[0005] Optionally, parsing the search term to obtain a plurality of parsed words includes: splitting each Chinese character in the search term according to radicals to obtain a plurality of Chinese character elements corresponding to the search term; and combining the plurality of Chinese character elements to obtain the plurality of parsed words.

[0006] Optionally, determining the return result corresponding to each parsed word based on the multiple parsed words and the word database includes: matching each parsed word in the multiple parsed words with the words in each word database respectively; determining the word database to which the parsed word belongs based on the matching result; and determining the return result corresponding to the parsed word based on the word database to which the parsed word belongs.

[0007] Optionally, the determining of the return result corresponding to the parsed vocabulary according to the vocabulary database to which the parsed vocabulary belongs includes: if the parsed vocabulary belongs to the general vocabulary database, determining that the return result corresponding to the parsed vocabulary includes the search result of the parsed vocabulary and first indication information, wherein the first indication information is used to indicate that the parsed vocabulary belongs to the general vocabulary database.

[0008] Optionally, the determining the return result corresponding to the parsed vocabulary based on the vocabulary database to which the parsed vocabulary belongs includes: if the parsed vocabulary belongs to the historical selection database, determining that the return result corresponding to the parsed vocabulary includes the search result of the parsed vocabulary and second indication information, the second indication information being used to indicate that the parsed vocabulary belongs to the historical selection database.

[0009] Optionally, the returned result corresponding to the parsed word also includes third indication information, and the third indication information is used to indicate the number of times the parsed word is selected.

[0010] Optionally, determining the return result corresponding to the parsed vocabulary according to the vocabulary database to which the parsed vocabulary belongs includes: if the parsed vocabulary belongs to the abnormal vocabulary database, determining that the return result corresponding to the parsed vocabulary includes fourth indication information, and the fourth indication information is used to indicate that the parsed vocabulary belongs to the abnormal vocabulary database.

[0011] Optionally, the method further includes: if the parsed vocabulary does not belong to the vocabulary database, adding the parsed vocabulary to the abnormal vocabulary database.

[0012] In a second aspect, the present application provides a search device, comprising: a receiving module, used to receive a search term input by a user; a parsing module, used to parse the search term to obtain multiple parsed words; a determining module, used to determine the return result corresponding to each parsed word based on the multiple parsed words and a word database, the word database comprising: a general word database, a historical selection database and an abnormal word database, the historical selection database including words previously selected by the user, and the abnormal word database including words that do not exist in the general word database and the historical selection database; an output module, used to output the return results corresponding to the multiple parsed words.

[0013] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the search method provided in the first aspect.

[0014] In a fourth aspect, the present application provides a terminal device, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to implement the search method provided in the first aspect by executing the executable instructions.

[0015] The search method and device provided by the present application. After receiving the search term input by the user, the search term is first parsed to obtain multiple parsed words, and then, based on the multiple parsed words and the word database, the return result corresponding to each parsed word is determined, and finally the return results corresponding to the multiple parsed words are output. Compared with the method based only on the search term in the prior art, the method provided by this embodiment can avoid the problem of unsatisfactory search results when the search term cannot accurately describe the content that the user wants to search. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of the first embodiment of the search method provided by the present application;

[0017] Figure 2 A corresponding diagram of the radicals and Chinese characters provided for this application;

[0018] Figure 3 A schematic diagram of the combined process provided for this application;

[0019] Figure 4 A flowchart of the second embodiment of the search method provided by the present application;

[0020] Figure 5 Schematic diagram of the user interface provided for this application Figure 1 ;

[0021] Figure 6 Schematic diagram of the user interface provided for this application Figure 2 ;

[0022] Figure 7 Schematic diagram of the user interface provided for this application Figure 3 ;

[0023] Figure 8 A schematic diagram of the structure of the search device provided by this application;

[0024] Fig. 9 A schematic diagram of the hardware structure of the terminal device provided for this application. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] In this application, it should be explained that "at least one" means one or more, and "multiple" means two or more. "And / or" describes the relationship between associated objects and indicates that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a alone, b alone, c alone, the combination of a and b, the combination of a and c, the combination of b and c, or the combination of a, b, and c, where a, b, and c can be single or multiple.

[0027] This application relates to a search scenario. When a user wants to search for desired information on the network, the user can enter a search term in a search tool. However, in some scenarios, for example, when the user is not sure about the exact Chinese characters that make up the search term and subjectively guesses the search term, the search results of existing search methods may be very different from the information the user wants, resulting in a low user experience.

[0028] For example, the user wants to search for an amino acid but is not sure about its exact Chinese character composition and guesses it might be "yuè guāng ān suān". After the user enters "yuè guāng ān suān" in the input box, the search results of the search tool may not be what the user wants, and the user's search experience is poor.

[0029] To solve the above technical problems, this application proposes a search method. After the user enters a search term, the search term is first parsed to obtain several words that the user might originally want to search for. Based on these several words, a search is conducted, and after obtaining the search results, they are displayed on the user interface for the user to view, which can avoid the problem of unsatisfactory search results when the search term cannot accurately describe what the user wants to search for.

[0030] The search method provided by this application can be applied to a terminal device. The terminal device can be a mobile phone, a tablet computer, a smart watch, a television, a wearable device, and other electronic devices that can provide search services. By way of example and not limitation, a wearable device can also be called a wearable intelligent device, which is a general term for devices developed by applying wearable technology to the intelligent design of daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is either directly worn on the body or integrated into the user's clothes or accessories.

[0031] The following uses specific embodiments to elaborate in detail on the specific implementation solutions of this application. These several specific embodiments can be combined with each other, and for the same or similar concepts or processes, they may not be elaborated again in some embodiments. The embodiments of this application will be described below in conjunction with the accompanying drawings.

[0032] Embodiment 1

[0033] Figure 1 It is a schematic flowchart of Embodiment 1 of the search method provided by this application. As Figure 1 shown, the search method provided in this embodiment includes:

[0034] S101. Receive the search term input by the user.

[0035] In a possible implementation, the user can enter the search term in the keyword input box of the search tool.

[0036] S102. Analyze the search term to obtain multiple parsed words.

[0037] Since there is a concept of radicals in the composition of Chinese characters, and some of these radicals are formed from specific Chinese characters. Therefore, ordinary radicals can be converted into Chinese characters. Based on this idea, this application proposes that after receiving the search term, each Chinese character in the search term is first split according to its radical to obtain multiple Chinese character elements corresponding to the search term, and then the multiple Chinese character elements are combined to obtain multiple parsed words.

[0038] Specifically, referring to Figure 2 shown, the three-dot water radical "氵" is restored to the Chinese character "水" (water). The moon radical "月" is restored to the Chinese character "月" (moon). The walking radical "辶" is restored to the Chinese character "走" (walk). For the Chinese characters restored from various radicals, reference can be made to the prior art, and this embodiment will not elaborate on them one by one here.

[0039] The following gives examples to illustrate the process of splitting Chinese characters:

[0040] Example 1. Suppose the search term is "洪水" (flood). The radical of "洪" is the three-dot water radical "氵", and "氵" is restored to the Chinese character "水", so "洪水" can be split into "水共水".

[0041] Example 2. Suppose the search term is "胖棍" (fat stick). The radical of "胖" is the moon radical "月", and "月" is restored to the Chinese character "月". The radical of "棍" is the wood radical "木", and "木" is restored to the Chinese character "木", so "胖棍" can be split into "月半木昆".

[0042] Example 3. Suppose the search term is "道" (road). The radical of "道" is the walking radical "辶", and "辶" is restored to the Chinese character "走", so "道" can be split into "走首".

[0043] The following gives examples to illustrate the combination process. Refer to Figure 3 As shown

[0044] Example 1: Suppose the search term is "selenocysteine". After the above splitting method, multiple Chinese character elements "moonlight gas amino acid" are obtained. By combining the multiple Chinese character elements in order, multiple parsed words can be obtained, including "selenocysteine", "cystine", "moonlight gas amino acid", and "moonlight amino acid".

[0045] Example 2: Suppose the search term is "rain night". After the above splitting method, multiple Chinese character elements "rain night" are obtained. By combining the multiple Chinese character elements in order, multiple parsed words can be obtained, including "rain night" and "night sky".

[0046] Example 2: Suppose the search term is "lysine". After the above splitting method, multiple Chinese character elements "lysine gas amino acid" are obtained. By combining the multiple Chinese character elements in order, multiple parsed words can be obtained, including "lysine", "lysine", "lysine gas amino acid", and "lysine amino acid".

[0047] It should be noted that: when combining multiple Chinese character elements, combination refers to combining adjacent elements and cannot skip elements for combination.

[0048] S103. Determine the return result corresponding to each parsed word according to the multiple parsed words and the vocabulary database.

[0049] S104. Output the return results corresponding to the multiple parsed words.

[0050] In a possible implementation, the vocabulary database in this step may include a general vocabulary database, a historical selection database, and an abnormal vocabulary database. Among them, the historical selection database includes the words previously selected by the user, and the abnormal vocabulary database includes the words that do not exist in the general vocabulary database and the historical selection database. Each parsed word in the multiple parsed words can be respectively matched with the words in each vocabulary database. According to the matching result, the vocabulary database to which the parsed word belongs is determined, and then according to the vocabulary database to which the parsed word belongs, the return result corresponding to the parsed word is determined.

[0051] For the search method provided in this embodiment, after receiving the search term input by the user, the search term is first parsed to obtain multiple parsed words. Then, based on the multiple parsed words and the vocabulary database, the return result corresponding to each parsed word is determined. Finally, the return results corresponding to the multiple parsed words are output. Compared with the existing technology that only relies on the search term, the method provided in this embodiment can avoid the problem of unsatisfactory search results when the search term cannot accurately describe the content that the user wants to search.

[0052] Embodiment 2

[0053] Figure 4 This is a schematic flowchart of the second embodiment of the search method provided for this application. As Figure 4 shown, the search method provided in this embodiment includes:

[0054] S401. Receive the search term input by the user.

[0055] S402. Parse the search term to obtain multiple parsed terms.

[0056] For the implementation manners of S401 - S402, reference can be made to S101 - S102 in the above embodiment, and details are not described herein again.

[0057] S403. Match each of the multiple parsed terms with the terms in each vocabulary database respectively.

[0058] S404. Determine the vocabulary database to which the parsed term belongs according to the matching result.

[0059] S405. Determine the return result corresponding to the parsed term according to the vocabulary database to which the parsed term belongs.

[0060] S406. Output the return results corresponding to the multiple parsed terms.

[0061] Specifically, for each of the multiple parsed terms, match the parsed term with the terms in each vocabulary database respectively. If a successful match can be made, it indicates that the parsed term belongs to the corresponding database.

[0062] In a possible implementation manner, if the parsed term belongs to the general vocabulary database, it is determined that the return result corresponding to the parsed term includes the search result of the parsed term and the first indication information, and the first indication information is used to indicate that the parsed term belongs to the general vocabulary database.

[0063] The following is an example for illustration:

[0064] Suppose the search term input by the user is "moonlight amino acid", and the multiple parsed terms obtained by parsing the search term include "moonlight amino acid", "cystine", "moonlight gas amino acid", "moonlight amino alcohol". Suppose it is determined through the process of S403 - S404 that "cystine" belongs to the general vocabulary database. Refer to Figure 5 shown, it can be determined that the return result for "cystine" includes: the search result of "cystine" and the first indication information, and the first indication information is used to indicate that "cystine" belongs to the general vocabulary database. Figure 5 The information in the first area 10 in is the first indication information.

[0065] If the parsed term belongs to the historical selection database, determine that the return result corresponding to the parsed term includes the search result of the parsed term and second indication information, where the second indication information is used to indicate that the parsed term belongs to the historical selection database.

[0066] The following is an example:

[0067] Suppose the search term entered by the user is "moonglow amino acid", and the multiple parsed terms obtained by parsing this search term include "moonglow amino acid", "cystine", "moonglow gas amino acid", "moonglow amino alcohol". Suppose it is determined through the process of S403 - S404 that "moonglow gas amino acid" belongs to the historical selection database. Continue to refer to Figure 5 As shown, it can be determined that the return result for "moonglow gas amino acid" includes: the search result of "moonglow gas amino acid" and second indication information, where the second indication information is used to indicate that "moonglow gas amino acid" belongs to the historical selection database. Figure 5 The information in the second area 11 in is the second indication information.

[0068] In the case where the parsed term belongs to the historical selection database, in order to prompt the user of the number of times the parsed term has been selected before, refer to Figure 6 As shown, the return result may further include third indication information, where the third indication information is used to indicate the number of times the parsed term has been selected. Figure 6 The information in the second area 11 in is the second indication information and the third indication information. The number "5" in the second area 11 represents the number of times "moonglow gas amino acid" has been selected.

[0069] If the parsed term belongs to the abnormal term database, determine that the return result corresponding to the parsed term includes fourth indication information, where the fourth indication information is used to indicate that the parsed term belongs to the abnormal term database.

[0070] The following is an example:

[0071] Suppose the search term entered by the user is "moonglow amino acid", and the multiple parsed terms obtained by parsing this search term include "moonglow amino acid", "cystine", "moonglow gas amino acid", "moonglow amino alcohol". Suppose it is determined through the process of S403 - S404 that "moonglow amino alcohol" belongs to the abnormal term database. Continue to refer to Figure 6 As shown, it is determined that the return result for "moonglow amino alcohol" includes fourth indication information, where the fourth indication information is used to indicate that "moonglow amino alcohol" belongs to the abnormal term database. Figure 5 The information in the third area 12 in is the fourth indication information.

[0072] In a possible implementation, if a parsed word does not belong to any of the general word database, the historical selection database, and the abnormal word database, the parsed word is added to the abnormal word database.

[0073] The user can learn what parsed words are available through the information in the first area 10, the second area 11, and the third area 12, and can also decide which word he really wants to search based on these parsed words and the search results of each parsed word. Clicking the area corresponding to the word can trigger the terminal device to only display the search results of this word. For example, if the user decides that the word he really wants to search is "cystine", and clicks the first area 10, the terminal device will jump to Figure 7 The interface shown, Figure 7 The interface shown only displays search results for "cystine".

[0074] In a possible implementation, if the user selects the second area 11, it means that the user has selected the word "moisture ester", and the number of selections of this word in the historical selection database can be increased by one.

[0075] Figure 8 This is a schematic diagram of the structure of the search device provided by this application. Figure 8 As shown, the search device provided by the present application includes:

[0076] The receiving module 801 is used to receive a search term input by a user;

[0077] A parsing module 802, used to parse the search term to obtain a plurality of parsed words;

[0078] A determination module 803 is used to determine the return result corresponding to each parsed word according to the multiple parsed words and the word database, wherein the word database includes: a general word database, a historical selection database and an abnormal word database, wherein the historical selection database includes words previously selected by the user, and the abnormal word database includes words that do not exist in the general word database and the historical selection database;

[0079] The output module 804 is used to output the return results corresponding to the multiple parsed words.

[0080] Optionally, the parsing module 802 is specifically used for:

[0081] Splitting each Chinese character in the search term according to radicals to obtain multiple Chinese character elements corresponding to the search term;

[0082] The multiple Chinese character elements are combined to obtain the multiple parsed words.

[0083] Optionally, the determination module 803 is specifically configured to:

[0084] Matching each of the plurality of resolved words with a word in each word database;

[0085] Determine the vocabulary database to which the parsed vocabulary belongs according to the matching result;

[0086] According to the vocabulary database to which the parsed vocabulary belongs, a return result corresponding to the parsed vocabulary is determined.

[0087] Optionally, the determination module 803 is specifically configured to:

[0088] If the parsed vocabulary belongs to the general vocabulary database, it is determined that the returned result corresponding to the parsed vocabulary includes the search result of the parsed vocabulary and first indication information, where the first indication information is used to indicate that the parsed vocabulary belongs to the general vocabulary database.

[0089] Optionally, the determination module 803 is specifically configured to:

[0090] If the parsed word belongs to the historical selection database, it is determined that the returned result corresponding to the parsed word includes the search result of the parsed word and second indication information, where the second indication information is used to indicate that the parsed word belongs to the historical selection database.

[0091] Optionally, the returned result corresponding to the parsed word also includes third indication information, and the third indication information is used to indicate the number of times the parsed word is selected.

[0092] Optionally, the determination module 803 is specifically configured to:

[0093] If the parsed word belongs to the abnormal word database, it is determined that the returned result corresponding to the parsed word includes fourth indication information, and the fourth indication information is used to indicate that the parsed word belongs to the abnormal word database.

[0094] Optionally, the determination module 803 is further configured to:

[0095] If the parsed word does not belong to the word database, the parsed word is added to the abnormal word database.

[0096] Figure 8 The search device shown can be used to execute the search method in any of the above method embodiments. Its implementation principle and technical effect are similar and will not be described in detail here.

[0097] Fig. 9 This is a schematic diagram of the hardware structure of the terminal device provided in this application. Fig. 9 As shown, the terminal device of this embodiment may include:

[0098] The memory 901 is used to store program instructions.

[0099] The processor 902 is used to implement the steps in any of the above method embodiments when the program instructions are executed. The implementation principles and technical effects are similar and will not be described in detail here.

[0100] The present application provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented. The implementation principles and technical effects are similar and will not be described in detail here.

[0101] The present application also provides a program product, the program product includes a computer program, the computer program is stored in a readable storage medium, at least one processor can read the computer program from the readable storage medium, and the at least one processor executes the computer program so that the processor implements the steps in any of the above method embodiments. The implementation principle and technical effect are similar and will not be repeated here.

[0102] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0103] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0104] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0105] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (English: Read-Only Memory, abbreviated: ROM), random access memory (English: Random Access Memory, abbreviated: RAM), disk or optical disk and other media that can store program codes.

[0106] It should be understood that the processor described in this application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this application can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0107] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A search method, characterized in that: include: Receive search terms input by users; Parsing the search term to obtain a plurality of parsed words; Determine the return result corresponding to each parsed word according to the multiple parsed words and the word database, the word database includes: a general word database, a historical selection database and an abnormal word database, the historical selection database includes words previously selected by the user, and the abnormal word database includes words that do not exist in the general word database and the historical selection database; Outputting the return results corresponding to the multiple parsed words; The search term is parsed to obtain a plurality of parsed words, including: Splitting each Chinese character in the search term according to radicals to obtain a plurality of Chinese character elements corresponding to the search term; wherein the Chinese character elements include Chinese characters converted from radicals; Combining the multiple Chinese character elements to obtain the multiple parsed words; The step of determining the return result corresponding to each parsed word according to the plurality of parsed words and the word database comprises: Matching each of the plurality of resolved words with a word in each vocabulary database; According to the matching result, determining the vocabulary database to which the parsed vocabulary belongs; According to the vocabulary database to which the parsed vocabulary belongs, a return result corresponding to the parsed vocabulary is determined, the return result including search results and indication information of the parsed vocabulary, the indication information being used to indicate the vocabulary database to which the parsed vocabulary belongs.

2. The method according to claim 1, characterized in that The step of determining the return result corresponding to the parsed vocabulary according to the vocabulary database to which the parsed vocabulary belongs includes: If the parsed vocabulary belongs to the general vocabulary database, it is determined that the returned result corresponding to the parsed vocabulary includes the search result of the parsed vocabulary and first indication information, where the first indication information is used to indicate that the parsed vocabulary belongs to the general vocabulary database.

3. The method according to claim 1, characterized in that The step of determining the return result corresponding to the parsed vocabulary according to the vocabulary database to which the parsed vocabulary belongs includes: If the parsed word belongs to the historical selection database, it is determined that the returned result corresponding to the parsed word includes the search result of the parsed word and second indication information, where the second indication information is used to indicate that the parsed word belongs to the historical selection database.

4. The method according to claim 3, characterized in that The returned result corresponding to the parsed word also includes third indication information, and the third indication information is used to indicate the number of times the parsed word is selected.

5. The method according to claim 1, characterized in that The step of determining the return result corresponding to the parsed vocabulary according to the vocabulary database to which the parsed vocabulary belongs includes: If the parsed word belongs to the abnormal word database, it is determined that the returned result corresponding to the parsed word includes fourth indication information, and the fourth indication information is used to indicate that the parsed word belongs to the abnormal word database.

6. The method according to claim 1, characterized in that The method further comprises: If the parsed word does not belong to the word database, the parsed word is added to the abnormal word database.

7. A search device, characterized in that: include: A receiving module, used for receiving a search term input by a user; A parsing module, used for parsing the search term to obtain a plurality of parsed words; A determination module, configured to determine a return result corresponding to each parsed word according to the plurality of parsed words and the word database, wherein the word database comprises: a general word database, a historical selection database and an abnormal word database, wherein the historical selection database comprises words previously selected by the user, and the abnormal word database comprises words not existing in the general word database and the historical selection database; An output module, used for outputting the return results corresponding to the plurality of parsed words; The parsing module is specifically used to split each Chinese character in the search term according to radicals to obtain multiple Chinese character elements corresponding to the search term; wherein the Chinese character elements include Chinese characters converted from radicals; Combining the multiple Chinese character elements to obtain the multiple parsed words; The determination module is specifically configured to match each parsed word in the plurality of parsed words with a word in each vocabulary database; Determine the vocabulary database to which the parsed vocabulary belongs according to the matching result; According to the vocabulary database to which the parsed vocabulary belongs, a return result corresponding to the parsed vocabulary is determined, the return result including search results and indication information of the parsed vocabulary, the indication information being used to indicate the vocabulary database to which the parsed vocabulary belongs.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. A terminal device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to implement the method according to any one of claims 1 to 6 by executing the executable instructions.

Images