Information search method and device, electronic equipment and storage medium

Abstract

The invention discloses an information search method and device, electronic equipment and a storage medium, and relates to the technical field of natural language processing. A specific embodiment of the method comprises the steps of obtaining a corresponding search text in response to a search instruction; obtaining each to-be-processed result associated with the search text and description information of each to-be-processed result from a preset search library; calling a preset word segmentation combination template, and performing word segmentation on the search text to determine a word segmentation combination corresponding to the search text; and calling a preset calculation model, calculating the correlation degree between the word segmentation combination and each piece of description information, and determining a search result corresponding to the search instruction from the to-be-processed result and sending the search result. According to the embodiment, the problems that in some application scenes, the search method cannot reflect the importance of some specific words, so that the search result accuracy is low, and the information search efficiency is reduced can be solved.

Description

Technical Field

[0001] The present invention relates to the field of natural language processing technology, and in particular to an information search method, device, electronic device and storage medium. Background Art

[0002] Information search has been applied in various scenarios. In a common information search scenario, after the user enters the search information, the corresponding results can be recalled from the preset dictionary. In the related technology, the BM (Best Match) 25 algorithm can be used to calculate the similarity between the search information and the information in the dictionary to obtain the search results. However, in some application scenarios, such as doctor information search scenarios, medical-related words such as disease words and department words are more important, which cannot be reflected by the BM25 algorithm, so the accuracy of the search results is low, which reduces the efficiency of information search. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides an information search method, device, electronic device and storage medium, which can solve the problem that in some application scenarios, the search method cannot reflect the importance of some specific words, resulting in low accuracy of search results and reduced information search efficiency.

[0004] To achieve the above objective, according to one aspect of an embodiment of the present invention, a method for information search is provided.

[0005] An information search method according to an embodiment of the present invention includes: obtaining corresponding search text in response to a search instruction;

[0006] Acquire each to-be-processed result associated with the search text and description information of each to-be-processed result from a preset search library;

[0007] Calling a preset word segmentation combination template to segment the search text to determine the word segmentation combination corresponding to the search text;

[0008] A preset calculation model is called to calculate the correlation between the word segmentation combination and each of the description information, so as to determine the search result corresponding to the search instruction from the results to be processed and send it.

[0009] In one embodiment, calculating the association between the word combination and each of the description information includes:

[0010] Each participle in the participle combination is matched with the description information of each of the results to be processed in turn, and the matching degree between each participle and each of the results to be processed is obtained to determine the correlation between the participle combination and each of the description information.

[0011] In yet another embodiment, each segmentation in the segmentation combination is matched with the description information of each of the results to be processed in turn to obtain the matching degree between each segmentation and each of the results to be processed, including:

[0012] For each word segmentation, the word segmentation is split into single characters, and the occurrence position of each single character is determined from each of the description information, so as to determine the character interval between the occurrence positions of adjacent single characters based on the order of each single character in the word segmentation, and obtain the matching degree between the word segmentation and each of the results to be processed.

[0013] In yet another embodiment, each segmentation in the segmentation combination is matched with the description information of each of the results to be processed in turn to obtain the matching degree between each segmentation and each of the results to be processed, including:

[0014] For each participle, the corresponding associated participle is obtained from a preset knowledge base, so as to match the participle and the associated participle with the description information of each of the results to be processed in turn, and obtain the matching degree between each participle and each of the results to be processed.

[0015] In yet another embodiment, the word segment combination includes a plurality of;

[0016] Calculating the correlation between the word combination and the description information includes:

[0017] The number of segmented words included in each of the multiple segmented word combinations is obtained to screen a target grouping combination, and the correlation between the target segmented word combination and the description information is calculated.

[0018] In yet another embodiment, the word segment combination includes a plurality of;

[0019] Calculating the correlation between the word combination and the description information to determine the search result corresponding to the processing instruction from the results to be processed, including:

[0020] Calculating the correlation between each of the word combinations and each of the description information;

[0021] For each of the description information, a corresponding statistical value is calculated based on the relevance to determine a total relevance value of the results to be processed, so as to determine the search result corresponding to the processing instruction from the results to be processed.

[0022] In yet another embodiment, determining and sending the search result corresponding to the processing instruction from the results to be processed includes:

[0023] Determine the to-be-processed results whose corresponding relevance is greater than a preset value as the search results corresponding to the processing instruction, and determine the arrangement order of the search results based on the relevance;

[0024] The search results and the arrangement order are sent.

[0025] To achieve the above objective, according to another aspect of an embodiment of the present invention, a device for information search is provided.

[0026] An information search device according to an embodiment of the present invention includes: an acquisition unit, configured to acquire corresponding search text in response to a search instruction;

[0027] A search unit, used for obtaining each to-be-processed result associated with the search text and description information of each to-be-processed result from a preset search library;

[0028] A word segmentation unit is used to call a preset word segmentation combination template to segment the search text to determine the word segmentation combination corresponding to the search text;

[0029] The determination unit is used to call a preset calculation model to calculate the correlation between the word combination and each of the description information, so as to determine the search result corresponding to the processing instruction from the results to be processed and send it.

[0030] In one embodiment, the determining unit is specifically configured to:

[0031] Each participle in the participle combination is matched with the description information of each of the results to be processed in turn, and the matching degree between each participle and each of the results to be processed is obtained to determine the correlation between the participle combination and each of the description information.

[0032] In yet another embodiment, the determining unit is specifically configured to:

[0033] For each word segmentation, the word segmentation is split into single characters, and the occurrence position of each single character is determined from each of the description information, so as to determine the character interval between the occurrence positions of adjacent single characters based on the order of each single character in the word segmentation, and obtain the matching degree between the word segmentation and each of the results to be processed.

[0034] In yet another embodiment, the determining unit is specifically configured to:

[0035] For each participle, the corresponding associated participle is obtained from a preset knowledge base, so as to match the participle and the associated participle with the description information of each of the results to be processed in turn, and obtain the matching degree between each participle and each of the results to be processed.

[0036] In yet another embodiment, the word segment combination includes a plurality of;

[0037] The determining unit is specifically configured to:

[0038] The number of segmented words included in each of the multiple segmented word combinations is obtained to screen a target grouping combination, and the correlation between the target segmented word combination and the description information is calculated.

[0039] In yet another embodiment, the word segment combination includes a plurality of;

[0040] The determining unit is specifically configured to:

[0041] Calculating the correlation between each of the word combinations and each of the description information;

[0042] For each of the description information, a corresponding statistical value is calculated based on the relevance to determine a total relevance value of the results to be processed, so as to determine the search result corresponding to the processing instruction from the results to be processed.

[0043] In yet another embodiment, the determining unit is specifically configured to:

[0044] Determine the to-be-processed results whose corresponding relevance is greater than a preset value as the search results corresponding to the processing instruction, and determine the arrangement order of the search results based on the relevance;

[0045] The search results and the arrangement order are sent.

[0046] To achieve the above objective, according to another aspect of an embodiment of the present invention, an electronic device is provided.

[0047] An electronic device according to an embodiment of the present invention includes: 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 search method provided by the embodiment of the present invention.

[0048] To achieve the above objective, according to another aspect of an embodiment of the present invention, a computer readable medium is provided.

[0049] A computer-readable medium according to an embodiment of the present invention stores a computer program, and when the program is executed by a processor, the information search method provided by the embodiment of the present invention is implemented.

[0050] To achieve the above objective, according to another aspect of an embodiment of the present invention, a computer program product is provided.

[0051] A computer program product according to an embodiment of the present invention includes a computer program, and when the program is executed by a processor, the information search method provided by the embodiment of the present invention is implemented.

[0052] One embodiment of the above invention has the following advantages or beneficial effects: In the embodiment of the present invention, for a search instruction, each result to be processed and the description information of each result to be processed associated with the search text can be first obtained in the preset search library, and then the search text can be segmented to obtain the corresponding segmentation combination to calculate the correlation between the segmentation combination and each description information, that is, to obtain the correlation between the search text and each result to be processed, and then the search result corresponding to the search instruction can be determined and sent. In the embodiment of the present invention, after each result to be processed is obtained from the preset search library, the search text can also be segmented to calculate the correlation between the segmentation combination and each description information again, that is, the correlation between the search text and the result to be processed can be further determined, and then the search result can be determined. In this way, the search results are obtained by combining the correlation obtained and calculated by the search library, thereby improving the accuracy of the search results and the efficiency of information search.

[0053] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with specific implementation examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0055] Figure 1 is a schematic diagram of a main process of the information search method according to an embodiment of the present invention;

[0056] Figure 2 is a schematic diagram of another main process of the information search method according to an embodiment of the present invention;

[0057] Figure 3 is a schematic diagram of another main process of the information search method according to an embodiment of the present invention;

[0058] Figure 4 is a schematic diagram of main units of an apparatus for information search according to an embodiment of the present invention;

[0059] Figure 5 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0060] Figure 6 It is a schematic diagram of the structure of a computer system suitable for implementing the embodiment of the present invention. DETAILED DESCRIPTION

[0061] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0062] It should be noted that the embodiments and features of the embodiments of the present invention can be combined with each other without conflict. The acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations.

[0063] An embodiment of the present invention provides an information search system, which can be used in a scenario of searching for information, and specifically, can be used in a scenario of searching for doctor information.

[0064] The embodiment of the present invention provides a method for information search, which can be executed by an information search system. Figure 1 As shown, the method includes:

[0065] S101: In response to a search instruction, obtain a corresponding search text.

[0066] In an embodiment of the present invention, the information search system can be connected to other devices to receive search instructions input by other devices. For example, the information search system can be connected to a user's terminal device, and the user can send search instructions through the terminal device; or, the information search system can be provided with a display device to display a search interface, and can receive search instructions input through the search interface.

[0067] After receiving the search instruction, the information search system responds and can obtain the search text corresponding to the search instruction, wherein the search text can be carried in the search instruction. The search text represents the query (search word) used for the search.

[0068] S102: Acquire each to-be-processed result associated with the search text and description information of each to-be-processed result from a preset search library.

[0069] Among them, the search library is pre-set and used for information search. The search library may include preset possible search results and description information of each possible search result, and the description information may include detailed descriptions of the corresponding results. In the embodiment of the present invention, taking the doctor search scenario as an example, the preset search library may include the names of each doctor and the description information corresponding to each doctor's name. For example, the doctor's name may include: Zhang San, and the corresponding description information may include: Doctor Zhang San, in a district hospital, provides diagnosis and treatment services to the people, and is good at coughing.

[0070] In the embodiments of the present invention, a search method can be set in a preset search library. In this step, various to-be-processed results associated with the search text can be obtained from the preset search library through the preset search method, and the description information of the to-be-processed results can also be obtained.

[0071] In the doctor search scenario, after the preset search library performs word segmentation on the search text by using an open-source word segmentation method and a medical core dictionary, corresponding results, that is, the to-be-processed results, can be recalled from the search library.

[0072] For example, the search text can be "A and B People's Hospital cough". Since fine-grained word segmentation can ensure sufficient recall volume, the search text can be segmented into "A and B / People / Hospital / cough". Then, through the search, the recalled to-be-processed results can be obtained: Doctor A, Doctor B, and Doctor C. Among them, the description information of Doctor A is: Doctor A in a certain district hospital, providing medical services for the people, being good at treating coughs and gynecology; the description information of Doctor B is: having interned at A and B People's Hospital and being good at treating coughs, internal medicine; the description information of Doctor C is: having interned at A and B People's Hospital and being good at treating coughs, orthopedics.

[0073] It should be noted that in the embodiments of the present invention, the search method set in the preset search library is not limited.

[0074] S103: Invoke a preset word segmentation combination template to perform word segmentation on the search text to determine the word segmentation combination corresponding to the search text.

[0075] Among them, in the embodiments of the present invention, a knowledge base can be preset. The knowledge base can include terms for word segmentation corresponding to application scenarios. Each term for word segmentation can be classified and combined according to the application scenario, so as to obtain a word segmentation combination template, which is convenient for determining the combination method of the search text based on the word segmentation combination template.

[0076] In the doctor search scenario, the terms for word segmentation in the knowledge base can be stored in the form shown in Table 1. In Table 1, for the term "cold" for word segmentation, it belongs to the disease type, and corresponding synonyms and corresponding departments are set. In this way, each term for word segmentation in the doctor search scenario is stored in the knowledge base. At the same time, based on the medical scenario, a word segmentation combination template can be set according to the type to which each term for word segmentation belongs. For example, the word segmentation combination template can include: disease, department, hospital name, disease + department, person name + department, disease + hospital, hospital + symptom, etc.

[0077] Table 1

[0078] Participle type Synonyms Corresponding department cold disease Wind Chill Internal Medicine

[0079] It should be noted that in the embodiments of the present invention, the storage form of word segmentation in the knowledge base can be set based on requirements. For the storage form shown in Table 1, it can be empty when there are no synonyms or corresponding departments for the word segmentation.

[0080] In the embodiments of the present invention, through the knowledge base and the word segmentation combination template, methods such as forward longest matching can be used to segment the search text to obtain the word segmentation combination corresponding to the search text. For example, if the search text is "A and B People's Hospital", it can be segmented into "A and B People's Hospital / cough", and the corresponding analysis combination template is "hospital + symptom", so the word segmentation combination "A and B People's Hospital / cough" can be obtained.

[0081] S104: Call a preset calculation model to calculate the correlation degree between the word segmentation combination and each description information, so as to determine the search result corresponding to the search instruction from the results to be processed and send it.

[0082] Among them, the calculation model is preset in advance. After obtaining the word segmentation combination of the search text, the correlation degree between it and the description information corresponding to each result to be processed can be calculated, that is, the correlation degree between the word segmentation combination and the result to be processed can be determined. Furthermore, based on the level of the correlation degree, the search result corresponding to the search instruction can be determined from the results to be processed, so as to send the search result and return the result of the search instruction to the user.

[0083] Specifically, generally, the higher the correlation degree, the higher the possibility that the result to be processed becomes the search result. Therefore, in this step, the results to be processed with a correlation degree greater than the preset value in the correlation degree corresponding to the results to be processed can be determined as the search results corresponding to the processing instruction, and the sorting order of the search results can be determined based on the size of the correlation degree corresponding to the search results. Then, the search results and the sorting order are sent to improve the accuracy of the search results.

[0084] In one implementation manner, the word segmentation combination represents the word segmentation method in the search text, and thus the included word segments can be determined. In this step, for each word segment in the word segmentation combination, the matching degree between it and each description information can be calculated, and then the correlation degree between the word segmentation combination and the description information can be determined based on the matching degree. Therefore, the calculation of the correlation degree in this step can be performed as follows: Each word segment in the word segmentation combination is sequentially matched with the description information of each result to be processed to obtain the matching degree between each word segment and each result to be processed, so as to determine the correlation degree between the word segmentation combination and the description information.

[0085] For example, for the word segmentation combination "A and B People's Hospital / cough", the "A and B People's Hospital" can be first matched with the description information of each result to be processed to obtain the matching degree between it and each result to be processed; then, "cough" can be matched with the description information of each result to be processed to obtain the matching degree between it and each result to be processed; and then, the matching degree between each description information and "A and B People's Hospital" and "cough" can be respectively corresponding to determine the association degree between each description information and the word segmentation combination.

[0086] Specifically, in the embodiment of the present invention, the method for matching the word segmentation with the description information may be to identify the word segmentation characters appearing in the description information, and then determine the matching degree according to the continuity of the word segmentation characters appearing in the description information. Therefore, the steps for calculating the matching degree between the word segmentation and the description information can be performed as follows: for each word segmentation, the word segmentation is split into each single character, the appearance positions of each single character are determined from each description information, and based on the sorting of each single character in the word segmentation, the character interval between the appearance positions of adjacent single characters is determined to obtain the matching degree between the word segmentation and each result to be processed.

[0087] The closer the appearance order of each single character in the description information is to the sorting of each single character in the word segmentation, the higher the matching degree between the description information and the word segmentation, and the fewer the character intervals between the appearance positions of adjacent single characters in the description information, the higher the matching degree between the description information and the word segmentation.

[0088] For example, for the word segmentation of "A and B People's Hospital", each single character in it can be matched with the description information. For example, the results to be processed include Doctor A, Doctor B, and Doctor C. Each single character in the word segmentation of "A and B People's Hospital" is respectively matched with the description information corresponding to Doctor A, Doctor B, and Doctor C. Among them, the result of matching "A and B People's Hospital" with the description information of Doctor A is that: "A and B", "People", and "Hospital" appear in the description information, but the appearance order of the three in the description information is different from the arrangement order in the word segmentation, and there are character intervals between the appearance positions of the three; the results of matching "A and B People's Hospital" with the description information of Doctor B and Doctor C are both that: "A and B People's Hospital" appears in the description information, the appearance order in the description information is the same as the arrangement order in the word segmentation, and there are no character intervals between the appearance positions. From this, it can be shown that the matching degree between the word segmentation "A and B People's Hospital" and the description information of Doctor B and Doctor C is higher than the matching degree between it and the description information of Doctor A.

[0089] It should be noted that in the embodiments of the present invention, a matching level and a matching degree corresponding to each matching level can be set. For example, in the embodiments of the present invention, it can be set that if the single characters of a word segmentation appear continuously in the description information in the order in the word segmentation, it can be determined that the word segmentation and the description file belong to sequential continuous matching, and the matching degree is determined to be 1; if the single characters of the word segmentation do not appear continuously in the description information in the order in the word segmentation, the matching degree is determined to be 0.5; for other cases except the above two, the matching degree can be determined to be 0. In this way, the matching degree between each word segmentation and the description information can be obtained. For the matching degrees of each word segmentation in the word segmentation combination corresponding to the description information of a to-be-processed result, the minimum value of the matching degrees can be determined as the correlation degree between the description information and the word segmentation combination, that is, the correlation degree between the to-be-processed result and the word segmentation combination. Taking the above example as an example, it can be determined that when "A and B People's Hospital" matches the description information of Doctor A, the order of appearance of "A and B", "People", and "Hospital" in the description information is different from the arrangement order in the word segmentation, so the matching degree can be determined to be 0; when "A and B People's Hospital" matches the description information of Doctor B and Doctor C, the order of appearance of "A and B People's Hospital" in the description information is the same as the arrangement order in the word segmentation, and there is no character interval between the appearance positions, so the matching degree can be determined to be 1.

[0090] In still other embodiments, in the knowledge base, the associated words of each word segmentation can also be stored for each word segmentation. As shown in Table 1, the associated words of the word segmentation can include synonyms and corresponding departments. Therefore, when calculating the matching degree between each word segmentation and each of the to-be-processed results, the following can be executed: for each word segmentation, obtain the corresponding associated word segmentations from the preset knowledge base, and sequentially match the word segmentation and the associated word segmentations with the description information of each to-be-processed result to obtain the matching degree between each word segmentation and each to-be-processed result. Specifically, the minimum value among the matching degrees between the word segmentation and the associated word segmentations and the description information of each to-be-processed result in sequence can be determined as the matching degree between the word segmentation and the description information of each to-be-processed result.

[0091] In still other embodiments, the word segmentation combinations obtained in step S103 may include multiple. For example, if the search text is "A and B People's Hospital cough", the word segmentation combinations obtained may include "A and B People's Hospital / cough" and "A and B / People's Hospital / cough".

[0092] In the scenario where the search text corresponds to a plurality of word combinations, on the one hand, the step of calculating the relevance can be performed as follows: obtaining the number of word combinations included in each word combination in the plurality of word combinations to screen the target word combination, and calculating the relevance between the target word combination and the description information. Since the fewer word combinations the search text corresponds to, the closer its meaning is to the meaning of the search text, in this step, the word combination with the smallest number of word combinations can be determined from the plurality of word combinations to be the target word combination, and then calculating the relevance between the target word combination and the description information, that is, executing step S104 on the target word combination,

[0093] In the scenario where the search text corresponds to a plurality of word combinations, on the other hand, step S104 can be specifically performed as follows: calculating the degree of association between each word combination and each description information; for each description information, calculating the corresponding statistical value based on the degree of association to determine the total value of the degree of association of the result to be processed, so as to determine the search result corresponding to the processing instruction from the result to be processed. In step S104, the degree of association between each word combination and each description information can be calculated first, and then the statistical value corresponding to the degree of association of each description information can be calculated to determine the total value of the degree of association of the description information corresponding to the result to be processed, so as to determine the search result based on the total value of the degree of association of each result to be processed. The statistical value can be specifically an average value, a minimum value, etc.

[0094] In an embodiment of the present invention, after obtaining each result to be processed from a preset search library, the search text can also be segmented to recalculate the correlation with each description information through word segmentation combination, that is, the correlation between the search text and the result to be processed can be further determined, and then the search result can be determined. In this way, the search result is obtained by combining the correlation obtained and calculated by the search library, thereby improving the accuracy of the search results and the efficiency of information search.

[0095] Combine the following Figure 1 The embodiment shown in the figure specifically describes the information search method in the embodiment of the present invention. Figure 2 As shown, the method includes:

[0096] S201: In response to a search instruction, obtain a corresponding search text.

[0097] S202: Acquire each to-be-processed result associated with the search text and description information of each to-be-processed result from a preset search library.

[0098] S203: calling a preset word segmentation combination template to segment the search text to determine a plurality of word segmentation combinations corresponding to the search text.

[0099] S204: Obtain the number of segmented words included in each segmented word combination in the multiple segmented word combinations to screen out the target grouping combination.

[0100] S205: Match each segmentation in the target segmentation combination with the description information of each result to be processed in turn, obtain the matching degree between each segmentation and each result to be processed, so as to determine the correlation between the target segmentation combination and each description information.

[0101] S206: Determine the search result corresponding to the search instruction from the results to be processed based on the relevance, and send the search result.

[0102] It should be noted that the data processing principle in the embodiment of the present invention is the same as Figure 1 The corresponding data processing principles in the illustrated embodiments are the same and will not be described in detail here.

[0103] Combine the following Figure 1 The embodiment shown in the figure specifically describes the information search method in the embodiment of the present invention. Figure 3 As shown, the method includes:

[0104] S301: In response to a search instruction, obtain a corresponding search text.

[0105] S302: Acquire each to-be-processed result associated with the search text and description information of each to-be-processed result from a preset search library.

[0106] S303: calling a preset word segmentation combination template to segment the search text to determine the word segmentation combination corresponding to the search text.

[0107] S304: Match each segmentation in the segmentation combination with the description information of each result to be processed in turn, and obtain the matching degree between each segmentation and each result to be processed.

[0108] S305: For each description information, determine the minimum value in the corresponding matching degree as the correlation between the description information and the word combination.

[0109] S306: Determine the to-be-processed results whose corresponding relevance is greater than a preset value as the search results corresponding to the processing instruction, and determine the arrangement order of the search results based on the relevance.

[0110] S307: Send the search results and the sorting order.

[0111] It should be noted that the data processing principle in the embodiment of the present invention is the same as Figure 1 The corresponding data processing principles in the illustrated embodiments are the same and will not be described in detail here.

[0112] In order to solve the problems existing in the prior art, an embodiment of the present invention provides an information search device 400, such as Figure 4 As shown, the device 400 includes:

[0113] The acquisition unit 401 is used to acquire the corresponding search text in response to the search instruction;

[0114] A search unit 402, configured to obtain, from a preset search library, each result to be processed associated with the search text and description information of each result to be processed;

[0115] The word segmentation unit 403 is used to call a preset word segmentation combination template to segment the search text to determine the word segmentation combination corresponding to the search text;

[0116] The determination unit 404 is used to call a preset calculation model to calculate the correlation between the word combination and each of the description information, so as to determine the search result corresponding to the processing instruction from the results to be processed and send it.

[0117] It should be understood that the manner of implementing the embodiments of the present invention is different from the Figure 1 The method of the illustrated embodiment is the same and will not be repeated here.

[0118] In one embodiment, the determining unit 404 is specifically configured to:

[0119] Each participle in the participle combination is matched with the description information of each of the results to be processed in turn, and the matching degree between each participle and each of the results to be processed is obtained to determine the correlation between the participle combination and each of the description information.

[0120] In yet another embodiment, the determining unit 404 is specifically configured to:

[0121] For each word segmentation, the word segmentation is split into single characters, and the occurrence position of each single character is determined from each of the description information, so as to determine the character interval between the occurrence positions of adjacent single characters based on the order of each single character in the word segmentation, and obtain the matching degree between the word segmentation and each of the results to be processed.

[0122] In yet another embodiment, the determining unit 404 is specifically configured to:

[0123] For each participle, the corresponding associated participle is obtained from a preset knowledge base, so as to match the participle and the associated participle with the description information of each of the results to be processed in turn, and obtain the matching degree between each participle and each of the results to be processed.

[0124] In yet another embodiment, the word segment combination includes a plurality of;

[0125] The determining unit 404 is specifically configured to:

[0126] The number of segmented words included in each of the multiple segmented word combinations is obtained to screen a target grouping combination, and the correlation between the target segmented word combination and the description information is calculated.

[0127] In yet another embodiment, the word segment combination includes a plurality of;

[0128] The determining unit 404 is specifically configured to:

[0129] Calculating the correlation between each of the word combinations and each of the description information;

[0130] For each of the description information, a corresponding statistical value is calculated based on the relevance to determine a total relevance value of the results to be processed, so as to determine the search result corresponding to the processing instruction from the results to be processed.

[0131] In yet another embodiment, the determining unit 404 is specifically configured to:

[0132] Determine the to-be-processed results whose corresponding relevance is greater than a preset value as the search results corresponding to the processing instruction, and determine the arrangement order of the search results based on the relevance;

[0133] The search results and the arrangement order are sent.

[0134] It should be understood that the manner of implementing the embodiments of the present invention is different from the Figure 1 , 2 , and 3 are the same as the embodiments shown in FIG. 3 and will not be described again here.

[0135] In an embodiment of the present invention, after obtaining each result to be processed from a preset search library, the search text can also be segmented to recalculate the correlation with each description information through word segmentation combination, that is, the correlation between the search text and the processing result can be further determined, and then the search result can be determined. In this way, the search result is obtained by combining the correlation obtained and calculated by the search library, thereby improving the accuracy of the search results and the efficiency of new searches.

[0136] According to an embodiment of the present invention, the embodiment of the present invention further provides an electronic device and a readable storage medium.

[0137] The electronic device of an embodiment of the present invention includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the one processor, and the instructions are executed by the at least one processor so that the at least one processor executes the information search method provided by the embodiment of the present invention.

[0138] Figure 5An exemplary system architecture 500 is shown to which the information search method or information search apparatus according to the embodiment of the present invention may be applied.

[0139] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, 503, a network 504 and a server 505. Network 504 is used to provide a medium for communication links between terminal devices 501, 502, 503 and server 505. Network 504 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0140] The user can use the terminal devices 501, 502, 503 to interact with the server 505 through the network 504 to receive or send messages, etc. Various client applications can be installed on the terminal devices 501, 502, 503.

[0141] The terminal devices 501 , 502 , and 503 may be, but are not limited to, smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0142] The server 505 may be a server that provides various services. The server may analyze and process the received data such as the product information query request, and feed back the processing result (such as product information - just an example) to the terminal device.

[0143] It should be noted that the information search method provided in the embodiment of the present invention is generally executed by the server 505 , and accordingly, the information search device is generally set in the server 505 .

[0144] It should be understood that Figure 5 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0145] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer system 600 suitable for implementing an embodiment of the present invention. Figure 6 The computer system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0146] like Figure 6As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0147] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0148] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present invention are executed.

[0149] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0150] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a unit, a program segment, or a part of a code, and the above-mentioned unit, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0151] The units involved in the embodiments of the present invention may be implemented by software or hardware. The units described may also be arranged in a processor, for example, it may be described as: a processor includes an acquisition unit, a search unit, a word segmentation unit, and a determination unit. The names of these units do not constitute a limitation on the units themselves in some cases, for example, the acquisition unit may also be described as a "unit of text acquisition function".

[0152] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device executes the information search method provided by the present invention.

[0153] As another aspect, the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the information search method provided by an embodiment of the present invention.

[0154] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for information search, characterized in that: include: In response to the search instruction, obtaining the corresponding search text; Acquire each to-be-processed result associated with the search text and description information of each to-be-processed result from a preset search library; Calling a preset word segmentation combination template to segment the search text to determine the word segmentation combination corresponding to the search text; A preset calculation model is called to calculate the correlation between the word segmentation combination and each of the description information, so as to determine the search result corresponding to the search instruction from the results to be processed and send it.

2. The method according to claim 1, characterized in that Calculating the correlation between the word combination and each of the description information includes: Each participle in the participle combination is matched with the description information of each of the results to be processed in turn, and the matching degree between each participle and each of the results to be processed is obtained to determine the correlation between the participle combination and each of the description information.

3. The method according to claim 2, characterized in that Matching each participle in the participle combination with the description information of each of the results to be processed in turn to obtain a matching degree between each participle and each of the results to be processed, including: For each word segmentation, the word segmentation is split into single characters, and the occurrence position of each single character is determined from each of the description information, so as to determine the character interval between the occurrence positions of adjacent single characters based on the order of each single character in the word segmentation, and obtain the matching degree between the word segmentation and each of the results to be processed.

4. The method according to claim 2, characterized in that: Matching each participle in the participle combination with the description information of each of the results to be processed in turn to obtain a matching degree between each participle and each of the results to be processed, including: For each participle, the corresponding associated participle is obtained from a preset knowledge base, so as to match the participle and the associated participle with the description information of each of the results to be processed in turn, and obtain the matching degree between each participle and each of the results to be processed.

5. The method according to claim 1, characterized in that The participle combination includes multiple; Calculating the correlation between the word combination and the description information includes: The number of segmented words included in each of the multiple segmented word combinations is obtained to screen a target grouping combination, and the correlation between the target segmented word combination and the description information is calculated.

6. The method according to claim 1, characterized in that The participle combination includes multiple; Calculating the correlation between the word combination and the description information to determine the search result corresponding to the processing instruction from the results to be processed, including: Calculating the correlation between each of the word combinations and each of the description information; For each of the description information, a corresponding statistical value is calculated based on the relevance to determine a total relevance value of the results to be processed, so as to determine the search result corresponding to the processing instruction from the results to be processed.

7. The method according to claim 1, characterized in that Determining the search result corresponding to the processing instruction from the results to be processed and sending the search result includes: Determine the to-be-processed results whose corresponding relevance is greater than a preset value as the search results corresponding to the processing instruction, and determine the arrangement order of the search results based on the relevance; The search results and the arrangement order are sent.

8. An information search device, characterized in that: include: An acquisition unit, configured to acquire corresponding search text in response to a search instruction; A search unit, used for obtaining each to-be-processed result associated with the search text and description information of each to-be-processed result from a preset search library; A word segmentation unit is used to call a preset word segmentation combination template to segment the search text to determine the word segmentation combination corresponding to the search text; The determination unit is used to call a preset calculation model to calculate the correlation between the word combination and each of the description information, so as to determine the search result corresponding to the processing instruction from the results to be processed and send it.

9. The device according to claim 8, characterized in that The determining unit is specifically configured to: Each participle in the participle combination is matched with the description information of each of the results to be processed in turn, and the matching degree between each participle and each of the results to be processed is obtained to determine the correlation between the participle combination and each of the description information.

10. The device according to claim 9, characterized in that The determining unit is specifically configured to: For each word segmentation, the word segmentation is split into single characters, and the occurrence position of each single character is determined from each of the description information, so as to determine the character interval between the occurrence positions of adjacent single characters based on the order of each single character in the word segmentation, and obtain the matching degree between the word segmentation and each of the results to be processed.

11. The device according to claim 9, characterized in that The determining unit is specifically configured to: For each participle, the corresponding associated participle is obtained from a preset knowledge base, so as to match the participle and the associated participle with the description information of each of the results to be processed in turn, and obtain the matching degree between each participle and each of the results to be processed.

12. The device according to claim 8, characterized in that The participle combination includes multiple; The determining unit is specifically configured to: The number of segmented words included in each of the multiple segmented word combinations is obtained to screen a target grouping combination, and the correlation between the target segmented word combination and the description information is calculated.

13. The device according to claim 8, characterized in that The participle combination includes multiple; The determining unit is specifically configured to: Calculating the correlation between each of the word combinations and each of the description information; For each of the description information, a corresponding statistical value is calculated based on the relevance to determine a total relevance value of the results to be processed, so as to determine the search result corresponding to the processing instruction from the results to be processed.

14. The device according to claim 8, characterized in that The determining unit is specifically configured to: Determine the to-be-processed results whose corresponding relevance is greater than a preset value as the search results corresponding to the processing instruction, and determine the arrangement order of the search results based on the relevance; The search results and the arrangement order are sent.

15. An electronic 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 method according to any one of claims 1 to 7.

16. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images