Data recommendation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a data recommendation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a to-be-processed retrieval field; segmenting the to-be-processed retrieval field to obtain at least one fuzzy segmented word group; if it is determined that the numerical value of each fuzzy segmented word group is smaller than the target list length, performing fuzzy matching processing on at least one fuzzy segmented word group based on a language analysis model to obtain at least one standard keyword; performing recombination screening processing on all data key segmented words in the at least one standard keyword to obtain fuzzy data; performing secondary definition processing on the fuzzy data to obtain to-be-recommended data; and recommending the to-be-recommended data to the target device. According to the method, accurate to-be-recommended data can be obtained, and the efficiency and accuracy of data recommendation are improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a data recommendation method, device, electronic device and storage medium. Background Art

[0002] Search engines are an important means of data recommendation. Search engines process input text descriptions and provide data to be recommended for recommendation.

[0003] In the existing technology, based on the search engine, the input document is divided into several words, and then the corresponding data is stored according to the meanings of the several words. The meanings of the words are matched with the indexed words, and the recommended data containing the keywords are returned to the user.

[0004] However, the above method requires multiple inputs to provide useful data, which reduces the efficiency and accuracy of data recommendation. Summary of the Invention

[0005] The embodiments of the present application provide a data recommendation method, device, electronic device, and storage medium, which can obtain accurate data to be recommended, thereby improving the efficiency and accuracy of data recommendation.

[0006] In a first aspect, an embodiment of the present application provides a data recommendation method, comprising: obtaining a search text segment to be processed; and segmenting the search text segment to be processed to obtain at least one fuzzy segmentation word group;

[0007] If it is determined that the value of each of the fuzzy segmentation groups is less than the target list length, then based on the language analysis model, fuzzy matching processing is performed on the at least one fuzzy segmentation group to obtain at least one standard keyword; wherein the standard keyword includes at least one data key segmentation;

[0008] Performing reorganization and screening processing on all data key words in the at least one standard keyword to obtain fuzzy data;

[0009] The fuzzy data is subjected to secondary definition processing to obtain data to be recommended; and the data to be recommended is recommended to a target device.

[0010] In a second aspect, an embodiment of the present application provides a data recommendation device, comprising:

[0011] A segmentation module is used to obtain a search text segment to be processed; and segment the search text segment to be processed to obtain at least one fuzzy segmentation word group;

[0012] a matching module configured to, if it is determined that the value of each of the fuzzy segmentation groups is less than the target list length, perform fuzzy matching processing on the at least one fuzzy segmentation group based on a language analysis model to obtain at least one standard keyword; wherein the standard keyword includes at least one data key segmentation;

[0013] A screening module, configured to perform a reorganization and screening process on all key words in the at least one standard keyword to obtain fuzzy data;

[0014] The recommendation module is used to perform secondary definition processing on the fuzzy data to obtain data to be recommended; and recommend the data to be recommended to the target device.

[0015] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0016] The memory stores computer-executable instructions;

[0017] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0018] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementation methods of the first aspect.

[0019] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0020] The data recommendation method, device, electronic device and storage medium provided in the embodiments of the present application, when the value of each fuzzy word group after the search text segmentation is less than the length of the target list, multiple fuzzy word groups are matched, reorganized, screened and redefined through a language analysis model to obtain the data to be recommended, so as to achieve the purpose of accurately obtaining data and recommend the data to be recommended to the target device; thereby improving the efficiency and accuracy of data recommendation. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0022] Figure 1 A schematic diagram of an application scenario provided for this application;

[0023] Figure 2A flowchart of a data recommendation method provided in an embodiment of the present application;

[0024] Figure 3 A flowchart of another data recommendation method provided in an embodiment of the present application;

[0025] Figure 4 A flowchart of another data recommendation method provided in an embodiment of the present application;

[0026] Figure 5 A schematic diagram of the structure of a data recommendation device provided in an embodiment of the present application;

[0027] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0028] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0029] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0030] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, processing, transmission, provision, disclosure and application of relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0031] In addition, this application involves big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.), and the use of artificial intelligence technology for automated decision-making, and a technical solution for making decisions that have a significant impact on personal rights and interests based on the results of automated decision-making. The application provides users with corresponding operation entrances for users to choose to agree or reject the results of automated decision-making; if the user chooses to reject, the expert decision-making process will be entered.

[0032] It should be noted that the present application can be used in the field of data processing technology, and can also be used in any field other than data processing technology. The application field of the present application is not limited.

[0033] Figure 1 A schematic diagram of an application scenario provided for this application, such as Figure 1 As shown, the specific application scenario of the present application is: the search engine in the device 101 processes the text description input by the user 102 to obtain the data to be recommended and recommend it to the user 102.

[0034] Based on the above scenario, it can be seen that based on the search engine, by dividing the input document into several words, then storing the corresponding data according to the meanings of the several words, matching the meanings of the words with the indexed words, and returning the recommended data containing keywords to the user, there is a technical problem of reduced efficiency and accuracy of data recommendation.

[0035] The data recommendation method provided in this application solves the technical problem of reduced efficiency and accuracy of data recommendation by matching, reorganizing, screening and re-defining multiple fuzzy word groups through a language analysis model when the value of each fuzzy word group after the search text segmentation is less than the length of the target list, thereby obtaining and recommending the data to be recommended.

[0036] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0037] Figure 2 A flow chart of a data recommendation method provided in an embodiment of the present application is shown as follows: Figure 2 As shown, the method includes:

[0038] 201. Obtain a search text segment to be processed; and segment the search text segment to be processed to obtain at least one fuzzy segmentation word group.

[0039] Exemplarily, the execution subject of this embodiment may be an electronic device, hereinafter referred to as a device. The device may be a virtual device or a physical device that executes the data recommendation method. A search engine is deployed in the device, and a user can perform data search based on the search engine. Based on the search engine, in response to the user's search instruction, a search text segment input by the user is obtained, i.e., the search text segment to be processed. Based on a preset text segmentation technology, the search text segment to be processed is segmented into phrases to obtain at least one fuzzy segmented phrase group.

[0040] For example, using the parsing function, the search engine data to be searched, that is, the search text segment to be processed, is parsed to obtain multiple fuzzy word groups. For example, the sentence "I like natural language processing." is segmented to obtain "I, like, natural language processing.", and it is determined whether all the characters in the search engine data to be searched have been parsed; if all have been completed, proceed to the next step.

[0041] 202. If it is determined that the value of each fuzzy word group is less than the target list length, then based on the language analysis model, fuzzy matching processing is performed on at least one fuzzy word group to obtain at least one standard keyword; wherein the standard keyword includes at least one data key word.

[0042] Exemplarily, based on a search engine, each fuzzy word group obtained is analyzed, the value of each fuzzy word group is determined, and the value of each fuzzy word group is compared with the length of the target list. If it is determined that the value of each fuzzy word group is less than the length of the target list, a preset language analysis model is called, and based on the language analysis model, all fuzzy word groups are fuzzy matched to obtain one or more standard keywords, each standard keyword including at least one data key word, i.e., an element. For example, the element is a data key word preset by the current search engine. If it is determined that the value of a fuzzy word group is not less than the length of the target list, the word segmentation is terminated, and the user is prompted in a flexible form to re-enter the search text segment and re-segment the process. By limiting the value of the word group, the subsequent language analysis model can be helped to better understand and process the word group, thereby improving the accuracy and efficiency of the search.

[0043] 203. Perform reorganization and screening processing on all data key words in at least one standard keyword to obtain fuzzy data.

[0044] Exemplarily, based on a search engine, all data key words in all standard keywords are reorganized to obtain reorganized text, and phrase screening processing is performed on the reorganized text to obtain processed data, namely fuzzy data.

[0045] For example, based on all the extracted data key words and the semantic structure of the search text segment to be processed, all the data key words are reorganized into a coherent sentence or paragraph. Through the summary output technology, the coherent sentence or paragraph is fuzzified, and finally a concise text summary, i.e. fuzzy data, is output, which retains the important information of the original text.

[0046] 204. Perform secondary definition processing on the fuzzy data to obtain data to be recommended; and recommend the data to be recommended to the target device.

[0047] Exemplarily, based on a search engine, the obtained fuzzy data can be redefined according to the semantic structure of the fuzzy data. For example, the semantics of the fuzzy data can be checked and updated to obtain updated fuzzy data, which is the data to be recommended. The data to be recommended is then recommended to the target device to recommend the data to the user.

[0048] For example, a natural language processing model is called to extract features from fuzzy data to obtain the semantic features of each character in the fuzzy data. Based on the semantic features of each character, the fuzzy data and all characters are updated to output more accurate data to be recommended.

[0049] In this embodiment, a data recommendation method is provided. When the value of each fuzzy word group after the search text segmentation is less than the length of the target list, multiple fuzzy word groups are matched, reorganized, screened and redefined through a language analysis model to obtain and recommend the data to be recommended. Accurate data to be recommended can be obtained without repeated input multiple times, thereby improving the accuracy and efficiency of data recommendation.

[0050] Figure 3 A flow chart of another data recommendation method provided in an embodiment of the present application is shown as follows: Figure 3 As shown, the method includes:

[0051] 301. Obtain a search text segment to be processed; and segment the search text segment to be processed to obtain at least one fuzzy segmentation word group.

[0052] For example, this step can refer to step 201 and will not be described in detail here.

[0053] 302. If it is determined that the value of each fuzzy word group is less than the target list length, determine the phrase type of each phrase in the fuzzy word group based on the language analysis model; wherein the language analysis model includes at least one preset phrase type and each preset phrase type corresponds to a preset sentence.

[0054] Exemplarily, based on a search engine, each obtained fuzzy word group is analyzed to determine the value of each fuzzy word group, and the value of each fuzzy word group is compared with the target list length. If it is determined that the value of each fuzzy word group is less than the target list length, a preset language analysis model is called, which includes at least one preset phrase type and a preset sentence corresponding to each preset phrase type. Based on the language analysis model, each phrase in each fuzzy word group is classified, and the preset phrase type corresponding to each phrase is determined as the final phrase type of each phrase. In particular, each phrase in the fuzzy word group is pre-parsed and segmented by the search engine.

[0055] In one example, before step 302, the following steps are further included:

[0056] Step 1: Acquire a language database; and perform sentence analysis on the language database to obtain a language training database; wherein the language database includes historical search input corpus; the language training database includes at least one preset search sentence, and the search sentence includes at least one preset phrase.

[0057] Step 2: Build a language analysis model based on all preset phrases in the language training library.

[0058] Exemplarily, by obtaining historical search input corpus, a language database is constructed, and sentence analysis and phrase analysis are performed on the historical search input corpus in the language database to obtain multiple preset search sentences, each search sentence includes at least one preset phrase, and a language training database is obtained. Based on the model construction method, phrase analysis and combination processing are performed on all preset phrases in the language training database to construct a language analysis model.

[0059] 303. Based on the language analysis model, determine at least one sentence corresponding to the fuzzy word group according to the word group type of each word group in the fuzzy word group.

[0060] Exemplarily, based on a search engine, the phrase type of each phrase in each obtained fuzzy phrase group is input into a language analysis model, so that at least one sentence corresponding to each fuzzy phrase group is matched and obtained from the language analysis model.

[0061] For example, for each sentence S, the language analysis model determines the categories of phrases h1 and h2, and then classifies the first sentence w1 and the second sentence w2 according to the categories of phrases h1 and h2. For multiple sentences S in the search text segment to be processed that contain the same multiple phrases h, the third sentence w3 is classified according to the categories of phrases h.

[0062] 304. Determine a standard keyword corresponding to the fuzzy word group according to the word group type of each word group in the fuzzy word group and at least one sentence corresponding to the fuzzy word group.

[0063] Exemplarily, based on the search engine, according to the mapping relationship between each preset phrase type and each sentence corresponding to each preset key data segmentation, for the phrase type of each phrase in each fuzzy phrase group and at least one sentence corresponding to the fuzzy phrase group, at least one preset key data segmentation corresponding to the fuzzy phrase group can be determined to obtain the standard keyword corresponding to each fuzzy phrase group.

[0064] For example, for each sentence S, the types of phrases h1 and h2 are determined using a language analysis model. The first sentence w1 and the second sentence w2 are then divided according to the types of phrases h1 and h2, yielding the elements corresponding to the type of phrase h in the first sentence w1 and the elements corresponding to the type of phrase h in the second sentence w2. For multiple sentences S in the search text segment to be processed, including multiple identical phrases h, the third sentence w3 is divided according to the type of phrase h, yielding the elements corresponding to the type of phrase h in the third sentence w3. The elements are the data keyword segmentations preset by the current search engine.

[0065] 305. Reassemble all data key words in at least one standard keyword to obtain at least one reassembled segment.

[0066] Exemplarily, based on the preset reorganization technology of the search engine, all data keyword segments in all standard keywords are reorganized and assembled. For example, all data keyword segments in each standard keyword are reorganized to obtain a recombined segment corresponding to each standard keyword.

[0067] Alternatively, all data key words in all standard keywords are randomly shuffled and reorganized multiple times to obtain all data key words with a new arrangement order after each reorganization, and all data key words with a new arrangement order after each reorganization are assembled to obtain corresponding multiple reorganized fragments.

[0068] For example, for each sentence S, phrases h1 and h2 are determined using a language analysis model. The first sentence w1 and the second sentence w2 are then divided according to the types of phrases h1 and h2, yielding elements corresponding to the type of phrase h in the first sentence w1 and elements corresponding to the type of phrase h in the second sentence w2. For several sentences S in the search text segment to be processed, including multiple identical phrases h, the third sentence w3 is divided according to the types of phrases h, yielding elements corresponding to the type of phrase h in the third sentence w3. The elements are data keyword segmentations preset by the current search engine. The elements corresponding to the type of phrase h1 in the first sentence w1, the elements corresponding to the type of phrase h2 in the second sentence w2, and the elements corresponding to the type of phrase h3 in the third sentence w3 are randomly combined to generate at least three possible random phrase meaning segments, thus yielding multiple recombined segments.

[0069] 306. Based on the language analysis model, align at least one recombinant segment to obtain fuzzy data.

[0070] Exemplarily, the obtained recombined segment is input into a language analysis model, and the recombined segment is analyzed and compared, for example, semantic structure features are extracted and feature processing is performed to obtain fuzzy data.

[0071] Alternatively, by comparing each standard data preset in the language analysis model with the recombined segment, the standard data with the closest semantics to the recombined segment is determined as the fuzzy data.

[0072] 307. Perform error correction processing on the fuzzy data to obtain at least one error correction candidate sentence.

[0073] Exemplarily, based on a preset text correction technology, such as a natural language processing model, the parameters of the natural language processing model are adjusted multiple times, and the obtained fuzzy data is corrected multiple times to obtain sentences after each correction, that is, multiple correction candidate sentences are obtained.

[0074] In one example, step 307 includes the following steps:

[0075] The first step is to perform error correction processing on the fuzzy data to obtain an error correction candidate set; wherein the error correction candidate set includes at least one candidate error correction word.

[0076] The second step is to perform phonetic and glyph replacement processing on the fuzzy data according to the candidate error correction words to obtain the error correction candidate sentences corresponding to the candidate error correction words.

[0077] Exemplarily, based on the error correction technology of the search engine, the fuzzy data is corrected to obtain a set of error correction candidates; wherein, the error correction candidate set includes at least one candidate error correction word, such as a word that is suspected to be erroneous; according to each candidate error correction word, the fuzzy data is processed by replacing the pronunciation and glyphs to obtain a candidate error correction sentence corresponding to each candidate error correction word for processing.

[0078] For example, the suspected erroneous words are put through an established dictionary, and the pronunciation and glyph of the fuzzy data are replaced to form multiple error correction candidate sentences for processing.

[0079] 308. Determine data to be recommended based on the sentence length of at least one error correction candidate sentence; and recommend the data to be recommended to a target device.

[0080] Exemplarily, based on a search engine, the sentence length of each error correction candidate sentence is determined, and based on the sentence lengths of all error correction candidate sentences, data to be recommended is obtained from multiple error correction candidate sentences, and the data to be recommended is recommended to a target device and to a user.

[0081] For example, the sentence length of each error correction candidate sentence can be calculated through a preset algorithm to obtain the priority of each error correction candidate sentence, and the error correction candidate sentence with the highest priority can be determined as the data to be recommended.

[0082] For example, Figure 4A flow chart of another data recommendation method provided in an embodiment of the present application is shown as follows: Figure 4 As shown, based on the acquired language database, a sentence analysis is established to form several sentences, and each sentence S includes several phrases to form a language training library; a language analysis model based on the language training library as a keyword is established; the content of the required search text segment is divided into keywords with single word meanings, that is, fuzzy word groups; each keyword is fuzzy matched in the language analysis model to obtain standard keywords; each keyword is fuzzy matched in the language analysis model to obtain standard keywords; the obtained standard keywords are reorganized and assembled, and the reorganized fragments are compared in the established language analysis model to screen out the fuzzy data containing the keywords; through the semantic analysis of the whole sentence and the secondary definition of the keywords, the unique data to be recommended for the keywords contained in the fuzzy data is selected and fed back to the user, thereby greatly increasing the accuracy of data retrieval and the accuracy of data recommendation.

[0083] In one example, step 308 includes the following steps:

[0084] The first step is to determine the perplexity of the candidate sentence according to the sentence length of the candidate sentence and the error probability of the candidate correction words in the candidate sentence; wherein the perplexity represents the fluency of the sentence.

[0085] The second step is to determine the error correction candidate sentence with the largest perplexity among at least one error correction candidate sentence as the data to be recommended.

[0086] For example, a search engine is used to perform error correction on fuzzy data. Each resulting error correction candidate sentence includes a corresponding candidate error correction word with a predicted error probability. Based on a preset algorithm, the sentence length of each error correction candidate sentence and the error probability of the candidate error correction word in the candidate sentence are calculated to obtain a perplexity for each error correction candidate sentence, thereby characterizing the fluency of the candidate sentence. Based on the perplexities of all error correction candidate sentences, the error correction candidate sentence with the greatest perplexity is determined as the data to be recommended.

[0087] For example, you can use the preset formula: Among them, m represents the sentence length of the error correction candidate sentence, P(wi) represents the predicted error probability of the candidate error correction word in the i-th error correction candidate sentence, wi represents the candidate error correction word in the i-th error correction candidate sentence, and the perplexity PPL(i) of the i-th error correction candidate sentence is calculated by 921; the error correction candidate sentence corresponding to the maximum value of PPL(i) is taken as the data to be recommended.

[0088] In this embodiment, based on the above embodiment, when the value of each fuzzy word group after the search text segmentation is less than the target list length, multiple fuzzy word groups are matched, reorganized, screened and redefined through the language analysis model, wherein the secondary definition obtains the data to be recommended by calculating the perplexity of the corrected sentence, so as to achieve the purpose of accurately obtaining data; thereby improving the efficiency and accuracy of data recommendation.

[0089] Figure 5 A structural diagram of a data recommendation device provided in an embodiment of the present application is shown in FIG. Figure 5 As shown, the device includes:

[0090] The segmentation module 401 is used to obtain a search text segment to be processed; and segment the search text segment to be processed to obtain at least one fuzzy segmentation word group;

[0091] Matching module 402 is configured to, if it is determined that the value of each fuzzy word group is less than the target list length, perform fuzzy matching on at least one fuzzy word group based on the language analysis model to obtain at least one standard keyword; wherein the standard keyword includes at least one data key word;

[0092] The screening module 403 is used to perform a reorganization and screening process on all data key words in at least one standard keyword to obtain fuzzy data;

[0093] The recommendation module 404 is configured to perform secondary definition processing on the fuzzy data to obtain data to be recommended; and recommend the data to be recommended to the target device.

[0094] In one example, the recommendation module 404 is specifically configured to: perform error correction processing on the fuzzy data to obtain at least one error-corrected candidate sentence; and determine the data to be recommended based on the sentence length of the at least one error-corrected candidate sentence.

[0095] In one example, the recommendation module 404 is specifically used to: perform error correction processing on fuzzy data to obtain an error correction candidate set; wherein the error correction candidate set includes at least one candidate error correction word; based on the candidate error correction word, perform phonetic and glyph replacement processing on the fuzzy data to obtain an error correction candidate sentence corresponding to the candidate error correction word.

[0096] In one example, the recommendation module 404 is further specifically used to: determine the perplexity of the error correction candidate sentence based on the sentence length of the error correction candidate sentence and the error probability of the candidate error correction word in the error correction candidate sentence; wherein the perplexity represents the fluency of the sentence; and determine the error correction candidate sentence with the largest perplexity among at least one error correction candidate sentence as the data to be recommended.

[0097] In one example, the matching module 402 is specifically used to: determine the phrase type of each phrase in the fuzzy phrase group based on a language analysis model; wherein the language analysis model includes at least one preset phrase type and a preset sentence corresponding to each preset phrase type; determine at least one sentence corresponding to the fuzzy phrase group based on the phrase type of each phrase in the fuzzy phrase group based on the language analysis model; determine the standard keyword corresponding to the fuzzy phrase group based on the phrase type of each phrase in the fuzzy phrase group and the at least one sentence corresponding to the fuzzy phrase group.

[0098] In one example, the screening module is specifically used to: reassemble all data key words in at least one standard keyword to obtain at least one recombined segment; and compare the at least one recombined segment based on a language analysis model to obtain fuzzy data.

[0099] In one example, the device is also used to: obtain a language database; and perform sentence analysis on the language database to obtain a language training database; wherein the language database includes historical search input corpus; the language training database includes at least one preset search sentence, and the search sentence includes at least one preset phrase; and construct a language analysis model based on all preset phrases in the language training database.

[0100] The device of this embodiment can execute the technical solution in the above method. Its specific implementation process and technical principles are the same and will not be repeated here.

[0101] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, the electronic device includes: a memory 501 and a processor 502; the memory 501 is a memory for storing instructions executable by the processor 502.

[0102] The processor 502 is configured to execute the method provided in the above embodiment.

[0103] The electronic device further includes a receiver 503 and a transmitter 504. The receiver 503 is used to receive instructions and data sent by other devices, and the transmitter 504 is used to send instructions and data to external devices.

[0104] The specific implementation process of the processor can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0105] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly implemented by a hardware processor or implemented by a combination of hardware and software modules in the processor.

[0106] An embodiment of the present application further provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed on a computer, the computer executes the technical solution of the above embodiment.

[0107] The readable storage medium may be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0108] An exemplary readable storage medium is coupled to a processor, such that the processor can read information from and write information to the readable storage medium. The readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an application-specific integrated circuit. The processor and the readable storage medium may also reside in a device as discrete components.

[0109] An embodiment of the present application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and when at least one processor executes the computer program, the technical solutions in the above embodiments can be implemented.

[0110] The division of units is merely a logical functional division; actual implementations may employ alternative divisions, such as combining or integrating multiple units or components into another system, or omitting or disabling certain features. Furthermore, any direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units, either through an interface, electrical, mechanical, or other means.

[0111] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0112] In addition, each functional unit in each embodiment of the present invention 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.

[0113] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and other media that can store program code.

[0114] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0115] Finally, it should be noted that those skilled in the art will readily identify other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein. The present invention is not limited to the precise structure described above and illustrated in the accompanying drawings, and various modifications and variations may be made without departing from the scope thereof. The scope of the present invention is limited solely by the appended claims.

Claims

1. A data recommendation method, characterized in that: include: Obtaining a search text segment to be processed; and segmenting the search text segment to be processed to obtain at least one fuzzy segmentation word group; If it is determined that the value of each of the fuzzy segmentation groups is less than the target list length, then based on the language analysis model, fuzzy matching processing is performed on the at least one fuzzy segmentation group to obtain at least one standard keyword; wherein the standard keyword includes at least one data key segmentation; Reorganize and filter all key words in the at least one standard keyword to obtain fuzzy data; The fuzzy data is subjected to secondary definition processing to obtain data to be recommended; and the data to be recommended is recommended to a target device.

2. The method according to claim 1, characterized in that The performing secondary definition processing on the fuzzy data to obtain the data to be recommended includes: performing error correction processing on the fuzzy data to obtain at least one error correction candidate sentence; The data to be recommended is determined according to the sentence length of the at least one error correction candidate sentence.

3. The method according to claim 2, characterized in that The performing error correction processing on the fuzzy data to obtain at least one error correction candidate sentence includes: Performing error correction processing on the fuzzy data to obtain an error correction candidate set; wherein the error correction candidate set includes at least one candidate error correction word; According to the candidate error-correcting words, the fuzzy data is processed by replacing the pronunciation and glyphs to obtain the error-correcting candidate sentences corresponding to the candidate error-correcting words.

4. The method according to claim 2, characterized in that The determining the data to be recommended according to the sentence length of the at least one error correction candidate sentence includes: Determining the perplexity of the candidate sentence according to the sentence length of the candidate sentence and the error probability of the candidate word in the candidate sentence; wherein the perplexity represents the fluency of the sentence; Determine the error correction candidate sentence with the largest perplexity among the at least one error correction candidate sentence as the data to be recommended.

5. The method according to claim 1, wherein The fuzzy matching process is performed on the at least one fuzzy word group based on the language analysis model to obtain at least one standard keyword, including: Determining the phrase type of each phrase in the fuzzy word group based on the language analysis model; wherein the language analysis model includes at least one preset phrase type and a preset sentence corresponding to each preset phrase type; Based on the language analysis model, determining at least one sentence corresponding to each phrase in the fuzzy phrase group according to the phrase type of each phrase in the fuzzy phrase group; The standard keyword corresponding to the fuzzy segmented word group is determined according to the phrase type of each phrase in the fuzzy segmented word group and at least one sentence corresponding to the fuzzy segmented word group.

6. The method according to claim 1, characterized in that The reorganization and screening of all data key words in the at least one standard keyword to obtain fuzzy data includes: Recombining and assembling all the data key words in the at least one standard keyword to obtain at least one recombined segment; Based on the language analysis model, the at least one recombinant fragment is compared to obtain the fuzzy data.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Acquire a language database; and perform sentence analysis on the language database to obtain a language training database; wherein the language database includes historical search input corpus; the language training database includes at least one preset search sentence, and the search sentence includes at least one preset phrase; The language analysis model is constructed based on all preset phrases in the language training library.

8. A data recommendation device, characterized in that: include: A segmentation module is used to obtain a search text segment to be processed; and segment the search text segment to be processed to obtain at least one fuzzy segmentation word group; a matching module configured to, if it is determined that the value of each of the fuzzy segmentation groups is less than the target list length, perform fuzzy matching processing on the at least one fuzzy segmentation group based on a language analysis model to obtain at least one standard keyword; wherein the standard keyword includes at least one data key segmentation; A screening module, configured to perform a reorganization and screening process on all key words in the at least one standard keyword to obtain fuzzy data; The recommendation module is used to perform secondary definition processing on the fuzzy data to obtain data to be recommended; and recommend the data to be recommended to the target device.

9. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images