CN111881316A - Search method, search device, server and computer-readable storage medium - Google Patents
Search method, search device, server and computer-readable storage medium Download PDFInfo
- Publication number
- CN111881316A CN111881316A CN202010738901.6A CN202010738901A CN111881316A CN 111881316 A CN111881316 A CN 111881316A CN 202010738901 A CN202010738901 A CN 202010738901A CN 111881316 A CN111881316 A CN 111881316A
- Authority
- CN
- China
- Prior art keywords
- search
- word
- term
- result
- node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 230000000875 corresponding effect Effects 0.000 claims abstract description 76
- 230000002596 correlated effect Effects 0.000 claims abstract description 13
- 230000011218 segmentation Effects 0.000 claims description 24
- 238000012163 sequencing technique Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 230000014759 maintenance of location Effects 0.000 claims 2
- 230000000717 retained effect Effects 0.000 claims 2
- 230000002452 interceptive effect Effects 0.000 description 13
- 230000008569 process Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 6
- 238000013473 artificial intelligence Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 210000004072 lung Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/686—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
- G06F16/635—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
- G06F16/638—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
Abstract
The application discloses a searching method, a searching device, a searching system, a server and a computer readable storage medium, wherein the method comprises the following steps: acquiring a search sentence, and determining all search terms in the search sentence; determining a necessary result of each search word according to the word information of each search word; wherein the obligate result is that the search word is a obligate search word or a non-obligate search word; generating a search keyword based on a necessary result of each search word, and searching by using the search keyword to obtain a search result corresponding to a search sentence; the search keywords comprise one or more search terms and at least one obligatory search term; ranking the search results based on the importance of each obligatory search term; the ranking priority of the search results corresponding to the search keywords is positively correlated with the sum of the importance of all the necessary search terms contained in the search keywords. The search method provided by the application improves the diversity of the search results while ensuring the relevance of the search results.
Description
Technical Field
The present application relates to the field of search technologies, and more particularly, to a search method, apparatus, server, and computer-readable storage medium.
Background
In the music field, a user can input a search sentence (query) to obtain a corresponding search result (Doc). Because a user lacks search experience, the problems of input errors, information redundancy, different expression habits and the like exist, and because retrieval resources are limited, all participle combinations in a search sentence cannot be exhaustively traversed for retrieval, and the input search sentence cannot directly retrieve results meeting the intention of the user, the core part of the search sentence needs to be reserved, and irrelevant parts are discarded.
In the related technology, the weight, namely the importance degree, of the keyword is determined by calculating the word frequency and the inverse document frequency of the keyword, unnecessary words are gradually discarded according to the importance degree of each keyword, the necessary words are utilized to recall and retrieve, and the result which is related to the search sentence as much as possible is recalled. In the process of implementing the invention, the inventor finds that at least the following problems exist in the related art: the search results are single, the diversity is lacked, and more choices cannot be given to the user.
Disclosure of Invention
The application aims to provide a searching method, a searching device, a server and a computer readable storage medium, which improve the diversity of search results while ensuring the relevance of the search results.
To achieve the above object, a first aspect of the present application provides a search method, including:
acquiring a search sentence, and determining all search terms in the search sentence;
determining a necessary result of each search word according to the word information of each search word; wherein the obligate result is that the search word is a obligate search word or a non-obligate search word;
generating a search keyword based on a necessary result of each search word, and searching by using the search keyword to obtain a search result corresponding to the search sentence; wherein the search keyword comprises one or more search terms and at least one obligatory search term;
ranking the search results based on the importance of each of the must-stay search terms; wherein the ranking priority of the search result corresponding to the search keyword is positively correlated with the sum of the importance of all obligatory search terms contained in the search keyword.
To achieve the above object, a second aspect of the present application provides a search apparatus comprising:
the acquisition module is used for acquiring a search statement and determining all search terms in the search statement;
the determining module is used for determining a necessary result of each search word according to the word information of each search word; wherein the obligate result is that the search word is a obligate search word or a non-obligate search word;
the search module is used for generating search keywords based on the necessary result of each search word and searching by using the search keywords to obtain a search result corresponding to the search sentence; wherein the search keyword comprises one or more search terms and at least one obligatory search term;
a ranking module for ranking the search results based on the importance of each of the obligatory search terms; wherein the ranking priority of the search result corresponding to the search keyword is positively correlated with the sum of the importance of all obligatory search terms contained in the search keyword.
To achieve the above object, a third aspect of the present application provides a server comprising:
a memory for storing a computer program;
a processor for implementing the steps of the search method as described above when executing the computer program.
To achieve the above object, a fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, where the computer program is executed by a processor to implement the steps of the above search method.
According to the scheme, the searching method provided by the application comprises the following steps: acquiring a search sentence, and determining all search terms in the search sentence; determining a necessary result of each search word according to the word information of each search word; wherein the obligate result is that the search word is a obligate search word or a non-obligate search word; generating a search keyword based on a necessary result of each search word, and searching by using the search keyword to obtain a search result corresponding to the search sentence; wherein the search keyword comprises one or more search terms and at least one obligatory search term; ranking the search results based on the importance of each of the must-stay search terms; wherein the ranking priority of the search result corresponding to the search keyword is positively correlated with the sum of the importance of all obligatory search terms contained in the search keyword.
According to the searching method, the necessary result is determined according to the word information of each searching word, the word information of the searching words can comprehensively consider the characteristics of music document structuralization and user clicking behavior in the music field, the accuracy of determining the necessary searching words is improved, and the relevance of the searching result is ensured. The search keywords comprise at least one obligatory search term, namely, each obligatory search term can be combined with any other search term for searching, so that a plurality of search term combination modes are provided, and the diversity of search results is improved. Therefore, the searching method provided by the application solves the technical problems of single searching result and lack of diversity in the related technology, and improves the diversity of the searching result while ensuring the relevance of the searching result. In addition, the search result ranking rule provided by the application is that the search result corresponding to the higher sum of the importance of all the necessary search terms included is closer to the search intention of the user, and the ranked result is closer to the front, so that the user experience is improved. The application also discloses a searching device, a server and a computer readable storage medium, which can also realize the technical effects.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure. In the drawings:
fig. 1 is an architecture diagram of a search system according to an embodiment of the present application;
fig. 2 is a flowchart of a first search method provided in an embodiment of the present application;
fig. 3 is a flowchart of a second search method provided in an embodiment of the present application;
fig. 4 is a flowchart of a third search method provided in the embodiment of the present application;
FIG. 5 is a block diagram of a search tree according to an embodiment of the present disclosure;
FIG. 6 is a block diagram of another search tree provided in an embodiment of the present application;
FIG. 7 is a block diagram of a search tree according to an embodiment of the present application;
fig. 8 is a flowchart of a fourth searching method provided in the embodiment of the present application;
fig. 9 is a structural diagram of a search apparatus according to an embodiment of the present application;
fig. 10 is a block diagram of a server according to an embodiment of the present application.
Detailed Description
In the related technology, the weight, namely the importance of the keyword is determined by calculating the word frequency and the inverse document frequency of the keyword, and then recall retrieval is performed by using the necessary word according to the importance of each keyword, and a result which is related to a search sentence as much as possible is recalled. The applicant of the present application has found through research that the above scheme may have a search word selection error, which leads to a recall result error. For example, for the search statement "reserve a new song of chua xun", since "reserve" is the name of the song, the search term is obligatory, and "new song of chua xun" is a search term that is not obligatory, the search results are all the results of the song "reserve". But in actual practice, the recall of the relevant search results for "chua xun kun" may be closer to the user's intent. Since the user can not click on the related search result of "chua xun kun", the online recall result is always poor, and automatic feedback correction cannot be performed. Therefore, in the present application, a search tree is built for a search sentence input by a user, and each leaf node in the search tree reserves a search term for necessity. The necessary result of each search word is determined according to the word information of all the participles in each search word, the characteristics of music document structuralization and user clicking behavior in the music field can be comprehensively considered, and the accuracy of determining the necessary search word is improved.
In addition, the applicant of the present application also finds that the scheme search results provided in the related art are single, lack of diversity, and cannot give more choices to the user, and cannot attract the user. For example, for the search statement "Zhougenqixiang," where "qilixiang" is a obligatory search term and "Zhougenjan" is a non-obligatory search term. The online recall results recalled various other versions of "qilixiang" in addition to the "zhou jeren" song "qilix". However, the search sentence input by the user is "zhou jenlong qilix" instead of the single "qilix", and the intention of the user can be understood based on this: after retrieving the "qilix" result of "zhougeny," it may be desirable to recall other songs of "zhougeny," not just the various versions of "qilix. Therefore, in the application, the search keywords comprise at least one obligatory search term, namely, each obligatory search term can be combined with any other search term for searching, so that a plurality of search term combination modes are provided, the recall results are enriched, the search is helped to obtain more diversified results, and more displays are given to users.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In order to facilitate understanding of the search statement response method provided in the present application, a system for use thereof will be described below. Referring to fig. 1, an architecture diagram of a search system provided by an embodiment of the present application is shown, and as shown in fig. 1, includes an interactive device 10, a server 20, and a data server 30. Wherein, the interactive device 10 and the server 20, and the server 20 and the data server 30 are connected by communication through the network 40.
The interactive device 10 is used for interacting with a user, and may be an AI (Artificial Intelligence, english will be called intelligent Intelligence) device, such as an intelligent sound box, or a fixed terminal such as a PC (Personal Computer, or mobile terminal such as a mobile phone), which is not specifically limited herein. The interactive device 10 can receive a search sentence input by a user, and can support voice input of the user and text input of the user, that is, the search sentence can be in a voice form and can also be in a text form. Specifically, after receiving the search sentence of the user, the interactive device 10 may first analyze whether the search sentence is in a voice form or a text form, and if the search sentence is in the voice form, perform voice recognition on the search sentence to obtain a corresponding text form, so that the server 20 processes the search sentence in the text form.
The server 20 is a background server corresponding to the interactive device 10, and is configured to process a search statement sent by the interactive device 10. First, for each search word in a search sentence, the server 20 determines its obligate result from the word information of all the participles contained therein, providing the data server 30 with a variety of obligate combinations of search words. And secondly, combining each necessary search word with any other search word to generate a search keyword, and searching by using the search keyword to obtain a search result corresponding to the search sentence. And finally, determining the ranking priority of the search results corresponding to each search keyword based on the importance of each obligatory search term, and displaying the search results to the user in the interactive device 10 according to the ranking priority of each search result.
The data server 30 stores a database of music documents, and is used for recalling in the database by using each search keyword transmitted by the server 20 and returning a recall result to the server 20.
The embodiment of the application discloses a searching method, which improves the diversity of searching results while ensuring the relevance of the searching results.
Referring to fig. 2, a flowchart of a first search method provided in an embodiment of the present application is shown in fig. 2, and includes:
s101: the interactive equipment sends a search statement to the server;
in this step, the interactive device obtains a search statement input by the user in a voice or text form, performs voice recognition on the search statement in the voice form to obtain a search statement in the text form, and sends the search statement in the text form to the corresponding server.
S102: the server determines all search terms in the search sentence;
in a specific implementation, a search sentence input by a user comprises a plurality of participles, and adjacent participles can form a search word, namely each search word comprises one or more participles. The search term is a term having a practical meaning, such as "Zhougelong", "Qilixiang", etc., which belongs to a named entity, such as "singer", "song", etc., for the field of music, and the search term "Zhougelong" belongs to the named entity "singer".
The purpose of this step is to determine all search terms in the search sentence input by the user, that is, to compose all participles in the search sentence into search terms, so that the following steps can perform word loss on the unnecessary search terms therein.
The embodiment does not specifically limit the process of determining the search term, and as a feasible implementation manner, the association relationship between adjacent participles may be used to determine whether the participles belong to the same search term, that is, the step of determining all search terms in the search sentence may include: searching in pairsPerforming word segmentation processing on the search sentence to obtain all the words in the search sentence; calculating a connection score between every two adjacent participles according to the participle information of every two adjacent participles; and placing the participles with the connection scores larger than the preset value in the same search word so as to determine all the search words in the search sentence. In specific implementation, firstly, a search sentence input by a user is participled to obtain all participles in the search sentence, (term)1,term2,…,termn) Segment () is a word segmentation function, term, wherein query is a search sentence input by a useriFor the ith participle in the search sentence, i is more than or equal to 1 and less than or equal to n. For example, the search sentence input by the user is "Zhou Ji Lun Qilixiang accompaniment", and the segmentation result is: zhou, Jie Lun, Qi, Li, Xiang and accompany. Secondly, calculating the connection score between every two adjacent participles according to the participle information of every two adjacent participles, and judging whether the participles are placed in the same search word or not through the connection score between the adjacent nodes, namely IsInSameNode (term)i,termj)＝NodeJudge(Info(termi),Info(termj) IsInSameNode () is a judging function for judging whether two adjacent participles should be placed in the same search word, NodeJudge () is a connection score and Info (term) between two adjacent participlesi) The word segmentation information is the ith word segmentation. The word segmentation information herein may include importance, closeness to adjacent word segmentation (meaning closeness between words, word with high closeness appears continuously), named entity to which the word belongs, etc., i.e. the word information of the target word segmentation in the search sentence includes any one or combination of importance of the target word segmentation in the search sentence, closeness of the target word segmentation to adjacent word in the search sentence, and named entity to which the target word segmentation belongs. It is understood that the value range of NodeJudge () can be [0,1 ]]The IsInSameNode () judges whether NodeJudge () is larger than a preset value, if so, the adjacent participles are required to be placed in the same search word, otherwise, the adjacent participles are not required to be placed in the same search word. Of course, the value of nodejdge () can also be 0 or 1, when it is 1, IsInSameNode () judges that the adjacent participles should be placed in the same search word, otherwise should not bePlaced in the same search term. In the above example, the connection score of "week" and "jeren" is 1, the connection score of "jeren" and "seven" is 0, the connection score of "seven" and "ri" is 1, the connection score of "li" and "xiang" is 1, the connection score of "xiang" and "accompaniment" is 0, and therefore, the search sentence includes the search word: zhou Jie Lun, Qili Xiang, accompany.
S103: determining a necessary result of each search word according to the word information of each search word; wherein the obligate result is that the search word is a obligate search word or a non-obligate search word;
the purpose of this step is to determine the obligatory result for each search term, i.e., whether the search term is a obligatory search term or a non-obligatory search term. In this embodiment, the word information of the search word is used to determine the necessary result, where the word information includes the word segmentation information of each word segmentation in the search word, that is, the importance of each word segmentation, the closeness between each word segmentation and an adjacent word segmentation, the named entity to which the word information belongs, and the like. In the above example, "zhou jilun" and "qilix" are the obligatory search words, and "accompaniment" is the non-obligatory search word.
S104: the server generates a search keyword based on the obligatory result of each search term;
in this step, the server generates a search keyword, where the search keyword may include one or more search terms, where a must-stay search term must be included, that is, any one must-stay search term may be combined with any other must-stay search term or non-must-stay search term for search, so as to improve the diversity of search results. In the above example, the search keywords are "zhou jeren", "qili", "zhou jeran accompaniment", "qili accompaniment", and "zhou jeran qili accompaniment", respectively.
S105: the server sends a search keyword to the data server;
s106: the data server returns a search result corresponding to the search keyword to the server;
in this step, the data server recalls in the database to obtain the search result corresponding to each search keyword, and returns the search result to the server.
S107: the server sorts the search results based on the importance of each obligatory search word; the ranking priority of the search results corresponding to the search keywords is positively correlated with the sum of the importance of all the necessary search terms contained in the search keywords.
In a specific implementation, the search results corresponding to all the search keywords with higher sum of importance of all the necessary search terms are closer to the search intention of the user, and the ranking priority is higher, that is, the ranking results are closer to the front. For the example given in the previous step, if the importance of "zhou jilun" is calculated to be 0.6, the shuffling probability of "qilix" is 0.9, the sum of the importance of all the necessary search words contained in the search keywords "zhou jilun qilix" and "zhou jilun qilix accompaniment" is 1.5, and the search results corresponding to the search words are ranked in the first rank, i.e., the top, because the search keyword "zhou jilun qilix accompaniment" is the original search sentence input by the user, the corresponding search result can be most close to the search intention of the user, and the search result is ranked at the top and is "zhou jilun qilix". The sum of the importance of all the necessary search terms contained in the search keywords "qilixiang" and "qilixiang accompaniment" is 0.9, and the search results corresponding to the search terms are ranked in the second echelon. The sum of the importance of all the necessary search words contained in the search keywords "zhou jilun" and "zhou jilun accompaniment" is 0.6, and the corresponding search results are ranked in the third echelon, and since more search words are contained in the search keyword "zhou jilun accompaniment", the corresponding search results are most close to the search intention of the user, and therefore the search results are ranked before the search results corresponding to the search keyword "zhou jilun".
S108: and the interactive equipment displays the search result corresponding to the search statement.
According to the searching method provided by the embodiment of the application, the necessary result of each searching word is determined according to the word information of each searching word, the word information of each searching word can comprehensively consider the characteristics of music document structuralization and user clicking behavior in the music field, the accuracy of determining the necessary searching word is improved, and the relevance of the searching result is ensured. The search keywords comprise at least one obligatory search term, namely, each obligatory search term can be combined with any other search term for searching, so that a plurality of search term combination modes are provided, and the diversity of search results is improved. Therefore, the searching method provided by the embodiment of the application solves the technical problems of single searching result and lack of diversity in the related technology, and improves the diversity of the searching result while ensuring the relevance of the searching result. In addition, the search result ranking rule provided by the embodiment of the application is that the higher the sum of the importance of all the necessary search terms contained in the search result corresponding to the search keyword is, the closer the search result is to the search intention of the user, the closer the ranking result is, and the user experience is improved.
Compared with the previous embodiment, the present embodiment further describes and optimizes the technical solution, and introduces the server as an execution subject. Specifically, the method comprises the following steps:
referring to fig. 3, a flowchart of a second search method provided in the embodiment of the present application is shown in fig. 3, and includes:
s201: acquiring a search sentence, and determining all search terms in the search sentence; wherein each search term comprises one or more participles;
s202: calculating the importance of each search word according to the importance and the number of the participles in each search word, and sequencing all the search words from small to large according to the importance;
in this embodiment, the importance of the search term is calculated according to the importance of each participle in the search term and the number of participles included in the search term, specifically, nodewightaSum (termweight)/count (termNum), wherein NodeweightaRepresenting the importance of the search term corresponding to the node a, sum (termweight) representing the sum of the importance of all the participles in the search term corresponding to the node a, and count (termNum) representing the number of the participles contained in the search term corresponding to the node a. In the example given in the above embodiment, it can be calculated that the importance of "zhou jeren" is 0.6, the importance of "qili jones" is 0.9, and the importance of "accompaniment" is 0.1.
In this step, all the search terms need to be sorted from small to large according to importance, and in the above example, the sorting result is: accompaniment, Zhou Jie Lun, Qili Xiang.
S203: determining a necessary result of each candidate necessary search word according to the word information of each participle in the candidate necessary search words; the candidate obligatory search terms are N search terms with the maximum importance degree in the sequencing result;
s204: determining the obligate result of the search word except the candidate obligate search word as a non-obligate search word;
in this embodiment, only N search terms with the largest importance are determined as the unnecessary search terms, and other search terms are determined as the unnecessary search terms, thereby improving the efficiency of determining the unnecessary result of each search term.
S205: ranking the search results based on the importance of each obligatory search term; the ranking priority of the search results corresponding to the search keywords is positively correlated with the sum of the importance of all the necessary search terms contained in the search keywords.
Therefore, in the embodiment, the importance degree of each participle in the search word is calculated according to the importance degree of each participle and the number of the participles contained in the search word, when determining the necessary result of each search word, only whether the N search words with the maximum importance degree are necessary search words is judged, and other search words are judged to be unnecessary search words, so that the efficiency of determining the necessary result of each search word is improved.
Compared with the previous embodiment, the embodiment further explains and optimizes the technical scheme, and introduces the technical scheme by taking the server as an execution subject. Specifically, the method comprises the following steps:
referring to fig. 4, a flowchart of a third search method provided in the embodiment of the present application is shown in fig. 4, and includes:
s301: acquiring a search sentence, and determining all search terms in the search sentence;
s302: determining a necessary result of each search word according to the word information of each search word; wherein the obligate result is that the search word is a obligate search word or a non-obligate search word;
s303: establishing a search tree corresponding to the search sentence based on the obligatory result of each search word; each search word is located at one node in the search tree, the unnecessary search words are located at leaf nodes in the search tree, the unnecessary search words are located at non-leaf nodes in the search tree, father nodes except the target father node only comprise one child node, and the target father node is a father node of the leaf node;
the purpose of this step is to build a search tree corresponding to the search statement. In specific implementation, all search terms in a search sentence are traversed, each search term is placed in one node, a search tree is established, leaf nodes in the search tree are obligatory search terms, other nodes are non-obligatory search terms, and other father nodes except father nodes of the leaf child nodes only comprise one child node. As can be seen, the search tree may clearly represent the necessary results for the search terms. For example, in the search sentence "zhou jilun qilix accompaniment", the "zhou jilun" and "qilix" are the essential search words, the "accompaniment" is the non-essential search word, and the search tree is created as shown in fig. 5.
As a possible implementation, the step may include: judging whether a target search word in a search sentence is a necessary search word; if yes, adding the target search word into the search tree as a child node of the target father node; if not, adding the target search word into the search tree as a child node of the first node and a father node of the second node, or adding the target search word into the search tree as a child node of the target father node and father nodes of all leaf nodes; and the search terms positioned at the first node and the second node are unnecessary search terms. For example, in the search sentence "zhou jiron qilixi accompaniment concert version", where "zhou jiron" and "qilixi" are obligate search words and "accompaniment" and "concert version" are non-obligate search words, then "zhou jiron" and "qilixi" are located at leaf nodes of the search tree and "accompaniment" and "concert version" are located at non-leaf nodes of the search tree.
It should be noted that, in this embodiment, the position relationship between the non-leaf nodes where each non-unnecessary search term is located is not limited, that is, it is not limited to which specific non-unnecessary search term is located in the target parent node. For the search sentence "Zhou Jieron Qilixiang accompaniment concert edition", the search tree can be established as shown in FIG. 6 or 7.
S304: generating a search keyword based on a necessary result of each search word, and searching by using the search keyword to obtain a search result corresponding to a search sentence; the search keywords comprise one or more search terms and at least one obligatory search term;
s305: calculating the mixed probability of each leaf node; the mixed-ranking probability is the ratio of the importance of the obligatory search words corresponding to the leaf nodes to the sum of the importance of the obligatory search words corresponding to all the leaf nodes;
s306: sequencing the search results based on the mixed probability of the leaf nodes where each obligatory search word is located; the ranking priority of the search results corresponding to the search keywords is positively correlated with the sum of the mixedness probabilities of leaf nodes where all the necessary search terms contained in the search keywords are located.
In this embodiment, the mixed-ranking probability of each leaf node is obtained by mixing all leaf nodes in the search tree, and may be understood as performing normalization processing on the importance of all the obligatory search terms, that is, the mixed-ranking probability of one leaf node is a ratio of the importance of the obligatory search term corresponding to the leaf node to the sum of the importance of the obligatory search terms corresponding to all the leaf nodes. The ranking priority of each search result can be determined by the mixedness probability of the leaf nodes, and for a search statement "Zhou Ji Lun Qilixiang accompaniment", wherein "Zhou Ji Lun" and "Qilixiang" are obligatory search terms, the corresponding importance degrees are 0.6 and 0.9 respectively, and the mixedness probability of the corresponding leaf nodes is 0.4 and 0.6 respectively. The sum of the mixedly arranged probabilities of leaf nodes where all the obligatory search words are located contained in the search keywords of Zhou Ji Lung Qilixiang and Zhou Ji Lung Qilixiang accompaniment is 1, the search results corresponding to the two are ranked in the first echelon, namely, the top, because the search keyword of Zhou Ji Lun Qilixiang accompaniment is the original search sentence input by the user, the corresponding search result can be most close to the search intention of the user, the search result is ranked at the top, and the second is Zhou Ji Lun Qilixiang. The sum of the mixedly arranged probabilities of leaf nodes where all the necessary search words are located, which are contained in the search keyword "qilixiang" and "qilixiang accompaniment", is 0.6, and the search results corresponding to the search keywords are ranked in the second echelon. The sum of the mixedly arranged probabilities of leaf nodes where all the necessary search words are located contained in the search keywords "Zhou Ji Lun" and "Zhou Ji Lun accompany" is 0.4, the search results corresponding to the search keywords "Zhou Ji Lun accompany" are ranked in the third echelon, and the search results are arranged before the search results corresponding to the search keyword "Zhou Ji Lun" because the search keywords "Zhou Ji Lun accompany" include more search words and the corresponding search results can be most close to the search intention of the user.
Therefore, in the embodiment, the search tree is established for the search statement input by the user, the leaf nodes in the search tree are obligatory search terms, other nodes are non-obligatory search terms, other father nodes except the father nodes of the leaf child nodes only comprise one child node, and the search tree can clearly represent obligatory results of the search terms. In addition, all leaf nodes in the search tree are arranged in a mixed mode, the ranking of all search results can be guided based on the mixed arrangement probability of the leaf nodes, the search results closer to the search intention of the user are ranked more forward, and the user experience is improved.
Compared with the previous embodiment, the embodiment further explains and optimizes the technical scheme, and introduces the technical scheme by taking the server as an execution subject. Specifically, the method comprises the following steps:
referring to fig. 8, a flowchart of a fourth search method provided in the embodiment of the present application is shown in fig. 8, and includes:
s401: acquiring a search sentence, and determining all search terms in the search sentence; wherein each search term comprises one or more participles;
s402: calculating the importance of each search word according to the importance and the number of the participles in each search word, and sequencing all the search words from small to large according to the importance;
s403: determining a necessary result of each candidate necessary search word according to the word information of each participle in the candidate necessary search words; the candidate obligatory search terms are N search terms with the maximum importance degree in the sequencing result;
s404: determining the obligate result of the search word except the candidate obligate search word as a non-obligate search word;
s405: determining a first search word in the sequencing result as a first search word, and determining a search word next to the first search word as a second search word;
s406: adding the first search word into a search tree corresponding to the search statement; the first search word is a child node of a root node in a search tree;
s407: judging whether the first search word is a necessary search word; if yes, entering S408; if not, entering S409;
s408: adding the second search word into the search tree as a child node of the target parent node; the target father node is a father node of the first search term;
s409: adding the second search word into the search tree as a child node of the first search word;
s410: judging whether the second search word is the last search word in the sequencing result; if yes, go to S412; if not, the step S411 is entered;
s411: updating the first search word to be the next search word of the first search word, updating the second search word to be the next search word of the second search word, and entering the step S407 again;
in specific implementation, a search word with the lowest importance (i.e., the first search word in the ranking result) is added as a first search word to the search tree, if the first search word is a must-leave search word, it indicates that all subsequent search words are must-leave search words, all subsequent search words and the first search word are child nodes of the same father node, i.e., the first search word and all subsequent search words are leaf nodes. If the first search term is an unnecessary search term, the next search term (i.e., the second search term) in the ranking result is a child node of the first search term.
S412: generating a search keyword based on a necessary result of each search word, and searching by using the search keyword to obtain a search result corresponding to a search sentence; the search keywords comprise one or more search terms and at least one obligatory search term;
s413: calculating the mixed probability of each leaf node; the mixed-ranking probability is the ratio of the importance of the obligatory search words corresponding to the leaf nodes to the sum of the importance of the obligatory search words corresponding to all the leaf nodes;
s414: sequencing the search results based on the mixed probability of the leaf nodes where each obligatory search word is located; the ranking priority of the search results corresponding to the search keywords is positively correlated with the sum of the mixedness probabilities of leaf nodes where all the necessary search terms contained in the search keywords are located.
Therefore, the embodiment provides a method for establishing a search tree, that is, whether a search term with the lowest importance is a must-leave search term is sequentially determined from the search term with the lowest importance, the must-leave search term is a child node of a non-must-leave search term with the highest importance, that is, the must-leave search term is a leaf node in the search tree.
For ease of understanding, the following description is made in conjunction with an application scenario of the present application. Referring to fig. 1, a user inputs a search sentence "zhou jilun chem accompaniment" in the interactive device 10, the interactive device 10 transmits the search sentence "zhou jilun chem accompaniment" to the server 20, the server 20 processes the search sentence as shown in table 1, and a generated search tree is shown in fig. 5:
TABLE 1
The search key is composed of: "zhou jiron", "qili xiang", "zhou jiron accompaniment", "qili xiang accompaniment", and "zhou jiron qili xiang accompaniment", the data server 30 recalls in the database based on the search key, arranges the recall result corresponding to the search sentence itself at the forefront of the search result if it exists, and if it does not exist, the ratio of the number of the recall results corresponding to "zhou jiron" and "qili" is 4:6, and the recall result corresponding to "qili" is ranked forward, the ratio of the number of the recall results corresponding to "zhou jiron accompaning" and "qili xiang accompaniment" is 4:6, and the recall result corresponding to "qili" is ranked forward.
In the following, a search apparatus provided by an embodiment of the present application is introduced, and a search apparatus described below and a search method described above may be referred to each other.
Referring to fig. 9, a structure diagram of a search apparatus according to an embodiment of the present application is shown in fig. 9, and includes:
an obtaining module 901, configured to obtain a search statement and determine all search terms in the search statement;
a determining module 902, configured to determine a necessary result of each search term according to term information of each search term; wherein the obligate result is that the search word is a obligate search word or a non-obligate search word;
a search module 903, configured to generate a search keyword based on a necessary result of each search term, and perform a search by using the search keyword to obtain a search result corresponding to a search statement; the search keywords comprise one or more search terms and at least one obligatory search term;
a ranking module 904 for ranking the search results based on the importance of each obligatory search term; the ranking priority of the search results corresponding to the search keywords is positively correlated with the sum of the importance of all the necessary search terms contained in the search keywords.
The searching device provided by the embodiment of the application determines the necessary result according to the word information of each searching word, and the word information of the searching words can comprehensively consider the characteristics of music document structuralization and user clicking behavior in the music field, so that the accuracy of determining the necessary searching words is improved, and the relevance of the searching result is ensured. The search keywords comprise at least one obligatory search term, namely, each obligatory search term can be combined with any other search term for searching, so that a plurality of search term combination modes are provided, and the diversity of search results is improved. Therefore, the searching device provided by the embodiment of the application solves the technical problems of single searching result and lack of diversity in the related technology, and improves the diversity of the searching result while ensuring the relevance of the searching result. In addition, the search result ranking rule provided by the embodiment of the application is that the higher the sum of the importance of all the necessary search terms contained in the search result corresponding to the search keyword is, the closer the search result is to the search intention of the user, the closer the ranking result is, and the user experience is improved.
On the basis of the foregoing embodiment, as a preferred implementation, the obtaining module 901 includes:
an acquisition unit configured to acquire a search sentence;
the word segmentation unit is used for carrying out word segmentation processing on the search sentence to obtain all the word segments in the search sentence;
the first calculation unit is used for calculating the connection score between every two adjacent participles according to the participle information of every two adjacent participles;
the first determining unit is used for placing the participles with the connection scores larger than the preset value into the same search word so as to determine all the search words in the search sentence.
On the basis of the foregoing embodiment, as a preferred implementation manner, the term information of the search term includes the participle information of each participle in the search term, and the participle information of a target participle in the search term includes any one or a combination of any several items of importance of the target participle in the search term, closeness of the target participle in the search term and an adjacent participle, and a named entity to which the target participle belongs.
On the basis of the foregoing embodiment, as a preferred implementation manner, the determining module 902 includes:
the second calculating unit is used for calculating the importance of each search word according to the importance and the word segmentation quantity of each word segmentation in each search word;
the second determining unit is used for determining the obligate result of each candidate obligate search word according to the word segmentation information of each word segmentation in the candidate obligate search words; the candidate must-remain search words are N search words with the maximum importance degree;
a third determining unit configured to determine a obligation result of the search word other than the candidate obligation search word as a non-obligation search word.
On the basis of the above embodiment, as a preferred implementation, the method further includes:
the establishing module is used for establishing a search tree corresponding to the search statement based on the obligatory result of each search word; each search word is located at one node in the search tree, a bound search word is located at a leaf node in the search tree, a non-bound search word is located at a non-leaf node in the search tree, a parent node except a target parent node only comprises one child node, and the target parent node is a parent node of the leaf node;
accordingly, the sorting module 904 comprises:
the third calculating unit is used for calculating the mixed row probability of each leaf node; the mixed ranking probability is the ratio of the importance of the obligatory search word corresponding to the leaf node to the sum of the importance of the obligatory search words corresponding to all the leaf nodes;
the first sequencing unit is used for sequencing the search results based on the mixed ranking probability of the leaf node where each obligatory search word is located; the ranking priority of the search results corresponding to the search keywords is positively correlated with the sum of the mixedness probabilities of leaf nodes where all the necessary search terms contained in the search keywords are located.
On the basis of the foregoing embodiment, as a preferred implementation, the establishing module includes:
the first judgment unit is used for judging whether a target search word in the search sentence is a necessary search word; if yes, starting the working process of the first joining unit; if not, starting the working process of the second joining unit;
a first adding unit, configured to add the target search term to the search tree as a child node of the target parent node;
a second adding unit, configured to add the target search term to the search tree as a child node of the first node and a parent node of the second node, or add the target search term to the search tree as a child node of the target parent node and parent nodes of all the leaf nodes; and the search words positioned at the first node and the second node are both unnecessary search words.
On the basis of the foregoing embodiment, as a preferred implementation, the establishing module includes:
the second sorting unit is used for sorting all the search terms from small to large according to the importance degrees;
a fourth determining unit, configured to determine a first search word in the sorting result as a first search word, and determine a search word next to the first search word as a second search word;
a third adding unit, configured to add the first search term to a search tree corresponding to the search statement; wherein the first search term is a child node of a root node in the search tree;
the second judging unit is used for judging whether the first search word is a reserved search word; if yes, starting the working process of the fourth adding unit; if not, starting the working process of the fifth import unit;
a fourth adding unit, configured to add the second search term to the search tree as a child node of the target parent node; wherein the target parent node is a parent node of the first search term;
a fifth adding unit, configured to add the second search term to the search tree as a child node of the first search term;
a third judging unit, configured to judge whether the second search term is a last search term in the sorting result; if not, updating the first search word to be a search word next to the first search word, updating the second search word to be a search word next to the second search word, and restarting the working process of the second judgment unit.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Those skilled in the art will appreciate that all or part of the steps in the method for implementing the above embodiments may be implemented by a program instructing the relevant hardware. For the hardware, the present application also provides a server, referring to fig. 10, and a structure diagram of a server 20 provided in the embodiment of the present application, as shown in fig. 10, may include a processor 201 and a memory 202.
The processor 201 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like. The processor 201 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 201 may also include a main processor and a coprocessor, where the main processor is a processor for processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 201 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the display screen. In some embodiments, the processor 201 may further include an AI (Artificial Intelligence) processor for processing computing operations related to machine learning.
Memory 202 may include one or more computer-readable storage media, which may be non-transitory. Memory 202 may also include high speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In this embodiment, the memory 202 is at least used for storing the following computer program 2021, wherein after being loaded and executed by the processor 201, the computer program can implement relevant steps in the search method executed by the server side disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 72 may also include an operating system 2022, data 2023, and the like, and the storage manner may be a transient storage manner or a permanent storage manner. The operating system 2022 may include Windows, Unix, Linux, and the like.
In some embodiments, the server 20 may also include a display 203, an input/output interface 204, a communication interface 205, sensors 206, a power source 207, and a communication bus 208.
Of course, the structure of the server shown in fig. 10 does not constitute a limitation to the server in the embodiment of the present application, and in practical applications, the server may include more or less components than those shown in fig. 10, or some components may be combined.
In another exemplary embodiment, a computer readable storage medium is also provided, which includes program instructions, which when executed by a processor, implement the steps of the search method performed by the server of any of the above embodiments.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
It is further noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Claims (10)
1. A method of searching, comprising:
acquiring a search sentence, and determining all search terms in the search sentence;
determining a necessary result of each search word according to the word information of each search word; wherein the obligate result is that the search word is a obligate search word or a non-obligate search word;
generating a search keyword based on a necessary result of each search word, and searching by using the search keyword to obtain a search result corresponding to the search sentence; wherein the search keyword comprises one or more search terms and at least one obligatory search term;
ranking the search results based on the importance of each of the must-stay search terms; wherein the ranking priority of the search result corresponding to the search keyword is positively correlated with the sum of the importance of all obligatory search terms contained in the search keyword.
2. The search method of claim 1, wherein said determining all search terms in the search statement comprises:
performing word segmentation processing on the search sentence to obtain all words in the search sentence;
calculating a connection score between every two adjacent participles according to the participle information of every two adjacent participles;
and placing the participles with the connection scores larger than a preset value into the same search word so as to determine all the search words in the search sentence.
3. The search method according to claim 2, wherein the term information of the search term includes term information of each term in the search term, and the term information of a target term in the search term includes any one or a combination of any several items of importance of the target term in the search term, closeness between the target term and an adjacent term in the search term, and a named entity to which the target term belongs.
4. The method according to claim 3, wherein the determining the retention result of each search term according to the term information of each search term comprises:
calculating the importance of each search word according to the importance and the number of the participles in each search word;
determining a necessary result of each candidate necessary search word according to the word segmentation information of each word in the candidate necessary search words; the candidate must-remain search words are N search words with the maximum importance degree;
determining a obligation result for the search term other than the candidate obligation search term as a non-obligation search term.
5. The search method according to any one of claims 1 to 4, further comprising, after determining a retention result for each of the search terms according to term information of each of the search terms:
establishing a search tree corresponding to the search sentence based on the obligatory result of each search word; each search word is located at one node in the search tree, a bound search word is located at a leaf node in the search tree, a non-bound search word is located at a non-leaf node in the search tree, a parent node except a target parent node only comprises one child node, and the target parent node is a parent node of the leaf node;
accordingly, the ranking the search results based on the importance of each of the obligatory search terms includes:
calculating the mixed row probability of each leaf node; the mixed ranking probability is the ratio of the importance of the obligatory search word corresponding to the leaf node to the sum of the importance of the obligatory search words corresponding to all the leaf nodes;
ranking the search results based on the mixed ranking probability of the leaf node where each obligatory search word is located; the ranking priority of the search results corresponding to the search keywords is positively correlated with the sum of the mixedness probabilities of leaf nodes where all the necessary search terms contained in the search keywords are located.
6. The search method according to claim 5, wherein the building a search tree corresponding to the search sentence based on the retained result of each search word comprises:
judging whether a target search word in the search sentence is a necessary search word;
if yes, adding the target search word into the search tree as a child node of the target father node;
if not, adding the target search word into the search tree as a child node of the first node and a father node of the second node, or adding the target search word into the search tree as a child node of the target father node and father nodes of all the leaf nodes; and the search words positioned at the first node and the second node are both unnecessary search words.
7. The search method according to claim 5, wherein the building a search tree corresponding to the search sentence based on the retained result of each search word comprises:
sorting all the search terms from small to large according to the importance;
determining a first search word in the sequencing result as a first search word, and determining a search word next to the first search word as a second search word;
adding the first search word into a search tree corresponding to the search statement; wherein the first search term is a child node of a root node in the search tree;
judging whether the first search word is a necessary search word;
if so, adding the second search word into the search tree as a child node of the target father node; wherein the target parent node is a parent node of the first search term;
if not, adding the second search word into the search tree as a child node of the first search word;
judging whether the second search word is the last search word in the sequencing result;
if not, updating the first search word to be a search word next to the first search word, updating the second search word to be a search word next to the second search word, and re-entering the step of judging whether the first search word is a necessary search word.
8. A search apparatus, comprising:
the acquisition module is used for acquiring a search statement and determining all search terms in the search statement;
the determining module is used for determining a necessary result of each search word according to the word information of each search word; wherein the obligate result is that the search word is a obligate search word or a non-obligate search word;
the search module is used for generating search keywords based on the necessary result of each search word and searching by using the search keywords to obtain a search result corresponding to the search sentence; wherein the search keyword comprises one or more search terms and at least one obligatory search term;
a ranking module for ranking the search results based on the importance of each of the obligatory search terms; wherein the ranking priority of the search result corresponding to the search keyword is positively correlated with the sum of the importance of all obligatory search terms contained in the search keyword.
9. An electronic device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the search method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the search method according to one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010738901.6A CN111881316A (en) | 2020-07-28 | 2020-07-28 | Search method, search device, server and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010738901.6A CN111881316A (en) | 2020-07-28 | 2020-07-28 | Search method, search device, server and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111881316A true CN111881316A (en) | 2020-11-03 |
Family
ID=73201861
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010738901.6A Pending CN111881316A (en) | 2020-07-28 | 2020-07-28 | Search method, search device, server and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111881316A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112434183A (en) * | 2020-11-30 | 2021-03-02 | 北京达佳互联信息技术有限公司 | Search result sorting method, device, equipment and storage medium |
| CN112836021A (en) * | 2021-02-24 | 2021-05-25 | 南京乐图软件技术有限公司 | Intelligent search system of library |
| CN113158091A (en) * | 2021-03-24 | 2021-07-23 | 北京奇艺世纪科技有限公司 | Recall method, apparatus, electronic device and storage medium |
| CN113343028A (en) * | 2021-05-31 | 2021-09-03 | 北京达佳互联信息技术有限公司 | Method and device for training intention determination model |
| CN117033563A (en) * | 2023-10-10 | 2023-11-10 | 北京轻松怡康信息技术有限公司 | Text retrieval method and device, electronic equipment and storage medium |
| CN117216423A (en) * | 2023-08-21 | 2023-12-12 | 湖南牙医帮科技有限公司 | Method, system, terminal equipment and storage medium for searching E-commerce commodity |
| CN117033563B (en) * | 2023-10-10 | 2024-04-26 | 北京轻松怡康信息技术有限公司 | Text retrieval method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101334796A (en) * | 2008-02-29 | 2008-12-31 | 浙江师范大学 | Personalized and synergistic integration network multimedia search and enquiry method |
| CN105808737A (en) * | 2016-03-10 | 2016-07-27 | 腾讯科技（深圳）有限公司 | Information retrieval method and server |
| CN105930376A (en) * | 2016-04-12 | 2016-09-07 | 广东欧珀移动通信有限公司 | Search method and device |
| CN109947902A (en) * | 2019-03-06 | 2019-06-28 | 腾讯科技（深圳）有限公司 | A kind of data query method, apparatus and readable medium |
| US20200012697A1 (en) * | 2018-07-03 | 2020-01-09 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and device for information retrieval, device and computer readable storage medium |
-
2020
- 2020-07-28 CN CN202010738901.6A patent/CN111881316A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101334796A (en) * | 2008-02-29 | 2008-12-31 | 浙江师范大学 | Personalized and synergistic integration network multimedia search and enquiry method |
| CN105808737A (en) * | 2016-03-10 | 2016-07-27 | 腾讯科技（深圳）有限公司 | Information retrieval method and server |
| CN105930376A (en) * | 2016-04-12 | 2016-09-07 | 广东欧珀移动通信有限公司 | Search method and device |
| US20200012697A1 (en) * | 2018-07-03 | 2020-01-09 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and device for information retrieval, device and computer readable storage medium |
| CN109947902A (en) * | 2019-03-06 | 2019-06-28 | 腾讯科技（深圳）有限公司 | A kind of data query method, apparatus and readable medium |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112434183A (en) * | 2020-11-30 | 2021-03-02 | 北京达佳互联信息技术有限公司 | Search result sorting method, device, equipment and storage medium |
| CN112836021A (en) * | 2021-02-24 | 2021-05-25 | 南京乐图软件技术有限公司 | Intelligent search system of library |
| CN112836021B (en) * | 2021-02-24 | 2022-04-26 | 南京乐图软件技术有限公司 | Intelligent search system of library |
| CN113158091A (en) * | 2021-03-24 | 2021-07-23 | 北京奇艺世纪科技有限公司 | Recall method, apparatus, electronic device and storage medium |
| CN113343028A (en) * | 2021-05-31 | 2021-09-03 | 北京达佳互联信息技术有限公司 | Method and device for training intention determination model |
| CN117216423A (en) * | 2023-08-21 | 2023-12-12 | 湖南牙医帮科技有限公司 | Method, system, terminal equipment and storage medium for searching E-commerce commodity |
| CN117033563A (en) * | 2023-10-10 | 2023-11-10 | 北京轻松怡康信息技术有限公司 | Text retrieval method and device, electronic equipment and storage medium |
| CN117033563B (en) * | 2023-10-10 | 2024-04-26 | 北京轻松怡康信息技术有限公司 | Text retrieval method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111881316A (en) | Search method, search device, server and computer-readable storage medium | |
| CN110704743B (en) | Semantic search method and device based on knowledge graph | |
| CN109542247B (en) | Sentence recommendation method and device, electronic equipment and storage medium | |
| US20170075985A1 (en) | Query transformation for natural language queries | |
| CN111566638B (en) | Adding descriptive metadata to an application programming interface for use by intelligent agents | |
| CN112487150B (en) | File management method, system, storage medium and electronic equipment | |
| KR102536775B1 (en) | Method and system for providing search results incorporating the intent of search query | |
| JP7093825B2 (en) | Man-machine dialogue methods, devices, and equipment | |
| CN111274358A (en) | Text processing method and device, electronic equipment and storage medium | |
| CN105354318A (en) | File searching method and device | |
| JP7160986B2 (en) | Search model training method, apparatus, device, computer storage medium, and computer program | |
| CN114328983A (en) | Document fragmenting method, data retrieval device and electronic equipment | |
| CN113704420A (en) | Method and device for identifying role in text, electronic equipment and storage medium | |
| CN111931034A (en) | Data searching method, device, equipment and storage medium | |
| CN116383340A (en) | Information searching method, device, electronic equipment and storage medium | |
| US20190057401A1 (en) | Identifying market-agnostic and market-specific search queries | |
| CN114595696A (en) | Entity disambiguation method, entity disambiguation apparatus, storage medium, and electronic device | |
| CN108846103B (en) | Data query method and device | |
| CN112685540A (en) | Search method, search device, storage medium and terminal | |
| CN112182177A (en) | User problem processing method and device, electronic equipment and storage medium | |
| CN111782958A (en) | Recommendation word determining method and device, electronic device and storage medium | |
| KR100740690B1 (en) | Information terminal set up the contents serching system | |
| CN117591624B (en) | Test case recommendation method based on semantic index relation | |
| US20240104297A1 (en) | Analysis of spreadsheet table in response to user input | |
| CN112836021B (en) | Intelligent search system of library |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |