Recommendation method

Abstract

The invention discloses a recommendation method, and relates to the technical field of network disks. The recommendation method comprises the steps that under the condition that a target search word input by a first user is received, a file link set of the same type as the target search word in historical search words of the first user is called, and search word associated data of the target search word is obtained; the retrieval word associated data is compared with link associated data of file links corresponding to the target retrieval word, the file links with the similarity larger than a similarity threshold value are recommended to the first user, and the link associated data of the file links are the file links with the similarity larger than the similarity threshold value under the condition that records of the file links exceed a record threshold value. And determining data according to the file name and the file introduction information corresponding to the file link.

Description

Technical Field

[0001] The present application relates to the technical field of network disks, and in particular to a recommendation method. Background Art

[0002] Netdisk is an online storage service launched by Internet companies. Netdisk system computer rooms allocate a certain amount of disk space for users, and provide users with file management functions such as file storage, access, backup, and sharing for free or for a fee, and have advanced disaster recovery backups around the world. When users share files with the outside world, they usually share files with the outside world in the form of external links. The external links contain very little information, such as only the file name and a randomly generated unique code (Identity document, ID).

[0003] In the related art, some service providers can provide shared file search services to facilitate users to obtain resources shared by other users. However, when searching for the required files, users can usually only compare the user's search terms with the file names of the shared files, and provide external links to files whose file names contain the search terms, which is not conducive to users finding the required files. Summary of the invention

[0004] An embodiment of the present application provides a recommendation method to solve the problem in the related art that when users search for the required files, they can usually only compare the user's search terms with the file names of the shared files, and provide external links to files whose file names contain the search terms, which is not conducive to users finding the required files.

[0005] In a first aspect, an embodiment of the present application provides a recommendation method, comprising:

[0006] When receiving a target search term input by a first user, retrieving a set of file links of the same type as the target search term from the first user's historical search terms to obtain search term associated data of the target search term;

[0007] The search term associated data is compared with the link associated data of the file link corresponding to the target search term, and the file link whose similarity is greater than a similarity threshold is recommended to the first user, wherein the link associated data of the file link is data determined based on the file name and file introduction information corresponding to the file link when the record of the file link exceeds a record threshold.

[0008] In a second aspect, an embodiment of the present application provides a recommendation device, including:

[0009] A retrieval module, configured to retrieve, upon receiving a target search term input by a first user, a set of file links of the same type as the target search term in the first user's historical search terms, and obtain search term associated data of the target search term;

[0010] A recommendation module is used to compare the search term associated data with the link associated data of the file link corresponding to the target search term, and recommend the file link whose similarity is greater than a similarity threshold to the first user, wherein the link associated data of the file link is data determined based on the file name and file introduction information corresponding to the file link when the record of the file link exceeds the record threshold.

[0011] In a third aspect, an embodiment of the present application provides a terminal device, comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.

[0012] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0013] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions, which, when executed by a computer, implement the steps of the method described in the first aspect.

[0014] In an embodiment of the present application, first, when a target search term input by a first user is received, a set of file links of the same type as the target search term in the historical search terms of the first user is retrieved to obtain the search term associated data of the target search term, and then the search term associated data is compared with the link associated data of the file link corresponding to the target search term, and the file link with a similarity greater than a similarity threshold is recommended to the first user, and the link associated data of the file link is data determined according to the file name and file introduction information corresponding to the file link when the record of the file link exceeds the record threshold. In an embodiment of the present application, a file link with more search records is used as a separate file link recommendation template. In the case of a new search by the user, a set of related file links is obtained according to the type of the new search term, that is, a reasonable search range of the search term is determined, and the search term associated data of the target search term in the file link set is compared with the link associated data of the file link corresponding to the target search term, and the file link with a higher similarity is recommended to the user first, thereby improving the accuracy and efficiency of file recommendation. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0016] Figure 1 is a flowchart of a recommended method provided in an embodiment of the present application;

[0017] Figure 2 is a schematic diagram of a recommended device provided in an embodiment of the present application;

[0018] Figure 3 It is a structural diagram of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here. In addition, the "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally represents that the objects associated with each other are in an "or" relationship.

[0021] The following is combined with Figures 1 to 3 , a recommended method provided in an embodiment of the present application is described in detail through specific embodiments and their application scenarios.

[0022] like Figure 1 As shown, it is a flowchart of a recommended method provided by an embodiment of the present application. Figure 1 As shown, the recommendation method may include: the contents shown in S101 to S102.

[0023] In S101, when a target search term input by a first user is received, a set of file links of the same type as the target search term in the first user's historical search terms is retrieved to obtain search term associated data of the target search term.

[0024] That is to say, the category of the target search term can be determined first to determine the search scope of the target search term, which can improve the recommendation efficiency.

[0025] For example, if the target search term and the search term AAA belong to the same category, the file link in the file link set corresponding to the search term AAA is retrieved to obtain the search term associated data of the target search term.

[0026] In this embodiment, if the target search term input by the first user and the search term AAA belong to the same category, then the corresponding record of the search term of this category of the first user in any statistical period is retrieved or generated, which can be the current statistical period or the previous historical statistical period. If there is already a search term of this category in the current statistical period, the current statistical period is used to achieve better results, and then the search term associated data corresponding to the search term input by the first user is generated.

[0027] Among them, after retrieving or generating the corresponding records of the search term of this category of the first user in any statistical period, the file links in multiple records can be deduplicated, and the file names and file introduction information of the deduplicated file links can be used as the search term associated data, or the file names and file introduction information of the file links in each record can be used to generate link associated features, such as link associated vectors or link associated matrices or link associated subgraphs, and then the link associated features are fused to obtain the search term associated data. It is worth noting that the determination of the search term associated data can be determined according to the actual situation. This embodiment only lists several examples, and the specific ones shall be subject to the actual application.

[0028] In S102, the search term associated data is compared with the link associated data of the file link corresponding to the target search term, and the file link having a similarity greater than a similarity threshold is recommended to the first user. The link associated data of the file link is data determined based on the file name and file introduction information corresponding to the file link when the record of the file link exceeds the record threshold.

[0029] The comparison method may be the distance between vectors or the similarity between graphs, which may be determined based on the form and generation method of the associated data. This embodiment does not limit this and is subject to actual application.

[0030] In an embodiment of the present application, first, when a target search term input by a first user is received, a set of file links of the same type as the target search term in the historical search terms of the first user is retrieved to obtain the search term associated data of the target search term, and then the search term associated data is compared with the link associated data of the file link corresponding to the target search term, and the file link with a similarity greater than a similarity threshold is recommended to the first user, and the link associated data of the file link is data determined according to the file name and file introduction information corresponding to the file link when the record of the file link exceeds the record threshold. In an embodiment of the present application, a file link with more search records is used as a separate file link recommendation template. In the case of a new search by the user, a set of related file links is obtained according to the type of the new search term, that is, a reasonable search range of the search term is determined, and the search term associated data of the target search term in the file link set is compared with the link associated data of the file link corresponding to the target search term, and the file link with a higher similarity is recommended to the user first, thereby improving the accuracy and efficiency of file recommendation.

[0031] In a possible implementation of the present application, the recommendation method may also include: obtaining historical search terms and file links of different users, where the file link is a link to the search results corresponding to the historical search terms clicked or downloaded by the user; classifying the historical search terms and file links of different users to obtain a set of file links corresponding to the historical search terms of each category, where the file link includes the file name and file introduction information of the file link.

[0032] Among them, multiple links will appear when searching for historical search terms, and the links that users click and download are file links.

[0033] The file introduction may include whether there is a sharing password, the specific password, the shared user, the file directory, the sharing time, etc. It may also include other information, which is subject to actual application and is not limited in this embodiment.

[0034] Furthermore, the recommendation method may also include: storing the historical search terms and file links respectively according to a preset statistical time period.

[0035] That is to say, we can first obtain the search terms of different users in the network disk file retrieval system, as well as the clicks and download operations on the links of the search results, to obtain historical search terms and file links, and then store the above data separately according to a certain statistical period, for example, 24 hours can be used as a period, or other statistical periods can be set, depending on the actual application, and this embodiment is not limited to this.

[0036] For example, user A's first search term within 24 hours is AAA, and the file links clicked and downloaded are file link AAA, file link AAABB, file link AAACC, and file link AABC respectively; the second search term is AAB, and the file links clicked and downloaded are file link AAB, file link AAABB, file link AAACC, file link AABC, and file link AABD respectively. Among them, the search terms AAA and AAB are historical search terms, and the file links AAA, file link AAABB, file link AAACC, and file link AABC corresponding to the search term AAA, and the file links AAB, file link AAABB, file link AAACC, file link AABC, and file link AABD corresponding to the search term AAB are the file links obtained in this application.

[0037] In a possible implementation of the present application, historical search terms and file links obtained from different users are classified to obtain a set of file links corresponding to the historical search terms of each category, which may include: classifying the search terms within each statistical period of each user, deduplicating the file links corresponding to the search terms of the same category, and obtaining a set of file links corresponding to the historical search terms of each category.

[0038] That is to say, the search terms in each statistical period of each user can be classified, and then the file links corresponding to the search terms in the same category can be deduplicated to reduce duplicate files. All the deduplicated file links are grouped into a set, namely a file link set, and the file name and file introduction information corresponding to each file link in the file link set can be stored as a record.

[0039] It is worth noting that synonyms and the like can be classified into the same category, and vocabulary in related fields can also be classified into the same category. The specific classification can be carried out according to actual applications and is not limited in this embodiment.

[0040] For example, the search terms AAA and AAB can be used as search terms of the same category. The file links corresponding to the category include information such as the file name and file introduction information. After the file links corresponding to the category are deduplicated, a file link set is obtained. The file link set may include file link AAA, file link AAABB, file link AAACC, file link AABC, file link AAB, and file link AABD. In other words, it includes both the file link corresponding to the search term AAA and the file link corresponding to the search term AAB, but they have been deduplicated.

[0041] In one embodiment, if there are file links in a sufficient number of records, link association data corresponding to the file links can be generated based on the file names and file introduction information of the file links in these records. The link association data can be used as a recommendation template for the file link to facilitate subsequent accurate recommendations.

[0042] The records may be records of the same user or records of different users, records within the same statistical period or records within different statistical periods, which shall be subject to actual application and is not limited in this embodiment.

[0043] For example, if the file link AAACC is located in a sufficient number of records, the link association data corresponding to the file link AAACC is generated according to the file name, file introduction information, etc. of the file link in these records. The link association data can be used as a recommended template for this file link AAACC.

[0044] In a possible implementation of the present application, upon receiving a target search term input by a first user, a set of file links of the same type as the target search term in the first user's historical search terms are retrieved to obtain search term associated data of the target search term, which may include: upon receiving a target search term input by the first user, a set of file links of the same type as the target search term of the first user within any statistical time period are retrieved; and the search term associated data of the target search term is obtained based on the file link set.

[0045] That is to say, if the target search term input by the first user and the search term AAA belong to the same category, then retrieve or generate a set of file links for the search terms of this category of the first user in any statistical period, and then generate search term association data corresponding to the search term input by the first user.

[0046] Among them, any statistical time period can be the current statistical period or any previous historical statistical period. If there are search terms of this category in the current statistical period, the current statistical period will be used to achieve better results.

[0047] There is usually a certain relationship between the files that users need to download within a period of time (statistical time period), for example, they are all related materials for an exam; by recording the file links actually used by users within the statistical time period, for each file link, the relevant information of the related file links in a sufficient number of records, such as the file name, file introduction information, etc., are integrated as reference information for this file link; when the user searches, the user's search term associated data is generated according to the information of the file link operated by the user, and based on the reference information of each file link and the user's search term associated data, it is determined whether to recommend this file link to the user.

[0048] In a possible implementation of the present application, obtaining search term associated data of a target search term based on a file link set may include: deduplicating file links in a file link set of multiple statistical time periods to obtain deduplicated file links; and using the file name and file introduction information of the deduplicated file link as the search term associated data of the target search term.

[0049] That is to say, the file links in the plurality of file link sets may be deduplicated, and the file names and file introduction information of the deduplicated file links may be used as search term associated data.

[0050] In a possible implementation of the present application, obtaining search term association data of a target search term based on a file link set may include: generating link association features based on the file names and file introduction information of file links in the file link set within each statistical time period; and fusing the link association features of multiple statistical time periods to obtain the search term association data of the target search term.

[0051] That is to say, in addition to determining the search term associated data by deduplication, the file name and file introduction information of the file link in each statistical time period can also be used to generate link associated features, such as link associated vectors or link associated matrices or link associated subgraphs, and then the link associated features are fused to obtain the search term associated data. It is worth noting that the determination of the search term associated data can be determined according to actual conditions, and this embodiment only lists several examples, and the specific ones shall be subject to actual applications.

[0052] In a possible implementation of the present application, a method for determining link-associated data of a file link may include: deduplicating file links in multiple records to obtain deduplicated file links; and using the file name and file introduction information of the deduplicated file link as the link-associated data of the file link.

[0053] That is to say, the file links in multiple records can be deduplicated, and the file names and file introduction information of the deduplicated file links are used as the link-related data corresponding to the file links.

[0054] In this embodiment, the file name and file introduction information in the deduplicated file link can be directly used as link-related data.

[0055] In other possible implementations, the method for determining link association data of a file link may include: for each record, obtaining link association features based on the file name and file introduction information of the file link in the record; and fusing the link association features of the file links in multiple records to obtain link association data of the file link.

[0056] The link association feature may include one of the following: a link association vector, a link association matrix, and a link association subgraph.

[0057] That is to say, in addition to directly using the file name and file introduction information in the deduplicated file link as link association data, it is also possible to obtain association features based on the file name and file introduction information of the file link in each record, and fuse the association features to obtain link association data of the file link.

[0058] In this embodiment, the link-related data corresponding to the file link can be formed and generated in various ways, as long as it can include rich information. The specific embodiments of this application are not limited and can be based on actual applications.

[0059] An embodiment of the present application also provides a recommendation system, which may include a network disk file management system and a retrieval system, wherein the network disk file management system is used to obtain historical search terms and file links, including file sharing links, passwords and other related information, and the retrieval system provides a retrieval interface, and displays recommended file links by entering search terms in the retrieval interface.

[0060] like Figure 2 As shown, it is a schematic diagram of a recommended device provided in an embodiment of the present application. Figure 2 As shown, the recommendation device may include: a calling module 201 and a recommendation module 201 .

[0061] Among them, the retrieval module 201 is used to retrieve a set of file links of the same type as the target search term in the historical search terms of the first user when receiving the target search term input, and obtain the search term associated data of the target search term; the recommendation module 202 is used to compare the search term associated data with the link associated data of the file link corresponding to the target search term, and recommend the file link with a similarity greater than a similarity threshold to the first user, and the link associated data of the file link is data determined according to the file name and file introduction information corresponding to the file link when the record of the file link exceeds the record threshold.

[0062] In the embodiment of the present application, first, when receiving the target search term input by the first user, the retrieval module 201 retrieves the file link set of the same type as the target search term in the historical search terms of the first user, and obtains the search term associated data of the target search term. Then, the recommendation module 202 compares the search term associated data with the link associated data of the file link corresponding to the target search term, and recommends the file link with a similarity greater than the similarity threshold to the first user. The link associated data of the file link is the data determined according to the file name and file introduction information corresponding to the file link when the record of the file link exceeds the record threshold. The embodiment of the present application uses the file link with more search records as a separate file link recommendation template. When the user makes a new search, the relevant file link set is obtained according to the type of the new search term, that is, the search range of the reasonable search term is determined, and the search term associated data of the target search term in the file link set is compared with the link associated data of the file link corresponding to the target search term. The file link with higher similarity is recommended to the user first, thereby improving the accuracy and efficiency of file recommendation.

[0063] In a possible implementation manner of the present application, the recommendation device may further include an acquisition module and a classification module.

[0064] Among them, the acquisition module is used to obtain the historical search terms and file links of different users. The file link is the link of the search result corresponding to the historical search terms clicked or downloaded by the user; the classification module is used to classify the historical search terms and file links of different users to obtain the file link set corresponding to the historical search terms of each category. The file link includes the file name and file introduction information of the file link.

[0065] In a possible implementation manner of the present application, the recommendation device may further include a storage module.

[0066] The storage module is used to store historical search terms and file links respectively according to a preset statistical time period.

[0067] In a possible implementation of the present application, the classification module 201 is used to classify the search terms of each user in each statistical period, deduplicate the file links corresponding to the search terms of the same category, and obtain a set of file links corresponding to the historical search terms of each category.

[0068] In a possible implementation of the present application, the retrieval module 201 is used to retrieve a set of file links of the same type as the target search term of the first user within any statistical time period upon receiving the target search term input by the first user; and obtain the search term association data of the target search term based on the file link set.

[0069] In a possible implementation of the present application, the calling module 201 is used to deduplicate the file links in the file link set of multiple statistical time periods to obtain deduplicated file links; and use the file name and file introduction information of the deduplicated file link as the search term associated data of the target search term.

[0070] In a possible implementation of the present application, the calling module 201 is used to generate link association features based on the file names and file introduction information of the file links in the file link set within each statistical time period; and fuse the link association features of multiple statistical time periods to obtain the search term association data of the target search term.

[0071] In a possible implementation of the present application, the recommendation module 203 is used to deduplicate file links in multiple records to obtain deduplicated file links; and use the file name and file introduction information of the deduplicated file link as link association data of the file link.

[0072] In a possible implementation of the present application, the recommendation module 203 is used to obtain link association features for each record based on the file name and file introduction information of the file link in the record; and fuse the link association features of the file links in multiple records to obtain link association data of the file link.

[0073] In a possible implementation manner of the present application, the link association feature includes one of the following: a link association vector, a link association matrix, and a link association subgraph.

[0074] The functions of the proposed device of this application have been Figure 1 The method embodiment shown is described in detail, so for matters that are not detailed in the description of this embodiment, please refer to the relevant description in the aforementioned embodiment, and will not be repeated here.

[0075] like Figure 3 As shown, an embodiment of the present application also provides a terminal device 300, including a processor 301, a memory 302, and a program or instruction stored in the memory 302 and executable on the processor 301. When the program or instruction is executed by the processor 301, each process of the above-mentioned recommended processing method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0076] Optionally, the embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, each process of the above-mentioned recommended method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0077] Optionally, an embodiment of the present application also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the various processes of the recommended method embodiment described above are implemented and the same technical effect can be achieved. To avoid repetition, they will not be repeated here.

[0078] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0079] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0080] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A recommendation method, characterized in that: include: When receiving a target search term input by a first user, retrieving a set of file links of the same type as the target search term from the first user's historical search terms to obtain search term associated data of the target search term; The search term associated data is compared with the link associated data of the file link corresponding to the target search term, and the file link whose similarity is greater than a similarity threshold is recommended to the first user, wherein the link associated data of the file link is data determined based on the file name and file introduction information corresponding to the file link when the record of the file link exceeds a record threshold.

2. The method according to claim 1, characterized in that The method further comprises: Obtaining historical search terms and file links of different users, wherein the file link is a link of a search result corresponding to the historical search term clicked or downloaded by the user; The historical search terms and the file links of different users are classified to obtain a set of file links corresponding to the historical search terms of each category, wherein the file links include the file names and file introduction information of the file links.

3. The method according to claim 2, characterized in that The method further comprises: The historical search terms and the file links are stored separately according to a preset statistical time period.

4. The method according to claim 2, characterized in that: The obtained historical search terms and file links of different users are classified to obtain a set of file links corresponding to the historical search terms of each category, including: The search terms of each user in each statistical period are classified, and the file links corresponding to the search terms of the same category are deduplicated to obtain a set of file links corresponding to the historical search terms of each category.

5. The method according to claim 1, characterized in that When receiving a target search term input by a first user, retrieving a set of file links of the same type as the target search term from the first user's historical search terms to obtain search term associated data of the target search term, including: In case of receiving a target search term input by a first user, retrieving a set of file links of the same type as the target search term of the first user within any statistical time period; According to the document link set, the search term associated data of the target search term is obtained.

6. The method according to claim 5, characterized in that The step of obtaining search term associated data of the target search term according to the file link set includes: Deduplication is performed on the file links in the file link sets of multiple statistical time periods to obtain deduplication file links; The file name and file introduction information of the deduplicated file link are used as search term associated data of the target search term.

7. The method according to claim 5, characterized in that The step of obtaining search term associated data of the target search term according to the file link set includes: Generate link association features according to the file names and file description information of the file links in the file link set within each statistical time period; The link association features of multiple statistical time periods are fused to obtain the search term association data of the target search term.

8. The method according to claim 1, characterized in that The method for determining the link associated data of the file link includes: Deduplication processing is performed on the file links in the multiple records to obtain deduplication file links; The file name and file introduction information of the deduplicated file link are used as link-associated data of the file link.

9. The method according to claim 1, characterized in that: The method for determining the link associated data of the file link includes: For each record, obtaining a link association feature according to the file name and file introduction information of the file link in the record; The link association features of the file links in the multiple records are fused to obtain the link association data of the file links.

10. The method according to claim 7 or 9, characterized in that: The link association feature includes one of the following: a link association vector, a link association matrix, and a link association subgraph.

Images