Search sorting method based on user tags and storage medium

Abstract

The invention discloses a search sorting method based on a user tag and a storage medium. The search sorting method based on the user tag comprises the steps that the user tag is acquired from user information according to a preset mode; the user tag is processed; and processing the search content based on the processed label, and outputting a processing result. According to the scheme, by introducing the user labels and improving the modeling technology of the user labels and the content, the defects in the prior art are overcome, the individuation and the dynamic adaptive capacity of a search sorting system are improved, and therefore the user experience and the correlation of search results are improved.

Description

Technical Field

[0001] The present application relates to the field of data identification technology, and in particular to a search and sorting method and storage medium based on user tags. Background Art

[0002] In existing search engine technologies, the ranking of search results usually depends on factors such as keyword matching, the relevance of page content, and the authority of external links. However, these traditional ranking methods have some significant limitations in user experience, especially in the face of massive amounts of information, and cannot effectively meet the personalized needs of users.

[0003] Existing search ranking systems mainly rely on the following common ranking algorithms and mechanisms:

[0004] 1. Content-based sorting: This type of system mainly sorts according to the degree of match between the search keywords and the content. Commonly used technologies include Boolean models, vector space models, etc.

[0005] 2. Link-based sorting: Such as the PageRank algorithm, which determines the importance of a web page based on link relationships and weights, thereby affecting the sorting of search results.

[0006] 3. Sorting based on user behavior: Optimize the sorting by analyzing user behavior data such as clicks, browsing, and dwell time. For example, use machine learning models to predict the content that users may be most interested in.

[0007] Although existing technologies are able to provide more relevant search results to a certain extent, there are still significant deficiencies in personalized search ranking.

[0008] 1. Lack of personalized considerations: Most existing systems use general sorting algorithms, which fail to fully consider the personalized needs and preferences of each user, resulting in inaccurate recommendation results.

[0009] 2. Limitations of tag usage: The association modeling between user tags and content is not accurate enough, resulting in low relevance of recommended content and poor user experience.

[0010] 3. Lack of dynamism: In the existing technology, the update of user tags and the system's adaptation to user needs are slow, and the sorting results cannot be adjusted in real time to reflect the user's latest interest changes. Summary of the invention

[0011] Based on the above problems, the purpose of this application is to provide a search ranking method and storage medium based on user tags. By introducing user tags and improving the modeling technology of user tags and content, the deficiencies in the existing technology are compensated, and the personalization and dynamic adaptability of the search ranking system are improved, thereby improving the user experience and the relevance of search results.

[0012] To achieve the above objectives, this application provides the following solutions:

[0013] In a first aspect, the present application provides a search ranking method based on user tags, comprising:

[0014] Obtaining a user tag from user information in a preset manner;

[0015] Processing the user tag;

[0016] The search content is processed based on the processed tags, and the processing results are output.

[0017] Optionally, the step of obtaining the user tag from the user information in a preset manner includes:

[0018] Get user tags based on user registration information;

[0019] Obtain user tags based on user behavior data;

[0020] Obtain user tags based on user interaction data;

[0021] Get user tags based on user preferences;

[0022] Obtain user tags based on user job search information;

[0023] Get user tags based on user profile information.

[0024] Optionally, the user information includes, but is not limited to: registration information, behavior data, interaction data, preference settings, job search information, resume information, and behavior data.

[0025] Optionally, processing the tag includes:

[0026] Classifying the user tags;

[0027] Weights are assigned to the classified labels.

[0028] Optionally, before the step of classifying the user tags, the method further includes:

[0029] Cleaning the user tags includes: removing noise tags and / or filtering low-frequency tags;

[0030] Merge and split the cleaned user tags;

[0031] Normalize the merged and split user labels.

[0032] Optionally, classifying the user tags includes:

[0033] Clustering the user tags based on a clustering algorithm to obtain tag groups;

[0034] Corresponding weights are assigned to the tag groups based on preset rules.

[0035] Optionally, the method further comprises:

[0036] Obtain user feedback during the search process for analysis;

[0037] The weights are adjusted based on the analysis results.

[0038] Optionally, processing the search content based on the processed tags includes:

[0039] Matching the processed tags with search results;

[0040] Sorting the search results corresponding to the search content according to the matching degree;

[0041] The search results are optimized based on a collaborative filtering algorithm and a content-based recommendation algorithm.

[0042] Optionally, before the step of matching the processed tags with the search content, the step includes:

[0043] Extracting keywords based on the search content;

[0044] Establish an index relationship between tags and keywords.

[0045] In a second aspect, the present application provides a computer-readable storage medium, comprising: when the computer program is executed by a processor, the steps of implementing the above-mentioned user tag-based search ranking method.

[0046] According to a user tag-based search and ranking method provided by the present application, after processing the acquired user tags and processing the searched content based on the user tags, the obtained search results meet the personalized needs of users. The present application scheme introduces user tags and improves the modeling technology of user tags and content to make up for the deficiencies in the prior art, improve the personalization and dynamic adaptability of the search and ranking system, and thus improve the user experience and the relevance of search results. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 A flowchart of a user tag-based search and sorting method provided in an embodiment of the present application;

[0049] Figure 2 A schematic diagram of a process for processing acquired tags provided in an embodiment of the present application;

[0050] Figure 3 A schematic diagram of a process for processing search content based on processed tags provided in an embodiment of the present application;

[0051] Figure 4 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] 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 only 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.

[0053] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0054] The search ranking systems in the prior art usually rely on general ranking algorithms and fail to fully consider the personalized needs and preferences of users, resulting in inaccurate search results. In particular, when users search for jobs on job search platforms, there is often a lot of job information that does not match the user's needs.

[0055] refer to Figure 1 As shown, the present application provides a search ranking method based on user tags, comprising:

[0056] Obtaining a user tag from user information in a preset manner;

[0057] Processing the user tag;

[0058] The search content is processed based on the processed tags, and the processing results are output.

[0059] In an embodiment of the present application, user tag information is first obtained from information related to the user in a preset manner, for example, user tags are obtained based on user registration information, user tags are obtained based on user behavior data, user tags are obtained based on user interaction data, user tags are obtained based on user preference settings, user tags are obtained based on user job search information, and user tags are obtained based on user resume information. Since there are usually many user tags extracted through different channels, it is necessary to further process the user tags so that the obtained user tags more accurately reflect the user's interests and needs. Furthermore, the searched content is matched with the processed user tags to improve the relevance of the search results, so that the search results are more in line with the user's personalized needs, and finally the search results matched with the user tags are output for the user to review.

[0060] In the embodiment of the present application, when obtaining user tags, user information is first obtained, which can be user registration information, such as age, gender, etc.; the information can be user interaction data, such as user comment information, user social interaction information; the information can also be user preference information, such as user interests and hobbies; the information can be information posted by users on the Internet, such as user job search information; it can also be user resume information in real life, such as education, interests and hobbies, etc.; it can also be user behavior data and other information. The obtained user information is further mined and analyzed to accurately extract user tags from it.

[0061] In a scenario of an embodiment, by deeply mining and analyzing the user's job search information, labels such as position type, position group type, working city, salary and benefits can be extracted; by deeply mining the user's resume information, labels such as subject information, educational information, talent information, etc. can be extracted; by analyzing the user's behavioral data, labels such as user status and user preferences can be extracted.

[0062] In a scenario of an embodiment, when obtaining user tags, the user can also input corresponding information tags according to their actual needs, such as social circle tags, personality tags, etc. In this embodiment, the user can also obtain corresponding tags through the social circle, for example, by sending a tag acquisition link to a friend to directly obtain the tag from the friend.

[0063] refer to Figure 2 As shown, when processing the acquired tags, the following steps are performed, including:

[0064] Classifying the user tags;

[0065] Weights are assigned to the classified labels.

[0066] In the embodiment of the present application, in order to more accurately reflect the personalized needs of users, a large number of user tags are obtained from different channels, but a large number of user tags often have messy information. Therefore, in this embodiment, the user tags are clustered by a clustering algorithm to obtain a tag group. Specifically, similar user tags are clustered, for example, the user's business hobbies and preferences are clustered; for another example, if the user's social circle is a professional circle, the tags of the social circle and the professional tags can be clustered, and then after clustering the obtained tags, a more abstract and general tag group is obtained, thereby improving the understanding and expression of user preferences. Further, according to the importance of different tags and user behavior characteristics, different weights are assigned to each tag. For example, high weights are set for the user's position tag, salary tag, work location tag, etc., and lower weights are set for the user's interest and hobby tags, user preference tags, etc. By setting different weights for tags, it is possible to more accurately reflect the user's actual needs and preferences.

[0067] In a scenario of one embodiment, when assigning weights to user tags, different weights can be set for user tags according to different search scenarios. For example, when a user is searching for job information, a higher weight is set for user work-related tags, such as position tags, salary tags, and welfare tags; when a user is searching for information related to work content, a higher weight is set for user occupation-related tags.

[0068] In another embodiment scenario, when weights are assigned to user tags, the weights of the tags may be adjusted according to the user's operations, thereby satisfying the user's actual needs and preferences.

[0069] In one embodiment, the user tag-based search ranking method of the present application further includes:

[0070] Obtain user feedback during the search process for analysis;

[0071] The weights are adjusted based on the analysis results.

[0072] In this embodiment, in order to ensure that the search results are always highly consistent with the user's current needs, the dynamic weight adjustment mechanism is used to respond to user feedback in real time. For example, the tag weight is dynamically adjusted according to the user's click, stay time and other behavioral data, so as to optimize the ranking of the search results in real time. Furthermore, based on the powerful learning and adaptive capabilities of the deep learning network, during the user's use, the search results will increasingly meet the user's long-term interests and preferences.

[0073] In an exemplary embodiment, before the step of classifying the user tags, the method further includes:

[0074] Cleaning the user tags includes: removing noise tags and / or filtering low-frequency tags;

[0075] Merge and split the cleaned user tags;

[0076] Normalize the merged and split user labels.

[0077] In this embodiment, after obtaining the user tags, first, the user tags are cleaned. Specifically, noise tags are removed, and some vague, unclear or meaningless tags are removed, such as "other", "unspecified", "none", etc. These tags have no practical value for subsequent analysis and application, and will affect the accuracy of the processing results. Exclude some abnormal or erroneous data, such as erroneous tags that may be generated due to system failure or user misoperation; filter low-frequency tags, and filter out tags that appear very rarely in the user group. Because these tags may only apply to a very small number of users, they may not be representative in the overall analysis and application, and may cause overfitting problems, affecting the effect of subsequent processing. Then, the cleaned user tags are merged and split. Specifically, synonymous tags are merged, and tags with similar or identical semantics are merged to reduce the redundancy of tags. For example, "like running", "running enthusiasts" and "people who run frequently" are merged into "running enthusiasts". Natural language processing technology (such as lexical analysis, semantic analysis) and pre-set synonym dictionaries are used to identify and merge tags with similar meanings to improve the consistency and manageability of tags. Split compound tags. If a tag contains multiple concepts, split it into multiple single-concept tags. For example, split "like outdoor hiking and photography" into "outdoor hiking enthusiasts" and "photography enthusiasts" to more accurately reflect the different interests or characteristics of users. Secondly, standardize the merged and split user tags. Specifically, unify the format: convert the tags to a unified format, such as converting all tags to lowercase or uppercase to avoid mismatches caused by different case. For example, unify "Running" and "running" into "running". Remove special characters or extra spaces in tags to ensure the simplicity and consistency of tags, such as converting "@book_lover" to "booklover". Data type conversion: ensure that the data type of the tags is unified, such as storing all tags as string types, and converting tags that may have been stored as numbers or other types accordingly to facilitate subsequent processing and analysis.

[0078] refer to Figure 3 As shown, the search content is processed based on the processed tags, and the steps are as follows, including:

[0079] Matching the processed tags with search results;

[0080] Sorting the search results corresponding to the search content according to the matching degree;

[0081] The search results are optimized based on a collaborative filtering algorithm and a content-based recommendation algorithm.

[0082] In an embodiment of the present application, before performing a content search, the content to be searched is first preprocessed through a preprocessing mechanism, keywords of the content to be searched are extracted, and an index of user tags and keywords is established. In this embodiment, the preprocessing mechanism and the establishment of a keyword index can greatly improve the efficiency of the search and reduce the response time of the system. After the search results are obtained by searching the content, a personalized sorting algorithm based on user tags is used to match the user tags with the search results, and the search results are sorted according to the degree of matching. Furthermore, the sorting results are optimized by combining the collaborative filtering algorithm and the content-based recommendation algorithm, so that the sorting results are more in line with the user's preferences.

[0083] In an embodiment of the present application, by setting up a content tag establishment and management mechanism, tags related to the search content are automatically generated and managed, and tags are dynamically updated according to changes in the content to ensure the accuracy and relevance between search results and tags.

[0084] In summary, the user tag-based search sorting solution provided by the present application reduces the interference of irrelevant information in search results by comprehensively considering user tags and personalized needs, so that users can efficiently find content that meets their interests and needs.

[0085] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store video tag processing data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a search and sorting method based on user tags is implemented.

[0086] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0087] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0088] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0089] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0090] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0091] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0092] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0093] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0094] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A search ranking method based on user tags, characterized in that: The search and sorting method based on user tags comprises: Obtaining a user tag from user information in a preset manner; Processing the user tag; The search content is processed based on the processed tags, and the processing results are output.

2. The search ranking method based on user tags according to claim 1 is characterized in that: The steps of obtaining the user tag from the user information in a preset manner include: Get user tags based on user registration information; Obtain user tags based on user behavior data; Obtain user tags based on user interaction data; Get user tags based on user preferences; Obtain user tags based on user job search information; Get user tags based on user profile information.

3. The search and ranking method based on user tags according to claim 2 is characterized in that: The user information includes but is not limited to: registration information, behavior data, interaction data, preference settings, job search information, resume information, and behavior data.

4. The search ranking method based on user tags according to claim 1 is characterized in that: Processing the tag includes: Classifying the user tags; Weights are assigned to the classified labels.

5. The search ranking method based on user tags according to claim 4 is characterized in that: Before the step of classifying the user tags, the method further includes: Cleaning the user tags includes: removing noise tags and / or filtering low-frequency tags; Merge and split the cleaned user tags; Normalize the merged and split user labels.

6. The search ranking method based on user tags according to claim 4 is characterized in that: Classifying the user tags includes: Clustering the user tags based on a clustering algorithm to obtain tag groups; Corresponding weights are assigned to the tag groups based on preset rules.

7. The user tag-based search ranking method according to claim 5 or 6, characterized in that: The method further comprises: Obtain user feedback during the search process for analysis; The weights are adjusted based on the analysis results.

8. The search ranking method based on user tags according to claim 1 is characterized in that: Processing the search content based on the processed tags includes: Matching the processed tags with search results; Sorting the search results corresponding to the search content according to the matching degree; The search results are optimized based on a collaborative filtering algorithm and a content-based recommendation algorithm.

9. The search ranking method based on user tags according to claim 8 is characterized in that: The step of matching the processed tags with the search content includes: Extracting keywords based on the search content; An index relationship between the tag and the keyword is established.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the user tag-based search ranking method described in any one of claims 1 to 9 are implemented.

Images