Network hotspot sniffing method and system based on user preference

Abstract

The invention relates to the related field of network hotspot retrieval and pushing, and discloses a network hotspot sniffing method and system based on user preferences, which realize sharing and synchronization of user preference information among a plurality of pieces of software of the same type through sharing mounting setting of a preference retrieval tree, and further can realize that when a user retrieves related information, the user preference information can be quickly and accurately retrieved. Complementary retrieval pushing is carried out through different retrieval logics of multiple software and a retrieval database available to the cloud, so that the preference content of the user is accurately judged and obtained, and compared with an independent software retrieval mode, the situation that preference judgment is inaccurate due to limitation of a software retrieval mode and the database can be effectively avoided, and the user experience is improved. And meanwhile, a low-efficiency behavior mode of manual multi-software retrieval of the user can be replaced.

Description

Technical Field

[0001] The present invention relates to the field related to network hotspot search and push, and in particular to a network hotspot sniffing method and system based on user preference. Background Art

[0002] Sniffing network hot spots and promoting content based on user preferences have many usage scenarios in daily life production and participation in social activities, such as the target group acquisition and promotion of products, hot information and video push based on user preferences, and user retrieval and acquisition of information or hot spots on the Internet, which facilitates users to efficiently obtain information from all aspects and effectively screen it, reducing the time users spend browsing non-preferred content.

[0003] In the prior art, for different software, the retrieval modes, retrieval concepts and total databases that can be searched of the retrieval systems that can be provided by their manufacturers are all different. Therefore, when a user uses a software's retrieval system to search for hot content, due to the limitations of the system itself, the efficiency of the retrieval results in meeting the user's expectations may be low. Even during the user's browsing and selection process, the retrieval target direction may be lost because the appropriate preferred keywords cannot be matched. Summary of the invention

[0004] The purpose of the present invention is to provide a network hotspot sniffing method and system based on user preference to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: A network hotspot sniffing method based on user preference, comprising: In the current search system, the user's historical preferences are obtained to match the hot information, and the hot information is matched with preferences through the user's browsing feedback to obtain the user's current preference search tree, which is used to characterize the relevance of the hot keywords and hot related words; Perform software switching detection on the user, and when a switching feedback signal is triggered, generate a shared mount based on the preference search tree, the shared mount is used to record and update the preference search tree, and the shared mount is independent of the software and the search system; Synchronize the preference search tree through shared mounts and match hot information based on the new search system to obtain hot information that complements the previous search system, perform preference matching through user browsing feedback, and update the shared mount based on the preference matching results; When the shared mount is updated, the heat information of multiple retrieval systems is re-matched based on the updated preference retrieval tree, a difference operation is performed based on the matching results and the corresponding historical push records of the current shared mount, and updated heat information is generated and pushed according to the operation results.

[0006] As a further solution of the present invention: the shared mount includes a permission group, the permission group is provided with an identity identification code for distinguishing a plurality of different permission groups, each permission group corresponds to a different shared permission list, and the shared permission list is used to record the permission status of the software; When a feedback signal is triggered to generate a shared mount, the shared permissions of the software that is subsequently switched and started are obtained to match the permission group shared with the current software, and the preference search tree in the shared mount is copied to be pushed and updated in real time between multiple search systems.

[0007] As a further solution of the present invention: it also includes a weight evaluation step, specifically including: A basic weight evaluation step, obtaining the heat data of several hot keywords in the preference search tree in the cloud, assigning values ​​to the hot keywords based on the heat data, and selecting the hot keyword with the highest heat as the current core weight object; The characterization weight evaluation step obtains user browsing feedback in real time, performs statistics based on the user browsing feedback, obtains the user's browsing statistics for different hot keywords and the corresponding content browsing completion rate, and assigns the browsing statistics and content browsing completion rate according to the preset weight ratio to obtain the characterization weight. The characterization weight is used to weaken the basic weight at a rated ratio and improve the weight relationship of multiple hot keywords.

[0008] As a further solution of the present invention: it also includes a local association step: Based on the high-weight hot keywords corresponding to the preference search tree, an input system is searched for association, and multiple associated phrases with the hot keywords are obtained through the user's historical search preferences, wherein the associated phrases are used to represent phrases similar to the hot keywords in the user's frequently used vocabulary; The preference search tree is updated through the associated phrases, and the hot information is matched and pushed simultaneously. The associated search acts on the corresponding multiple software with sharing permissions based on the current permission group.

[0009] As a further solution of the present invention: it also includes the steps of: When the user switches software, the software corresponding retrieval system searches through the cloud hotspot information and the user preference information in the software to generate a personalized push list, which is used to represent the basic push content of the software; Generate a promotion replacement data link based on the hot information obtained from the preference search tree. The promotion replacement data link is parallel to the basic push content and is in an independent user space. The user preference browsing behavior generated based on the promotion replacement data link does not affect the user preference record of the software itself. A selection signal of the user for the promotion replacement data link is obtained, and the personalized push list or hot spot information is selected and pushed based on the selection signal.

[0010] The embodiment of the present invention aims to provide a network hotspot sniffing system based on user preferences, comprising: A preference evaluation module is used to obtain the user's historical preferences in the current search system to match hot information, and to perform preference matching on the hot information through user browsing feedback to obtain the user's current preference search tree, which is used to characterize the relevance of hot keywords and hot associated words; A shared mount module, used for detecting software switching of users, and when a switching feedback signal is triggered, generating a shared mount based on the preference search tree, wherein the shared mount is used for recording and updating the preference search tree, and the shared mount is independent of the software and the search system; A complementary matching module is used to synchronize the preference search tree through the shared mount and match the hot information based on the new search system, obtain the hot information that complements the previous search system, perform preference matching through user browsing feedback, and update the shared mount based on the preference matching results; The update synchronization module is used to rematch the heat information of multiple retrieval systems based on the updated preference retrieval tree when the shared mount is updated, perform difference set operations based on the matching results and the corresponding historical push records of the current shared mount, generate and push updated heat information based on the operation results.

[0011] As a further solution of the present invention: the shared mount includes a permission group, the permission group is provided with an identity identification code for distinguishing a plurality of different permission groups, each permission group corresponds to a different shared permission list, the shared permission list is used to record the permission ownership status of the software, and also includes a clone grouping unit; The clone grouping unit is used to obtain the sharing permissions of the software that is subsequently switched and started when a feedback signal is triggered to generate a shared mount to match the permission group shared with the current software, and to copy the preference retrieval tree in the shared mount to push and update it in real time between multiple retrieval systems.

[0012] As a further solution of the present invention: it also includes a weight evaluation module, specifically including: A basic weight evaluation unit, used to obtain the heat data of several hot keywords in the preference search tree in the cloud, assign values ​​to the hot keywords based on the heat data, and select the hot keyword with the highest heat as the current core weight object; The characterization weight evaluation unit is used to obtain user browsing feedback in real time, perform statistics based on user browsing feedback, obtain user browsing statistics for different hot keywords and corresponding content browsing completion rates, and assign values ​​to the browsing statistics and content browsing completion rates according to preset weight ratios to obtain characterization weights. The characterization weights are used to weaken the basic weights at a rated ratio and improve the weight relationship between multiple hot keywords.

[0013] As a further solution of the present invention: it also includes a local association optimization module, specifically including: An input search matching unit, used to perform an associated search on the input system based on the high-weight hot keywords corresponding to the preference search tree, and obtain multiple associated phrases with the hot keywords through the user's historical search preferences, wherein the associated phrases are used to represent phrases similar to the hot keywords in the user's frequently used vocabulary; The input feature updating unit is used to update the preference search tree through the associated phrases, and simultaneously match and push hot information. The associated search acts on the corresponding multiple software with shared permissions based on the current permission group.

[0014] As a further solution of the present invention: it also includes a promotion switching management module, specifically including: A basic search unit, which is used for when a user switches software, the software corresponding search system searches through the cloud hot spot information and the user preference information in the software to generate a personalized push list, and the personalized push list is used to represent the basic push content of the software; An interactive retrieval unit, used to generate a promotion replacement data link based on the hot information obtained from the preference retrieval tree, wherein the promotion replacement data link is parallel to the basic push content and is in an independent user space, and the user preference browsing behavior generated based on the promotion replacement data link does not affect the user preference record of the software itself; The retrieval output unit is used to obtain a selection signal of the user for the promotion replacement data link, and select and push the personalized push list or hot spot information based on the selection signal.

[0015] Compared with the prior art, the beneficial effects of the present invention are: through the shared mounting setting of the preference retrieval tree, the sharing and synchronization of user preference information among multiple software of the same type is realized, so that when the user searches for relevant information, the different retrieval logics of multiple software and the retrieval database available in the cloud can be used for complementary retrieval push, so as to accurately judge and obtain the user's preference content. Compared with the independent software retrieval method, it can effectively avoid the inaccurate preference judgment caused by the limitations of the software retrieval mode and database, and can also replace the inefficient behavior mode of the user's own manual multi-software retrieval. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The figure is a flowchart of a network hotspot sniffing method based on user preference.

[0017] Figure 2 The present invention is a flowchart of the software switching judgment step in a network hotspot sniffing method based on user preference.

[0018] Figure 3 The block diagram of a network hotspot sniffing system based on user preferences. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0021] like Figure 1 The method for sniffing a network hotspot based on user preference provided by an embodiment of the present invention comprises the following steps: S10, in the current search system, obtaining the user's historical preferences to match the hot information, and performing preference matching on the hot information through the user's browsing feedback to obtain the user's current preference search tree, wherein the preference search tree is used to characterize the relevance of the hot keywords and the hot associated words; S20, performing software switching detection on the user, and when a switching feedback signal is triggered, generating a shared mount based on the preference search tree, the shared mount being used to record and update the preference search tree, and the shared mount being independent of the software and the search system; S30, synchronizing the preference search tree through the shared mount and matching hotspot information based on the new search system, obtaining hotspot information that complements the previous search system, performing preference matching through user browsing feedback, and updating the shared mount based on the preference matching result; S40, when the shared mount is updated, rematch the heat information of multiple retrieval systems based on the updated preference retrieval tree, perform a difference operation based on the matching result and the corresponding historical push record of the current shared mount, generate and push the updated heat information according to the operation result.

[0022] In this embodiment, a network hotspot sniffing method based on user preference is provided, which realizes the sharing and synchronization of user preference information among multiple software of the same type through the shared mounting setting of the preference retrieval tree, so that when the user performs relevant information retrieval, the different retrieval logics of multiple software and the retrieval database available in the cloud can be used for complementary retrieval push, so as to accurately judge and obtain the user's preference content. Compared with the independent software retrieval method, it can effectively avoid the inaccurate preference judgment caused by the limitations of the software retrieval mode and database, and can also replace the inefficient behavior mode of the user's own manual multi-software retrieval; in the prior art, for different software, its The search modes, search concepts and total databases that can be searched of the search systems provided by manufacturers are all different. Therefore, when users use a software's search system to search for hot content, due to the limitations of the system itself, the search results may not meet the user's expectations efficiently. Even in the user's browsing and selection process, the search target direction may be lost because of the inability to match the appropriate preferred keywords. In daily life, when we search for content, in order to obtain content that better meets our needs, we may use multiple software to search, select and accept content at the same time. This active process is actually difficult because the data between software cannot be shared. The efficiency and effect are both poor. To address this technical problem, the technical solution provided by this application is: when a user searches and browses hot information in a certain software, the search preference is judged based on the push and user browsed content feedback, so as to obtain the user's search preference tree during this period of time (that is, the correlation between search-related words and keywords). During a continuous period of time, if the system detects that the user switches software, it indicates that the user may need to search for content again through the search system of other search software to supplement the valid content that the current software cannot push to it. Therefore, the current system can export the preference search tree and mount it on a shared disk. In this way, the search results are separated from the software, so that multiple software participating in the search can synchronously share the acquisition and update. At this time, the preferences established by users in multiple software will be synchronized, and because the databases and search system search push logics provided by different software are different, the preference search trees generated by multiple software will be synchronized and updated complementary in the shared mount, so as to further accurately judge and determine the user's preferences and needs, optimize the sniffing search and promotion effects of hot data, and for content that is less popular in software A and cannot be effectively pushed, after complementary updates by software BC, effective sniffing and retrieval can be achieved to meet the user's search needs.

[0023] As another preferred embodiment of the present invention, the shared mount corresponds to a permission group, and the permission group corresponds to an identity identification code for distinguishing a plurality of different permission groups, and each permission group corresponds to a different shared permission list, and the shared permission list is used to record the permission ownership status of the software; When a feedback signal is triggered to generate a shared mount, the shared permissions of the software that is subsequently switched and started are obtained to match the permission group shared with the current software, and the preference search tree in the shared mount is copied to be pushed and updated in real time between multiple search systems.

[0024] In this embodiment, a setting scheme of permission groups is added to the shared mount. The purpose of setting permission groups is to group several different types of software in the user's device based on needs and manage information permissions at the same time. For example, when a user searches for short video content and information, the software they use is definitely different. How the shared mount is triggered and who can read it needs to be defined and restricted. Therefore, the user can set it according to his daily usage habits. For example, ABC software are all short video software, and the user habitually uses the three software for collaborative retrieval, then they can be set in the same permission group. However, because software B may have some information security issues, the user does not set sharing permissions for software B, which can limit B software obtains data in the shared mount, that is, for this permission group, its shared permission list includes AC software, that is, when AC software is switched, it will trigger and establish a shared mount and update the content of both parties in real time; the step of copying the preference retrieval tree is also added here. This setting is suitable for when the same software exists in multiple permission groups at the same time. For example, A is also in another group with DF software. When it switches to C software, if the original preference retrieval tree in the shared mount is directly updated synchronously, the following situation may occur: the user switches to D software again, but at this time the preference retrieval tree in the shared mount has been updated by C, but DF software cannot share the user preference content of C software. Therefore, the original preference retrieval tree can be retained by copying to adapt to complex application scenarios.

[0025] As another preferred embodiment of the present invention, it also includes a weight evaluation step, specifically including: A basic weight evaluation step, obtaining the heat data of several hot keywords in the preference search tree in the cloud, assigning values ​​to the hot keywords based on the heat data, and selecting the hot keyword with the highest heat as the current core weight object; The characterization weight evaluation step obtains user browsing feedback in real time, performs statistics based on the user browsing feedback, obtains the user's browsing statistics for different hot keywords and the corresponding content browsing completion rate, and assigns the browsing statistics and content browsing completion rate according to the preset weight ratio to obtain the characterization weight. The characterization weight is used to weaken the basic weight at a rated ratio and improve the weight relationship of multiple hot keywords.

[0026] In this embodiment, a weight evaluation step is added. The process of obtaining the user's preference search tree and weight keywords is a step-by-step judgment process. Therefore, when performing the initial push, it includes two types. First, when the user has not performed a keyword search, push is performed based on hot information. Second, when the user performs a keyword search, push is performed based on hot content that matches or is relatively consistent with the keyword, that is, a process of assigning values ​​to different keywords based on popularity. Based on the initial push, the user's browsing behavior for each pushed content can be used to judge the user's interest level. The judgment can be based on the number of views of each keyword, the browsing completion rate of the content corresponding to the keyword (the proportion of a pushed content that is browsed by the user to the total content), etc. For keywords with higher user interest, the characterized weight assignment is performed accordingly, so that more related content can be retrieved in subsequent searches.

[0027] As another preferred embodiment of the present invention, it also includes a local association step: Based on the high-weight hot keywords corresponding to the preference search tree, an input system is searched for association, and multiple associated phrases with the hot keywords are obtained through the user's historical search preferences, wherein the associated phrases are used to represent phrases similar to the hot keywords in the user's frequently used vocabulary; The preference search tree is updated through the associated phrases, and the hot information is matched and pushed simultaneously. The associated search acts on the corresponding multiple software with sharing permissions based on the current permission group.

[0028] In this embodiment, when in another software, if the user has never searched for related content, the system's first search may be slow in judging the user's preference and requires a training process. Therefore, in order to facilitate the realization of efficient search and matching purposes, the software can obtain related key words by recording requests to local tool software, such as the user's text input software, which can record the user's historical output vocabulary and sentence content, so that the user can match and screen similar keywords.

[0029] like Figure 2 As shown, as another preferred embodiment of the present invention, it also includes the steps of: S51, when the user switches software, the software corresponding retrieval system searches through the cloud hot spot information and the user preference information in the software to generate a personalized push list, where the personalized push list is used to represent the basic push content of the software; S52, generating a promotion replacement data link based on the hot information obtained from the preference search tree, wherein the promotion replacement data link is parallel to the basic push content and is in an independent user space, and the user preference browsing behavior generated based on the promotion replacement data link does not affect the user preference record of the software itself; S53, obtaining a selection signal of the user for the promotion replacement data link, and selecting and pushing the personalized push list or hot spot information based on the selection signal.

[0030] In this embodiment, relevant content is further optimized and supplemented based on a common usage scenario. The specific scenario is: when the user switches the software within the permission group, it is not for the auxiliary retrieval of multiple software, but just for daily software usage switching; therefore, a distinction process is set up here. The software can provide two sets of push content, namely, basic push content based on the software's own network hotspot information and user preferences, and retrieval content based on shared mounting (i.e., promotion replacement data). When the user needs to perform collaborative hotspot preference sniffing retrieval of multiple software, it is triggered through the promotion replacement data link.

[0031] like Figure 3 As shown, the present invention also provides a network hotspot sniffing system based on user preferences, which includes: The preference evaluation module 100 is used to obtain the user's historical preferences in the current search system to match the hot information, and to perform preference matching on the hot information through the user's browsing feedback to obtain the user's current preference search tree, wherein the preference search tree is used to characterize the relevance of the hot keywords and hot associated words; A shared mount module 200, used to detect the software switching of the user, and when a switching feedback signal is triggered, a shared mount is generated based on the preference search tree, and the shared mount is used to record and update the preference search tree, and the shared mount is independent of the software and the search system; A complementary matching module 300 is used to synchronize the preference search tree through the shared mount and match the hot information based on the new search system, obtain the hot information that complements the previous search system, perform preference matching through user browsing feedback, and update the shared mount based on the preference matching result; The update synchronization module 400 is used to rematch the heat information of multiple retrieval systems based on the updated preference retrieval tree when the shared mount is updated, perform a difference operation based on the matching results and the corresponding historical push records of the current shared mount, and generate and push updated heat information based on the operation results.

[0032] As another preferred embodiment of the present invention, the shared mount includes a permission group, the permission group is provided with an identity code for distinguishing a plurality of different permission groups, each permission group corresponds to a different shared permission list, the shared permission list is used to record the permission ownership status of the software, and also includes a clone grouping unit; The clone grouping unit is used to obtain the sharing permissions of the software that is subsequently switched and started when a feedback signal is triggered to generate a shared mount to match the permission group shared with the current software, and to copy the preference retrieval tree in the shared mount to push and update it in real time between multiple retrieval systems.

[0033] As another preferred embodiment of the present invention, it also includes a weight evaluation module, specifically including: A basic weight evaluation unit, used to obtain the heat data of several hot keywords in the preference search tree in the cloud, assign values ​​to the hot keywords based on the heat data, and select the hot keyword with the highest heat as the current core weight object; The characterization weight evaluation unit is used to obtain user browsing feedback in real time, perform statistics based on user browsing feedback, obtain user browsing statistics for different hot keywords and corresponding content browsing completion rates, and assign values ​​to the browsing statistics and content browsing completion rates according to preset weight ratios to obtain characterization weights. The characterization weights are used to weaken the basic weights at a rated ratio and improve the weight relationship between multiple hot keywords.

[0034] As another preferred embodiment of the present invention, it also includes a local association optimization module, specifically including: An input search matching unit, used to perform an associated search on the input system based on the high-weight hot keywords corresponding to the preference search tree, and obtain multiple associated phrases with the hot keywords through the user's historical search preferences, wherein the associated phrases are used to represent phrases similar to the hot keywords in the user's frequently used vocabulary; The input feature updating unit is used to update the preference search tree through the associated phrases, and simultaneously match and push hot information. The associated search acts on the corresponding multiple software with shared permissions based on the current permission group.

[0035] As another preferred embodiment of the present invention, it also includes a promotion switching management module, specifically including: A basic search unit, which is used for when a user switches software, the software corresponding search system searches through the cloud hot spot information and the user preference information in the software to generate a personalized push list, and the personalized push list is used to represent the basic push content of the software; An interactive retrieval unit, used to generate a promotion replacement data link based on the hot information obtained from the preference retrieval tree, wherein the promotion replacement data link is parallel to the basic push content and is in an independent user space, and the user preference browsing behavior generated based on the promotion replacement data link does not affect the user preference record of the software itself; The retrieval output unit is used to obtain a selection signal of the user for the promotion replacement data link, and select and push the personalized push list or hot spot information based on the selection signal.

[0036] 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 program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0037] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the disclosure in the specification and examples. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

[0038] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A network hotspot sniffing method based on user preference, characterized in that: Include: In the current search system, the user's historical preferences are obtained to match the hot information, and the hot information is matched with preferences through the user's browsing feedback to obtain the user's current preference search tree, which is used to characterize the relevance of the hot keywords and hot related words; Perform software switching detection on the user, and when a switching feedback signal is triggered, generate a shared mount based on the preference search tree, the shared mount is used to record and update the preference search tree, and the shared mount is independent of the software and the search system; Synchronize the preference search tree through shared mounts and match hot information based on the new search system to obtain hot information that complements the previous search system, perform preference matching through user browsing feedback, and update the shared mount based on the preference matching results; When the shared mount is updated, the heat information of multiple retrieval systems is re-matched based on the updated preference retrieval tree, a difference operation is performed based on the matching results and the corresponding historical push records of the current shared mount, and updated heat information is generated and pushed according to the operation results.

2. According to the method for sniffing network hotspots based on user preference according to claim 1, it is characterized in that: The shared mount corresponds to a permission group, and the permission group corresponds to an identity identification code for distinguishing a plurality of different permission groups. Each permission group corresponds to a different shared permission list, and the shared permission list is used to record the permission ownership status of the software; When a feedback signal is triggered to generate a shared mount, the shared permissions of the software that is subsequently switched and started are obtained to match the permission group shared with the current software, and the preference search tree in the shared mount is copied to be pushed and updated in real time between multiple search systems.

3. A network hotspot sniffing method based on user preference according to claim 2, characterized in that: It also includes a weight evaluation step, including: A basic weight evaluation step, obtaining the heat data of several hot keywords in the preference search tree in the cloud, assigning values ​​to the hot keywords based on the heat data, and selecting the hot keyword with the highest heat as the current core weight object; The characterization weight evaluation step obtains user browsing feedback in real time, performs statistics based on the user browsing feedback, obtains the user's browsing statistics for different hot keywords and the corresponding content browsing completion rate, and assigns the browsing statistics and content browsing completion rate according to the preset weight ratio to obtain the characterization weight. The characterization weight is used to weaken the basic weight at a rated ratio and improve the weight relationship of multiple hot keywords.

4. According to the method for sniffing network hotspots based on user preferences according to claim 3, it is characterized in that: A local association step is also included: Based on the high-weight hot keywords corresponding to the preference search tree, an input system is searched for association, and multiple associated phrases with the hot keywords are obtained through the user's historical search preferences, wherein the associated phrases are used to represent phrases similar to the hot keywords in the user's frequently used vocabulary; The preference search tree is updated through the associated phrases, and the hot information is matched and pushed simultaneously. The associated search acts on the corresponding multiple software with sharing permissions based on the current permission group.

5. According to the method for sniffing network hotspots based on user preference according to claim 2, it is characterized in that: Also includes the steps: When the user switches software, the software corresponding retrieval system searches through the cloud hotspot information and the user preference information in the software to generate a personalized push list, which is used to represent the basic push content of the software; Generate a promotion replacement data link based on the hot information obtained from the preference search tree. The promotion replacement data link is parallel to the basic push content and is in an independent user space. The user preference browsing behavior generated based on the promotion replacement data link does not affect the user preference record of the software itself. A selection signal of the user for the promotion replacement data link is obtained, and the personalized push list or hot spot information is selected and pushed based on the selection signal.

6. A network hotspot sniffing system based on user preference, characterized in that: Include: A preference evaluation module is used to obtain the user's historical preferences in the current search system to match hot information, and to perform preference matching on the hot information through user browsing feedback to obtain the user's current preference search tree, which is used to characterize the relevance of hot keywords and hot associated words; A shared mount module, used for detecting software switching of users, and when a switching feedback signal is triggered, generating a shared mount based on the preference search tree, wherein the shared mount is used for recording and updating the preference search tree, and the shared mount is independent of the software and the search system; A complementary matching module is used to synchronize the preference search tree through the shared mount and match the hot information based on the new search system, obtain the hot information that complements the previous search system, perform preference matching through user browsing feedback, and update the shared mount based on the preference matching results; The update synchronization module is used to rematch the heat information of multiple retrieval systems based on the updated preference retrieval tree when the shared mount is updated, perform difference set operations based on the matching results and the corresponding historical push records of the current shared mount, generate and push updated heat information based on the operation results.

7. A network hotspot sniffing system based on user preference according to claim 6, characterized in that: The shared mount includes a permission group, and the permission group is provided with an identity code for distinguishing a plurality of different permission groups. Each permission group corresponds to a different shared permission list, and the shared permission list is used to record the permission ownership status of the software, and also includes a clone grouping unit; The clone grouping unit is used to obtain the sharing permissions of the software that is subsequently switched and started when a feedback signal is triggered to generate a shared mount to match the permission group shared with the current software, and to copy the preference retrieval tree in the shared mount to push and update it in real time between multiple retrieval systems.

8. A network hotspot sniffing system based on user preference according to claim 7, characterized in that: It also includes a weight evaluation module, including: A basic weight evaluation unit, used to obtain the heat data of several hot keywords in the preference search tree in the cloud, assign values ​​to the hot keywords based on the heat data, and select the hot keyword with the highest heat as the current core weight object; The characterization weight evaluation unit is used to obtain user browsing feedback in real time, perform statistics based on user browsing feedback, obtain user browsing statistics for different hot keywords and corresponding content browsing completion rates, and assign values ​​to the browsing statistics and content browsing completion rates according to preset weight ratios to obtain characterization weights. The characterization weights are used to weaken the basic weights at a rated ratio and improve the weight relationship between multiple hot keywords.

9. A network hotspot sniffing system based on user preference according to claim 8, characterized in that: It also includes a local association optimization module, including: An input search matching unit, used to perform an associated search on the input system based on the high-weight hot keywords corresponding to the preference search tree, and obtain multiple associated phrases with the hot keywords through the user's historical search preferences, wherein the associated phrases are used to represent phrases similar to the hot keywords in the user's frequently used vocabulary; The input feature updating unit is used to update the preference search tree through the associated phrases, and simultaneously match and push hot information. The associated search acts on the corresponding multiple software with shared permissions based on the current permission group.

10. A network hotspot sniffing system based on user preference according to claim 7, characterized in that: It also includes a promotion switching management module, including: A basic search unit, which is used for when a user switches software, the software corresponding search system searches through the cloud hot spot information and the user preference information in the software to generate a personalized push list, and the personalized push list is used to represent the basic push content of the software; An interactive retrieval unit, used to generate a promotion replacement data link based on the hot information obtained from the preference retrieval tree, wherein the promotion replacement data link is parallel to the basic push content and is in an independent user space, and the user preference browsing behavior generated based on the promotion replacement data link does not affect the user preference record of the software itself; The retrieval output unit is used to obtain a selection signal of the user for the promotion replacement data link, and select and push the personalized push list or hot spot information based on the selection signal.

Images