Potential user priority determination method, apparatus, device, and storage medium

Abstract

This invention belongs to the field of data mining technology and discloses a method, apparatus, device, and storage medium for determining the priority of potential users. The method includes: obtaining search keywords corresponding to the user to be mined; searching for the search keywords through multiple different search engines to obtain search results from each search engine; determining the recall relationship between each search engine and the search keywords based on the search results; and determining the potential priority of the user to be mined based on the recall relationship. Through the above method, the potential priority of users is determined based on the recall relationship between each search engine and the search keywords, and the user's multimedia information delivery intention is determined based on the multimedia information already delivered to the user. This provides data support for search engine operators to expand their business and facilitates search engine operators in understanding users' multimedia information delivery needs.

Description

Technical Field

[0001] This invention relates to the field of data mining technology, and in particular to a method, apparatus, device, and storage medium for determining the priority of potential users. Background Technology

[0002] Once a company partners with a search engine operator, the operator will distribute relevant multimedia information to achieve advertising and promotional goals. However, search engine operators cannot know in advance which companies intend to cooperate, thus hindering their ability to meet business expansion needs.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this invention is to provide a method, apparatus, device, and storage medium for determining the priority of potential users, aiming to solve the technical problem that current search engine operators cannot know in advance which companies have the intention to cooperate, thus failing to meet the needs of business expansion.

[0005] To achieve the above objectives, the present invention provides a method for determining the priority of potential users, the method comprising the following steps:

[0006] Obtain the search keywords corresponding to the users to be mined;

[0007] The search keywords were searched using multiple different search engines to obtain the search results from each search engine.

[0008] The recall relationship between each search engine and the search keywords is determined based on the search results returned by each search engine;

[0009] The potential priority of the users to be mined is determined based on the recall relationship.

[0010] Optionally, determining the recall relationship between each search engine and the search keyword based on the search results returned by each search engine includes:

[0011] Detect the homepage layout information of the search results returned by each search engine;

[0012] Determine whether the homepage layout information contains preset multimedia tags to obtain the layout detection result;

[0013] The recall relationship between each search engine and the search keywords is determined based on the layout detection results.

[0014] Optionally, determining the recall relationship between each search engine and the search keyword based on the layout detection results includes:

[0015] When the layout detection result of the target search engine shows that the homepage layout information contains preset multimedia tags, it is determined that there is a recall relationship between the target search engine and the search keywords.

[0016] Optionally, determining the recall relationship between each search engine and the search keyword based on the search results returned by each search engine includes:

[0017] The first search result is determined from the search results returned by each search engine;

[0018] The system detects whether the first search result contains an image and determines the pixel value corresponding to the image to obtain the detection result.

[0019] The recall relationship between each search engine and the search keywords is determined based on the detection results.

[0020] Optionally, determining the recall relationship between each search engine and the search keyword based on the detection results includes:

[0021] When the current search engine's detection result shows that the first search result contains an image and the pixel value is greater than a preset threshold, it is determined that there is a recall relationship between the target search engine and the search keyword.

[0022] Optionally, before obtaining the search keywords corresponding to the user to be mined, the method further includes:

[0023] Generate industry keywords based on multiple different preset industry types;

[0024] User mining is performed based on the industry keywords to determine multiple user information corresponding to each of the preset industry types;

[0025] Generate a list of users to be mined for each of the preset industry types based on the multiple user information;

[0026] Iterate through the list of users to be mined, and use the users found during the iteration as the users to be mined.

[0027] Optionally, after determining the potential priority corresponding to the user to be mined based on the recall relationship, the method further includes:

[0028] Determine the next list of users to be mined according to the industry mining order, select users to be mined from the next list of users to be mined, and return to the step of obtaining the search keywords corresponding to the users to be mined.

[0029] Optionally, determining the potential priority corresponding to the user to be mined based on the recall relationship includes:

[0030] Determine the number of search engines among the plurality of different search engines that have a recall relationship with the search keywords;

[0031] The potential priority of the user to be mined is determined based on the number of engines.

[0032] Optionally, determining the potential priority of the user to be mined based on the number of engines includes:

[0033] The number of engines is compared with the standard evaluation range corresponding to each potential priority to obtain the comparison results;

[0034] The potential priority of the user to be mined is determined based on the comparison results.

[0035] Optionally, the method further includes:

[0036] A recommendation list is generated based on the potential priority of the users to be explored.

[0037] The recommended list is pushed to the target server.

[0038] Furthermore, to achieve the above objectives, the present invention also proposes a potential user priority determination device, the potential user priority determination device comprising:

[0039] The acquisition module is used to acquire the search keywords corresponding to the users to be mined;

[0040] The search module is used to search for the search keywords through multiple different search engines and obtain the search results returned by each search engine;

[0041] The determination module is used to determine the recall relationship between each search engine and the search keywords based on the search results returned by each search engine;

[0042] The determining module is further configured to determine the potential priority corresponding to the user to be mined based on the recall relationship.

[0043] Optionally, the determining module is further configured to detect the homepage layout information of the search results returned by each search engine, determine whether the homepage layout information contains preset multimedia tags, obtain layout detection results, and determine the recall relationship between each search engine and the search keywords based on the layout detection results.

[0044] Optionally, the determining module is further configured to determine that there is a recall relationship between the target search engine and the search keyword when the layout detection result of the target search engine is that the homepage layout information contains preset multimedia tags.

[0045] Optionally, the determining module is further configured to determine the first search result from the search results returned by each search engine, detect whether the first search result contains an image, determine the pixel value corresponding to the image, obtain a detection result, and determine the recall relationship between each search engine and the search keyword based on the detection result.

[0046] Optionally, the determining module is further configured to determine that there is a recall relationship between the target search engine and the search keyword when the detection result of the current search engine is that the first search result contains an image and the pixel value is greater than a preset threshold.

[0047] Optionally, the potential user priority determination device further includes a mining module;

[0048] The mining module is used to generate industry keywords according to multiple different preset industry types, perform user mining based on the industry keywords, determine multiple user information corresponding to each preset industry type, generate a list of users to be mined for each preset industry type based on the multiple user information, traverse the list of users to be mined, and take the traversed users as users to be mined.

[0049] Optionally, the acquisition module is further configured to determine the next list of users to be acquired according to the industry mining order, select users to be acquired from the next list of users to be acquired, and return to the step of acquiring the search keywords corresponding to the users to be acquired.

[0050] Optionally, the determining module is further configured to determine the number of engines among the plurality of different search engines that have a recall relationship with the search keywords, and determine the potential priority corresponding to the user to be mined based on the number of engines.

[0051] Furthermore, to achieve the above objectives, the present invention also proposes a potential user priority determination device, the potential user priority determination device comprising: a memory, a processor, and a potential user priority determination program stored in the memory and executable on the processor, the potential user priority determination program being configured to implement the potential user priority determination method as described above.

[0052] In addition, to achieve the above objectives, the present invention also proposes a storage medium storing a potential user priority determination program, which, when executed by a processor, implements the potential user priority determination method as described above.

[0053] This invention obtains the search keywords corresponding to the users to be mined; searches for the search keywords using multiple different search engines to obtain the search results from each search engine; determines the recall relationship between each search engine and the search keywords based on the search results; and determines the potential priority of the users to be mined based on the recall relationship. Through the above methods, the potential priority of users is determined based on the recall relationship between each search engine and the search keywords, and the user's multimedia information delivery intention is determined based on the multimedia information already delivered to the user. This provides data support for search engine operators to expand their business and facilitates search engine operators in understanding users' multimedia information delivery needs. Attached Figure Description

[0054] Figure 1 This is a schematic diagram of the structure of a potential user priority determination device in the hardware operating environment involved in the embodiments of the present invention;

[0055] Figure 2 This is a flowchart illustrating the first embodiment of the potential user priority determination method of the present invention;

[0056] Figure 3 This is a flowchart illustrating the second embodiment of the potential user priority determination method of the present invention;

[0057] Figure 4 This is a flowchart illustrating the third embodiment of the potential user priority determination method of the present invention;

[0058] Figure 5 This is a flowchart illustrating the fourth embodiment of the potential user priority determination method of the present invention.

[0059] Figure 6 This is a structural block diagram of a first embodiment of the potential user priority determination device of the present invention.

[0060] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0061] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0062] Reference Figure 1 , Figure 1 This is a schematic diagram of the device structure for determining the potential user priority of the hardware operating environment involved in the embodiments of the present invention.

[0063] like Figure 1As shown, the potential user priority determination device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0064] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the device for prioritizing potential users and may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0065] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a potential user priority determination program.

[0066] exist Figure 1 In the potential user priority determination device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the potential user priority determination device of the present invention can be set in the potential user priority determination device, and the potential user priority determination device calls the potential user priority determination program stored in the memory 1005 through the processor 1001 and executes the potential user priority determination method provided in the embodiment of the present invention.

[0067] This invention provides a method for determining the priority of potential users, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the potential user priority determination method of the present invention.

[0068] In this embodiment, the method for determining the priority of potential users includes the following steps:

[0069] Step S10: Obtain the search keywords corresponding to the users to be mined.

[0070] It is understood that the execution subject of this embodiment is a potential user priority determination device. The potential user priority determination device can be a computer, a server, or other devices with the same or similar functions. This embodiment does not limit this.

[0071] It should be noted that the user to be mined can be the username entered by the staff. In the specific implementation, search keywords are extracted from the user information of the user to be mined, mainly including the username and the industry. In the specific implementation, a prefix word library and a suffix word library of company names are built in advance. The username is segmented and search keywords are extracted based on the prefix word library and the suffix word library of company names. For example, if the prefix word library contains "City A" and the suffix word library contains "Company B (company type)", when the username of the user to be mined is "City A, Name B, Company B", the extracted search keyword is "Name C". In another implementation method, the search keyword is generated by concatenating the username keyword and the industry keyword. For example, if the username keyword is "Name C" and the industry keyword is "Industry D", the generated search keyword is "Industry D, Name C".

[0072] It should be understood that the users to be mined can also be obtained by iterating through the user list. In the specific implementation, multiple preset industry types are set in advance to classify a large number of companies, and competitor companies in each industry type are mined. A list of companies to be mined is generated based on the mined company names, and the users to be mined are obtained by iterating through the list of companies to be mined.

[0073] Step S20: Search for the search keywords using multiple different search engines to obtain the search results from each search engine.

[0074] It should be noted that a search engine table is pre-configured, storing the URLs of each search engine. URLs are selected sequentially from this table. In the actual implementation, when executing a search task, a corresponding number of virtual machines are launched based on the number of search engines. A virtual machine is assigned to each search engine, and the search keywords and their corresponding search engine URLs are sent to the respective virtual machines for synchronous searching. The system also receives the search results from each search engine.

[0075] Step S30: Determine the recall relationship between each search engine and the search keywords based on the search results returned by each search engine.

[0076] It should be understood that recall relationships include those with and without recall relationships. Having a recall relationship indicates that the search engine's response to the search keywords meets expectations, while not having a recall relationship indicates that the search engine's response to the search keywords does not meet expectations. In this specific implementation, this embodiment determines whether a user has a need for multimedia information delivery based on the search results returned by each search engine.

[0077] Step S40: Determine the potential priority of the user to be mined based on the recall relationship.

[0078] It should be noted that if any search engine has a recall relationship with the search keyword, it indicates that the user has a need for multimedia information delivery, and this user is classified as a priority user. If no search engine has a recall relationship with the search keyword, it indicates that the user does not have a need for multimedia information delivery, and this user is classified as a regular user.

[0079] Specifically, step S40 includes: determining the number of engines among the plurality of different search engines that have a recall relationship with the search keyword; and determining the potential priority corresponding to the user to be mined based on the number of engines.

[0080] It should be understood that the more search engines that have a recall relationship with the search keywords, the higher the potential priority of the user. For example, if users A and B are searched for keywords by 10 search engines respectively, and one search engine has a recall relationship with user A's search keywords, while five search engines have a recall relationship with user B's search keywords, then user B's potential priority is determined to be higher than user A's.

[0081] Further, determining the potential priority corresponding to the user to be mined based on the number of engines includes: comparing the number of engines with the standard evaluation range corresponding to each potential priority to obtain a comparison result; and determining the potential priority corresponding to the user to be mined based on the comparison result.

[0082] It should be noted that multiple standard evaluation ranges are pre-constructed, each corresponding to a potential priority level. Specifically, the size of the standard evaluation range is related to the total number of search engines and the number of potential priority levels. The currently determined number of engines is compared with the standard evaluation ranges for each potential priority level to determine the corresponding potential priority. For example, if there are 9 search engines and 3 potential priority levels (low, medium, and high), the standard evaluation ranges for each potential priority are [1,3], [4,6], and [7,9]. If the currently determined number of engines is [1,3], the potential priority for the user to be mined is low; if it is [4,6], it is medium; and if it is [7,9], it is high.

[0083] Furthermore, the method also includes: generating a recommendation list based on the potential priority of the user to be mined; and pushing the recommendation list to the target server.

[0084] In the implementation, the potential priority of users to be mined is determined. Multiple users are then sorted from highest to lowest potential priority to generate a recommendation list. Ordinary users who have no recall relationship with any search engine or search keyword are not recommended. An operations system is installed on the target server to push the recommendation list to the target server, enabling the search engine operators to understand users' multimedia information delivery needs.

[0085] This embodiment obtains the search keywords corresponding to the users to be mined; searches for the search keywords through multiple different search engines to obtain the search results from each search engine; determines the recall relationship between each search engine and the search keywords based on the search results; and determines the potential priority of the users to be mined based on the recall relationship. Through the above method, the potential priority of users is determined based on the recall relationship between each search engine and the search keywords, and the user's multimedia information delivery intention is determined based on the multimedia information already delivered to the user. This provides data support for search engine operators to expand their business and facilitates search engine operators in understanding users' multimedia information delivery needs.

[0086] refer to Figure 3 , Figure 3 This is a flowchart illustrating the second embodiment of the potential user priority determination method of the present invention.

[0087] Based on the first embodiment described above, step S30 of the potential user priority determination method in this embodiment includes:

[0088] Step S301: Detect the homepage layout information of the search results returned by each search engine.

[0089] Step S302: Determine whether the homepage layout information contains preset multimedia tags, and obtain the layout detection result.

[0090] It is understood that the homepage layout information refers to the layout information of the first page of search results. Since the same user may have placed multiple multimedia messages on the search engine, this embodiment detects the layout information of the top-ranked search results. The homepage layout information of the search results is crawled using a crawling tool to determine whether it contains preset multimedia tags. This determines whether the search engine's retrieval results for the search keywords meet the requirements. Specifically, if the homepage layout information contains preset multimedia tags, the retrieval results are deemed to meet the requirements, meaning it is determined that the user to be mined has placed multimedia messages on that search engine. Preset multimedia tags, such as the tag containing the word "advertisement," are considered acceptable when the homepage layout information contains such a tag.

[0091] Step S303: Determine the recall relationship between each search engine and the search keywords based on the layout detection results.

[0092] Specifically, step S303 includes: when the layout detection result of the target search engine is that the homepage layout information contains preset multimedia tags, determining that there is a recall relationship between the target search engine and the search keywords.

[0093] It should be noted that the layout detection result is the flag value corresponding to the pre-set flag. In the specific implementation, it checks whether the homepage layout information contains preset multimedia tags. If so, flag=1 is set; otherwise, flag=0 is set. The recall relationship between each search engine and the search keywords is determined based on the flag value. When flag=1, it is determined that there is a recall relationship between the target search engine and the search keywords; when flag=0, it is determined that there is no recall relationship between the target search engine and the search keywords.

[0094] This embodiment obtains the search keywords corresponding to the user to be mined; searches for the search keywords through multiple different search engines to obtain the search results returned by each search engine; detects the homepage layout information of the search results returned by each search engine; determines whether the homepage layout information contains preset multimedia tags, obtaining layout detection results; determines the recall relationship between each search engine and the search keywords based on the layout detection results; and determines the potential priority corresponding to the user to be mined based on the recall relationship. Through the above method, it determines whether the homepage layout information returned by each search engine contains preset multimedia tags, determines the recall relationship between each search engine and the search keywords based on the layout detection results, thereby determining whether each search engine contains multimedia information already delivered by the user to be mined, determining the user's multimedia information delivery intention based on the recall relationship, setting potential priorities for the user to be mined, providing data support for search engine operators to expand their business, and facilitating search engine operators to understand users' multimedia information delivery needs.

[0095] refer to Figure 4 , Figure 4 This is a flowchart illustrating the third embodiment of the potential user priority determination method of the present invention.

[0096] Based on the first embodiment described above, step S30 of the potential user priority determination method in this embodiment includes:

[0097] Step S304: Determine the first search result from the search results returned by each search engine.

[0098] Understandably, when a search engine performs a search based on search keywords, it can obtain several search results. It then selects the first search result from these results, which represents the first search result among all search results.

[0099] Step S305: Detect whether the first search result contains an image, and determine the pixel value corresponding to the image to obtain the detection result.

[0100] It should be noted that in the specific implementation, if a company publishes multimedia information on a search engine, the first search result returned by the search engine for the search keywords will contain an image. In this embodiment, the search engine determines whether the recall results for the search keywords meet the requirements by detecting whether the first search result contains an image. To avoid the influence of other webpage thumbnails on the detection results, this embodiment uses a crawling tool to crawl the image information contained in the first search result and determines the corresponding pixel value based on the image information. If the pixel value of the image is less than a certain value, it indicates that the first search result does not meet the preset requirements.

[0101] Step S306: Determine the recall relationship between each search engine and the search keywords based on the detection results.

[0102] Specifically, step S306 includes: when the detection result of the current search engine is that the first search result contains an image and the pixel value is greater than a preset threshold, determining that there is a recall relationship between the target search engine and the search keyword.

[0103] It should be understood that the detection result is the flag value corresponding to the pre-set flag. In the specific implementation, it checks whether the first search result contains an image and determines whether the pixel value corresponding to that image is greater than a preset threshold. If the first search result contains an image and the pixel value corresponding to that image is greater than the preset threshold, then flag=1; if the first search result does not contain an image or the pixel value of the image is less than or equal to the preset threshold, then flag=0. The recall relationship between each search engine and the search keyword is determined based on the flag value. When flag=1, it is determined that there is a recall relationship between the target search engine and the search keyword; when flag=0, it is determined that there is no recall relationship between the target search engine and the search keyword.

[0104] This embodiment obtains the search keywords corresponding to the user to be mined; searches for the search keywords through multiple different search engines to obtain the search results returned by each search engine; determines the first search result from the search results returned by each search engine; detects whether the first search result contains an image and determines the corresponding pixel value of the image to obtain the detection result; determines the recall relationship between each search engine and the search keywords based on the detection result; and determines the potential priority of the user to be mined based on the recall relationship. Through the above method, it detects whether the first search result returned by each search engine contains an image and determines the pixel value of the image to obtain the detection result. Based on the detection result, it determines the recall relationship between each search engine and the search keywords, thereby determining whether each search engine contains multimedia information already delivered by the user to be mined. Based on the recall relationship, it determines the user's multimedia information delivery intention, sets the potential priority for the user to be mined, provides data support for search engine operators to expand their business, and facilitates search engine operators to understand the user's multimedia information delivery needs.

[0105] refer to Figure 5 , Figure 5 This is a flowchart illustrating the fourth embodiment of the potential user priority determination method of the present invention.

[0106] Based on the first embodiment described above, the potential user priority determination method in this embodiment further includes, before step S10:

[0107] Step S101: Generate industry keywords based on multiple different preset industry types.

[0108] It should be understood that multiple pre-defined industry types are pre-set to categorize a large number of companies. These include, for example, new energy vehicles, remote work, vocational training, home appliances, mobile games, and web games. Industry keywords are generated based on these industry types, and data is searched and mined using search engines and big data websites. In the specific implementation, leading companies corresponding to each of the pre-defined industry types are identified, and these leading companies are used as the basis for user data mining; that is, industry keywords are generated based on the leading companies in each pre-defined industry type.

[0109] Step S102: Perform user mining based on the industry keywords to determine multiple user information corresponding to each of the preset industry types.

[0110] It should be noted that, based on search engines and big data websites, we analyze well-known companies and competitors in various industries through industry keyword analysis to obtain multiple user information for each industry type.

[0111] Step S103: Generate a list of users to be mined corresponding to each preset industry type based on the multiple user information.

[0112] Step S104: Traverse the list of users to be mined and select the users found during the traversal as users to be mined.

[0113] It should be understood that the user information mined from each industry type is filled into a blank list to generate a list of users to be mined for each industry type. When performing the task of determining the priority of potential users, the list of users to be mined for each industry type is traversed, and the corresponding potential user priority determination operation is performed on the user information that is traversed.

[0114] Furthermore, after step S40, the method further includes: determining the next list of users to be mined according to the industry mining order, selecting users to be mined from the next list of users to be mined, and returning to the step of obtaining the search keywords corresponding to the users to be mined.

[0115] It should be noted that the industry mining order corresponding to each preset industry type is set in advance. According to the industry mining order, the list of users to be mined in the corresponding industry is retrieved from the preset storage area in turn. The list of users to be mined is traversed, and the corresponding potential user priority determination task is performed on the users to be mined, so as to realize the multimedia information delivery intention mining of potential users in each industry.

[0116] This embodiment generates industry keywords based on multiple preset industry types; it performs user mining based on these industry keywords to identify multiple user information corresponding to each preset industry type; it generates a list of users to be mined for each preset industry type based on this user information; it iterates through the list of users to be mined and identifies the users found; it obtains the search keywords corresponding to the users to be mined; it searches for these search keywords using multiple different search engines to obtain the search results from each search engine; it determines the recall relationship between each search engine and the search keywords based on the search results; and it determines the potential priority of the users to be mined based on the recall relationship. Through this method, a user list corresponding to multiple industry types is pre-built, keyword searches are performed on users within each industry, the recall relationship between multiple search engines and the search keywords is determined, and the user's multimedia information delivery intention is determined based on the recall relationship. This assigns potential priorities to each user, providing data support for search engine operators to expand their business and facilitating their understanding of users' multimedia information delivery needs.

[0117] Furthermore, this embodiment of the invention also proposes a storage medium storing a potential user priority determination program, which, when executed by a processor, implements the potential user priority determination method as described above.

[0118] Since this storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought about by the technical solutions of the above embodiments, which will not be repeated here.

[0119] Reference Figure 6 , Figure 6 This is a structural block diagram of a first embodiment of the potential user priority determination device of the present invention.

[0120] like Figure 6 As shown, the potential user priority determination device proposed in this embodiment of the invention includes:

[0121] Module 10 is used to obtain the search keywords corresponding to the users to be mined.

[0122] The search module 20 is used to search for the search keywords through multiple different search engines and obtain the search results returned by each search engine.

[0123] The determination module 30 is used to determine the recall relationship between each search engine and the search keywords based on the search results fed back by each search engine.

[0124] The determining module 30 is further configured to determine the potential priority corresponding to the user to be mined based on the recall relationship.

[0125] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0126] This embodiment obtains the search keywords corresponding to the users to be mined; searches for the search keywords through multiple different search engines to obtain the search results from each search engine; determines the recall relationship between each search engine and the search keywords based on the search results; and determines the potential priority of the users to be mined based on the recall relationship. Through the above method, the potential priority of users is determined based on the recall relationship between each search engine and the search keywords, and the user's multimedia information delivery intention is determined based on the multimedia information already delivered to the user. This provides data support for search engine operators to expand their business and facilitates search engine operators in understanding users' multimedia information delivery needs.

[0127] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0128] In addition, for technical details not described in detail in this embodiment, please refer to the potential user priority determination method provided in any embodiment of the present invention, which will not be repeated here.

[0129] In one embodiment, the determining module 30 is further configured to detect the homepage layout information of the search results returned by each search engine, determine whether the homepage layout information contains preset multimedia tags, obtain layout detection results, and determine the recall relationship between each search engine and the search keywords based on the layout detection results.

[0130] In one embodiment, the determining module 30 is further configured to determine that there is a recall relationship between the target search engine and the search keyword when the layout detection result of the target search engine is that the homepage layout information contains preset multimedia tags.

[0131] In one embodiment, the determining module 30 is further configured to determine the first search result from the search results returned by each search engine, detect whether the first search result contains an image, determine the pixel value corresponding to the image, obtain a detection result, and determine the recall relationship between each search engine and the search keyword based on the detection result.

[0132] In one embodiment, the determining module 30 is further configured to determine that there is a recall relationship between the target search engine and the search keyword when the detection result of the current search engine is that the first search result contains an image and the pixel value is greater than a preset threshold.

[0133] In one embodiment, the potential user priority determination device further includes a mining module;

[0134] The mining module is used to generate industry keywords according to multiple different preset industry types, perform user mining based on the industry keywords, determine multiple user information corresponding to each preset industry type, generate a list of users to be mined for each preset industry type based on the multiple user information, traverse the list of users to be mined, and take the traversed users as users to be mined.

[0135] In one embodiment, the acquisition module is further configured to determine the next list of users to be acquired according to the industry mining order, select users to be acquired from the next list of users to be acquired, and return to the step of acquiring the search keywords corresponding to the users to be acquired.

[0136] In one embodiment, the determining module 30 is further configured to determine the number of engines among the plurality of different search engines that have a recall relationship with the search keyword, and determine the potential priority corresponding to the user to be mined based on the number of engines.

[0137] In one embodiment, the determining module 30 is further configured to compare the number of engines with the standard evaluation range corresponding to each potential priority, obtain the comparison result, and determine the potential priority corresponding to the user to be mined based on the comparison result.

[0138] In one embodiment, the potential user priority determination device further includes a recommendation module;

[0139] The recommendation module is used to generate a recommendation list based on the potential priority of the user to be mined, and push the recommendation list to the target server.

[0140] Furthermore, it should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0141] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0142] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0143] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for determining the priority of potential users, characterized in that, The method for determining the priority of potential users includes: Obtain the search keywords corresponding to the users to be mined; The search keywords were searched using multiple different search engines to obtain the search results from each search engine. Based on the search results fed back by each search engine, a recall relationship between each search engine and the search keyword is determined. The recall relationship is used to characterize whether the search results contain multimedia promotional information delivered to the user to be mined. The potential priority of the users to be mined is determined based on the recall relationship; Wherein, determining the potential priority corresponding to the user to be mined based on the recall relationship includes: Determine the number of search engines among the plurality of different search engines that have a recall relationship with the search keywords; The potential priority of the user to be mined is determined based on the number of engines. The step of determining the potential priority of the user to be mined based on the number of engines includes: The number of engines is compared with the standard evaluation range corresponding to each potential priority to obtain the comparison results; The potential priority of the user to be mined is determined based on the comparison results.

2. The method for determining the priority of potential users as described in claim 1, characterized in that, The step of determining the recall relationship between each search engine and the search keyword based on the search results returned by each search engine includes: Detect the homepage layout information of the search results returned by each search engine; Determine whether the homepage layout information contains preset multimedia tags to obtain the layout detection result; The recall relationship between each search engine and the search keywords is determined based on the layout detection results.

3. The method for determining the priority of potential users as described in claim 2, characterized in that, The step of determining the recall relationship between each search engine and the search keywords based on the layout detection results includes: When the layout detection result of the target search engine shows that the homepage layout information contains preset multimedia tags, it is determined that there is a recall relationship between the target search engine and the search keywords.

4. The method for determining the priority of potential users as described in claim 1, characterized in that, The step of determining the recall relationship between each search engine and the search keyword based on the search results returned by each search engine includes: The first search result is determined from the search results returned by each search engine; The system detects whether the first search result contains an image and determines the pixel value corresponding to the image to obtain the detection result. The recall relationship between each search engine and the search keywords is determined based on the detection results.

5. The method for determining the priority of potential users as described in claim 4, characterized in that, The step of determining the recall relationship between each search engine and the search keyword based on the detection results includes: If the current search engine's detection result shows that the first search result contains an image and the pixel value is greater than a preset threshold, it is determined that there is a recall relationship between the target search engine and the search keyword.

6. The method for determining the priority of potential users as described in claim 1, characterized in that, Before obtaining the search keywords corresponding to the user to be mined, the method further includes: Generate industry keywords based on multiple different preset industry types; User mining is performed based on the industry keywords to determine multiple user information corresponding to each of the preset industry types; Generate a list of users to be mined for each of the preset industry types based on the multiple user information; Iterate through the list of users to be mined, and use the users found during the iteration as the users to be mined.

7. The method for determining the priority of potential users as described in claim 6, characterized in that, After determining the potential priority of the user to be mined based on the recall relationship, the method further includes: Determine the next list of users to be mined according to the industry mining order, select users to be mined from the next list of users to be mined, and return to the step of obtaining the search keywords corresponding to the users to be mined.

8. The method for determining the priority of potential users as described in any one of claims 1-7, characterized in that, The method further includes: A recommendation list is generated based on the potential priority of the users to be explored. The recommended list is pushed to the target server.

9. A device for determining the priority of potential users, characterized in that, The potential user priority determination device includes: The acquisition module is used to acquire the search keywords corresponding to the users to be mined; The search module is used to search for the search keywords through multiple different search engines and obtain the search results returned by each search engine; The determination module is used to determine the recall relationship between each search engine and the search keyword based on the search results fed back by each search engine. The recall relationship is used to characterize whether the search results contain the multimedia promotion information delivered to the user to be mined. The determining module is further configured to determine the potential priority corresponding to the user to be mined based on the recall relationship; Wherein, determining the potential priority corresponding to the user to be mined based on the recall relationship includes: Determine the number of search engines among the plurality of different search engines that have a recall relationship with the search keywords; The potential priority of the user to be mined is determined based on the number of engines. The step of determining the potential priority of the user to be mined based on the number of engines includes: The number of engines is compared with the standard evaluation range corresponding to each potential priority to obtain the comparison results; The potential priority of the user to be mined is determined based on the comparison results.

10. The potential user priority determination device as described in claim 9, characterized in that, The determining module is further configured to detect the homepage layout information of the search results returned by each search engine, determine whether the homepage layout information contains preset multimedia tags, obtain layout detection results, and determine the recall relationship between each search engine and the search keywords based on the layout detection results.

11. The potential user priority determination device as described in claim 10, characterized in that, The determining module is further configured to determine that there is a recall relationship between the target search engine and the search keyword when the layout detection result of the target search engine is that the homepage layout information contains preset multimedia tags.

12. The potential user priority determination device as described in claim 9, characterized in that, The determining module is further configured to determine the first search result from the search results returned by each search engine, detect whether the first search result contains an image, determine the pixel value corresponding to the image, obtain a detection result, and determine the recall relationship between each search engine and the search keyword based on the detection result.

13. The potential user priority determination device as described in claim 12, characterized in that, The determining module is further configured to determine that there is a recall relationship between the target search engine and the search keywords when the detection result of the current search engine is that the first search result contains an image and the pixel value is greater than a preset threshold.

14. The potential user priority determination device as described in claim 9, characterized in that, The potential user priority determination device also includes a mining module; The mining module is used to generate industry keywords according to multiple different preset industry types, perform user mining based on the industry keywords, determine multiple user information corresponding to each preset industry type, generate a list of users to be mined for each preset industry type based on the multiple user information, traverse the list of users to be mined, and take the traversed users as users to be mined.

15. The potential user priority determination device as described in claim 14, characterized in that, The acquisition module is further configured to determine the next list of users to be acquired according to the industry mining order, select users to be acquired from the next list of users to be acquired, and return to the step of acquiring the search keywords corresponding to the users to be acquired.

16. The potential user priority determination device as described in claim 9, characterized in that, The determining module is further configured to determine the number of engines among the plurality of different search engines that have a recall relationship with the search keywords, and determine the potential priority corresponding to the user to be mined based on the number of engines.

17. A potential user priority determination device, characterized in that, The device includes: a memory, a processor, and a potential user priority determination program stored on the memory and executable on the processor, the potential user priority determination program being configured to implement the potential user priority determination method as described in any one of claims 1 to 8.

18. A storage medium, characterized in that, The storage medium stores a potential user priority determination program, which, when executed by a processor, implements the potential user priority determination method as described in any one of claims 1 to 8.

Images