Information recommendation method and device, computer device, and storage medium

Abstract

The application relates to precise recommendation by using natural language technology, and provides an information recommendation method and device, computer equipment and a storage medium. The method comprises the following steps: receiving a user login request, wherein the user login request carries a user identifier; when the user login request is verified, obtaining a to-be-processed keyword set and a historical keyword set corresponding to the user identifier; when there is a regional keyword in the to-be-processed keyword set, obtaining a keyword filtering parameter selected by the user, performing regional filtering on the to-be-processed keyword set according to the keyword filtering parameter, obtaining a target regional keyword set, and filtering the target regional keyword set according to the historical keyword set to obtain a target keyword set; when there is no regional keyword in the to-be-processed keyword set, filtering the to-be-processed keyword set according to the historical keyword set to obtain a target keyword set and pushing the target keyword set. The method can realize precise information recommendation.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to an information recommendation method, apparatus, computer device, and storage medium. Background Technology

[0002] With the development of computer technology, information recommendation technology has emerged. Information recommendation technology refers to recommending information to users and can be widely applied in various fields. For example, in the field of advertising, information recommendation technology is mainly used to recommend advertising slogans to users.

[0003] In traditional technologies, information recommendation methods involve acquiring documents associated with the user, performing statistical analysis on the documents to derive keywords, and then recommending information based on these keywords.

[0004] However, traditional methods rely solely on statistical analysis of user-related documents to derive keywords for information recommendations, resulting in inaccurate recommendations. Summary of the Invention

[0005] Therefore, it is necessary to provide an information recommendation method, apparatus, computer equipment, and storage medium that can achieve accurate information recommendation in response to the above-mentioned technical problems.

[0006] An information recommendation method, the method comprising:

[0007] Receive user login requests, which carry the user identifier;

[0008] When the user login request is successfully verified, obtain the set of keywords to be processed and the set of historical keywords corresponding to the user identifier;

[0009] When a regional keyword exists in the keyword set to be processed, the keyword filtering parameters selected by the user are obtained, and the keyword set to be processed is filtered by region according to the keyword filtering parameters to obtain the target regional keyword set. The target regional keyword set is then filtered according to the historical keyword set to obtain the target keyword set.

[0010] When there are no regional keywords in the set of keywords to be processed, the set of keywords to be processed is filtered according to the historical keyword set to obtain the target keyword set;

[0011] The set of target keywords obtained from the push notification.

[0012] An information recommendation device, the device comprising:

[0013] The receiving module is used to receive user login requests, which carry the user identifier.

[0014] The acquisition module is used to acquire the set of keywords to be processed and the set of historical keywords corresponding to the user identifier when the user login request is verified.

[0015] The first filtering module is used to obtain the keyword filtering parameters selected by the user when there are regional keywords in the keyword set to be processed, to filter the keyword set to be processed by region according to the keyword filtering parameters, to obtain the target regional keyword set, and to filter the target regional keyword set according to the historical keyword set to obtain the target keyword set.

[0016] The second filtering module is used to filter the set of keywords to be processed based on the historical keyword set when there are no regional keywords in the set of keywords to be processed, so as to obtain the target keyword set.

[0017] The push module is used to push the obtained set of target keywords.

[0018] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program performing the following steps:

[0019] Receive user login requests, which carry the user identifier;

[0020] When the user login request is successfully verified, obtain the set of keywords to be processed and the set of historical keywords corresponding to the user identifier;

[0021] When a regional keyword exists in the keyword set to be processed, the keyword filtering parameters selected by the user are obtained, and the keyword set to be processed is filtered by region according to the keyword filtering parameters to obtain the target regional keyword set. The target regional keyword set is then filtered according to the historical keyword set to obtain the target keyword set.

[0022] When there are no regional keywords in the set of keywords to be processed, the set of keywords to be processed is filtered according to the historical keyword set to obtain the target keyword set;

[0023] The set of target keywords obtained from the push notification.

[0024] A computer-readable storage medium having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0025] Receive user login requests, which carry the user identifier;

[0026] When the user login request is successfully verified, obtain the set of keywords to be processed and the set of historical keywords corresponding to the user identifier;

[0027] When a regional keyword exists in the keyword set to be processed, the keyword filtering parameters selected by the user are obtained, and the keyword set to be processed is filtered by region according to the keyword filtering parameters to obtain the target regional keyword set. The target regional keyword set is then filtered according to the historical keyword set to obtain the target keyword set.

[0028] When there are no regional keywords in the set of keywords to be processed, the set of keywords to be processed is filtered according to the historical keyword set to obtain the target keyword set;

[0029] The set of target keywords obtained from the push notification.

[0030] The aforementioned information recommendation method, apparatus, computer equipment, and storage medium, upon successful verification of a user login request, acquire a set of keywords to be processed and a set of historical keywords corresponding to the user identifier. When a regional keyword exists in the set of keywords to be processed, the system acquires the keyword filtering parameters selected by the user, uses these parameters to filter the set of keywords to be processed by region, obtains a target regional keyword set, and then filters the target regional keyword set based on the historical keyword set to obtain a target keyword set. Furthermore, when no regional keyword exists in the set of keywords to be processed, the system directly filters the set of keywords to be processed based on the historical keyword set to obtain the target keyword set. Throughout this process, the system utilizes keyword filtering parameters and the historical keyword set to accurately filter the set of keywords to be processed, thereby obtaining a target keyword set that meets the requirements and achieving precise information recommendation. Attached Figure Description

[0031] Figure 1 This is a flowchart illustrating an information recommendation method in one embodiment;

[0032] Figure 2 This is a schematic diagram of an information recommendation method in one embodiment;

[0033] Figure 3 This is a schematic diagram of an information recommendation method in one embodiment;

[0034] Figure 4 This is a schematic diagram of an information recommendation method in one embodiment;

[0035] Figure 5 This is a schematic diagram of an information recommendation method in one embodiment;

[0036] Figure 6 This is a schematic diagram of an information recommendation method in one embodiment;

[0037] Figure 7 This is a schematic diagram of an information recommendation method in one embodiment;

[0038] Figure 8 This is a flowchart illustrating the information recommendation method in another embodiment;

[0039] Figure 9 This is a structural block diagram of an information recommendation device in one embodiment;

[0040] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0041] This application relates to Natural Language Processing (NLP) technology within artificial intelligence (AI), primarily focusing on achieving accurate recommendations using NLP and big data. Artificial intelligence (AI) utilizes digital computers or computer-controlled machines to simulate, extend, and expand human intelligence, perceiving the environment, acquiring knowledge, and using that knowledge to obtain optimal results—theories, methods, technologies, and application systems. In other words, AI is a comprehensive technology within computer science that attempts to understand the essence of intelligence and produce new intelligent machines capable of reacting in a manner similar to human intelligence. AI studies the design principles and implementation methods of various intelligent machines, enabling them to possess perception, reasoning, and decision-making capabilities. Natural Language Processing (NLP) is an important direction within both computer science and AI. It studies various theories and methods that enable effective communication between humans and computers using natural language. NLP is a science integrating linguistics, computer science, and mathematics. Therefore, research in this field involves natural language—the language people use daily—and thus has a close connection to linguistic research. NLP technologies typically include text processing, semantic understanding, machine translation, question answering, and knowledge graphs. Big data refers to data sets that cannot be captured, managed, and processed within a certain timeframe using conventional software tools. It represents massive, rapidly growing, and diverse information assets that require new processing models to achieve stronger decision-making, insightful discovery, and process optimization capabilities. With the advent of the cloud era, big data has attracted increasing attention. Big data requires specialized technologies to effectively process large amounts of data within a tolerable timeframe. Technologies suitable for big data include massively parallel processing databases, data mining, distributed file systems, distributed databases, cloud computing platforms, the internet, and scalable storage systems.

[0042] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0043] In one embodiment, such as Figure 1As shown, an information recommendation method is provided. This embodiment illustrates the application of this method to a terminal. It is understood that this method can also be applied to a server, or to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. The terminal and server can be directly or indirectly connected via wired or wireless communication, which is not limited herein. In this embodiment, the method includes the following steps:

[0044] Step 102: Receive user login request, which carries the user identifier.

[0045] Among them, the user login request refers to the request sent by the user when logging into the terminal. The user login request carries the user identifier and the user password. The user identifier is used to distinguish the user's identity. For example, the user identifier can specifically refer to the user account.

[0046] Specifically, when a user needs to log in to the terminal, a login request is sent to the terminal. The terminal receives the login request and verifies it against pre-stored user information in a pre-configured database. If the corresponding user information exists in the database, the login request is considered verified. The login request can be input by the user into the terminal. For example, when a user needs to publish information, they will log in to the terminal so that the terminal can recommend information. As a further example, when a user needs to place advertisements, they will log in to the terminal so that the terminal can recommend advertising keywords.

[0047] Step 104: When the user login request is verified, obtain the set of keywords to be processed and the set of historical keywords corresponding to the user identifier.

[0048] The "keyword set to be processed" refers to a set of user-related, unfiltered keywords obtained based on user identifiers. For example, in advertising, this could specifically refer to an unfiltered set of keywords related to the advertiser's industry or product. The "historical keyword set" refers to a set of keywords that have been recommended to and selected by the user in the past. For example, in advertising, this could specifically refer to a set of keywords that have been recommended to and selected by the advertiser.

[0049] Specifically, after the user login request is verified, the terminal will use the user identifier to retrieve the corresponding related documents and historical keyword set from the preset database, and extract the keyword set to be processed from the related documents by splitting the related documents and performing word frequency analysis.

[0050] Step 106: When there are regional keywords in the keyword set to be processed, obtain the keyword filtering parameters selected by the user, filter the keyword set to be processed by region according to the keyword filtering parameters to obtain the target regional keyword set, and filter the target regional keyword set according to the historical keyword set to obtain the target keyword set.

[0051] Among them, regional keywords refer to keywords related to a specific region. For example, regional keywords can specifically refer to keywords that include the name of a region, such as "Kunming to Dali travel route" or "Lijiang to Dali travel". Another example is keywords that include regionally unique architecture, such as "Forbidden City travel route". Regional filtering refers to selecting a set of target regional keywords that meet the regional requirements from the set of keywords to be processed, based on the regional filtering parameters in the keyword filtering parameters.

[0052] Keyword filtering parameters refer to the filtering conditions selected by the user, used to filter the set of keywords to be processed. These parameters include geographic filtering parameters and device filtering parameters. Geographic filtering parameters represent the specific region selected by the user, such as Beijing, Hebei, Taiyuan, Fuzhou, etc., while device filtering parameters represent the specific device selected by the user, such as computer, mobile terminal, etc. For example, in the field of advertising, geographic filtering parameters represent the region where the advertiser chooses to place ads, and device filtering parameters represent the device on which the advertiser chooses to place ads.

[0053] The target keyword set refers to the filtered set of keywords excluding historical keywords. When the keyword set to be processed contains regional keywords, the target keyword set specifically refers to the filtered set of target regional keywords excluding historical keywords. When the keyword set to be processed does not contain regional keywords, the target keyword set specifically refers to the filtered set of keywords to be processed excluding historical keywords, meaning no regional filtering is required. For example, in the field of advertising, the target keyword set can specifically refer to the set of keywords recommended to advertisers after filtering based on keyword filtering parameters, excluding the keyword set already selected by the advertiser.

[0054] Specifically, when the set of keywords to be processed contains regional keywords, the terminal needs to obtain the keyword filtering parameters selected by the user. Based on the regional filtering parameters, the terminal filters the keywords in the set of keywords to be processed according to their regional requirements to obtain a target set of keywords that meet the regional requirements set by the regional filtering parameters. Furthermore, the target set of keywords is filtered using historical keyword sets to obtain the target keyword set. The method for obtaining the keyword filtering parameters selected by the user can be to push keyword filtering parameter selection prompts to the terminal, allowing the user to make selections based on these prompts. The terminal then confirms the selected keyword filtering parameters by responding to the user's selection.

[0055] Step 108: When there are no regional keywords in the keyword set to be processed, filter the keyword set to be processed according to the historical keyword set to obtain the target keyword set.

[0056] Specifically, when there are no regional keywords in the set of keywords to be processed, it means that the terminal does not need to filter the keywords in the set of keywords to be processed by region. It can obtain the target keyword set by directly filtering the set of keywords to be processed based on the historical keyword set.

[0057] The aforementioned information recommendation method, upon successful user login verification, obtains a set of keywords to be processed and a set of historical keywords corresponding to the user identifier. When a regional keyword exists in the set of keywords to be processed, it retrieves the keyword filtering parameters selected by the user and uses these parameters to filter the set of keywords to be processed by region, obtaining a target regional keyword set. Furthermore, it filters the target regional keyword set based on the historical keyword set to obtain the target keyword set. Even when no regional keyword exists in the set of keywords to be processed, it directly filters the set of keywords to be processed based on the historical keyword set to obtain the target keyword set. Throughout this process, the keyword filtering parameters and the historical keyword set are used to accurately filter the set of keywords to be processed, thereby obtaining a target keyword set that meets the requirements and achieving precise information recommendation.

[0058] In one embodiment, when a user login request is successfully verified, obtaining the set of keywords to be processed and the set of historical keywords corresponding to the user identifier includes:

[0059] When the user login request is verified, the associated documents and historical keyword set corresponding to the user identifier are obtained, and the keyword set to be processed is extracted from the associated documents.

[0060] In this context, "related documents" refers to documents that are relevant to the user's industry, products, etc. For example, related documents could refer to the latest industry news within the user's industry, such as updates from sister companies and industry policies. These related documents are pre-acquired and stored in a pre-defined database; for instance, they can be obtained by periodically crawling web pages.

[0061] Specifically, when a user login request is successfully verified, the terminal retrieves the associated documents and historical keyword set corresponding to the user identifier from a preset database. By splitting and performing word frequency analysis on the associated documents, a set of keywords to be processed is extracted from them. Furthermore, the method for extracting the set of keywords to be processed from the associated documents through splitting and performing word frequency analysis can include using the tf-idf (term frequency–inverse document frequency) algorithm, etc., but this embodiment does not specify a particular method.

[0062] In this embodiment, by obtaining the associated documents and historical keyword set corresponding to the user identifier, and extracting the keyword set to be processed from the associated documents, the acquisition of the keyword set to be processed can be achieved.

[0063] In one embodiment, after obtaining the set of keywords to be processed and the set of historical keywords corresponding to the user identifier when the user login request is verified, the method further includes:

[0064] The keywords to be processed in the set of keywords to be processed are split to obtain the set of keyword phrases to be processed corresponding to the keywords to be processed;

[0065] Match the set of keyword phrases to be processed based on the preset set of regional phrases;

[0066] If a region-specific term exists in any set of keywords to be processed, it is determined that a region-specific keyword exists in the set of keywords to be processed.

[0067] If no regional terms are found in the set of keywords to be processed, it is determined that no regional keywords exist in the set of keywords to be processed.

[0068] Among them, regional phrases refer to phrases related to a specific region. For example, a regional phrase could include the name of a region, such as Kunming, Dali, or Lijiang. Another example is a regional phrase referring to a unique building of that region, such as the Forbidden City. A preset regional phrase set is a collection of pre-defined regional phrases that establishes a correspondence between regions and their related phrases. For instance, a preset regional phrase set could be a regional phrase table, storing regional phrases in a region-region phrase format. Regional keywords are keywords in the keyword set to be processed that include regional phrases.

[0069] Specifically, the terminal first splits the keywords in the set of keywords to be processed according to a preset dictionary, dividing them into sets of keyword phrases. Then, it matches these sets with regional phrases from a preset set of regional phrases to determine if any regional phrase exists. If a regional phrase exists in any set of keyword phrases, the terminal determines that a regional keyword exists in the set of keywords to be processed; otherwise, it determines that no regional keyword exists in the set of keyword phrases. The preset dictionary refers to a pre-set dictionary composed of fixed, commonly used phrases. Using this preset dictionary, the keywords to be processed can be split into sets of keyword phrases composed of commonly used phrases.

[0070] In this embodiment, by splitting the keywords to be processed in the set of keywords to be processed, a set of keyword phrases corresponding to the keywords to be processed is obtained. By matching the set of keyword phrases to be processed with the preset set of regional phrases, it is possible to determine whether there are regional keywords in the set of keywords to be processed.

[0071] In one embodiment, when a geographic keyword exists in the keyword set to be processed, the keyword filtering parameters selected by the user are obtained, and the keyword set to be processed is filtered by geographic region according to the keyword filtering parameters to obtain a target geographic keyword set. The target geographic keyword set is then filtered based on the historical keyword set to obtain a target keyword set including:

[0072] When a regional keyword exists in the set of keywords to be processed, obtain the keyword filtering parameters selected by the user and the historical regional records corresponding to the user identifier;

[0073] Based on historical geographic records and the geographic filtering parameters in the keyword filtering parameters, the set of keywords to be processed is filtered by geographic region to obtain the target geographic keyword set;

[0074] The target keyword set is obtained by filtering the target region keyword set based on the historical keywords in the historical keyword set and the device filtering parameters in the keyword filtering parameters.

[0075] Historical geographic records refer to the regions a user has previously selected in previous information recommendations. For example, in the field of advertising, historical geographic records specifically refer to the regions that advertisers have previously selected for ad placement.

[0076] Specifically, when a geographic keyword exists in the set of keywords to be processed, it indicates that the terminal needs to perform geographic filtering on the set of keywords. The terminal obtains the keyword filtering parameters selected by the user and retrieves historical geographic records corresponding to the user identifier from a preset database. Based on the geographic regions in the historical geographic records and the geographic filtering parameters in the keyword filtering parameters, the terminal matches each keyword in the set of keywords to be processed to obtain a target geographic keyword set that meets the geographic requirements. Here, meeting the geographic requirements means matching the geographic region in the historical geographic records or the geographic region in the geographic filtering parameters. After obtaining the target geographic keyword set, the terminal further matches each keyword in the target geographic keyword set against historical keywords in the historical keyword set, filtering out the target geographic keyword set that does not contain historical keywords. Then, it filters the target geographic keyword set that does not contain historical keywords according to the device filtering parameters to obtain the target keyword set.

[0077] Specifically, the keywords in the pending keyword set all carry device attributes. Device attributes refer to whether the keywords are related to computers or mobile terminals. Here, "computer" mainly refers to non-mobile terminals. The target keyword set is obtained by filtering the target region keyword set (excluding historical keywords) based on the device filtering parameters. For example, when the device filtering parameter is "computer," the terminal will filter out the set of keywords with the device attribute "computer" from the target region keyword set excluding historical keywords. Similarly, when the device filtering parameter is "mobile terminal," the terminal will filter out the set of keywords with the device attribute "mobile terminal" from the target region keyword set excluding historical keywords.

[0078] It should be noted that the device attribute of the keywords to be processed is related to the target audience of the associated documents. When the associated documents are mainly delivered to computers, the device attribute of the keywords to be processed extracted from those documents will be "computer". When the associated documents are mainly delivered to mobile devices, the device attribute of the keywords to be processed extracted from those documents will be "mobile device". When users select device filtering parameters, in addition to selecting computers or mobile devices, they can also select all devices. In this case, the terminal will not filter the target region keywords based on device attributes, and the resulting target keyword set will be the target region keyword set excluding historical keywords.

[0079] In this embodiment, the target keyword set is obtained by filtering the set of keywords to be processed according to historical regional records and regional filtering parameters in the keyword filtering parameters. The target keyword set is then filtered according to historical keywords in the historical keyword set and device filtering parameters in the keyword filtering parameters. This allows for the acquisition of the target keyword set through multiple filtering methods.

[0080] In one embodiment, when no geographic keywords exist in the keyword set to be processed, the keyword set to be processed is filtered based on the historical keyword set to obtain the target keyword set, which includes:

[0081] When there are no regional keywords in the keyword set to be processed, the keyword filtering parameters selected by the user are obtained, and the keyword set to be processed is filtered according to the historical keywords in the historical keyword set and the device filtering parameters in the keyword filtering parameters to obtain the target keyword set.

[0082] Specifically, when there are no regional keywords in the set of keywords to be processed, it means that the terminal does not need to perform regional filtering on the set of keywords to be processed. The terminal will obtain the keyword filtering parameters selected by the user, match the set of keywords to be processed one by one according to the historical keywords in the historical keyword set, filter out the set of keywords to be processed that does not include historical keywords, and filter the set of keywords to be processed that does not include historical keywords according to the device filtering parameters to obtain the target keyword set.

[0083] In this embodiment, the target keyword set is obtained by filtering the set of keywords to be processed according to the historical keywords in the historical keyword set and the device filtering parameters in the keyword filtering parameters. The target keyword set can be obtained through filtering.

[0084] In one embodiment, the set of target keywords obtained from the push includes:

[0085] The target keywords in the target keyword set are split to obtain the target keyword phrase set corresponding to the target keywords;

[0086] Geographic extraction is performed on the target keyword phrase set to obtain geographic information corresponding to the target keywords, and hot keywords are obtained. Based on the hot keywords, recommendation reasons are mined for the target keyword phrase set to obtain recommendation reasons corresponding to the target keywords.

[0087] Push the target keyword set, the corresponding geographic information, and the corresponding recommendation reason.

[0088] Among them, geographic information refers to the geographic phrases contained in the target keywords. Hot keywords refer to popular phrases within a preset statistical period. The preset statistical period can be set as needed; for example, if the preset statistical period is one month, then hot keywords can specifically refer to popular phrases within the past month. Furthermore, according to the hot attribute of hot keywords, they can be divided into PC (Personal Computer) dark horse keywords, wireless dark horse keywords, nighttime keywords, weekend keywords, etc.

[0089] Among them, "PC dark horse keywords" refer to trending keywords appearing on non-mobile terminals, "wireless dark horse keywords" refer to trending keywords appearing on mobile terminals, "nighttime keywords" refer to trending keywords that are mainly active at night, and "weekend keywords" refer to trending keywords that are mainly active on weekends. "Active" here can specifically refer to factors such as high search volume. The recommendation reason refers to the reason presented to the user during the information recommendation process for recommending the target keyword, used to assist the user's decision-making and achieve accurate recommendations. In this embodiment, the recommendation reason mainly refers to the trending attribute of the target keyword.

[0090] Specifically, after obtaining the target keyword set, the terminal needs to further perform geographic and recommendation reason mining on the target keywords in the target keyword set, and simultaneously push the target keywords, geographic information, and recommendation reasons to the user to help the user make better decisions. The terminal will first break down the target keywords in the target keyword set according to a preset dictionary to obtain a set of target keyword phrases corresponding to the target keywords, and then extract the geographic information corresponding to the target keywords by matching the target keyword phrase set according to a preset set of geographic phrases.

[0091] Specifically, the terminal retrieves pending logs corresponding to user identifiers, extracts trending keywords from these logs, and mines recommendation reasons by matching the target keyword phrase set with these trending keywords. This yields the recommendation reasons corresponding to the target keywords, which are then pushed to the user along with the target keyword set, corresponding geographic information, and the recommended reasons. Furthermore, the terminal also simultaneously pushes the search volume of the target keywords within a preset search statistics period. This preset search statistics period can be set as needed; for example, it can be one week.

[0092] In this embodiment, by extracting the geographic information of the target keyword phrase set, the geographic information corresponding to the target keyword is obtained, and hot keywords are acquired. Based on the hot keywords, the recommendation reasons for the target keyword phrase set are mined to obtain the recommendation reasons corresponding to the target keyword. This enables the acquisition of geographic information and recommendation reasons for the target keyword, thereby achieving accurate recommendation.

[0093] In one embodiment, hot keywords are obtained, and recommendation reasons are mined from the target keyword phrase set based on the hot keywords to obtain recommendation reasons corresponding to the target keywords, including:

[0094] Retrieve the logs to be processed corresponding to the user identifier;

[0095] The log to be processed is split to obtain a set of log phrases corresponding to the log to be processed.

[0096] Based on the set of log phrases to be processed and the preset hot keyword judgment rules, the hot keywords and their hot attributes are obtained.

[0097] Match the target keyword phrase set with trending keywords to determine the matching keywords.

[0098] Based on trending attributes, the reasons for recommending the relevant keywords are derived.

[0099] Among them, the pending logs refer to the industry search logs corresponding to user identifiers, representing the search situation for keywords within the industry. The industry search logs for each industry are periodically pre-compiled and stored in a preset database. The preset hot keyword judgment rules refer to the pre-set rules for judging hot keywords, used to determine hot keywords and their corresponding hot attributes. Hit keywords refer to the target keywords that appear among the hot keywords in the target keyword phrase set.

[0100] Specifically, the terminal determines the user's industry based on the user's identifier, retrieves corresponding logs to be processed from a pre-set database based on the user's industry, and splits the logs according to a pre-set dictionary to obtain a set of log phrases to be processed. It then statistically analyzes the log phrases in this set to determine the search attributes and search frequency of each phrase. Based on the search attributes, search frequency, and pre-set hot keyword judgment rules, it obtains hot keywords and their hot attributes. Finally, it matches the target keyword phrase set with the hot keywords to determine the matching keywords, and uses the hot attributes of those hot keywords as the recommendation reason for those matching keywords. It should be noted that if there are target keywords that do not include hot keywords, no recommendation reason will be pushed for those target keywords.

[0101] Specifically, the preset hot keyword judgment rules pre-set search thresholds and hot attributes for various hot keywords. The terminal uses these search thresholds and hot attributes to match the search attributes and search frequency of each log phrase to be processed. Only when the search attribute is the same as the hot attribute, and the search frequency under that search attribute is greater than the search threshold, will the log phrase to be processed be considered a hot keyword, and the search attribute be considered a hot attribute. The search attributes here can include the search device and the search time period, where the search device includes mobile terminals and non-mobile terminals, corresponding to PC and wireless in the hot attribute, respectively. The search time period includes weekends and nighttime, corresponding to nighttime and weekends in the hot attribute, respectively.

[0102] In this embodiment, by acquiring the logs to be processed corresponding to the user identifier, and based on the logs to be processed and the preset hot keyword judgment rules, hot keywords and their hot attributes are obtained. The target keyword phrase set is matched with the hot keywords to determine the matching keywords. Based on the hot attributes, the recommendation reason for the matching keywords is obtained, thus enabling the determination of the recommendation reason.

[0103] This application also provides an application scenario in which the above-described information recommendation method is applied. Specifically, the information recommendation method is applied in this scenario as follows:

[0104] When advertisers need to place ads, after logging into the terminal, the terminal will proactively push suitable keywords to the advertisers and disclose the reasons for recommending the keywords as well as search volume and other data, providing advertisers with a reference before placing ads.

[0105] like Figure 2 As shown, the advertiser logs into the terminal. The terminal receives a user login request, which carries a user identifier. When the user login request is verified, the terminal obtains the set of keywords to be processed corresponding to the user identifier and the set of historical keywords (i.e., the corresponding...). Figure 2 The process involves generating basic data (keyword recommendations from data sources and third-party data). When a geographic keyword exists in the keyword set to be processed, the user-selected keyword filtering parameters are retrieved. Based on these parameters, the keyword set is filtered geographically to obtain the target geographic keyword set. This target geographic keyword set is then filtered based on the historical keyword set to obtain the target keyword set. Conversely, if no geographic keyword exists in the keyword set to be processed, the target keyword set is obtained by filtering based on the historical keyword set. Figure 2 The filter module performs purchased keyword filtering and geographic filtering. The purchased keywords here correspond to the historical keyword set.

[0106] The diagram of word filtering is shown below. Figure 3 As shown, the terminal pre-aggregates pre-formed keywords at the customer level, obtaining a pre-formed keyword table (i.e., a historical keyword set) corresponding to the user identifier. Based on this pre-formed keyword table, the recommendation base data is filtered item by item. If a recommended keyword is in the customer's pre-formed keyword list, it is deleted, resulting in the filtered pre-formed keyword result. A diagram illustrating the regional filtering is shown below. Figure 4 As shown, after obtaining the basic recommendation data (i.e., the set of keywords to be processed), the terminal first determines whether a region exists in the basic recommendation data. If not, it directly performs pre-formed word filtering. If a region exists, it needs to identify the customer's target region and match each keyword according to the customer's target region. If the keyword does not match the target region, it is deleted; otherwise, it is kept. Then, the remaining keywords are filtered using pre-formed word filtering to obtain the filtered results. The customer's target region includes the user identifier-target region (i.e., historical region records) and the planned target region (i.e., region filtering parameters).

[0107] In addition, Figure 2 This also includes user deduplication filtering, which refers to filtering advertisers who are advertising the same product as the advertiser. In other words, if other advertisers have already placed similar ads for the same product, the keywords recommended to the advertiser will be filtered based on the already placed ads. Furthermore, such as... Figure 2 As shown, in the product line, after obtaining the target keyword set, the terminal also needs to extract regional information and mine recommendation reasons based on this target keyword set to achieve accurate and proactive recommendations. The specific process of extracting regional information and mining recommendation reasons can be described as follows: Figure 5 As shown, the terminal first obtains hot keywords (i.e., recommendation reason data), then uses hot keywords and search data to concatenate recommendation reasons and calculate regional information to obtain recommendation reasons and regional information (i.e., Xbox readable data generated by the interface). The search data is obtained by integrating, sorting, and truncating upstream keyword data and third-party data.

[0108] Furthermore, such as Figure 6 and Figure 7 As shown, the terminal display interface for the above application scenarios is provided, such as... Figure 6 As shown, after a user logs into the terminal, the terminal will proactively recommend keywords that might be suitable for them. Users can select their region and device on this screen, as well as choose the reason for display or other custom options. After the user makes their selections, the target keyword and the reason for display (i.e., the recommendation reason) will be displayed at the bottom of the page. Additionally, information such as the target keyword's overall daily average search volume, mobile daily average search volume, and suggested retail price will also be displayed. Figure 7As shown, when a user selects to add a keyword on this interface, the selected keyword will be displayed in the buffer on the right side of the interface. The user can then quickly save the selection and proceed to the next step.

[0109] In one embodiment, such as Figure 8 As shown, an embodiment is provided to illustrate the information recommendation method of this application. The information recommendation method specifically includes the following steps:

[0110] Step 802: Receive user login request, the user login request carries user identifier;

[0111] Step 804: When the user login request is verified, obtain the associated documents and historical keyword set corresponding to the user identifier, and extract the keyword set to be processed from the associated documents;

[0112] Step 806: Split the keywords to be processed in the set of keywords to be processed to obtain a set of keyword phrases corresponding to the keywords to be processed;

[0113] Step 808: Match the set of keyword phrases to be processed according to the preset set of regional phrases;

[0114] Step 810: When a regional term exists in any set of keywords to be processed, determine that a regional keyword exists in the set of keywords to be processed, and proceed to step 812; when no regional term exists in the set of keywords to be processed, determine that no regional keyword exists in the set of keywords to be processed, and proceed to step 818.

[0115] Step 812: Obtain the keyword filtering parameters selected by the user and the historical regional records corresponding to the user identifier;

[0116] Step 814: Based on historical regional records and the regional filtering parameters in the keyword filtering parameters, perform regional filtering on the set of keywords to be processed to obtain the target regional keyword set;

[0117] Step 816: Filter the target region keyword set according to the historical keywords in the historical keyword set and the device filtering parameters in the keyword filtering parameters to obtain the target keyword set, then proceed to step 820;

[0118] Step 818: Obtain the keyword filtering parameters selected by the user; filter the keyword set to be processed based on the historical keywords in the historical keyword set and the device filtering parameters in the keyword filtering parameters to obtain the target keyword set.

[0119] Step 820: Split the target keywords in the target keyword set to obtain a set of target keyword phrases corresponding to the target keywords;

[0120] Step 822: Extract the geographic region from the target keyword phrase set to obtain the geographic information corresponding to the target keywords;

[0121] Step 824: Obtain the logs to be processed corresponding to the user identifier;

[0122] Step 826: Split the log to be processed to obtain a set of log phrases corresponding to the log to be processed;

[0123] Step 828: Based on the set of log phrases to be processed and the preset hot keyword judgment rules, obtain the hot keywords and the hot attributes of the hot keywords;

[0124] Step 830: Match the target keyword phrase set with hot keywords to determine the matching keywords corresponding to the hot keywords;

[0125] Step 832: Based on the hot topic attributes, obtain the set of target keywords for push notifications, the corresponding regional information, and the corresponding recommendation reasons for the hit keywords.

[0126] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps.

[0127] In one embodiment, such as Figure 9 As shown, an information recommendation device is provided. This device can be a software module, a hardware module, or a combination of both integrated into a computer device. Specifically, the device includes: a receiving module 902, an acquiring module 904, a first filtering module 906, a second filtering module 908, and a push module 910, wherein:

[0128] The receiving module 902 is used to receive user login requests, which carry user identifiers.

[0129] The acquisition module 904 is used to acquire the set of keywords to be processed and the set of historical keywords corresponding to the user identifier when the user login request is verified.

[0130] The first filtering module 906 is used to obtain the keyword filtering parameters selected by the user when there are regional keywords in the keyword set to be processed, to perform regional filtering on the keyword set to be processed according to the keyword filtering parameters to obtain the target regional keyword set, and to filter the target regional keyword set according to the historical keyword set to obtain the target keyword set.

[0131] The second filtering module 908 is used to filter the set of keywords to be processed based on the historical keyword set when there are no regional keywords in the set of keywords to be processed, so as to obtain the target keyword set.

[0132] The push module 910 is used to push the obtained set of target keywords.

[0133] The aforementioned information recommendation device, upon successful verification of a user's login request, acquires a set of keywords to be processed and a set of historical keywords corresponding to the user's identifier. When a regional keyword exists in the set of keywords to be processed, it acquires the keyword filtering parameters selected by the user and uses these parameters to filter the set of keywords to be processed by region, obtaining a target regional keyword set. Furthermore, it filters the target regional keyword set based on the historical keyword set to obtain a target keyword set. Even when no regional keyword exists in the set of keywords to be processed, it directly filters the set of keywords to be processed based on the historical keyword set to obtain the target keyword set. Throughout this process, the device accurately filters the set of keywords to be processed using keyword filtering parameters and the historical keyword set, thereby obtaining a target keyword set that meets the requirements and achieving precise information recommendation.

[0134] In one embodiment, the acquisition module is further configured to acquire the associated documents and historical keyword set corresponding to the user identifier when the user login request is verified, and extract the keyword set to be processed from the associated documents.

[0135] In one embodiment, the information recommendation device further includes a region detection module. The region detection module is used to split the keywords to be processed in the set of keywords to be processed to obtain a set of keyword phrases to be processed corresponding to the keywords to be processed. The region detection module matches the set of keyword phrases to be processed according to a preset set of regional phrases. When a regional phrase exists in any set of keyword phrases to be processed, it is determined that a regional keyword exists in the set of keywords to be processed. When a regional phrase does not exist in the set of keyword phrases to be processed, it is determined that a regional keyword does not exist in the set of keywords to be processed.

[0136] In one embodiment, the first filtering module is further configured to, when there are regional keywords in the set of keywords to be processed, obtain the keyword filtering parameters selected by the user and the historical regional records corresponding to the user identifier, perform regional filtering on the set of keywords to be processed according to the historical regional records and the regional filtering parameters in the keyword filtering parameters to obtain the target regional keyword set, and filter the target regional keyword set according to the historical keywords in the historical keyword set and the device filtering parameters in the keyword filtering parameters to obtain the target keyword set.

[0137] In one embodiment, the second filtering module is further configured to obtain the keyword filtering parameters selected by the user when there are no regional keywords in the keyword set to be processed, and filter the keyword set to be processed according to the historical keywords in the historical keyword set and the device filtering parameters in the keyword filtering parameters to obtain the target keyword set.

[0138] In one embodiment, the push module is further configured to split the target keywords in the target keyword set to obtain a target keyword phrase set corresponding to the target keywords, extract the geographic location of the target keyword phrase set to obtain geographic information corresponding to the target keywords, obtain hot keywords, mine recommendation reasons for the target keyword phrase set based on the hot keywords to obtain recommendation reasons corresponding to the target keywords, and push the target keyword set, the corresponding geographic information, and the corresponding recommendation reasons.

[0139] In one embodiment, the push module is further configured to obtain logs to be processed corresponding to user identifiers, split the logs to be processed to obtain a set of log phrases to be processed corresponding to the logs to be processed, obtain hot keywords and hot attributes of hot keywords based on the set of log phrases to be processed and preset hot keyword judgment rules, match the target keyword phrase set with the hot keywords to determine the hit keywords corresponding to the hot keywords, and obtain the recommendation reason for the hit keywords based on the hot attributes.

[0140] Specific limitations regarding the information recommendation device can be found in the limitations of the information recommendation method described above, and will not be repeated here. Each module in the aforementioned information recommendation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0141] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 10As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements an information recommendation method. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0142] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0143] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0144] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0145] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, causing the computer device to perform the steps in the above method embodiments.

[0146] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0147] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0148] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. An information recommendation method, characterized in that, The method includes: Receive a user login request, the user login request carrying a user identifier; When the user login request is verified, the associated documents and historical keyword set corresponding to the user identifier are obtained, and the keyword set to be processed is extracted from the associated documents; the associated documents refer to documents that are associated with at least one of the user's industry and the user's product; the keywords to be processed in the keyword set carry device attributes, and the device attributes are related to the target area of ​​the associated documents; the historical keyword set refers to the set of keywords that have been recommended to the user and selected by the user in the past. The keywords to be processed in the set of keywords to be processed are split to obtain a set of keyword phrases to be processed corresponding to the keywords to be processed. The set of keyword phrases to be processed is matched according to the preset set of regional phrases; If a regional term exists in any set of keywords to be processed, it is determined that a regional keyword exists in the set of keywords to be processed; if no regional term exists in the set of keywords to be processed, it is determined that no regional keyword exists in the set of keywords to be processed. When a regional keyword exists in the set of keywords to be processed, the keyword filtering parameters selected by the user are obtained. The set of keywords to be processed is then filtered by region according to the regional filtering parameters in the keyword filtering parameters to obtain a target regional keyword set. The target regional keyword set is then filtered according to the historical keyword set and the device filtering parameters in the keyword filtering parameters to obtain a target keyword set whose device attribute is the device filtering parameters. The regional filtering parameters represent the specific region selected by the user, and the device filtering parameters represent the specific device selected by the user. The target keyword set does not include the historical keyword set. When there are no regional keywords in the keyword set to be processed, the keyword filtering parameters selected by the user are obtained, and the keyword set to be processed is filtered according to the historical keyword set and the device filtering parameters in the keyword filtering parameters to obtain the target keyword set whose device attribute is the device filtering parameters; The target keyword set obtained through push notifications.

2. The method according to claim 1, characterized in that, When a regional keyword exists in the set of keywords to be processed, the keyword filtering parameters selected by the user are obtained, and the set of keywords to be processed is filtered by region according to the regional filtering parameters in the keyword filtering parameters to obtain the target regional keyword set, including: When a regional keyword exists in the set of keywords to be processed, obtain the keyword filtering parameters selected by the user and the historical regional records corresponding to the user identifier; Based on the historical geographic records and the geographic filtering parameters in the keyword filtering parameters, the set of keywords to be processed is filtered by geographic region to obtain the target geographic keyword set.

3. The method according to claim 1, characterized in that, The target keyword set obtained from the push includes: The target keywords in the target keyword set are split to obtain a set of target keyword phrases corresponding to the target keywords; Geographic extraction is performed on the target keyword phrase set to obtain geographic information corresponding to the target keywords, and hot keywords are obtained. Recommendation reasons are mined on the target keyword phrase set based on the hot keywords to obtain recommendation reasons corresponding to the target keywords. The system pushes the target keyword set, the corresponding geographic information, and the corresponding recommendation reason.

4. The method according to claim 3, characterized in that, The process of acquiring trending keywords and mining recommendation reasons based on these trending keywords to obtain recommendation reasons corresponding to the target keyword phrase set includes: Retrieve the logs to be processed corresponding to the user identifier; The log to be processed is split to obtain a set of log phrases to be processed corresponding to the log to be processed. Based on the set of log phrases to be processed and the preset hot keyword judgment rules, hot keywords and hot attributes of the hot keywords are obtained; Match the target keyword phrase set with the hot keywords to determine the matching keywords corresponding to the hot keywords; Based on the aforementioned hot topic attributes, the recommendation reason for the hit keyword is obtained.

5. An information recommendation device, characterized in that, The device includes: The receiving module is used to receive user login requests, wherein the user login requests carry a user identifier; The acquisition module is used to acquire, when the user login request is verified, the associated documents and historical keyword set corresponding to the user identifier, and extract the keyword set to be processed from the associated documents; the associated documents refer to documents that are associated with at least one of the user's industry and the user's product; the keywords to be processed in the keyword set carry device attributes, and the device attributes are related to the target audience of the associated documents; the historical keyword set refers to the set of keywords that have been recommended to the user and selected by the user in the past. The region detection module is used to split the keywords to be processed in the set of keywords to be processed to obtain a set of keyword phrases to be processed corresponding to the keywords to be processed. The module matches the set of keyword phrases to be processed with a preset set of regional phrases. When a regional phrase exists in any set of keyword phrases to be processed, it is determined that a regional keyword exists in the set of keywords to be processed. When a regional phrase does not exist in the set of keyword phrases to be processed, it is determined that a regional keyword does not exist in the set of keywords to be processed. The first filtering module is used to, when the set of keywords to be processed contains regional keywords, obtain the keyword filtering parameters selected by the user, perform regional filtering on the set of keywords to be processed according to the regional filtering parameters in the keyword filtering parameters to obtain a target regional keyword set, and filter the target regional keyword set according to the historical keyword set and the device filtering parameters in the keyword filtering parameters to obtain a target keyword set whose device attribute is the device filtering parameters; the regional filtering parameters are used to represent the specific region selected by the user, and the device parameters are used to represent the specific device selected by the user; the target keyword set does not include the historical keyword set; The second filtering module is used to obtain the keyword filtering parameters selected by the user when there are no regional keywords in the keyword set to be processed, and to filter the keyword set to be processed according to the historical keyword set and the device filtering parameters in the keyword filtering parameters to obtain the target keyword set whose device attribute is the device filtering parameters. The push module is used to push the obtained set of target keywords.

6. The apparatus according to claim 5, characterized in that, The first filtering module is further configured to, when there are regional keywords in the set of keywords to be processed, obtain the keyword filtering parameters selected by the user and the historical regional records corresponding to the user identifier, and perform regional filtering on the set of keywords to be processed according to the historical regional records and the regional filtering parameters in the keyword filtering parameters to obtain the target regional keyword set.

7. The apparatus according to claim 5, characterized in that, The push module is further configured to split the target keywords in the target keyword set to obtain a target keyword phrase set corresponding to the target keywords, extract the geographic information of the target keyword phrase set to obtain the geographic information corresponding to the target keywords, obtain hot keywords, mine recommendation reasons for the target keyword phrase set based on the hot keywords to obtain recommendation reasons corresponding to the target keywords, and push the target keyword set, the corresponding geographic information, and the corresponding recommendation reasons.

8. The apparatus according to claim 7, characterized in that, The push module is also used to obtain logs to be processed corresponding to the user identifier, split the logs to be processed to obtain a set of log phrases to be processed corresponding to the logs to be processed, obtain hot keywords and hot attributes of the hot keywords based on the set of log phrases to be processed and preset hot keyword judgment rules, match the target keyword phrase set with the hot keywords to determine the hit keywords corresponding to the hot keywords, and obtain the recommendation reason for the hit keywords based on the hot attributes.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images