Target recommendation method, apparatus, device, and medium

Abstract

The application relates to the technical field of data processing, in particular to a target recommendation method and device, equipment and medium. The method comprises the following steps: acquiring virtual resource demand information input by a user; determining a virtual resource demand market based on the virtual resource demand information; acquiring a dynamic board mapping table corresponding to the virtual resource demand market in a current period; determining a target recommended virtual resource board resource set by using a preset virtual resource recommendation model based on the virtual resource demand information, the virtual resource demand market and the dynamic board mapping table; and determining a target virtual resource object according to the target recommended virtual resource board resource set, so that accurate matching of related board information is realized according to dynamically updated board data in a target market, accurate target recommendation is realized, and accurate target recommendation query conditions are formed.

Description

Technical Field

[0001] This disclosure generally relates to the field of data processing technology, and specifically to a method, apparatus, device, and medium for target recommendation. Background Technology

[0002] With the widespread application of artificial intelligence technology in the financial sector, intelligent stock selection systems have become an important tool for investors. For example, users describe their stock selection needs using natural language, and the stock selection analysis model recommends stocks based on this analysis. Sector identification is a crucial step in the stock selection process. However, because sector information is dynamic—new sectors are constantly emerging, and old sectors may be adjusted or removed—accurately identifying the sectors involved in the stock selection needs and matching them with the latest sector data has become a pressing problem. Summary of the Invention

[0003] In view of the above-mentioned defects or deficiencies in the prior art, it is desirable to provide a target recommendation method, apparatus, device and medium that can effectively match relevant sector information based on dynamically updated sector data in the target market, thereby forming accurate target recommendation query conditions to achieve precise target recommendation.

[0004] In a first aspect, embodiments of this application provide a target recommendation method, including: Obtain the user's input information regarding virtual resource requirements; Based on the aforementioned virtual resource demand information, the virtual resource demand market is determined; Obtain the dynamic sector mapping table corresponding to the virtual resource demand market in the current time period; the dynamic sector mapping table is used to represent the mapping relationship between the virtual resource demand market, the virtual resource trading sector, and the resource set of the virtual resource sector in the current time period. Using a pre-defined virtual resource recommendation model, based on the virtual resource demand information, the virtual resource demand market, and the dynamic sector mapping table, a set of target recommended virtual resource sectors is determined. Based on the target, a set of virtual resource modules is recommended to determine the target virtual resource object.

[0005] Secondly, embodiments of this application provide a target recommendation device, including: The acquisition module is used to acquire the virtual resource requirement information input by the user; The determination module is used to determine the virtual resource demand market based on the virtual resource demand information; The update module is used to obtain a dynamic sector mapping table corresponding to the virtual resource demand market in the current time period; the dynamic sector mapping table is used to represent the mapping relationship between the virtual resource demand market, the virtual resource trading sector, and the resource set of the virtual resource sector in the current time period. The matching module is used to determine the target recommended virtual resource module resource set based on the virtual resource demand information, the virtual resource demand market, and the dynamic module mapping table using a preset virtual resource recommendation model. The recommendation module is used to recommend a set of virtual resource modules based on the target and to determine the target virtual resource object.

[0006] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in embodiments of this application.

[0007] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in embodiments of this application.

[0008] Fifthly, embodiments of this application provide a computer program product, including a computer program, characterized in that, when the computer program is executed by a processor, it implements the method described in embodiments of this application.

[0009] The target recommendation method provided in this application obtains virtual resource demand information input by the user, determines the virtual resource demand market based on the virtual resource demand information, obtains the dynamic sector mapping table corresponding to the virtual resource demand market in the current time period, and then uses a preset virtual resource recommendation model to determine the target recommended virtual resource sector resource set based on the virtual resource demand information, the virtual resource demand market, and the dynamic sector mapping table. Based on the target recommended virtual resource sector resource set, the target virtual resource object is determined. This effectively realizes accurate matching of relevant sector information based on dynamically updated sector data in the target market, thereby forming accurate target recommendation query conditions to achieve precise target recommendation.

[0010] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0011] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This diagram illustrates the implementation environment architecture of the target recommendation method provided in an embodiment of this application. Figure 2 A flowchart illustrating a target recommendation method provided in an embodiment of this application is shown; Figure 3A timing diagram of dynamic block mapping table updates provided in an embodiment of this application is shown; Figure 4 A schematic diagram of the target recommendation device provided in one embodiment of this application is shown; Figure 5 A schematic diagram of the structure of a computer system suitable for implementing an electronic device or server according to embodiments of this application is shown. Detailed Implementation

[0012] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0013] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0014] For the specific implementation environment of the target recommendation method proposed in this application, please refer to [link / reference]. Figure 1 . Figure 1 The implementation environment architecture diagram of the target recommendation method provided in the embodiments of this application is shown.

[0015] like Figure 1 As shown, the implementation environment architecture includes: terminal device 101, server 102 and multiple virtual resource demand market servers 103.

[0016] Terminal device 101 is used to run an application client and provide an interactive interface to the user. This interface receives virtual resource request information input by the user, displays filtering factors and target virtual resource objects, etc. Terminal device 101 can be a desktop computer, laptop computer, smartphone, tablet computer, e-book reader, smart glasses, smartwatch, in-vehicle device, ultra-mobile personal computer (UMPC), netbook, as well as cellular phones, personal digital assistants (PDAs), augmented reality (AR), and virtual reality (VR) devices, but is not limited to these.

[0017] Server 102 is connected to terminal device 101 and multiple virtual resource demand market servers 103. Server 102 is used to execute the target recommendation method proposed in the application embodiment, to determine the virtual resource demand market based on the virtual resource demand information input by the user on terminal device 101, and to recommend target stocks from multiple real-time sectors of the virtual resource demand market. The multiple virtual resource demand market servers 103 maintain sector data for their respective virtual resource demand markets.

[0018] Server 102 can be a standalone 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. Server 102 is used to provide replacement terms to terminal device 101 and execute strategies for identifying anomalies in target terms.

[0019] Server 102 is directly or indirectly connected to terminal device 101 and multiple virtual resource demand marketplace servers 103 via wired or wireless communication. Optionally, the aforementioned wireless or wired network uses standard communication technologies and / or protocols. The network is typically the Internet, but can also be any network, including but not limited to any combination of Local Area Network (LAN), Metropolitan Area Network (MAN), Wide Area Network (WAN), mobile, wired or wireless network, private network, or virtual private network.

[0020] The target recommendation method proposed in this application can be implemented by a target recommendation device, which can be installed on a terminal device or a server.

[0021] To further illustrate the technical solutions provided in the embodiments of this application, a detailed description is provided below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiments of this application provide method operation instruction steps as shown in the following embodiments or drawings, the method may include more or fewer operation instruction steps based on conventional or non-creative effort. In steps where there is no logically necessary causal relationship, the execution order of these steps is not limited to the execution order provided in the embodiments of this application. In actual processing or when the device executes the method, it may be executed sequentially or in parallel according to the method shown in the embodiments or drawings.

[0022] It should be noted that the acquisition or use of data in the embodiments of this application requires the user's consent. The relevant data can only be obtained after the user's authorization and permission, and the acquisition or use of the data complies with the laws and regulations of the relevant regions.

[0023] Please refer to Figure 2 , Figure 2 A flowchart illustrating a target recommendation method provided in an embodiment of this application is shown. Figure 2 As shown, the method includes: Step 201: Obtain the virtual resource requirement information input by the user.

[0024] It should be noted that virtual resource demand information describes the user's requirements for the recommendation results (i.e., the virtual resource objects to be recommended to the user). This virtual resource demand information can be text or voice; no specific limitation is made here.

[0025] Furthermore, a virtual resource object can be an object that can be deemed valuable in a specific usage scenario. For example, it could be a transaction object in a buying and selling scenario; an object deemed valuable by both parties in a barter scenario; stocks, funds, or other objects used as transaction objects in a financial scenario; or game resource objects (such as game equipment or game skins) set up in a game scenario that can be used as transaction objects. No specific limitations are imposed. This application embodiment primarily uses stocks as an example of a virtual resource object for illustration; other cases are not listed.

[0026] Taking stocks as an example of virtual resource objects, the virtual resource demand information can specifically be stock selection demand information. Specifically, the financial investment application client can provide an intelligent question-and-answer system. Users can input their stock selection demand information in the display interface of the intelligent question-and-answer system on the financial investment application client. This stock selection demand information represents the user's proposed stock screening needs. The intelligent question-and-answer system processes the stock selection demand information through a virtual resource recommendation model and outputs target virtual resource objects to recommend to the user.

[0027] Step 202: Based on the virtual resource demand information, determine the virtual resource demand market.

[0028] In other words, after a user inputs information about their virtual resource needs, the system can identify the trading market where the user's desired recommendation results are located based on that information. These trading markets can be categorized by region, for example, they could include trading markets in country A, country B, country C, etc.

[0029] Taking the virtual resource object as a stock object as an example, the virtual resource demand market refers to the trading market where the recommended results (i.e., stock objects) expected by users are located. For example, the virtual resource demand market includes, but is not limited to, the US market, the Singapore market, the Japanese market, etc.

[0030] In a feasible embodiment, the virtual resource demand market corresponding to the virtual resource demand information can be obtained through semantic understanding based on a preset virtual resource demand market analysis model.

[0031] Specifically, the virtual resource demand information input by the user is input into the virtual resource demand market analysis model to obtain the virtual resource demand market corresponding to the virtual resource demand information. Among them, the virtual resource demand market analysis model can be a prediction model constructed using the DSPy framework. By analyzing information such as keywords and semantic features in the virtual resource demand information, a probability prediction is made for the virtual resource demand market corresponding to the virtual resource demand information, and the virtual resource demand market corresponding to the virtual resource demand information is obtained.

[0032] It should be noted that when the virtual resource demand market keywords are directly included in the virtual resource demand information, such as "Hong Kong stocks", "US stocks", "A shares", etc., the virtual resource demand market analysis model can better identify the virtual resource demand market.

[0033] To further improve the reliability of the virtual resource demand market analysis model, the present application further presets an expression mapping table for each virtual resource demand market, so that before analyzing the virtual resource demand information, the virtual resource demand market analysis model normalizes the features related to the virtual resource demand market in the virtual resource demand information. For example, "US stock market", "US market", etc. are mapped to the standard virtual resource demand market name, such as "US stocks". Thus, the stability of identifying the virtual resource demand market for user inputs with different language habits is effectively improved.

[0034] Optionally, if the virtual resource demand market analysis model cannot directly identify the virtual resource demand market corresponding to the virtual resource demand information, the default virtual resource demand market can be used as the virtual resource demand market corresponding to the virtual resource demand information. Among them, the default virtual resource demand market can be set according to actual needs, and the present application does not make specific limitations.

[0035] Step 203, obtain a dynamic sector mapping table corresponding to the virtual resource demand market in the current period; the dynamic sector mapping table is used to represent the mapping relationship between the virtual resource demand market, the virtual resource trading sector, and the virtual resource sector resource set in the current period.

[0036] Among them, the virtual resource trading sector refers to the category name under a certain category to which virtual resources belong, according to a certain classification method; the virtual resource sector resource collection refers to the collection of all virtual resources under a certain virtual resource trading sector, that is, virtual resources with certain common characteristics are divided into a category to form a collection, which corresponds to a virtual resource trading sector.

[0037] Different trading markets use different methods to classify virtual resources into different sectors. When virtual resource objects are used as stock objects, they can be grouped into a specific virtual resource trading sector based on similar businesses, related industries, or common characteristics, resulting in a corresponding set of virtual resource sectors. For example, they can be divided according to the industry to which the stock objects belong, resulting in stock objects under different industry sectors, such as the technology sector, the financial sector, and the consumer sector. Alternatively, they can be divided according to the concept to which the stock objects belong, resulting in stock objects under different concept sectors, such as the metaverse sector, the carbon neutrality sector, and the digital currency sector.

[0038] In other words, after obtaining the virtual resource demand market corresponding to the virtual resource demand information, the system further obtains the latest sector information of the virtual resource demand market, namely the dynamic sector mapping table for the current period.

[0039] Because the information on market segments is dynamic, meaning that the virtual resources in the virtual resource trading segments under the virtual resource demand market, or the virtual resources in the resource sets corresponding to those segments, will change—for example, a virtual resource trading segment under the virtual resource demand market may be deleted or added, and other virtual resources may be deleted or added to the resource sets corresponding to those segments—this application updates the dynamic segment mapping table of the virtual resource demand market according to time periods. Specifically, it updates the mapping relationship between the virtual resource demand market, virtual resource trading segments, and virtual resource resource sets for the current time period. This allows for accurate recommendations of target virtual resources based on the actual segment data for the current time period when using a pre-defined virtual resource recommendation model, effectively avoiding the decrease in accuracy caused by static or lagging data.

[0040] In one feasible embodiment, obtaining the dynamic sector mapping table corresponding to the virtual resource demand market in the current time period includes: obtaining the input time of the virtual resource demand information; if the input time meets the update conditions of the current time period, obtaining the main mapping table of the sector set updated in the previous time period; the main mapping table of the sector set is used to reflect the mapping relationship between each virtual resource demand market and the sector set; traversing the main mapping table of the sector set to obtain multiple virtual resource trading sectors corresponding to the current virtual resource demand market and the detailed information corresponding to the virtual resource trading sectors; and constructing the dynamic sector mapping table corresponding to the virtual resource market based on the virtual resource trading sectors and their corresponding detailed information.

[0041] Specifically, after obtaining virtual resource demand information, the input time of the virtual resource demand information is determined, and the corresponding dynamic module mapping table is matched according to the actual input time of the virtual resource demand information. The update condition for the dynamic module mapping table is a preset time interval. Specifically, if the difference between the input time and the previous update time of the dynamic module mapping table is greater than or equal to the preset time interval, it is determined that the input time of the virtual resource demand information meets the update condition for the current time period, and the dynamic module mapping table needs to be updated. If the difference between the input time and the previous update time of the dynamic module mapping table is less than the preset time interval, it is determined that the input time of the virtual resource demand information does not meet the update condition for the current time period, and the dynamic module mapping table does not need to be updated; that is, the dynamic module mapping table can be directly obtained as the dynamic module mapping table for the current time period.

[0042] Optionally, the time interval for updating the dynamic module mapping table can be determined based on the module update patterns of multiple virtual resource demand markets, or it can be determined based on the freshness of the dynamic module mapping table and the system load capacity.

[0043] Preferably, the time interval can be 3600 seconds, equivalent to 1 hour. Choosing a time interval of 3600 seconds effectively avoids the increased system load caused by too short an interval, and the problem of insufficiently up-to-date data due to too long an interval.

[0044] In a preferred embodiment, the server may also maintain a timer to periodically update the dynamic module mapping table according to the timer's set intervals. That is, when no virtual resource demand information is received, the dynamic module mapping table can be automatically updated according to the timer's set intervals, thereby reducing the time consumed in updating the dynamic module mapping table after receiving virtual resource demand information and improving the efficiency of target recommendations.

[0045] Therefore, by setting a fixed update frequency for the dynamic tile mapping table, this embodiment of the application can effectively monitor and manage the dynamic tile mapping table. Simultaneously, by controlling the synchronization frequency, it effectively balances the freshness of the dynamic tile mapping table and system consumption, avoiding excessive consumption of system resources. Furthermore, time-driven updates to the dynamic tile mapping table effectively improve its fault tolerance; even if an update fails, the update steps will be re-executed at the next time interval, preventing the dynamic tile mapping table from stopping due to a single update failure.

[0046] Furthermore, when the input time of the virtual resource demand information is found to meet the update conditions of the current time period, the updated main mapping table of the sector set from the previous time period is obtained. It should be understood that this main mapping table of the sector set is the one obtained after the previous dynamic update of the sector mapping table. The main mapping table of the sector set is used to represent the mapping relationship between the set identifier of the sector set and the market identifier of the virtual resource demand market. The sector set may include all virtual resource trading sectors under the virtual resource demand market, that is, a set constructed from all or some virtual resource trading sectors under a certain virtual resource demand market. It should be understood that in the main mapping table of the sector set, a virtual resource demand market may correspond to one sector set or multiple sector sets, specifically determined by the main mapping table of the sector set, and this application does not specifically limit this. In other words, the main mapping table of the sector set can reflect the situation of virtual resource trading sectors under each virtual resource demand market in the previous time period. By obtaining the updated main mapping table of the sector set from the previous time period, sector information with relatively small changes compared to the current time period can be obtained, and the sector data can be ensured to be as comprehensive and reliable as possible.

[0047] In one specific embodiment, each virtual resource demand market corresponds to a main mapping table of a sector set. In this embodiment, when the input time of the virtual resource demand information meets the update condition, the dynamic sector mapping table of the previous time period is obtained. Then, for each virtual resource demand market, the mapping relationship between the virtual resource demand market and the sector set is extracted from the dynamic sector mapping table to obtain the main mapping table of the sector set corresponding to each virtual resource demand market. This achieves comprehensive acquisition of sector information, realizes synchronous updating of the dynamic sector mapping tables of multiple virtual resource demand markets, and ensures the consistency of the target virtual resource object in multiple virtual resource demand markets.

[0048] After obtaining the updated master mapping table of the sector set from the previous time period, the table is traversed to retrieve the multiple virtual resource trading sectors corresponding to each virtual resource demand market, along with detailed information about each sector. This detailed information includes, but is not limited to, the sector name and sector identifier. The sector name includes multilingual names, such as the sector names in different virtual resource trading markets. For example, a list of sector identifiers for all sectors under the sector set can be obtained by calling the RPC interface of the sector service.

[0049] Then, by constructing a mapping relationship between the virtual resource demand market, the virtual resource trading sector, and their corresponding detailed information, a dynamic sector mapping table corresponding to the virtual resource demand market is built. It should be understood that, for each virtual resource demand market, the mapping relationship between the virtual resource trading sector and its corresponding detailed information can be used to construct a dynamic sector mapping table corresponding to each virtual resource demand market, thereby obtaining the dynamic sector mapping table corresponding to the virtual resource demand market for the virtual resource demand information.

[0050] In a feasible embodiment, in order to further improve the query speed of the pre-set virtual resource recommendation model based on the dynamic module mapping table, this application further proposes to construct the dynamic module mapping table into a multi-layer mapping structure to support efficient data query and transformation.

[0051] Specifically, the following relationships are obtained: a first mapping relationship between the market identifier of the virtual resource demand market and the standard segment name of the virtual resource trading segment; a second mapping relationship between the market identifier of the virtual resource demand market and the standard segment name of the virtual resource trading segment and the segment identifier of the virtual resource trading segment; a third mapping relationship between the segment identifier of the virtual resource trading segment and the set identifier of the resource collection of the virtual resource segment; and a fourth mapping relationship between the segment identifier of the virtual resource trading segment and the multilingual name of the virtual resource trading segment. Based on the first, second, third, and fourth mapping relationships, a dynamic segment mapping table is constructed.

[0052] The dynamic module mapping table is constructed into a multi-level mapping table based on multiple mapping relationships. For example, each mapping relationship corresponds to a mapping table, namely, the first mapping relationship corresponds to the first-level mapping table, the second mapping relationship corresponds to the second-level mapping table, the third mapping relationship corresponds to the third-level mapping table, and the fourth mapping relationship corresponds to the fourth-level mapping table.

[0053] Specifically, the structure of the first-level mapping table (market_id_to_plate_name_list_map) can be {market identifier of virtual resource demand market: [standard plate name 1, standard plate name 2, ...]}, used to quickly obtain all plate names under a certain virtual resource demand market, providing initial recommendations for virtual resource trading plates for subsequent use in the preset virtual resource recommendation model. The first-level mapping table can include multiple virtual resource demand markets, for example, it can be denoted as {1: ["Technology Plate", "Finance Plate", ...], 2: ["Technology", "Finance", ...]}.

[0054] The second-level mapping table (market_plate_name_to_plate_id_map) can have the structure {Market ID of Virtual Resource Demand Market_Standard Plate Name of Virtual Resource Trading Sector: [Sector ID 1, Sector ID 2,...]}. It is used to quickly find the corresponding sector ID of a virtual resource sector based on the market ID of the virtual resource demand market and the standard plate name of the virtual resource trading sector. For example, it can be represented as {"1_Technology Sector": 1001,"2_Technology": 2001}.

[0055] The third-level mapping table (plate_id_to_plate_set_id_map) can have the structure {plate identifier of virtual resource trading plate: set identifier of virtual resource plate resource set}. It is used to find the corresponding virtual resource plate resource set based on the plate identifier of the virtual resource trading plate. This virtual resource plate resource set is used for subsequent target virtual resource object recommendation queries. For example, it can be represented as {1001: 6601, 2001: 6603}.

[0056] The fourth-level mapping table (plate_id_to_all_names_map) can have the structure {virtual resource trading board identifier: {"language tag":"standard board name"}}, used to support multilingual scenarios and return the board name in the corresponding language based on the user's language preference. For example, it can be represented as {1001: {"zh-cn":"Technology Board","en-us":"Technology"}}, where zh-cn is the language tag for Simplified Chinese, zh-hk is the language tag for Traditional Chinese, and en-us is the language tag for English, etc.

[0057] It should be noted that, in this embodiment of the application, the standard section name is a standardized mapping of the multilingual section name, in order to ensure data consistency in the multi-virtual resource demand market.

[0058] Therefore, the embodiments of this application construct a four-layer mapping table in the stage of obtaining the dynamic sector mapping table, which can effectively improve the consistency and integrity of the virtual resource trading sector in the virtual resource demand market.

[0059] Step 204: Using a pre-defined virtual resource recommendation model, based on virtual resource demand information, virtual resource demand market, and dynamic sector mapping table, determine the target recommended virtual resource sector resource set.

[0060] In other words, after obtaining the dynamic sector mapping table corresponding to the virtual resource demand market, the system uses a preset virtual resource recommendation model to analyze the virtual resource demand information, the virtual resource demand market, and the dynamic sector mapping table to determine the target recommended virtual resource sector resource set.

[0061] The preset virtual resource recommendation model can be a semantic matching model (GetPlateWithHintModule) built using the DSPy framework.

[0062] In one feasible embodiment, a pre-defined virtual resource recommendation model is used to determine a target set of recommended virtual resource sectors based on virtual resource demand information, the virtual resource demand market, and a dynamic sector mapping table. This includes: obtaining preliminary recommended virtual resource trading sectors corresponding to the virtual resource demand market based on the virtual resource demand market and the dynamic sector mapping table; determining candidate recommended virtual resource trading sectors from the preliminary recommended virtual resource trading sectors using the pre-defined virtual resource recommendation model; verifying the candidate recommended virtual resource trading sectors based on the dynamic sector mapping table; and determining the target set of recommended virtual resource sectors based on the candidate recommended virtual resource trading sectors and the dynamic sector mapping table after the candidate recommended virtual resource trading sectors have passed verification.

[0063] In other words, after obtaining the dynamic sector mapping table corresponding to the virtual resource demand market, the initial recommended virtual resource trading sectors corresponding to the virtual resource demand market can be determined based on the market identifier of the virtual resource demand market and the first-level mapping table of the dynamic sector mapping table. That is, all virtual resource trading sectors in the current period of the virtual resource demand market corresponding to the stock selection recommendations described by the virtual resource demand information entered by the user.

[0064] Then, using a pre-defined virtual resource recommendation model, semantic matching is performed between the virtual resource demand information and the initially recommended virtual resource transaction sections to determine candidate recommended virtual resource transaction sections—that is, virtual resource transaction sections in the virtual resource demand market that match the user's input virtual resource demand information. The pre-defined virtual resource recommendation model is configured to only identify virtual resource transaction sections explicitly mentioned in the virtual resource demand information, ignoring irrelevant content. Therefore, the pre-defined virtual resource recommendations may or may not match any virtual resource transaction sections that meet the criteria. In other words, if the virtual resource demand information does not explicitly mention any relevant information about virtual resource transaction sections, the pre-defined virtual resource recommendation model cannot match any virtual resource transaction sections that meet the criteria.

[0065] In some embodiments, if the preset virtual resource recommendation model matches a virtual resource trading section that meets the conditions, i.e., a candidate recommended virtual resource trading section is obtained, the candidate recommended virtual resource trading section is further verified based on a dynamic section mapping table. This verification may involve checking whether the candidate recommended virtual resource trading section completely matches the initial recommended virtual resource trading section. The section name can be any of the multilingual section names of the virtual resource trading section. In other words, to avoid semantic illusions caused by the preset virtual resource recommendation model, a secondary verification is performed on the candidate recommended virtual resource trading sections matched by the preset virtual resource recommendation model to ensure that each candidate recommended virtual resource trading section originates from the initial recommended virtual resource trading section.

[0066] After the candidate recommended virtual resource trading sector is verified, the standard sector name of the candidate recommended virtual resource trading sector is extracted. According to the second-level mapping table of the dynamic sector mapping table, the standard sector name of the candidate recommended virtual resource trading sector is converted into the sector identifier of the candidate recommended virtual resource trading sector. Then, according to the third-level mapping table of the dynamic sector mapping table, the sector identifier of the candidate recommended virtual resource trading sector is converted into the set identifier of the candidate recommended resource trading sector set. The set identifier of the candidate recommended resource trading sector set is used as the resource set of the target recommended virtual resource sector.

[0067] It should be noted that the embodiments of this application utilize a dynamic sector mapping table constructed based on a multi-layer mapping table, which can transform the query calculation of virtual resource sector resource sets into a simple hash table lookup, significantly improving query efficiency. Specifically, the first-layer mapping table can narrow the matching range, that is, it can match only the sectors corresponding to the virtual resource demand market, without having to match all sectors of the virtual resource demand market, thereby greatly reducing the amount of matching computation. The second-layer mapping table enables fast positioning, that is, the key value of the second-layer mapping table can uniquely identify a sector, avoiding the overhead of convenient lookup. The third-layer mapping table performs data conversion, that is, the subsequent selection of target virtual resource objects requires the use of the set identifier of the sector set rather than the sector identifier of the trading sector, and the third-layer mapping table can quickly complete the conversion. The fourth-layer mapping table enables internationalization support, that is, it provides sector names in different languages ​​for users of different languages, improving the user's reading experience.

[0068] In other embodiments, if the preset virtual resource recommendation model does not match a virtual resource trading section that meets the conditions, that is, no candidate recommended virtual resource trading section is obtained, an empty list is returned directly, without affecting the normal execution of other functions.

[0069] In a preferred embodiment, to further improve the accuracy and success rate of the preset virtual resource recommendation model, a hint mechanism can be set for the preset virtual resource recommendation model. This involves attaching guidance and hint rules to the virtual resource demand information input by the user, thereby increasing the clarity of the sector descriptions in the virtual resource demand information. For example, adding "new stocks" and "Singapore stocks" to the user's input virtual resource demand information enables the preset virtual resource recommendation model to match candidate virtual resource trading sectors among Singapore stocks.

[0070] It should be understood that the pre-defined virtual resource recommendation model can also determine the screening factors and factor parameters used to filter target virtual resource objects. Screening factors refer to factors that can describe the characteristics of virtual resource objects, or virtual objects, across different dimensions. In essence, screening factors can serve as screening conditions (or conditional factors) used in the target virtual resource object screening system to filter virtual resource objects. By limiting certain screening conditions through screening factors, specific recommended objects can be selected from all candidate virtual resource objects. Factor parameters are range parameters used when filtering based on screening factors.

[0071] Step 205: Based on the target recommended virtual resource module resource set, determine the target virtual resource object.

[0072] The target recommended virtual resource section includes a set of multiple virtual resource objects. The target recommended virtual resource section can be used as a candidate set to determine the target virtual resource object.

[0073] Specifically, after obtaining the resource set of the target recommended virtual resource section, a preset virtual resource recommendation model can be used to obtain target screening factors and their corresponding factor parameters based on virtual resource demand information. Then, based on the target screening factors, the factor parameters of the target screening factors, and the resource set of the target recommended virtual resource section, query conditions for target screening are constructed. Then, the constructed query conditions are used as request information, so that the server responds to the request information. According to the query conditions, virtual resource objects are screened in the resource set of the target recommended virtual resource section to obtain target virtual resource objects that meet the target screening factors and their factor parameters.

[0074] Among them, virtual resource recommendation factors refer to factors that can describe virtual resource objects or the characteristics of virtual objects in different dimensions. It can be understood that virtual resource recommendation factors can serve as screening conditions (or conditional factors) in a target virtual resource object screening system to filter virtual resource objects. By limiting certain screening conditions through virtual resource recommendation factors, specific recommended objects can be selected from all candidate virtual resource objects. Furthermore, target recommendation factors refer to virtual resource recommendation factors that can be extracted from virtual resource demand information.

[0075] Taking virtual resource objects as stock objects as an example, virtual resource recommendation factors refer to factors that can describe the characteristics of stock objects or stock objects in different dimensions. For example, virtual resource recommendation factors can be stock selection factors, including indicators of stock objects in different dimensions, such as stock price, trading volume, turnover rate, MA indicator, MACD indicator, price-earnings ratio, net profit, growth rate, etc.

[0076] Furthermore, a virtual resource recommendation model can be used to analyze virtual resource demand information and determine target recommendation factors and corresponding target recommendation parameters from a set of candidate recommendation factors; the set of candidate recommendation factors refers to a collection pre-constructed for virtual resource recommendation factors. Specifically, virtual resource demand information is input into the virtual resource recommendation model to analyze it, and target recommendation factors and corresponding target recommendation parameters are determined from the set of candidate recommendation factors based on the analysis results. The virtual resource recommendation model can perform various analytical operations on the demand text information, such as semantic analysis, matching analysis, and parameter analysis; this application does not impose specific limitations on these operations. Optionally, the recommendation model can determine target recommendation factors and target recommendation parameters simultaneously, or it can do so step by step, for example, first determining the target recommendation factors and then determining the corresponding target recommendation parameters based on the target recommendation factors.

[0077] Therefore, the target recommendation method provided in this application obtains the virtual resource demand information input by the user, determines the virtual resource demand market based on the virtual resource demand information, obtains the dynamic sector mapping table corresponding to the virtual resource demand market in the current time period, and then uses a preset virtual resource recommendation model to determine the target recommended virtual resource sector resource set based on the virtual resource demand information, the virtual resource demand market and the dynamic sector mapping table. Based on the target recommended virtual resource sector resource set, the target virtual resource object is determined. This effectively realizes accurate matching of relevant sector information based on dynamically updated sector data under the target market, thereby forming accurate target recommendation query conditions to achieve accurate target recommendation.

[0078] In one feasible embodiment, since the preset virtual resource recommendation model needs to be analyzed through the updated dynamic section mapping table, especially in a multi-threaded environment where multiple requests may access the dynamic section mapping table simultaneously, this application further proposes to use read-write locks to update the dynamic section mapping table in order to ensure the atomicity of the dynamic section mapping table update and avoid data inconsistency problems caused by partial updates.

[0079] On the one hand, before acquiring the updated master mapping table of the sector set from the previous time period, the process also includes: acquiring a write lock on the dynamic sector mapping table to block read requests for each dynamic sector mapping table. Read requests do not distinguish between virtual resource demand markets.

[0080] After constructing a dynamic sector mapping table corresponding to the virtual resource demand market based on the virtual resource trading sectors and their corresponding detailed information, the process also includes: updating the main mapping table of the sector set based on the dynamic sector mapping table, and releasing the write lock.

[0081] In other words, a write lock needs to be acquired before updating the dynamic block mapping table. This write lock is an exclusive lock; once acquired, all other read and write operations are blocked until the write operation is complete and the lock is released, effectively ensuring the atomicity of updating the dynamic block mapping table.

[0082] On the other hand, for each read request, in response to the read request, the read lock corresponding to the read request is acquired, and after obtaining the dynamic module mapping table, the read lock is released.

[0083] It should be noted that all operations involving reading the dynamic module mapping table require acquiring a read lock first. This read lock is a shared lock, allowing multiple threads to read concurrently but prohibiting write operations, thus ensuring that the data is not tampered with during the reading process.

[0084] In a preferred embodiment, in addition to the locking mechanism, an update status flag (_syncing) can be maintained to prevent multiple threads from triggering update operations simultaneously. That is, if an update is in progress and other threads detect that the flag is True, they will not trigger an update to the dynamic module mapping table, thus avoiding resource waste caused by duplicate updates.

[0085] Therefore, this application effectively ensures the consistency of data access in a multi-threaded environment through a locking mechanism, avoiding data races and misidentification.

[0086] In one specific embodiment, such as Figure 3 As shown, the timer triggers the section service to check update conditions at preset intervals, such as once every 3600 seconds. The section service checks the interval and update status. If an update is needed, the section service acquires a write lock from the locking mechanism and blocks read requests from multiple threads. Then, it iterates through the main mapping table of the section collection, and for each section collection, calls the RPC interface to obtain a list of section identifiers, retrieves detailed section information in batches (e.g., 50 per batch), constructs a multi-layered temporary mapping table, atomically replaces the main mapping table of the section collection, and releases the write lock. The locking mechanism allows read operations from multiple read request threads.

[0087] For each read thread, acquire a read lock from the locking mechanism, read the main mapping table of the block set from the mapping table, and then release the read lock.

[0088] It should be noted that although the operation of the method of the present invention is described in a specific order in the accompanying drawings, this does not require or imply that the operations must be performed in that specific order, or that all the operations shown must be performed in order to achieve the desired result.

[0089] Figure 4 A schematic diagram of the target recommendation device provided in an embodiment of this application is shown.

[0090] like Figure 4 As shown, the target recommendation device 10 includes: The acquisition module 11 is used to acquire the virtual resource requirement information input by the user; The determining module 12 is used to determine the virtual resource demand market based on the virtual resource demand information; Update module 13 is used to obtain a dynamic sector mapping table corresponding to the virtual resource demand market in the current time period; the dynamic sector mapping table is used to represent the mapping relationship between the virtual resource demand market, the virtual resource trading sector, and the virtual resource sector resource set in the current time period; Matching module 14 is used to determine the target recommended virtual resource module resource set based on the virtual resource demand information, the virtual resource demand market and the dynamic module mapping table using a preset virtual resource recommendation model; Recommendation module 15 is used to recommend a set of virtual resource modules based on the target and determine the target virtual resource object.

[0091] In some embodiments, the updating module 13 is specifically used for: The input time for obtaining the virtual resource demand information is determined. If the input time meets the update conditions of the current time period, the main mapping table of the sector set updated in the previous time period is obtained. The main mapping table is used to reflect the mapping relationship between each virtual resource demand market and the sector set. Traverse the main mapping table of the aforementioned sector set to obtain multiple virtual resource trading sectors corresponding to each virtual resource demand market and the detailed information corresponding to each virtual resource trading sector; Based on the virtual resource trading sector and its corresponding detailed information, a dynamic sector mapping table corresponding to the virtual resource demand market is constructed.

[0092] In some embodiments, the updating module 13 is specifically used for: The system obtains the following mapping relationships: a first mapping relationship between the market identifier of the virtual resource demand market and the standard section name of the virtual resource trading section; a second mapping relationship between the market identifier of the virtual resource demand market and the standard section name of the virtual resource trading section and the section identifier of the virtual resource trading section; a third mapping relationship between the section identifier of the virtual resource trading section and the set identifier of the resource collection of the virtual resource section; and a fourth mapping relationship between the section identifier of the virtual resource trading section and the multilingual name of the virtual resource trading section. The dynamic module mapping table is constructed based on the first mapping relationship, the second mapping relationship, the third mapping relationship, and the fourth mapping relationship.

[0093] In some embodiments, the updating module 13 is specifically used for: Before obtaining the updated main mapping table of the segment set from the previous time period: Acquire a write lock on the dynamic partition map table to block each read request to the dynamic partition map table, the read requests being indiscriminate in terms of the virtual resource demand market; and After constructing the dynamic sector mapping table corresponding to the virtual resource demand market based on the virtual resource trading sector and its corresponding detailed information: Update the main mapping table of the block set according to the dynamic block mapping table, and release the write lock.

[0094] In some embodiments, the updating module 13 is specifically used for: For each read request, in response to the read request, acquire the read lock corresponding to the read request; After obtaining the dynamic module mapping table, release the read lock.

[0095] In some embodiments, the matching module 14 is specifically used for: Based on the virtual resource demand market and the dynamic sector mapping table, obtain the preliminary recommended virtual resource trading sector corresponding to the virtual resource demand market; Using the preset virtual resource recommendation model, candidate recommended virtual resource trading sectors are determined from the initially selected recommended virtual resource trading sectors; The candidate recommended virtual resource trading sectors are verified based on the dynamic sector mapping table. After the candidate recommended virtual resource trading sectors are verified, the resource set of the target recommended virtual resource sector is determined based on the candidate recommended virtual resource trading sectors and the dynamic sector mapping table.

[0096] It should be understood that the modules or modules described in the target recommendation device 10 are related to the reference. Figure 2 The steps in the described method correspond to each other. Therefore, the operations and features described above for the method also apply to the target recommendation device 10 and the modules contained therein, and will not be repeated here. The target recommendation device 10 can be pre-implemented in the browser or other security applications of an electronic device, or it can be loaded into the browser or other security applications of an electronic device by means of downloading. The corresponding modules in the target recommendation device 10 can cooperate with the modules in the electronic device to implement the solution of the embodiments of this application.

[0097] The division of modules or units mentioned in the detailed description above is not mandatory. In fact, according to the embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0098] The following is for reference. Figure 5 , Figure 5 A schematic diagram of the structure of a computer system suitable for implementing the embodiments of this application is shown. like Figure 5As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 502 or programs loaded from storage section 508 into random access memory (RAM) 503. RAM 503 also stores various programs and data required for the system's operating instructions. CPU 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0099] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to I / O interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 510 as needed so that computer programs read from it can be installed into storage section 508 as needed.

[0100] Specifically, according to embodiments of this application, the flowchart above refers to... Figure 2 The described process can be implemented as a computer software program. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. In such an embodiment, the computer program contains program code for performing the methods shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by central processing unit (CPU) 501, it performs the functions defined in the system of this application.

[0101] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0102] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operational instructions of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two connected blocks may actually be executed substantially in parallel, or they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified functions or operational instructions, or using a combination of dedicated hardware and computer instructions.

[0103] The units or modules described in the embodiments of this application can be implemented in software or hardware. The described units or modules can also be housed in a processor; for example, a processor can be described as including an acquisition module, a determination module, an update module, a matching module, and a recommendation module. The names of these units or modules do not necessarily limit the specific unit or module itself; for example, an acquisition module can also be described as "acquiring virtual resource requirement information input by the user."

[0104] In another aspect, this application also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments, or may exist independently and not assembled into the electronic device. The aforementioned computer-readable storage medium stores one or more programs that, when used by one or more processors, execute the target recommendation method described in this application.

[0105] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A target recommendation method, characterized in that, include: Obtain the user's input information regarding virtual resource requirements; Based on the aforementioned virtual resource demand information, the virtual resource demand market is determined; Obtain the dynamic sector mapping table corresponding to the virtual resource demand market in the current time period; the dynamic sector mapping table is used to represent the mapping relationship between the virtual resource demand market, the virtual resource trading sector, and the resource set of the virtual resource sector in the current time period. Using a pre-defined virtual resource recommendation model, based on the virtual resource demand information, the virtual resource demand market, and the dynamic sector mapping table, a set of target recommended virtual resource sectors is determined. Based on the target, a set of virtual resource modules is recommended to determine the target virtual resource object.

2. The target recommendation method according to claim 1, characterized in that, The process of obtaining the dynamic sector mapping table corresponding to the virtual resource demand market in the current time period includes: The input time for obtaining the virtual resource demand information is obtained. If the input time meets the update conditions of the current time period, the main mapping table of the sector set updated in the previous time period is obtained. The main mapping table is used to reflect the mapping relationship between each virtual resource demand market and the sector set. Traverse the main mapping table of the aforementioned sector set to obtain multiple virtual resource trading sectors corresponding to each virtual resource demand market and the detailed information corresponding to each virtual resource trading sector; Based on the virtual resource trading sector and its corresponding detailed information, a dynamic sector mapping table corresponding to the virtual resource demand market is constructed.

3. The target recommendation method according to claim 2, characterized in that, The step of constructing a dynamic sector mapping table corresponding to the virtual resource demand market based on the virtual resource trading sector and its corresponding detailed information includes: The system obtains the following mapping relationships: a first mapping relationship between the market identifier of the virtual resource demand market and the standard section name of the virtual resource trading section; a second mapping relationship between the market identifier of the virtual resource demand market and the standard section name of the virtual resource trading section and the section identifier of the virtual resource trading section; a third mapping relationship between the section identifier of the virtual resource trading section and the set identifier of the resource collection of the virtual resource section; and a fourth mapping relationship between the section identifier of the virtual resource trading section and the multilingual name of the virtual resource trading section. The dynamic module mapping table is constructed based on the first mapping relationship, the second mapping relationship, the third mapping relationship, and the fourth mapping relationship.

4. The target recommendation method according to claim 2, characterized in that, Before obtaining the updated main mapping table of the sector set from the previous time period, the following steps are also included: Acquire a write lock on the dynamic partition map table to block each read request to the dynamic partition map table, the read requests being indiscriminate in terms of the virtual resource demand market; and After constructing the dynamic sector mapping table corresponding to the virtual resource demand market based on the virtual resource trading sector and its corresponding detailed information, the method further includes: Update the main mapping table of the block set according to the dynamic block mapping table, and release the write lock.

5. The target recommendation method according to claim 4, characterized in that, Also includes: For each read request, in response to the read request, acquire the read lock corresponding to the read request; After obtaining the dynamic module mapping table, release the read lock.

6. The target recommendation method according to claim 1, characterized in that, The step of using a preset virtual resource recommendation model, based on the virtual resource demand information, the virtual resource demand market, and the dynamic sector mapping table, to determine the target recommended virtual resource sector resource set includes: Based on the virtual resource demand market and the dynamic sector mapping table, obtain the preliminary recommended virtual resource trading sector corresponding to the virtual resource demand market; Using the preset virtual resource recommendation model, candidate recommended virtual resource trading sectors are determined from the initially selected recommended virtual resource trading sectors; The candidate recommended virtual resource trading sectors are verified based on the dynamic sector mapping table. After the candidate recommended virtual resource trading sectors are verified, the resource set of the target recommended virtual resource sector is determined based on the candidate recommended virtual resource trading sectors and the dynamic sector mapping table.

7. A target recommendation device, characterized in that, include: The acquisition module is used to acquire the virtual resource requirement information input by the user; The determination module is used to determine the virtual resource demand market based on the virtual resource demand information; The update module is used to obtain the dynamic sector mapping table corresponding to the virtual resource demand market in the current time period; the dynamic sector mapping table is used to represent the mapping relationship between the virtual resource demand market, the virtual resource trading sector, and the resource set of the virtual resource sector in the current time period. The matching module is used to determine the target recommended virtual resource module resource set based on the virtual resource demand information, the virtual resource demand market, and the dynamic module mapping table using a preset virtual resource recommendation model. The recommendation module is used to recommend a set of virtual resource modules based on the target and to determine the target virtual resource object.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the target recommendation method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the target recommendation method as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the target recommendation method as described in any one of claims 1-6.

Images