Object recommendation method based on computing power of intelligent computing center and related equipment

Abstract

The invention provides an object recommendation method based on computing power of an intelligent computing center and related equipment, and relates to the technical field of computing power infrastructure, the method comprises the following steps: S1, obtaining a plurality of objects to be displayed and a feature set corresponding to a target user, the feature set being used for representing information related to the target user; s2, screening the plurality of objects based on the feature set to obtain N target objects, N being a positive integer greater than 1; step S3, sorting the N target objects; and S4, generating a recommendation list based on the N sorted target objects. The object recommendation effect can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of computing power infrastructure, and in particular to an object recommendation method and related equipment based on the computing power of an intelligent computing center. Background Art

[0002] "Intelligent computing center" refers to a facility that provides the required computing power, data and algorithms for artificial intelligence applications (such as artificial intelligence deep learning model development, model training and model reasoning) by using large-scale heterogeneous computing resources, including general computing power and intelligent computing power. The intelligent computing center covers facilities, hardware, and software, and can provide full-stack capabilities from bottom-level computing power to top-level application enablement.

[0003] Recommending different types of products to users in an application is one of the common promotion methods, such as recommending different types of videos to users in video software, or recommending different types of goods to users in shopping software.

[0004] At present, the method of recommending products usually involves first setting rule tags and then recalling some products from all products, then filtering the products that users are interested in from these products and sorting them to obtain a list of products recommended to users. However, the method of filtering by setting rule tags is too simple and direct, and it is easy to filter out the products that users are interested in in advance, thereby reducing the recommendation conversion effect.

[0005] It can be seen that the existing technology has the problem of poor object recommendation conversion effect. Summary of the invention

[0006] The embodiment of the present invention provides an object recommendation method and related equipment based on the computing power of an intelligent computing center to solve the problem of poor object display effect in the prior art.

[0007] To solve the above problems, the present invention is achieved as follows:

[0008] In a first aspect, an embodiment of the present invention provides an object display method based on the computing power of an intelligent computing center, including:

[0009] Step S1: acquiring a plurality of objects to be displayed and a feature set corresponding to a target user, wherein the feature set is used to represent information related to the target user;

[0010] Step S2: screening the multiple objects based on the feature set to obtain N target objects, where N is a positive integer greater than 1;

[0011] Step S3, sorting the N target objects;

[0012] Step S4: Generate a recommendation list based on the sorted N target objects.

[0013] In one embodiment, the feature set includes at least one of a user feature, an object feature, and a scene feature, wherein the user feature is a feature of the user-related information, the object feature is used to describe the multiple objects, and the scene feature is a feature of the interaction behavior between the object and the target user under different scene conditions.

[0014] In one embodiment, step S2 includes:

[0015] Step S21: when the feature set includes one of the user feature, the object feature and the scene feature, each object is evaluated based on the one feature to obtain a first probability corresponding to each object;

[0016] Step S22: Screen the multiple objects based on the corresponding first probabilities to obtain the N target objects.

[0017] In one embodiment, step S2 includes:

[0018] Step S23: when the feature set includes at least two features among the user feature, the object feature and the scene feature, each object is evaluated based on each feature to obtain a second probability that each object corresponds to each feature;

[0019] Step S24, weighting all the second probabilities corresponding to the at least two features to obtain a third probability corresponding to each object;

[0020] Step S25: Screen the multiple objects based on the corresponding third probabilities to obtain the N target objects.

[0021] In one embodiment, before step S4, the method further includes:

[0022] Step S5: Obtain the policy corresponding to the target user, wherein the policy includes at least one of historical data and preset data, wherein:

[0023] The historical data includes historical object types related to the target user within a preset time period, and the types of the N target objects are different from the historical object types;

[0024] The preset data includes the registration information data of the target user, and at least one of the external platform data and label feature data, wherein the label feature data is used to characterize the type of object of interest selected by the target user;

[0025] The step S4 comprises:

[0026] Step S41: Screening the N target objects based on at least one of the historical data and the preset data to obtain K objects, where K is a positive integer greater than 1 and less than or equal to N;

[0027] Step S42: Generate a recommendation list based on the K objects.

[0028] In one embodiment, the method further comprises:

[0029] Step S7: Generate a display page based on the recommendation list, where two adjacent target objects in the display page are of different types.

[0030] In a second aspect, an embodiment of the present invention further provides an object recommendation device based on the computing power of an intelligent computing center, comprising:

[0031] A first acquisition module, used to acquire a plurality of objects to be displayed and a feature set corresponding to a target user, wherein the feature set is used to represent information related to the target user;

[0032] A screening module, used for screening the multiple objects based on the feature set to obtain N target objects, where N is a positive integer greater than 1;

[0033] A sorting module, used to sort the N target objects;

[0034] The first generating module is used to generate a recommendation list based on the sorted N target objects.

[0035] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the object recommendation method based on the computing power of an intelligent computing center as described in the first aspect above are implemented.

[0036] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the object recommendation method based on the computing power of an intelligent computing center as described in the first aspect above are implemented.

[0037] In a fifth aspect, an embodiment of the present invention further provides a computer program product, comprising computer instructions, which, when executed by a processor, implement the steps in the object recommendation method based on the computing power of an intelligent computing center as described in the first aspect above.

[0038] In an embodiment of the present invention, multiple objects to be displayed and a feature set corresponding to a target user are obtained, wherein the feature set is used to characterize information related to the target user; the multiple objects are screened based on the feature set to obtain N target objects, where N is a positive integer greater than 1; the N target objects are sorted; and a recommendation list is generated based on the sorted N target objects. In this way, multiple objects are screened by the feature set to obtain N target objects, thereby avoiding the situation where multiple objects are screened according to preset rules and there are still objects of interest to the target user among the unscreened objects, so that all the objects of interest to the target user are in the N target objects; then the N target objects are sorted and a recommendation list is generated, so that the objects of interest to the target user can be more accurately recommended to the target user, thereby improving the effect of recommending objects to the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0040] Figure 1 is a flow chart of an object recommendation method based on the computing power of an intelligent computing center provided by an embodiment of the present invention;

[0041] Figure 2 This is one of the flowcharts of the object recommendation provided by the embodiment of the present invention;

[0042] Figure 3 This is the second flowchart of the object recommendation provided by the embodiment of the present invention;

[0043] Figure 4 It is a structural diagram of an object recommendation device based on the computing power of an intelligent computing center provided by an embodiment of the present invention;

[0044] Figure 5 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] The "computing power" mentioned in the present invention is the ability of computer equipment or computing / data center to process information. It is the ability of computer hardware and software to work together to execute certain computing requirements. It is the computing power to achieve target result output by processing information data. It is a new type of productivity that integrates information computing power, network carrying capacity, and data storage capacity. It mainly provides services to the society through computing power infrastructure.

[0047] The "computing power" (Computational Power, CP) described in the present invention is the ability of a data center server to process data and output results. It is a comprehensive indicator to measure the computing power of a data center, including general computing power, super computing power and intelligent computing power. The commonly used unit of measurement is the number of floating point operations performed per second (FLOPS: Floating Point Operations Per Second, 1EFLOPS = 10^18FLOPS). The larger the value, the stronger the comprehensive computing power. According to calculations, 1EFLOPS is approximately the computing power output of 5 Tianhe-2A or 500,000 mainstream server CPUs or 2 million mainstream notebooks. The calculation formula is: CP = CP 通用 +CP 智能 +CP 超级 .

[0048] The "Network Power" (NP) described in the present invention is a manifestation of the data transmission capability of computing facilities, including comprehensive capabilities such as network architecture, network bandwidth, transmission latency, intelligent management and scheduling, etc. The carrying capacity involves network transmission within and between data centers, and is a comprehensive indicator for measuring network transmission scheduling capabilities. In the embodiment of the present invention, the carrying capacity uses the memory bandwidth.

[0049] The "Storage Power" (SP) described in the present invention is the comprehensive ability of a data center in terms of data storage capacity, performance, safety and reliability, and green and low-carbon. It is a comprehensive indicator for measuring the data storage capacity of a data center, including external storage devices such as storage arrays and server built-in storage devices. The commonly used unit of measurement for storage capacity is exabyte (EB, 1EB = 2^60bytes), and the commonly used unit of measurement for performance is the number of reads and writes per second per unit capacity (IOPS / TB, Input / Output Operations Per Second / TB). The disaster recovery ratio is an important manifestation of safety and reliability.

[0050] The "computing power infrastructure" described in the present invention is a new type of information infrastructure that integrates information computing power, network carrying capacity, and data storage capacity. It can realize centralized computing, storage, transmission and application of information, and presents characteristics such as diversity and ubiquity, intelligence and agility, safety and reliability, green and low-carbon. It is of great significance to promote industrial transformation and upgrading, enable my country's scientific and technological innovation, meet the needs of a better life and achieve high-efficiency social governance.

[0051] The “computing power” mentioned in the present invention includes general computing power, intelligent computing power and super computing power.

[0052] The “general computing power” mentioned in the present invention refers to the computing power provided by a server based on a central processing unit (CPU) chip, which is used to support basic general computing such as cloud computing and edge computing.

[0053] The "intelligent computing power" described in the present invention is a computing platform for large-scale deployment of special chips such as graphics processing units (GPUs), field programmable gate arrays (FPGAs), and application-specific integrated circuits (ASICs) for various innovative applications of artificial intelligence, such as natural language processing and machine vision.

[0054] The "super computing power" mentioned in the present invention is mainly the computing power provided by high-performance computing clusters such as supercomputers. It utilizes the centralized computing resources of multiple computer systems working in parallel and uses a dedicated operating system to handle extremely complex or data-intensive problems. It is mainly used for calculations in cutting-edge scientific fields, such as planetary simulation, drug molecule design, and gene analysis.

[0055] The "intelligent computing center" mentioned in the present invention refers to a facility that provides the required computing power, data and algorithms for artificial intelligence applications (such as artificial intelligence deep learning model development, model training and model reasoning) by using large-scale heterogeneous computing resources, including general computing power (CPU) and intelligent computing power (GPU, FPGA, etc.). The intelligent computing center covers facilities, hardware, and software, and can provide full-stack capabilities from bottom-level computing power to top-level application enablement.

[0056] The "computing resources" mentioned in the present invention refer to the technologies and facilities with information calculation, transmission, storage and application capabilities required for the development of the digital society, including but not limited to computing resources such as CPUs and GPUs, network resources such as switches and routers, storage resources such as storage arrays and distributed storage, security resources such as firewalls and intrusion detection systems, and supporting and guarantee resources such as wind, fire, water and electricity.

[0057] The "object" in the present invention refers to an object that needs to be displayed in the application interface, which can be a physical product, such as a water heater, a refrigerator, etc., or a virtual service product, such as stocks, fund services, etc. It can be understood that the object has been pre-configured with relevant attributes according to the content, and the relevant attributes include display cover and detailed content, etc., so that the object can be displayed directly through the relevant attributes of the object when it is screened and displayed.

[0058] The "feature set" mentioned in the present invention refers to a feature set used to screen objects. The features in the feature set can be set according to actual needs, such as filtering objects with high relevance to the user through features, or filtering currently popular objects through features, etc. The specific types are shown in subsequent embodiments.

[0059] The "recommendation list" mentioned in the present invention refers to a list including multiple objects to be recommended, in which the objects to be recommended are arranged in order. The objects at the front of the order are more likely to be of interest to the user, while the objects at the back of the order are less likely to be of interest to the user.

[0060] The "display page" mentioned in the present invention refers to an interface including one or more objects. The number of objects in the display interface is pre-configured, and the number of objects and the size of the display area of ​​the objects can be flexibly changed according to different scenarios. For example, the display area of ​​the object that the user may be most interested in is set to the maximum to improve the display effect.

[0061] See also Figure 1 , Figure 1 is a flow chart of an object recommendation method based on the computing power of an intelligent computing center provided by an embodiment of the present invention. Figure 1 As shown, the following steps are included:

[0062] Step S1: acquiring a plurality of objects to be displayed and a feature set corresponding to a target user, wherein the feature set is used to represent information related to the target user;

[0063] Step S2: screening the multiple objects based on the feature set to obtain N target objects, where N is a positive integer greater than 1;

[0064] Step S3, sorting the N target objects;

[0065] Step S4: Generate a recommendation list based on the sorted N target objects.

[0066] In an embodiment of the present invention, multiple objects to be displayed and a feature set corresponding to a target user are obtained, wherein the feature set is used to characterize information related to the target user; the multiple objects are screened based on the feature set to obtain N target objects, where N is a positive integer greater than 1; the N target objects are sorted; and a recommendation list is generated based on the sorted N target objects. In this way, multiple objects are screened by the feature set to obtain N target objects, thereby avoiding the situation where multiple objects are screened according to preset rules and there are still objects of interest to the target user among the unscreened objects, so that all the objects of interest to the target user are in the N target objects; then the N target objects are sorted and a recommendation list is generated, so that the objects of interest to the target user can be more accurately recommended to the target user, thereby improving the effect of recommending objects to the user.

[0067] It should be noted that if Figure 2 As shown, when it is necessary to recommend an object, multiple objects are obtained from the candidate product library, and the multiple objects may be part or all of the objects in the candidate product library. After obtaining multiple objects, the multiple objects are screened and sorted by the model according to the feature set, etc., to obtain N target objects. Furthermore, since the present invention is completed by the computing power of the intelligent computing center, when obtaining multiple objects, all objects are directly obtained from the candidate product library, and they are directly sorted and then screened, without the need to obtain only part of the objects according to preset rules when obtaining objects due to computing power limitations, thereby avoiding the problem in the prior art that there are still products that users are interested in that have not been recalled, thereby improving the object recommendation effect.

[0068] Furthermore, if Figure 3 As shown, the object recommendation method based on the computing power of the intelligent computing center of the present invention can be packaged in the model or service of the intelligent computing center, and multiple objects are obtained and N target objects are screened through the recall layer, and multiple objects are sorted through the sorting layer, and then N target objects are screened through the supplementary strategy (i.e., user data) to generate a display page for display.

[0069] Among them, the sorting model is used to fine-sort the coarsely screened candidate sets. The number of candidate sets that need to be processed is relatively small, and more features and more complex models can be used. The supplementary strategy is also called "re-sorting". In order to take into account the "diversity" and "real-time" indicators of the results, some strategies or algorithms are used to make certain sorting adjustments to the recommendation list before returning the display interface to the user to form the final recommendation list.

[0070] The feature set includes at least one of a user feature, an object feature, and a scene feature. The user feature is a feature of the user-related information. The object feature is used to describe the multiple objects. The scene feature is a feature of the interaction behavior between the object and the target user under different scene conditions.

[0071] In an embodiment of the present invention, the preset feature set includes at least one of user features, object features and scene features, so that different features can be set according to needs, and then when N objects are sorted based on the preset feature set, different sorting of N objects can be achieved according to needs.

[0072] In an optional implementation, user features can be set based on user-related data, such as user profiles, historical behaviors, or relationship networks. In an optional implementation, product features are constructed based on product data to be displayed, such as product features are constructed based on the definition of financial products. In an optional implementation, scene features can be constructed based on the scene in which the user is located, such as the user's browsing time, location, and current state (such as walking or home state).

[0073] In one embodiment, step S2 includes:

[0074] Step S21: when the feature set includes one of the user feature, the object feature and the scene feature, each object is evaluated based on the one feature to obtain a first probability corresponding to each object;

[0075] Step S22: Screen the multiple objects based on the corresponding first probabilities to obtain the N target objects.

[0076] The first probability is used to represent the probability that the target user is interested in the object. The greater the first probability is, the greater the probability that the target user is interested in the object is.

[0077] In the embodiment of the present invention, when the feature set includes one of the user feature, the object feature and the scene feature, each object is evaluated based on the one feature to obtain a first probability corresponding to each object; step S22, the multiple objects are screened based on the corresponding first probability to obtain the N target objects. In this way, the screening of N objects is achieved through a single feature.

[0078] Exemplarily, when the feature set includes a user feature, the first probability between each of the multiple objects and the target user is calculated using the user feature, and then the multiple objects are screened using the first probability to obtain N target objects whose first probabilities meet the requirements.

[0079] In one embodiment, step S2 includes:

[0080] Step S23: when the feature set includes at least two features among the user feature, the object feature and the scene feature, each object is evaluated based on each feature to obtain a second probability that each object corresponds to each feature;

[0081] Step S24, weighting all the second probabilities corresponding to the at least two features to obtain a third probability corresponding to each object;

[0082] Step S25: Screen the multiple objects based on the corresponding third probabilities to obtain the N target objects.

[0083] The second probability is the probability that the target user is interested in the object from a single feature, and the third probability is the probability that the target user is interested in the object from multiple features. The larger the third probability is, the greater the probability that the target user is interested in the object.

[0084] In the embodiment of the present invention, when the feature set includes at least two features among the user feature, the object feature and the scene feature, each object is evaluated based on each feature to obtain the second probability of each object corresponding to each feature; all the second probabilities corresponding to the at least two features are weighted to obtain the third probability corresponding to each object; the multiple objects are screened based on the corresponding third probabilities to obtain the N target objects. In this way, when the feature set includes at least two features, the third probability is obtained by weighting the second probabilities of different features, thereby implementing the screening of multiple objects from the dimensions of at least two features.

[0085] In one embodiment, before step S4, the method further includes:

[0086] Step S5: Obtain the policy corresponding to the target user, wherein the policy includes at least one of historical data and preset data, wherein:

[0087] The historical data includes historical object types related to the target user within a preset time period, and the types of the N target objects are different from the historical object types;

[0088] The preset data includes the registration information data of the target user, and at least one of the external platform data and label feature data, wherein the label feature data is used to characterize the type of object of interest selected by the target user;

[0089] The step S4 comprises:

[0090] Step S41: Screening the N target objects based on at least one of the historical data and the preset data to obtain K objects, where K is a positive integer greater than 1 and less than or equal to N;

[0091] Step S42: Generate a recommendation list based on the K objects.

[0092] It should be noted that when recommending objects to users, other types of objects may need to be recommended to users for reasons other than user considerations, such as recommending current mainstream products to users. In this case, the N target objects need to be adjusted through strategies so that the final generated recommendation list better meets the needs of the object provider.

[0093] In an embodiment of the present invention, the strategy includes at least one of historical data and preset data, wherein the historical data includes the historical object types related to the target user within a preset time period, and the types of the N target objects are different from the historical object types; the preset data includes the registration information data of the target user, and at least one of the external platform data and label feature data, and the label feature data is used to characterize the object type of interest selected by the target user. In this way, by screening the N target objects based on at least one of the historical data and the preset data, K objects are obtained, and a recommendation list is generated based on the K objects, thereby further improving the recommendation effect of the object.

[0094] Among them, historical data can be used to determine the objects that users have browsed or purchased within a preset time period, thereby reducing the appearance of objects of this type and effectively improving the recommendation effect.

[0095] In addition, the preset data includes the registration information data of the target user, and at least one of the external platform data and label feature data, and the label feature data is used to characterize the type of object of interest selected by the target user. It should be noted that when a user uses an application for the first time or the first few times, the user's historical data is relatively small, and it is necessary to assist in sorting and filtering based on other data to improve the display effect of the object. In an embodiment of the invention, the objects are filtered through the registration information data of the target user, and at least one of the external platform data and label feature data to improve the recommendation effect of the objects.

[0096] Among them, the registration information data of the target user may include demographic information, geographic location information, etc., such as the age and region of the target user; external platform data includes user-related attribute characteristics obtained through other platforms, such as interests, hobbies, income level and purchasing tendencies, etc.; label feature data is the characteristics of the object label of interest selected by the user according to the guidance of the application when registering, such as financial product type (structured deposits, wealth management, large-denomination certificates of deposit, etc.), interest rate, risk level, etc.

[0097] Furthermore, the user data may also include preset sensitive words to filter multiple objects, so as to filter out, for example, objects that are maliciously placed or objects that do not comply with relevant regulations.

[0098] In one embodiment, the method further comprises:

[0099] Step S7: Generate a display page based on the recommendation list, where two adjacent target objects in the display page are of different types.

[0100] In the embodiment of the present invention, a display page is generated through a recommendation list to display different target objects in the recommendation list. In the process of generating the display page, the types of two adjacent target objects in the display page are different to avoid user browsing fatigue and thus improve the display effect.

[0101] See also Figure 4 , Figure 4 is a structural diagram of an object recommendation device based on intelligent computing center computing power provided by an embodiment of the present invention, such as Figure 4 As shown, the object recommendation device 400 based on the computing power of the intelligent computing center includes:

[0102] A first acquisition module 401 is used to acquire a plurality of objects to be displayed and a feature set corresponding to a target user, wherein the feature set is used to represent information related to the target user;

[0103] A screening module 402 is used to screen the multiple objects based on the feature set to obtain N target objects, where N is a positive integer greater than 1;

[0104] A sorting module 403 is used to sort the N target objects;

[0105] The first generating module 404 is configured to generate a recommendation list based on the sorted N target objects.

[0106] In one embodiment, the feature set includes at least one of a user feature, an object feature, and a scene feature, wherein the user feature is a feature of the user-related information, the object feature is used to describe the multiple objects, and the scene feature is a feature of the interaction behavior between the object and the target user under different scene conditions.

[0107] In one embodiment, the screening module 402 includes:

[0108] A first evaluation unit is configured to evaluate each object based on one feature among the user feature, the object feature and the scene feature to obtain a first probability corresponding to each object when the feature set includes the one feature among the user feature, the object feature and the scene feature;

[0109] The first screening unit screens the multiple objects based on the corresponding first probabilities to obtain the N target objects.

[0110] In one embodiment, the screening module 402 includes:

[0111] a second evaluation unit, configured to evaluate each object based on each feature to obtain a second probability that each object corresponds to each feature when the feature set includes at least two of the user feature, the object feature and the scene feature;

[0112] A weighting unit, configured to weight all second probabilities corresponding to the at least two features to obtain a third probability corresponding to each object;

[0113] The second screening unit is used to screen the multiple objects based on the corresponding third probability to obtain the N target objects.

[0114] In one embodiment, before the first generating module 404, the apparatus further includes:

[0115] The second acquisition module is used to acquire the strategy corresponding to the target user, wherein the strategy includes at least one of historical data and preset data, wherein:

[0116] The historical data includes historical object types related to the target user within a preset time period, and the types of the N target objects are different from the historical object types;

[0117] The preset data includes the registration information data of the target user, and at least one of the external platform data and label feature data, wherein the label feature data is used to characterize the type of object of interest selected by the target user;

[0118] The first generating module 404 includes:

[0119] A third screening unit, configured to screen the N target objects based on at least one of the historical data and the preset data to obtain K objects, where K is a positive integer greater than 1 and less than or equal to N;

[0120] A generating unit is used to generate a recommendation list based on the K objects.

[0121] In one embodiment, the apparatus further comprises:

[0122] The second generating module is used to generate a display page based on the recommendation list, and the types of two adjacent target objects in the display page are different.

[0123] The object recommendation device based on the computing power of an intelligent computing center provided in an embodiment of the present invention is capable of implementing each process of each embodiment of the above-mentioned object recommendation method based on the computing power of an intelligent computing center. The technical features correspond one to one and can achieve the same technical effect. To avoid repetition, they will not be described here.

[0124] It should be noted that the object display device based on the computing power of the intelligent computing center in the embodiment of the present invention can be a device, or a component, integrated circuit, or chip in an electronic device.

[0125] The embodiment of the present invention further provides an electronic device, see Figure 5 , Figure 5 is a schematic diagram of the structure of an electronic device provided by the present invention, the electronic device includes a memory 501, a processor 502 and a program or instruction stored in the memory 501 and running on the memory 501. When the program or instruction is executed by the processor 502, Figure 1 Any steps in the corresponding embodiment of the object recommendation method based on the computing power of the intelligent computing center and the same beneficial effects are achieved will not be repeated here.

[0126] The processor 502 may be a CPU, an ASIC, an FPGA or a GPU.

[0127] A person skilled in the art can understand that all or part of the steps of implementing the above-mentioned object recommendation method embodiment based on the computing power of an intelligent computing center can be completed by hardware related to program instructions, and the program can be stored in a readable medium.

[0128] The embodiment of the present invention further provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above Figure 1 The corresponding steps in the object recommendation method embodiment based on the computing power of the intelligent computing center can achieve the same technical effect, and will not be repeated here to avoid repetition. The storage medium is such as a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0129] The embodiment of the present invention also provides a computer program product, including computer instructions, which can achieve the above-mentioned Figure 1 Any steps in the corresponding embodiment of the object recommendation method based on the computing power of the intelligent computing center can achieve the same technical effect. To avoid repetition, they will not be repeated here.

[0130] The terms "first", "second" etc. in the embodiments of the present invention are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. In addition, the terms "include" and "have" and any variation thereof are intended to cover non-exclusive inclusions, for example, the process, method, system, product or equipment comprising a series of steps or units need not be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment. In addition, "and / or" is used in the present application to represent at least one of the connected objects, such as A and / or B and / or C, indicating that A alone, B alone, C alone, and A and B all exist, B and C all exist, A and C all exist, and 7 situations in which A, B and C all exist.

[0131] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0132] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a second terminal device, etc.) to execute the methods of each embodiment of the present application.

[0133] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. An object recommendation method based on the computing power of an intelligent computing center, characterized in that: include: Step S1: acquiring a plurality of objects to be displayed and a feature set corresponding to a target user, wherein the feature set is used to represent information related to the target user; Step S2: screening the multiple objects based on the feature set to obtain N target objects, where N is a positive integer greater than 1; Step S3, sorting the N target objects; Step S4: Generate a recommendation list based on the sorted N target objects.

2. The method according to claim 1, characterized in that The feature set includes at least one of a user feature, an object feature, and a scene feature. The user feature is a feature of the user-related information. The object feature is used to describe the multiple objects. The scene feature is a feature of the interaction behavior between the object and the target user under different scene conditions.

3. The method according to claim 2, characterized in that The step S2 comprises: Step S21: when the feature set includes one of the user feature, the object feature and the scene feature, each object is evaluated based on the one feature to obtain a first probability corresponding to each object; Step S22: Screen the multiple objects based on the corresponding first probabilities to obtain the N target objects.

4. The method according to claim 2, characterized in that The step S2 comprises: Step S23: when the feature set includes at least two features among the user feature, the object feature and the scene feature, each object is evaluated based on each feature to obtain a second probability that each object corresponds to each feature; Step S24, weighting all the second probabilities corresponding to the at least two features to obtain a third probability corresponding to each object; Step S25: Screen the multiple objects based on the corresponding third probabilities to obtain the N target objects.

5. The method according to claim 1, characterized in that Before step S4, the method further includes: Step S5: Obtain the policy corresponding to the target user, wherein the policy includes at least one of historical data and preset data, wherein: The historical data includes historical object types related to the target user within a preset time period, and the types of the N target objects are different from the historical object types; The preset data includes the registration information data of the target user, and at least one of the external platform data and label feature data, wherein the label feature data is used to characterize the type of object of interest selected by the target user; The step S4 comprises: Step S41: Screening the N target objects based on at least one of the historical data and the preset data to obtain K objects, where K is a positive integer greater than 1 and less than or equal to N; Step S42: Generate a recommendation list based on the K objects.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Step S7: Generate a display page based on the recommendation list, where two adjacent target objects in the display page are of different types.

7. An object recommendation device based on the computing power of an intelligent computing center, characterized in that: include: A first acquisition module, used to acquire a plurality of objects to be displayed and a feature set corresponding to a target user, wherein the feature set is used to represent information related to the target user; A screening module, used for screening the multiple objects based on the feature set to obtain N target objects, where N is a positive integer greater than 1; A sorting module, used to sort the N target objects; The first generating module is used to generate a recommendation list based on the sorted N target objects.

8. An electronic device, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the steps of the object recommendation method based on the computing power of an intelligent computing center are implemented as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the object recommendation method based on the computing power of an intelligent computing center as described in any one of claims 1 to 6.

10. A computer program product, characterized in that It comprises computer instructions, which, when executed by a processor, implement the steps of the object recommendation method based on the computing power of an intelligent computing center as described in any one of claims 1 to 6.

Images