Method and device for recommending information

By using the time gap between user refresh requests in the information flow recommendation system, using the first predetermined time length to quickly retrieve the initial recommendation information and cache the second predetermined time more detailed information, the contradiction between the existing system computing resources and the user waiting time is solved. , achieving improvements in recommendation capabilities and improvements in user experience.

CN114880562BActive Publication Date: 2024-11-22BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210504668.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-05-10
Publication Date
2024-11-22
Estimated Expiration
2042-05-10

AI Technical Summary

Technical Problem

When the existing information flow recommendation system feedbacks recommendation results in real time, it faces the contradiction between computing resources and user waiting time, and it is difficult to provide efficient recommendation results in a short period of time.

Method used

By introducing a time gap between user refresh requests, quickly searching and returning initial recommendation information using the first predetermined time, retrieving and cacheing more detailed recommendation information using the second predetermined time longer, and directly returning cached results during subsequent refreshes. Improve calculation time and recommendation capabilities.

Benefits of technology

It significantly improves the calculation time and recommendation capabilities of the recommendation system, reduces the waiting time of users, and forms a major innovation in the existing recommendation system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114880562B_ABST
    Figure CN114880562B_ABST
Patent Text Reader

Abstract

The present disclosure provides a method and apparatus for recommending information, which relates to the field of artificial intelligence, and in particular to the field of intelligent search. The specific implementation scheme is: receiving a first refresh request from a client; taking a first predetermined time to retrieve first recommended information according to the first refresh request, and returning the first recommended information to the client; taking a second predetermined time to retrieve second recommended information according to the first refresh request, and caching the second recommended information, wherein the second predetermined time is greater than the first predetermined time; in response to receiving a second refresh request from the client, returning the second recommended information to the client. This implementation can improve the structure of the recommendation system, and while satisfying the real-time feedback to the user, it can also greatly enhance the recommendation capability of the recommendation system on the original basis, allowing users to have a better experience.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, and in particular to the field of intelligent search, and specifically to a method and device for recommending information. Background Art

[0002] In common information flow recommendation systems, users need to be given real-time feedback (within 1 second). Producing recommendation results in such a short time poses a great challenge to the recommendation system.

[0003] Common information flow recommendation systems, such as Figure 3a As shown in the figure, users usually refresh multiple times (the first refresh is called the first refresh, and so on). After each refresh, the recommendation system will go through the recall and sorting process, and give the user real-time feedback on the results of this refresh. For example, for the first refresh, assuming that it takes 50ms for the user to request the recommendation system, and it takes 500ms for the recommendation system to calculate the first refresh result, and it takes 50ms to feed back the result to the user, the total time consumption is 600ms, or 0.6 seconds, which is acceptable to users.

[0004] In the current recommendation system, if you want to optimize the recommendation ability of the recommendation system, you usually optimize the computing power and algorithm, and the computing power is determined by the number of machines and the computing time. Therefore, the number of machines, the algorithm, and the computing time are called the three elements of the recommendation system. The traditional method of optimizing the recommendation system is also to optimize around these three elements: (1) increase the number of machines, but this will increase a lot of costs; (2) optimize the recommendation algorithm. The entire industry is doing this optimization, but after decades of potential mining, the marginal effect is very significant, and it is becoming increasingly difficult to make a profit; (3) increase the computing time, but this will also increase the user's waiting time, and the user's physical examination will deteriorate. Summary of the invention

[0005] The present disclosure provides a method, apparatus, device, storage medium, and computer program product for recommending information.

[0006] According to a first aspect of the present disclosure, a method for recommending information is provided, comprising: receiving a first refresh request from a client; spending a first predetermined time to retrieve first recommended information according to the first refresh request, and returning the first recommended information to the client; spending a second predetermined time to retrieve second recommended information according to the first refresh request, and caching the second recommended information, wherein the second predetermined time is greater than the first predetermined time; in response to receiving the second refresh request from the client, returning the second recommended information to the client.

[0007] According to a second aspect of the present disclosure, a device for recommending information is provided, comprising: a receiving unit, configured to receive a first refresh request from a client; a first retrieval unit, configured to spend a first predetermined time to retrieve first recommended information according to the first refresh request, and return the first recommended information to the client; a second retrieval unit, configured to spend a second predetermined time to retrieve second recommended information according to the first refresh request, and cache the second recommended information, wherein the second predetermined time is greater than the first predetermined time; and a sending unit, configured to return the second recommended information to the client in response to receiving the second refresh request from the client.

[0008] According to a third aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the methods described in the first aspect.

[0009] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any one of the methods according to the first aspect.

[0010] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program implements any one of the methods according to the first aspect when executed by a processor.

[0011] The method and device for recommending information provided by the embodiments of the present disclosure utilize the interval between two user refreshes to greatly improve the calculation time and the recommendation capability. This is a dimensionality reduction attack on the existing recommendation system in terms of calculation time, which is a major innovation in the recommendation field.

[0012] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0014] Figure 1 is an exemplary system architecture diagram in which an embodiment of the present disclosure may be applied;

[0015] Figure 2 is a flow chart of an embodiment of a method for recommending information according to the present disclosure;

[0016] Figure 3a , 3b is a schematic diagram of an application scenario of the method for recommending information according to the present disclosure;

[0017] Figure 4 is a flow chart of another embodiment of a method for recommending information according to the present disclosure;

[0018] Figure 5 is a structural schematic diagram of an embodiment of a device for recommending information according to the present disclosure;

[0019] Figure 6 It is a structural diagram of a computer system of an electronic device suitable for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0020] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0021] Figure 1 An exemplary system architecture 100 is shown to which an embodiment of a method for recommending information or an apparatus for recommending information of the present disclosure can be applied.

[0022] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0023] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as live broadcast applications, video applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0024] Terminal devices 101, 102, 103 can be hardware or software. When terminal devices 101, 102, 103 are hardware, they can be various electronic devices with display screens and supporting multimedia browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Group Audio Layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Group Audio Layer 4) players, laptop computers and desktop computers, etc. When terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules (for example, to provide distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0025] The server 105 may be a server that provides various services, such as a background video server that supports the videos displayed on the terminal devices 101, 102, and 103. The background video server may analyze and process the received data such as the video playback request, and feed back the processing result (such as the recommended video) to the terminal device.

[0026] It should be noted that the server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (for example, multiple software or software modules used to provide distributed services), or it can be implemented as a single software or software module. No specific limitation is made here. The server can also be a server of a distributed system, or a server combined with a blockchain. The server can also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0027] It should be noted that the method for recommending information provided in the embodiments of the present disclosure is generally executed by the server 105 , and accordingly, the device for recommending information is generally disposed in the server 105 .

[0028] It should be noted that the method for recommending information provided in the embodiments of the present disclosure may be executed by the terminal devices 101, 102, 103, or by the server 105. Accordingly, the device for recommending information may be provided in the terminal devices 101, 102, 103, or in the server 105. No specific limitation is made here.

[0029] It should be understood that Figure 1The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0030] Continue to refer Figure 2 , shows a process 200 of an embodiment of a method for recommending information according to the present disclosure. The method for recommending information includes the following steps:

[0031] Step 201: receiving a first refresh request from a client.

[0032] In this embodiment, the execution subject of the method for recommending information (eg Figure 1 The server shown in the figure) can receive a first refresh request from a terminal used by a user to browse web pages, audio and video through a wired connection or a wireless connection. The first refresh request includes user information (for example, a user account or a cookie of the client). The server can query the user's behavior information based on the user information, such as videos played, videos liked, videos collected, videos forwarded, videos shared, etc. Information is recommended based on the behavior information. Each time the user refreshes, the recommended information is updated based on the user's behavior information before the refresh. For example, after the user clicks refresh on the video app of the client, the client will send the first refresh request including the user information to the server of the video app. The server finds the user's behavior information based on the user information, searches for candidate videos matching the user's behavior information from the first database according to the first recommendation algorithm, recalls them, and then sorts them according to the matching score, and sends a predetermined number of videos with the highest scores as recommendation information to the client.

[0033] Step 202: Retrieve first recommended information according to a first refresh request in a first predetermined time period, and return the first recommended information to the client.

[0034] In this embodiment, the first predetermined duration can be the duration used by traditional recommendation methods, which is no longer than 1 second, so that the user will not feel the waiting time. The first refresh request includes user information, and the user's historical behavior information is found based on the user information. Then, recommendations are made based on the historical behavior information. For example, if the user browses dance videos for hundreds of hours and makeup videos for hundreds of hours, the first recommendation information may include dance videos and makeup videos. Videos that the user may be interested in are retrieved from a small range of video libraries within the first predetermined duration and output to the client as the first recommendation information.

[0035] Step 203: Retrieve the second recommended information according to the first refresh request in a second predetermined time period, and cache the second recommended information.

[0036] In this embodiment, the second predetermined duration is greater than the first predetermined duration, for example, the second predetermined duration is 50 seconds. Videos that may be of interest to the user can be retrieved as the second recommendation information in a video library (second database) that is larger than the first database. For example, in the above example, the dancing and makeup videos in the video library can be further retrieved, and further screened according to the dance style and makeup style that the user has watched in the past, and folk dances and nude makeup videos can be selected. The works of dancers, anchors, etc. that the user has watched can also be further searched. At this time, the retrieved second recommendation information is not fed back to the user immediately, but is cached in the server and fed back to the user when the user refreshes next time. The same recommendation algorithm as step 202 can be used to retrieve the second information.

[0037] Optionally, a recommendation algorithm different from step 202 may be used to retrieve the second recommendation information. Since real-time feedback of the recommendation information is not required, a more complex recommendation algorithm may be used for recall and sorting, thereby increasing the recommendation hit rate and improving the user experience.

[0038] Step 204: in response to receiving the second refresh request from the client, return the second recommendation information to the client.

[0039] In this embodiment, when the user refreshes for the second time, it is not necessary to make recommendations based on the behavior information before the second refresh, but directly call the second recommendation information calculated based on the behavior information before the first refresh. The recommendation information obtained in this way is more accurate and more targeted. At this time, the behavior information before the second refresh is ignored.

[0040] The method provided by the above embodiment of the present disclosure provides a recommendation system that estimates the result of the user's next refresh. It takes a different approach to the recommendation system structure and cleverly uses the interval between two user refreshes to greatly improve the calculation time and recommendation capability. It forms a dimensionality reduction attack on the existing recommendation system in terms of calculation time, which is a major innovation in the recommendation field.

[0041] In some optional implementations of this embodiment, the method further includes: in response to receiving a second refresh request from the client, retrieving third recommendation information based on the second refresh request after spending a second predetermined time, and caching the third recommendation information. When the user refreshes again, the behavior information before the last refresh is used to calculate the recommendation information. It is still stored in the cache and fed back to the user at the next refresh. Except for the first refresh when the recommended information is calculated using the first predetermined time, the recommended information can be calculated using the second predetermined time subsequently. By increasing the calculation time, the recommendation capability is improved, and the user will not feel the extension of the calculation time.

[0042] In some optional implementations of this embodiment, the second predetermined duration is determined according to the average refresh time interval of the client. In order to avoid receiving a refresh request from the user before the recommended information is calculated, the average refresh time interval can be calculated according to the historical refresh time interval of the user. The average refresh time interval can be used directly as the second predetermined duration, and the average refresh time interval can also be multiplied by a coefficient less than 1 (for example, 0.8) as the second predetermined duration. Optionally, the second predetermined duration can also be determined based on the average refresh time interval of all users recorded by the server. Optionally, the second predetermined duration can be determined based on the average duration or minimum duration of the recommended information. For example, if the length of the recommended videos does not exceed 30 seconds, the second predetermined duration must be less than 30 seconds. It can avoid receiving a refresh request from the user before the recommended information is calculated.

[0043] Optionally, a recommendation algorithm or a search range may be selected based on the second predetermined duration, and the longer the second predetermined duration is, the more complex the algorithm is selected, and the larger the search range is selected. For example, when the second predetermined duration is 50 seconds, a more complex recommendation algorithm and a larger search range may be selected than when the second predetermined duration is 30 seconds. When the second predetermined duration is 50 seconds, recommended videos matching user behavior information may be retrieved from 10,000 candidate videos, while when the second predetermined duration is 30 seconds, recommended videos matching user behavior information may be retrieved from 5,000 candidate videos. When the second predetermined duration is 50 seconds, videos with similar video frame image features to videos previously viewed by the user may be searched, while when the second predetermined duration is 50 seconds, videos with similar subtitle text features to videos previously viewed by the user may be searched.

[0044] Complex recommendation algorithms can compare multiple features, such as image features, text features, bloggers, protagonists, etc. Simple algorithms compare fewer features and usually select features with low computational complexity, such as bloggers, protagonists, etc. Complex recommendation algorithms need to extract image features and text features from each frame, and then calculate the similarity of image features and text features between the videos that the user has browsed and the videos in the database, which is very time-consuming. Simple recommendation algorithms only need to calculate the similarity between the names of the videos that the user has browsed and the names of the videos in the database, which is very fast, but not as accurate as complex algorithms.

[0045] Continue to see Figure 3b , Figure 3b FIG. 1 is a schematic diagram of an application scenario of the method for recommending information according to this embodiment. Figure 3bIn the application scenario, when the user refreshes for the first time, the server will output the first and second refresh results. The first refresh result is returned to the user within 0.6 seconds (50ms+500ms+50ms), and the second refresh result will be calculated for 50 seconds, plus the network transmission time, the overall time is 50.1 seconds (50ms+50s+50ms), and then stored in the cache. When the user refreshes for the second time, the second refresh result is read from the cache and returned to the user. In other words, the recommendation system calculates the second refresh result in 50 seconds, and the user can also get the second refresh result in real time. The calculation time of the recommendation system has been increased from 500 milliseconds to 50 seconds, an increase of 2 orders of magnitude.

[0046] When the user performs the second refresh, the recommendation system starts calculating the third refresh result, and so on. Except for the first refresh, the subsequent refreshes can get a longer calculation time, which greatly increases the recommendation ability.

[0047] 50 seconds is just an example, and the actual value needs to be set according to the interval between two refreshes of the user. But what is certain is that this value must be an order of magnitude higher than the calculation time of the existing recommendation system.

[0048] Further references Figure 4 , which shows a process 400 of another embodiment of a method for recommending information. The process 400 of the method for recommending information includes the following steps:

[0049] Step 401: Receive a first refresh request from a client.

[0050] In this embodiment, the execution subject of the method for recommending information (eg Figure 1 The server shown in the figure can receive the first refresh request from the terminal used by the user to browse the web page, audio and video through a wired connection or a wireless connection. The server can obtain the user's behavior information based on the user information (for example, the user account or the client's cookie). Recommend information based on the behavior information. Each time the user refreshes, the recommended information is updated based on the user's behavior information before the refresh.

[0051] Step 402: Retrieve first recommended information according to a first refresh request in a first predetermined time period, and return the first recommended information to the client.

[0052] In this embodiment, the first predetermined duration may be the duration used by traditional recommendation methods, which does not exceed 1 second. The first refresh request includes user information, and the user's historical behavior information is found based on the user information. Then, the first recommendation algorithm is used to make recommendations based on the historical behavior information. For example, if the user browses dance videos for hundreds of hours and makeup videos for hundreds of hours, the first recommendation information may include dance videos and makeup videos. Videos that the user may be interested in are retrieved from a small range of video libraries within the first predetermined duration and output to the client as the first recommendation information.

[0053] Step 403: Retrieve second recommended information according to the first refresh request in a second predetermined time period.

[0054] In this embodiment, the second predetermined duration is greater than the first predetermined duration, for example, the second predetermined duration is 50 seconds. Videos that the user may be interested in can be retrieved from a wide range of video libraries as the second recommendation information. For example, in the above example, dancing and makeup videos in the video library can be further retrieved, and further screened according to the dance style and makeup style that the user has watched in the past, and folk dance and nude makeup videos can be selected. The works of dancers, anchors, etc. that the user has watched can also be further searched.

[0055] The second recommendation algorithm (more time-consuming and complex than the first recommendation algorithm) can be used to search according to the first request, and intermediate results are continuously obtained during the search process, and the intermediate results are continuously screened and optimized. For example, 10,000 candidate recommendation information are continuously screened and filtered, and finally 10 are retained as the final recommendation information. The intermediate results may be 5,000, 500, 50, etc.

[0056] The intermediate results of the retrieval are stored in the memory, and when the second predetermined time is reached, the final second recommendation information is obtained and stored in the cache.

[0057] Step 404: in response to receiving a second refresh request from the client and the time interval between the second refresh request and the first refresh request being less than a second predetermined time period, retrieving fourth recommendation information according to the second refresh request within a first predetermined time period.

[0058] In this embodiment, since the second predetermined time is relatively long, the second refresh request may be received before the second recommended information is calculated and released, and the calculation of the second recommended information will be stopped and the intermediate results in the memory will be cleared. At this time, the recommended information can be recalculated according to the recommendation algorithm of the first recommended information and the user behavior information before the second refresh request. Between the first refresh request and the second refresh request, the user may browse, like, collect or share videos. These behaviors can be used to calculate the scores of the candidate recommended information. Therefore, after the second refresh, the updated second recommended information is different from the first recommended information.

[0059] Optionally, the intermediate result of step 403 may be stored in a cache, the intermediate result in the memory may be cleared, and the fourth recommended information may be screened out from the intermediate result according to the first recommendation algorithm, so as to narrow the search scope and improve the accuracy.

[0060] Step 405: Return the fourth recommendation information to the client.

[0061] In this embodiment, since the recommendation calculated by the second recommendation algorithm is interrupted before a final result is obtained, the fourth recommendation information calculated by the first recommendation algorithm is returned to the client.

[0062] Optionally, the intermediate result calculated according to the second recommendation algorithm in step 403 may be combined with the intermediate result calculated in the first recommendation algorithm to increase the score of the common recommendation information so that the common recommendation information is ranked in front and is more likely to be used as the fourth recommendation information.

[0063] from Figure 4 It can be seen that Figure 2 Compared with the corresponding embodiment, the process 400 of the method for recommending information in this embodiment embodies the steps for handling emergencies. Therefore, the solution described in this embodiment can automatically switch to the traditional recommendation algorithm without letting the user feel the delay. Some intermediate results can also be used to optimize the recommended information. Thereby improving the hit rate of the recommendation.

[0064] Further references Figure 5 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a device for recommending information. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0065] like Figure 5 As shown, the device 500 for recommending information in this embodiment includes: a receiving unit 501, a first retrieval unit 502, a second retrieval unit 503 and a sending unit 504. The receiving unit 501 is configured to receive a first refresh request from a client; the first retrieval unit 502 is configured to spend a first predetermined time to retrieve the first recommended information according to the first refresh request, and return the first recommended information to the client; the second retrieval unit 503 is configured to spend a second predetermined time to retrieve the second recommended information according to the first refresh request, and cache the second recommended information, wherein the second predetermined time is greater than the first predetermined time; the sending unit 504 is configured to return the second recommended information to the client in response to receiving the second refresh request from the client.

[0066] In this embodiment, the specific processing of the receiving unit 501, the first retrieval unit 502, the second retrieval unit 503 and the sending unit 504 of the device for recommending information 500 can refer to Figure 2 Corresponding to step 201, step 202, step 203, and step 204 in the embodiment.

[0067] In some optional implementations of this embodiment, the second retrieval unit 503 is further configured to: in response to receiving a second refresh request from the client, spend a second predetermined time to retrieve third recommendation information according to the second refresh request, and cache the third recommendation information.

[0068] In some optional implementations of this embodiment, the first retrieval unit 502 is further configured to: if the time interval between the second refresh request and the first refresh request is less than the second predetermined time length, then take the first predetermined time length to retrieve the fourth recommendation information according to the second refresh request, and return the fourth recommendation information to the client.

[0069] In some optional implementations of this embodiment, the second predetermined duration is determined according to an average refresh time interval of the client.

[0070] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0071] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0072] An electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in process 200 or 400.

[0073] A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the method described in process 200 or 400.

[0074] A computer program product includes a computer program, wherein the computer program implements the method described in flow 200 or 400 when executed by a processor.

[0075] Figure 6A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0076] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0077] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0078] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as a method for recommending information. For example, in some embodiments, the method for recommending information may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the method for recommending information described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform a method for recommending information in any other appropriate manner (e.g., by means of firmware).

[0079] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0080] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0081] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0082] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0083] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0084] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0085] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0086] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for recommending information, comprising: receiving a first refresh request from a client; Retrieving first recommendation information according to the first refresh request in a first database using a first recommendation algorithm and consuming a first predetermined time, and returning the first recommendation information to the client; Retrieving second recommendation information according to the first refresh request in a second database for a second predetermined time according to a second recommendation algorithm, and caching the second recommendation information, wherein the second predetermined time is greater than the first predetermined time, and the longer the second predetermined time is, the more complex the second recommendation algorithm is selected, and the second database with a larger search range is selected; In response to receiving a second refresh request from the client, the second recommendation information is returned to the client.

2. The method according to claim 1, wherein: The method further comprises: In response to receiving a second refresh request from the client, a second predetermined time period is spent to retrieve third recommendation information according to the second refresh request, and the third recommendation information is cached.

3. The method according to claim 1, wherein: The method further comprises: If the time interval between the second refresh request and the first refresh request is less than the second predetermined time period, the first predetermined time period is consumed to retrieve the fourth recommendation information according to the second refresh request, and the fourth recommendation information is returned to the client.

4. The method according to claim 1, wherein: The second predetermined duration is determined according to an average refresh time interval of the client.

5. A device for recommending information, comprising: A receiving unit, configured to receive a first refresh request from a client; A first retrieval unit is configured to retrieve first recommendation information according to the first refresh request in a first database based on a first recommendation algorithm and spending a first predetermined time, and return the first recommendation information to the client; A second retrieval unit is configured to retrieve second recommendation information according to the first refresh request in a second database using a second recommendation algorithm and consuming a second predetermined time, and cache the second recommendation information, wherein the second predetermined time is greater than the first predetermined time, and the longer the second predetermined time is, the more complex the second recommendation algorithm is selected, and the second database with a larger search range is selected; The sending unit is configured to return the second recommendation information to the client in response to receiving a second refresh request from the client.

6. The device according to claim 5, wherein: The second retrieval unit is further configured to: In response to receiving a second refresh request from the client, a second predetermined time period is spent to retrieve third recommendation information according to the second refresh request, and the third recommendation information is cached.

7. The device according to claim 5, wherein: The first retrieval unit is further configured to: If the time interval between the second refresh request and the first refresh request is less than the second predetermined time period, the first predetermined time period is consumed to retrieve the fourth recommendation information according to the second refresh request, and the fourth recommendation information is returned to the client.

8. The device according to claim 5, wherein: The second predetermined duration is determined according to an average refresh time interval of the client.

9. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 4.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-4.

11. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 4.