Recommendation method, device, electronic device and storage medium

Abstract

The present disclosure provides a recommendation method, device, electronic device, storage medium and program product, which relate to the field of data processing technology, and in particular to the field of intelligent search and deep learning technology. The specific implementation scheme is: in response to a request from a target user, determine the recommendation value of each of multiple objects; determine at least one initial first target object and at least one second target object among the multiple objects; based on the recommendation value of each of the at least one initial first target object and the recommendation threshold of each of the at least one initial first target object, determine at least one first target object from at least one initial first target object; and based on the recommendation value of each of the at least one first target object and the recommendation value of each of the at least one second target object, determine the target recommendation object from at least one first target object and at least one second target object, so as to recommend the target recommendation object to the target user.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, in particular to the field of intelligent search and deep learning technology, and specifically to a recommendation method, device, electronic device, storage medium and program product. Background Art

[0002] With the rapid development of information technology and network technology, the expansion and redundancy of information flow resources have brought confusion to people's social activities and entertainment activities. It is extremely challenging to find the required information flow resources from the vast information flow resources. The personalized recommendation service of the Internet can provide different personalized recommendation service strategies for different users. Automated information flow resource recommendations are made based on different characteristics and requirements of users. However, in the recommendation process, the satisfaction of the recommendation results and the recommendation requirements in meeting the personalized needs of users needs to be improved. Summary of the invention

[0003] The present disclosure provides a recommendation method, device, electronic device, storage medium and program product.

[0004] According to one aspect of the present disclosure, a recommendation method is provided, comprising: determining, in response to a request from a target user, a recommendation value of each of a plurality of objects, wherein the recommendation value of each of the plurality of objects is used to characterize the target user's interest level in each of the plurality of objects at the current moment; determining at least one initial first target object and at least one second target object among the plurality of objects; determining at least one first target object from the at least one initial first target object based on the recommendation value of each of the at least one initial first target object and the recommendation threshold of each of the at least one initial first target object; and determining a target recommendation object from the at least one first target object and the at least one second target object based on the recommendation value of each of the at least one first target object and the recommendation value of each of the at least one second target object, so as to recommend the target recommendation object to the target user.

[0005] According to another aspect of the present disclosure, a recommendation device is provided, comprising: a response module, for determining a recommendation value of each of a plurality of objects in response to a request from a target user, wherein the recommendation value of each of the plurality of objects is used to characterize the degree of interest of the target user in each of the plurality of objects at the current moment; a classification module, for determining at least one initial first target object and at least one second target object among the plurality of objects; a screening module, for determining at least one first target object from the at least one initial first target object based on the recommendation value of each of the at least one initial first target object and the recommendation threshold of each of the at least one initial first target object; and an object determination module, for determining a target recommendation object from the at least one first target object and the at least one second target object based on the recommendation value of each of the at least one first target object and the recommendation value of each of the at least one second target object, so as to recommend the target recommendation object to the target user.

[0006] According to another 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 a method as disclosed in the present disclosure.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method of the present disclosure.

[0008] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the method of the present disclosure when executed by a processor.

[0009] 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

[0010] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0011] Figure 1 An exemplary system architecture to which the recommended method and apparatus according to an embodiment of the present disclosure can be applied is schematically shown;

[0012] Figure 2 A flowchart of a recommendation method according to an embodiment of the present disclosure is schematically shown;

[0013] Figure 3A schematic diagram schematically shows a method for determining a recommendation threshold according to an embodiment of the present disclosure;

[0014] Figure 4 The flowchart of the recommendation method according to another embodiment of the present disclosure is schematically shown;

[0015] Figure 5 A block diagram schematically shows a recommendation device according to an embodiment of the present disclosure; and

[0016] Figure 6 A block diagram of an electronic device suitable for implementing a recommendation method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0017] 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.

[0018] The present disclosure provides a recommendation method, device, electronic device, storage medium and program product.

[0019] According to an embodiment of the present disclosure, a recommendation method is provided, comprising: determining, in response to a request from a target user, a recommendation value of each of a plurality of objects, wherein the recommendation value of each of the plurality of objects is used to characterize the target user's interest level in each of the plurality of objects at the current moment; determining at least one initial first target object and at least one second target object among the plurality of objects; determining at least one first target object from at least one initial first target object based on the recommendation value of each of the at least one initial first target object and the recommendation threshold of each of the at least one initial first target object; and determining a target recommendation object from at least one first target object and at least one second target object based on the recommendation value of each of the at least one first target object and the recommendation value of each of the at least one second target object, so as to recommend the target recommendation object to the target user.

[0020] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information involved comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.

[0021] In the technical solution of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0022] Figure 1An exemplary system architecture to which the recommendation method and apparatus according to an embodiment of the present disclosure can be applied is schematically shown.

[0023] It should be noted that Figure 1 The examples shown are only examples of system architectures to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios. For example, in another embodiment, the exemplary system architecture to which the recommendation method and apparatus can be applied may include a terminal device, but the terminal device may implement the recommendation method and apparatus provided by the embodiments of the present disclosure without interacting with the server.

[0024] like Figure 1 As shown, the system architecture 100 according to this embodiment 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 and / or wireless communication links, etc.

[0025] 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 knowledge reading applications, web browser applications, search applications, instant messaging tools, email clients and / or social platform software, etc. (only as examples).

[0026] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0027] The server 105 may be a server that provides various services, such as a background management server (only an example) that provides support for the content browsed by the user using the terminal devices 101, 102, and 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0028] It should be noted that the recommendation method provided in the embodiment of the present disclosure can generally be executed by the terminal device 101, 102, or 103. Accordingly, the recommendation device provided in the embodiment of the present disclosure can also be set in the terminal device 101, 102, or 103.

[0029] Alternatively, the recommendation method provided in the embodiment of the present disclosure may also be generally performed by the server 105. Accordingly, the recommendation device provided in the embodiment of the present disclosure may generally be arranged in the server 105. The recommendation method provided in the embodiment of the present disclosure may also be performed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the recommendation device provided in the embodiment of the present disclosure may also be arranged in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0030] For example, when a target user browses a web page online, the terminal devices 101, 102, and 103 can send the target user's request to the server 105, and the server 105 determines the recommendation value of each of the multiple objects; determines at least one initial first target object and at least one second target object among the multiple objects; determines at least one first target object from the at least one initial first target object based on the recommendation value of each of the at least one initial first target object and the recommendation threshold of each of the at least one initial first target object; determines a target recommended object from the at least one first target object and at least one second target object based on the recommendation value of each of the at least one first target object and the recommendation value of each of the at least one second target object, so as to recommend the target recommended object to the target user. Alternatively, a server or server cluster capable of communicating with the terminal devices 101, 102, 103 and / or the server 105 analyzes the multiple objects, and finally determines the target recommended object from the multiple objects, and recommends the target recommended object to the target user.

[0031] It should be understood that Figure 1 The 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.

[0032] It should be noted that the sequence numbers of the operations in the following method are only used as representations of the operations for the purpose of description, and should not be regarded as representing the execution order of the operations. Unless explicitly stated, the method does not need to be executed completely in the order shown.

[0033] Figure 2 The flowchart of the recommendation method according to the embodiment of the present disclosure is schematically shown.

[0034] like Figure 2 As shown, the method includes operations S210 to S240.

[0035] In operation S210 , in response to a request from a target user, a recommendation value of each of the plurality of objects is determined, wherein the recommendation value of each of the plurality of objects is used to represent the interest level of the target user in each of the plurality of objects at the current moment.

[0036] In operation S220, at least one initial first target object and at least one second target object among a plurality of objects are determined.

[0037] In operation S230, at least one first target object is determined from the at least one initial first target object based on the recommendation value of each of the at least one initial first target objects and the recommendation threshold of each of the at least one initial first target object.

[0038] In operation S240, a target recommendation object is determined from the at least one first target object and the at least one second target object based on the recommendation value of each of the at least one first target object and the recommendation value of each of the at least one second target object, so as to recommend the target recommendation object to the target user.

[0039] According to an embodiment of the present disclosure, the target user's request may include a target user's request for browsing. For example, the target user's operation of clicking to enter a certain webpage or a certain application may be used as the target user's request. However, it is not limited to this. The target user's request may also include a request for retrieval. For example, after the target user enters a certain webpage or a certain application, the target user may use the input interface of the webpage or the application to input information for retrieval in order to perform further browsing. The target user's operation for retrieval may be used as the target user's request.

[0040] According to an embodiment of the present disclosure, an object may refer to an information stream resource. For example, a short video, live video, picture or text on a network platform. However, it is not limited thereto. It may also refer to other video or audio content, such as a movie, TV series, variety show, news or audio. It may also refer to a recommendation introduction of an item on other platforms, a web link, etc.

[0041] According to an embodiment of the present disclosure, a target recommended object can be determined from multiple objects in response to a request from a target user, so as to recommend the target recommended object to the target user. For example, a target recommended short video can be determined from multiple short videos, and the target recommended short video can be recommended to the target user.

[0042] According to an embodiment of the present disclosure, multiple objects may include at least one initial first object and at least one second object. The initial first target object may include an object with a traffic distribution requirement, i.e., a recommendation requirement. An object with a traffic distribution requirement may refer to an object that needs to be recommended a predetermined number of times within a predetermined recommendation duration. However, it is not limited to this. The initial first target object may also be an object with other recommendation requirements. An object with other recommendation requirements may refer to an object that meets the personalized requirements of the target user. The personalized requirements may include, for example, requirements such as release time and popularity. At least one second target object is an object among the multiple objects other than the at least one initial first target object.

[0043] According to an embodiment of the present disclosure, the recommendation values ​​of the multiple objects can be used to characterize the interest of the target user in the multiple objects at the current moment. The target recommendation object can be determined from the multiple objects based on the recommendation values ​​of the multiple objects. For example, the recommendation values ​​of the multiple objects are sorted in descending order, and the objects with the top 20 recommendation values ​​are recommended to the target user as the target recommendation objects.

[0044] According to another embodiment of the present disclosure, at least one initial first target object can also be determined from multiple objects according to, for example, traffic distribution requirements. A weight related to traffic distribution is configured for each recommendation value of the at least one initial first target object as a new recommendation value. For example, each recommendation value of the at least one initial first target object is multiplied by a fixed weight to serve as a new recommendation value of the at least one initial first target object. The recommendation values ​​of the at least one second target object and the new recommendation values ​​of the at least one initial first target object are sorted in order from high to low, and the objects with the top 20 recommendation values ​​are recommended to the target user as target recommendation objects.

[0045] According to another embodiment of the present disclosure, at least one initial first target object may be determined from a plurality of objects according to, for example, traffic distribution requirements. And a recommendation threshold is configured for each of the at least one initial first target objects. Based on the respective recommendation value of the at least one initial first target object and the respective recommendation threshold of the at least one initial first target object, at least one first target object is determined from the at least one initial first target object. Based on the respective recommendation value of the at least one first target object and the respective recommendation value of the at least one second target object, a target recommendation object is determined from the at least one first target object and the at least one second target object.

[0046] For example, for each of the at least one initial first target object, the recommendation value of the initial first target object is compared with the recommendation threshold of the initial first target object. When the recommendation value of the initial first target object is greater than or equal to the recommendation threshold of the initial first target object, the initial first target object is used as the first target object. Then at least one first target object is obtained. When the recommendation value of the initial first target object is less than the recommendation threshold of the initial first target object, the initial first target object is abandoned for subsequent operations. Based on the recommendation value of each of the at least one first target object and the recommendation value of each of the at least one second target object, a target recommendation object is determined from the at least one first target object and the at least one second target object.

[0047] By using the recommendation method provided by the embodiment of the present disclosure, a target recommended object is determined from at least one first target object and at least one second target object based on the recommendation value of each of at least one first target object and the recommendation value of each of at least one second target object. Among them, the recommendation value can reflect the target user's interest in the object, and determining the target recommended object recommended to the target user based on the recommendation value can better meet the user experience. In addition, multiple objects are classified and processed, at least one initial first target object is determined from the multiple objects, and at least one first target object is determined from at least one initial first target object using the recommendation threshold of each of at least one initial first target object and the recommendation value of each of at least one initial first target object. The recommendation threshold can be used to screen the initial first target objects. Through this screening operation, for example, the recommendation speed of the initial first target object can be reasonably controlled to avoid the problem of poor recommendation effect due to excessively high recommendation frequency.

[0048] Figure 3 A schematic diagram of determining a recommendation threshold according to another embodiment of the present disclosure is schematically shown.

[0049] like Figure 3 As shown, determining the recommendation threshold may include operations S310 to S340.

[0050] In operation S310 , for each of at least one initial first target object, attention values ​​of a plurality of users for the initial first target object in a predetermined time period are determined.

[0051] According to an embodiment of the present disclosure, the attention values ​​of multiple users for the initial first target object within a predetermined time period can be determined based on the attention value log. For multiple initial first target objects, there can be multiple attention value logs corresponding to the multiple initial first target objects, but it is not limited to this, and one attention value log can also record the attention value data of multiple initial first target objects. In addition to recording the attention value data of multiple users for the initial first target object, the attention value log also records the time of the predetermined time period, and other information related to the initial first target object, users, etc. I will not go into details here.

[0052] According to an embodiment of the present disclosure, the attention values ​​of multiple users can be used to characterize the interest of each of the multiple users in the initial first target object within a predetermined time period. The predetermined time period can refer to the current time period, the future time period, or the historical time period. The future time period can refer to the next time period of the current time period, but is not limited to this, and can also be any future time period of the current time period. The historical time period can be the previous historical time period of the current time period, but is not limited to this, and can also be any historical time period of the current time period.

[0053] According to an embodiment of the present disclosure, the attention values ​​of multiple users can be determined based on the point spread ratio of the multiple users to the initial first target object. The point spread ratio may refer to the ratio of the number of times the initial first target object is clicked to the number of times the initial first target object is recommended. However, it is not limited to this. The attention values ​​of multiple users can also be data related to whether the user collects the object, follows the object, or likes the object. As long as the attention value can represent the user's interest in the initial first target object.

[0054] In operation S320, a first initial recommendation threshold of the initial first target object may be determined based on the attention values ​​of the multiple users to the initial first target object within the predetermined time period and the number of times the initial first target object is to be recommended within the predetermined time period.

[0055] According to an embodiment of the present disclosure, the number of times M of the initial first target object to be recommended within a predetermined time period may include formula (1).

[0056] M = remaining number of recommendations / remaining recommendation duration × duration of scheduled time period; (1)

[0057] According to an embodiment of the present disclosure, the remaining number of recommendation times may include a difference between a predetermined number of recommendation times and a number of recommended times.

[0058] In operation S330 , a second initial recommendation threshold of the initial first target object is determined based on the attention values ​​of each of the plurality of users to the initial first target object within a predetermined time period and a predetermined attention threshold.

[0059] In operation S340 , a recommendation threshold is determined based on the first initial recommendation threshold and the second initial recommendation threshold.

[0060] It should be noted that the serial numbers of operation S320 and operation S330 are only used as representations of the operations for the convenience of description, and should not be regarded as representing the execution order of the operations.

[0061] According to an embodiment of the present disclosure, the first initial recommendation threshold is determined based on the number of recommendations to be made within a predetermined time period. The recommendation threshold can be used to control the number of recommendations for the initial first target object, thereby achieving global control.

[0062] According to an embodiment of the present disclosure, for operation S320, determining a first initial recommendation threshold of the initial first target object based on the attention values ​​of multiple users to the initial first target object within a predetermined time period and the number of times the initial first target object is to be recommended within the predetermined time period may include the following operations.

[0063] For example, the attention values ​​of the multiple users to the initial first target object within a predetermined time period are sorted to obtain a sorting result. Based on the number of times the initial first target object is to be recommended within the predetermined time period, the target attention value is determined from the sorting result. The target attention value is determined as the first initial recommendation threshold of the initial first target object.

[0064] According to an embodiment of the present disclosure, the attention values ​​may be sorted in descending order to obtain a sorting result, but it is not limited thereto, and the attention values ​​may also be sorted in descending order to obtain a sorting result. As long as the first initial recommendation threshold can be determined based on the sorting result and the number of times to be recommended, it will be sufficient.

[0065] For example, the plurality of users may include, for example, 5 users: user A, user B, user C, user D, and user E. For the initial first target object NID_1 in at least one initial first target object, the attention values ​​of the 5 users regarding the initial first target object NID_1 in a predetermined time period may be determined. For example, user A_NID_1_attention value, user B_NID_1_attention value, user C_NID_1_attention value, user D_NID_1_attention value, and user E_NID_1_attention value. These 5 attention values ​​are sorted in descending order to obtain a sorting result, such as user A_NID_1_attention value, user E_NID_1_attention value, user D_NID_1_attention value, user B_NID_1_attention value, and user C_NID_1_attention value.

[0066] For example, the remaining number of recommendations is determined based on the predetermined number of recommendations and the number of recommendations. The number of times to be recommended within the predetermined time period is determined based on the remaining number of recommendations, the remaining recommendation duration, and the duration of the predetermined time period, for example, the number of times to be recommended is 2. Based on the sorting result and the number of times to be recommended, the second largest attention value among the 5 attention values ​​can be used as the target attention value, for example, the user E_NID_1_attention value can be used as the target attention value, that is, the first initial recommendation threshold. However, it is not limited to this. For example, the number of times to be recommended is 8, and the sorting result includes the attention values ​​of 5 users for the initial first target object. The number of times to be recommended is greater than the number of users. In this case, based on the sorting result, the smallest attention value among the 5 attention values ​​can be used as the target attention value, for example, the user C_NID_1_attention value can be used as the target attention value, that is, the first initial recommendation threshold.

[0067] According to one embodiment of the present disclosure, the first initial recommendation threshold is determined based on the number of times to be recommended and the attention values ​​of multiple users to the initial first target object within a predetermined time period. Using the first initial recommendation threshold as the recommendation threshold or determining the recommendation threshold based on the first initial recommendation threshold can control the recommendation frequency of the initial first target object and avoid the problem of recommendation failure caused by too many recommendations in a short time period.

[0068] According to an embodiment of the present disclosure, for operation S330, determining a second initial recommendation threshold of the initial first target object based on the attention values ​​of multiple users to the initial first target object within a predetermined time period and a predetermined attention threshold may include the following operations.

[0069] For example, the attention values ​​of multiple users to the initial first target object within a predetermined time period are sorted, for example, in a descending order to obtain a sorting result. Based on the sorting result, when the average attention value of the first K users is greater than or equal to the predetermined attention threshold, and the average attention value of the first K+1 users is less than the predetermined attention threshold, the attention value of the K-th user to the initial first target object within the predetermined time period is determined as the second initial recommendation threshold of the initial first target object. However, it is not limited to this. The attention values ​​of multiple users to the initial first target object within a predetermined time period can also be sorted, for example, in a descending order to obtain a sorting result. Based on the sorting result, when the average attention value of the first J+1 users is greater than or equal to the predetermined attention threshold, and the average attention value of the first J users is less than the predetermined attention threshold, the attention value of the J-th user to the initial first target object within the predetermined time period is determined as the second initial recommendation threshold of the initial first target object.

[0070] For example, the five attention values ​​are sorted in descending order to obtain a sorting result, such as user A_NID_1_attention value, user E_NID_1_attention value, user D_NID_1_attention value, user B_NID_1_attention value, and user C_NID_1_attention value. After calculation, if the average value of the first three attention values ​​is greater than the predetermined attention threshold, and the average value of the first four attention values ​​is less than the predetermined attention threshold, the user D_NID_1_attention value can be used as the second initial recommendation threshold of the initial first target object.

[0071] According to an embodiment of the present disclosure, the predetermined attention threshold may be a fixed value or a dynamically adjusted threshold. As long as it is a threshold that can meet the minimum attention standard. For example, the predetermined attention threshold may be a threshold determined based on the recommendation values ​​of multiple users for the initial first target object and objects related to the initial first target object. For example, half of the recommendation values ​​of multiple users for the initial first target object and objects related to the initial first target object in a historical time period may be used as the predetermined attention threshold.

[0072] According to one embodiment of the present disclosure, the second initial recommendation threshold is determined based on a predetermined attention threshold. Using the second initial recommendation threshold as the recommendation threshold or determining the recommendation threshold based on the second initial recommendation threshold can ensure the completion of the task of recommending the initial first target object to multiple users for a predetermined number of times within a predetermined recommendation time.

[0073] According to an embodiment of the present disclosure, for operation S340, based on the first initial recommendation threshold and the second initial recommendation threshold, determining the recommendation threshold may include: comparing the first initial recommendation threshold and the second initial recommendation threshold, and taking the larger value as the recommendation threshold. However, the method for determining the recommendation threshold is not limited to this. The recommendation threshold may also be the average value of the first initial recommendation threshold and the second initial recommendation threshold. As long as it is a recommendation threshold that can be determined based on the first initial recommendation threshold and the second initial recommendation threshold, it will be fine.

[0074] According to the embodiments of the present disclosure, the larger value of the first initial recommendation threshold and the second initial recommendation threshold is used as the recommendation threshold to achieve dynamic decision-making, which can improve the user experience while meeting the recommendation requirements, so that the target recommendation object recommended to the target user is more in line with the interest level of the target user. This avoids the situation where only considering the first initial recommendation threshold as the recommendation threshold results in the inability to complete the task of recommending the initial first target object for a predetermined number of times within a predetermined recommendation time.

[0075] According to an embodiment of the present disclosure, in the case of determining the recommendation threshold of at least one initial first target object, the first target object can be determined from the at least one initial first target object based on the recommendation threshold of the at least one initial first target object and the recommendation value of the at least one initial first target object. And operation S240 is performed to determine the target recommendation object from the at least one first target object and the at least one second target object based on the recommendation value of the at least one first target object and the recommendation value of the at least one second target object.

[0076] According to an embodiment of the present disclosure, the recommendation value of each of the at least one first target object can be weighted using a dynamic recommendation weight to obtain a target recommendation value of each of the at least one first target object. However, it is not limited to this. The recommendation value of each of the at least one first target object can also be weighted using a fixed weight to obtain a target recommendation value of each of the at least one first target object. Based on the target recommendation value of each of the at least one first target object and the recommendation value of each of the at least one second target object, a target recommendation object is determined from the at least one first target object and the at least one second target object.

[0077] According to an embodiment of the present disclosure, dynamic recommendation weights are used to weight the recommendation values ​​of at least one first target object. The dynamic recommendation weights can be used to give priority based on recommendation needs, thereby achieving global optimization and enabling the first target object to complete a predetermined number of recommendations within a predetermined recommendation duration.

[0078] Figure 4 The flowchart of the recommendation method according to another embodiment of the present disclosure is schematically shown.

[0079] like Figure 4As shown, the multiple objects may include NID_1, NID_2, NID_3, NID_4 and NID_5, but are not limited to 5, and may also be any integer greater than 5. Two initial first target objects 410 and three second target objects 420 may be determined from the five objects. The initial first target objects 410 are, for example, NID_1 and NID_2, and the second target objects 420 are, for example, NID_3, NID_4 and NID_5. For target user A, the initial first target objects are screened based on the recommendation values ​​and recommendation thresholds of NID_1 and NID_2, respectively, to determine whether NID_1 and NID_2 are first target objects. When the recommendation value of NID_1 is greater than the recommendation threshold, NID_1 is determined as the first target object 430. When the recommendation value of NID_2 is less than the recommendation threshold, the initial first target object NID_2 is deleted. The recommendation value of NID_1, such as user A_NID_1_recommendation value, is weighted using the dynamic recommendation weight to obtain a target recommendation value of NID_1, such as user A_NID_1_target recommendation value. And the recommendation values ​​of the three second target objects NID_3, NID_4 and NID_5 are determined, such as user A_NID_3_recommendation value, user A_NID_4_recommendation value and user A_NID_5_recommendation value. The target recommendation object can be determined based on the target recommendation value of the first target object NID_1 and the recommendation values ​​of the three second target objects NID_3, NID_4 and NID_5.

[0080] For example, based on the target recommendation value of the first target object NID_1 and the recommendation values ​​of the three second target objects NID_3, NID_4 and NID_5, the four objects can be sorted to obtain, for example, a sorting result in which the recommendation values ​​are sorted in order from high to low, such as user A_NID_3_recommended value, user A_NID_1_target recommended value, user A_NID_4_recommended value and user A_NID_5_recommended value. Based on the sorting result, the object with the highest recommendation value, such as object NID_3, can be used as the target recommended object. It is also possible to select the same number of objects as the recommended object threshold as the target recommended objects in the order of the recommended values ​​from high to low based on the sorting result and the predetermined recommended object threshold.

[0081] According to an embodiment of the present disclosure, the recommendation value of each of the multiple objects can be determined based on the point spread ratio of the target user to the object. The point spread ratio may refer to the ratio of the number of times the object is clicked by the target user to the number of times the object is recommended to the target user. However, it is not limited to this. The recommendation value of each of the multiple objects can also be data related to whether the target user has collected the object, followed the object, or liked the object. As long as the recommendation value can represent the target user's interest in the object.

[0082] According to an embodiment of the present disclosure, the dynamic recommendation weight may be determined by the following operations.

[0083] For example, for each first target object in at least one first target object, the remaining number of recommendations is determined based on the predetermined number of recommendations and the number of recommendations that have been made for the first target object. The dynamic recommendation weight of the first target object is determined based on the remaining number of recommendations and the executable number of recommendations. The executable number of recommendations is used to characterize the number of recommendations that meet the predetermined conditions.

[0084] According to an embodiment of the present disclosure, the dynamic recommendation weight P may be as shown in formula (2).

[0085] P = remaining number of recommendations / executable number of recommendations; (2)

[0086] According to an embodiment of the present disclosure, the dynamic recommendation weight may also be referred to as the allocation probability. Based on the dynamic recommendation weight, the first object with a large number of remaining recommendations or a small number of executable recommendations may be recommended first, so as to achieve global optimization, so that the first target object completes the recommendation of a predetermined number of recommendations within a predetermined recommendation time.

[0087] According to the embodiments of the present disclosure, the recommendation threshold and dynamic recommendation weight of the initial first target object are dynamically adjusted. The recommendation threshold is used to screen at least one initial first target object, so that objects with recommendation needs can be recommended at a relatively stable speed, and a better user experience can be obtained while completing a predetermined number of recommendations within a predetermined recommendation time. Furthermore, the recommendation value of the first target object is adjusted using the dynamic recommendation weight, and global optimization can be performed to give priority to the recommendation of the first target object with a more urgent recommendation need, so that the recommendation effect is improved.

[0088] According to an embodiment of the present disclosure, with respect to operation S210 , in response to a request from a target user, determining recommendation values ​​of each of a plurality of objects may include the following operations.

[0089] For example, in response to a request from a target user, multiple initial objects are screened to determine multiple objects, and based on object attribute information of each of the multiple objects and user attribute information of the target user, recommendation values ​​of each of the multiple objects are determined.

[0090] According to an embodiment of the present disclosure, a preliminary screening deep learning model may be used to estimate the recommendation values ​​of each of a plurality of initial objects, and a plurality of initial objects whose recommendation values ​​are greater than or equal to a preliminary screening threshold may be determined as a plurality of objects.

[0091] According to the embodiments of the present disclosure, the initial screening threshold can be pre-set according to actual conditions and will not be elaborated here.

[0092] According to the embodiments of the present disclosure, the same structure as the initial deep learning model can be used to estimate the recommendation values ​​of multiple objects, but it is not limited to this. A more complex fine screening deep learning model can also be used to estimate the recommendation values ​​of multiple objects. As long as it is a deep learning model that can determine the target user's recommendation value for the object based on the object attribute information of the object and the user attribute information of the target user, it will not be repeated here.

[0093] According to an embodiment of the present disclosure, the target user's attribute information may include user personal information such as the target user's age, gender, occupation, etc., but is not limited to this, and may also include the target user's browsing information, attention information, etc., which are related to the object.

[0094] According to an embodiment of the present disclosure, the object attribute information of an object may include information such as the type, popularity, and release time of the object.

[0095] Figure 5 The block diagram of a recommendation device according to an embodiment of the present disclosure is schematically shown.

[0096] like Figure 5 As shown, the recommendation device 500 may include a response module 510 , a classification module 520 , a screening module 530 , and an object determination module 540 .

[0097] The response module 510 is used to determine the recommendation value of each of the multiple objects in response to a request from the target user, wherein the recommendation value of each of the multiple objects is used to represent the interest degree of the target user in each of the multiple objects at the current moment.

[0098] The classification module 520 is configured to determine at least one initial first target object and at least one second target object among the multiple objects.

[0099] The screening module 530 is configured to determine at least one first target object from the at least one initial first target object based on the recommendation value of each of the at least one initial first target objects and the recommendation threshold of each of the at least one initial first target object.

[0100] The object determination module 540 is used to determine a target recommendation object from at least one first target object and at least one second target object based on the recommendation value of each of the at least one first target object and the recommendation value of each of the at least one second target object, so as to recommend the target recommendation object to the target user.

[0101] According to an embodiment of the present disclosure, the object determination module may include a weighting unit and an object determination unit.

[0102] The weighting unit is used to weight the recommendation value of each of the at least one first target object using the dynamic recommendation weight to obtain the target recommendation value of each of the at least one first target object.

[0103] The object determination unit is used to determine a target recommendation object from at least one first target object and at least one second target object based on the target recommendation value of each of the at least one first target object and the recommendation value of each of the at least one second target object.

[0104] According to an embodiment of the present disclosure, the recommendation device may further include a first threshold determination module, a second threshold determination module, and a threshold determination module.

[0105] A first threshold determination module is used to determine, for each of at least one initial first target object, a first initial recommendation threshold of the initial first target object based on the attention values ​​of multiple users to the initial first target object within a predetermined time period and the number of times the initial first target object is to be recommended within the predetermined time period, wherein the attention values ​​of multiple users are used to characterize the degree of interest of multiple users in the initial first target object within the predetermined time period.

[0106] The second threshold determination module is used to determine a second initial recommendation threshold of the initial first target object based on the attention values ​​of multiple users to the initial first target object within a predetermined time period and a predetermined attention threshold.

[0107] The threshold determination module is used to determine the recommendation threshold based on the first initial recommendation threshold and the second initial recommendation threshold.

[0108] According to an embodiment of the present disclosure, the first threshold determination module may include a first sorting unit, a focus value determination unit, and a first threshold determination unit.

[0109] The first sorting unit is used to sort the attention values ​​of multiple users to the initial first target object within a predetermined time period to obtain a sorting result.

[0110] The attention value determination unit is used to determine the target attention value from the sorting results based on the number of times the initial first target object is to be recommended within a predetermined time period.

[0111] A first threshold determination unit is configured to determine a target attention value as a first initial recommendation threshold of an initial first target object.

[0112] According to an embodiment of the present disclosure, the second threshold determination module may include a second sorting unit and a second threshold determination unit.

[0113] The second sorting unit is used to sort the attention values ​​of multiple users to the initial first target object within a predetermined time period to obtain a sorting result.

[0114] A second threshold determination unit is used to determine, based on the sorting result, the attention value of the Kth user to the initial first target object within a predetermined time period as the second initial recommendation threshold of the initial first target object when the average attention value of the first K users is greater than or equal to the predetermined attention threshold and the average attention value of the first K+1 users is less than the predetermined attention threshold.

[0115] According to an embodiment of the present disclosure, the threshold determination module may include a threshold determination unit.

[0116] The threshold determination unit is used to compare the first initial recommended threshold and the second initial recommended threshold, and use the larger value as the recommended threshold.

[0117] According to an embodiment of the present disclosure, the object determination module may further include a number determination unit and a weight determination unit.

[0118] The number determination unit is used to determine the remaining number of recommendations for each first target object among the at least one first target object based on the predetermined number of recommendations and the number of recommendations of the first target object.

[0119] The weight determination unit is used to determine the dynamic recommendation weight of the first target object based on the remaining recommendation times and the executable recommendation times, wherein the executable recommendation times is used to represent the number of recommendations that meet the predetermined conditions.

[0120] According to an embodiment of the present disclosure, the response module may include a preliminary screening unit and a recommendation value determination unit.

[0121] The initial screening unit is used to screen multiple initial objects and determine multiple objects.

[0122] The recommendation value determination unit is used to determine the recommendation value of each of the multiple objects based on the object attribute information of each of the multiple objects and the user attribute information of the target user.

[0123] 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.

[0124] According to an embodiment of the present disclosure, an electronic device includes: 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 a method as in the embodiment of the present disclosure.

[0125] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute a method as described in an embodiment of the present disclosure.

[0126] According to an embodiment of the present disclosure, a computer program product includes a computer program, and when the computer program is executed by a processor, the method according to the embodiment of the present disclosure is implemented.

[0127] Figure 6 A 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.

[0128] 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.

[0129] 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.

[0130] 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 the recommendation method. For example, in some embodiments, the recommendation method 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 recommendation method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the recommendation method in any other appropriate manner (e.g., by means of firmware).

[0131] 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), complex 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] A computer system may include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises through computer programs running on respective computers and having a client-server relationship to each other. The server may be a cloud server, a server in a distributed system, or a server combined with a blockchain.

[0137] 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.

[0138] 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 recommendation method, comprising: In response to a request from a target user, determining a recommendation value of each of the multiple objects, wherein the recommendation value of each of the multiple objects is used to represent the interest level of the target user in each of the multiple objects at a current moment; Determine at least one initial first target object and at least one second target object among the multiple objects, wherein the initial first target object includes objects having recommendation requirements, and the second target object includes objects among the multiple objects except the at least one initial first target object; determining at least one first target object from the at least one initial first target object based on the recommendation value of each of the at least one initial first target object and the recommendation threshold of each of the at least one initial first target object; Using a dynamic recommendation weight to weight the recommendation value of each of the at least one first target object to obtain a target recommendation value of each of the at least one first target object, wherein the dynamic recommendation weight is an allocation probability determined based on the recommendation requirement; and Based on the target recommendation value of each of the at least one first target object and the recommendation value of each of the at least one second target object, a target recommendation object is determined from the at least one first target object and the at least one second target object so as to recommend the target recommendation object to the target user.

2. The method according to claim 1, further comprising: For each of the at least one initial first target object, based on the attention values ​​of multiple users to the initial first target object within a predetermined time period and the number of times the initial first target object is to be recommended within the predetermined time period, determining a first initial recommendation threshold of the initial first target object, wherein the attention values ​​of the multiple users are used to represent the degree of interest of the multiple users in the initial first target object within the predetermined time period; Determining a second initial recommendation threshold of the initial first target object based on the attention values ​​of each of the multiple users to the initial first target object within a predetermined time period and a predetermined attention threshold; and The recommendation threshold is determined based on the first initial recommendation threshold and the second initial recommendation threshold.

3. The method according to claim 2, wherein: The determining of a first initial recommendation threshold of the initial first target object based on the attention values ​​of the plurality of users to the initial first target object within a predetermined time period and the number of times the initial first target object is to be recommended within the predetermined time period comprises: Sorting the attention values ​​of the multiple users to the initial first target object within a predetermined time period to obtain a sorting result; Determining a target attention value from the ranking result based on the number of times the initial first target object is to be recommended within the predetermined time period; and The target attention value is determined as a first initial recommendation threshold of the initial first target object.

4. The method according to claim 2, wherein: The determining, based on the attention values ​​of the multiple users to the initial first target object within a predetermined time period and a predetermined attention threshold, a second initial recommendation threshold of the initial first target object comprises: sorting the attention values ​​of the multiple users to the initial first target object within a predetermined time period to obtain a sorting result; and Based on the sorting result, when the average attention value of the first K users is greater than or equal to the predetermined attention threshold and the average attention value of the first K+1 users is less than the predetermined attention threshold, the attention value of the Kth user to the initial first target object within the predetermined time period is determined as the second initial recommendation threshold of the initial first target object.

5. The method according to any one of claims 2 to 4, wherein: The determining the recommendation threshold based on the first initial recommendation threshold and the second initial recommendation threshold comprises: The first initial recommended threshold and the second initial recommended threshold are compared, and the larger value is used as the recommended threshold.

6. The method according to claim 1, wherein: The determining a target recommended object from the at least one first target object and the at least one second target object based on the respective recommendation values ​​of the at least one first target object and the respective recommendation values ​​of the at least one second target object further comprises: For each first target object of the at least one first target object, determining a remaining number of recommendations based on a predetermined number of recommendations and a number of recommendations for the first target object; and The dynamic recommendation weight of the first target object is determined based on the remaining number of recommendations and the executable number of recommendations, wherein the executable number of recommendations is used to represent the number of recommendations that meet a predetermined condition.

7. The method according to any one of claims 1 to 4, wherein: The determining, in response to a request from a target user, a recommendation value of each of the plurality of objects comprises: Screening a plurality of initial objects to determine the plurality of objects; and Based on the object attribute information of each of the plurality of objects and the user attribute information of the target user, a recommendation value of each of the plurality of objects is determined.

8. A recommendation device, comprising: A response module, configured to determine, in response to a request from a target user, a recommendation value of each of the plurality of objects, wherein the recommendation value of each of the plurality of objects is used to represent the interest level of the target user in each of the plurality of objects at a current moment; a classification module, configured to determine at least one initial first target object and at least one second target object among the plurality of objects, wherein the initial first target object includes objects having recommendation requirements, and the second target object includes objects among the plurality of objects other than the at least one initial first target object; a screening module, configured to determine at least one first target object from the at least one initial first target object based on the recommendation value of each of the at least one initial first target object and the recommendation threshold of each of the at least one initial first target object; and an object determination module, configured to determine a target recommendation object from the at least one first target object and the at least one second target object based on the recommendation value of each of the at least one first target object and the recommendation value of each of the at least one second target object, so as to recommend the target recommendation object to the target user; Wherein, the object determination module includes: a weighting unit, configured to weight the recommendation value of each of the at least one first target object using a dynamic recommendation weight to obtain a target recommendation value of each of the at least one first target object, wherein the dynamic recommendation weight is an allocation probability determined based on a recommendation requirement; and The object determination unit is used to determine the target recommendation object from the at least one first target object and the at least one second target object based on the target recommendation value of each of the at least one first target object and the recommendation value of each of the at least one second target object.

9. The apparatus according to claim 8, further comprising: A first threshold determination module is used to determine, for each of the at least one initial first target object, a first initial recommendation threshold of the initial first target object based on the attention values ​​of multiple users to the initial first target object within a predetermined time period and the number of times the initial first target object is to be recommended within the predetermined time period, wherein the attention values ​​of the multiple users are used to represent the interest levels of the multiple users in the initial first target object within the predetermined time period; A second threshold determination module, configured to determine a second initial recommendation threshold of the initial first target object based on the attention values ​​of the multiple users to the initial first target object within a predetermined time period and a predetermined attention threshold; and A threshold determination module is used to determine the recommendation threshold based on the first initial recommendation threshold and the second initial recommendation threshold.

10. The device according to claim 9, wherein: The first threshold determination module comprises: A first sorting unit, configured to sort the attention values ​​of the multiple users to the initial first target object within a predetermined time period to obtain a sorting result; an attention value determining unit, configured to determine a target attention value from the ranking result based on the number of times the initial first target object is to be recommended within the predetermined time period; and The first threshold determination unit is used to determine the target attention value as a first initial recommendation threshold of the initial first target object.

11. The device according to claim 9, wherein: The second threshold determination module includes: A second sorting unit is used to sort the attention values ​​of the multiple users to the initial first target object within a predetermined time period to obtain a sorting result; and A second threshold determination unit is used to determine, based on the sorting result, the attention value of the Kth user to the initial first target object within the predetermined time period as the second initial recommendation threshold of the initial first target object when the average attention value of the first K users is greater than or equal to the predetermined attention threshold and the average attention value of the first K+1 users is less than the predetermined attention threshold.

12. The device according to any one of claims 9 to 11, wherein: The threshold determination module comprises: The threshold determination unit is used to compare the first initial recommended threshold and the second initial recommended threshold, and use the larger value as the recommended threshold.

13. The device according to claim 8, wherein: The object determination module also includes: a times determining unit, configured to determine, for each first target object among the at least one first target object, a remaining number of recommendations based on a predetermined number of recommendations and a number of recommendations for the first target object; and A weight determination unit is used to determine the dynamic recommendation weight of the first target object based on the remaining recommendation times and the executable recommendation times, wherein the executable recommendation times is used to represent the number of recommendations that meet a predetermined condition.

14. The device according to any one of claims 8 to 11, wherein: The response module comprises: a primary screening unit, configured to screen a plurality of initial objects to determine the plurality of objects; and The recommendation value determination unit is used to determine the recommendation value of each of the multiple objects based on the object attribute information of each of the multiple objects and the user attribute information of the target user.

15. 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 7.

16. 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 to 7.

17. 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 7.

Images