A personalized recommendation method and system based on user scenario

Abstract

The present application is applicable to the technical field of data prediction, and provides a personalized recommendation method and system based on user scenarios, wherein the method includes first obtaining current time information, first scene information of a first user, and second scene information of a second user, and then quickly generating first recommended item information based on current time information, first geographic location information, and first ambient light intensity value information, and simultaneously quickly generating second recommended item information based on current time information, second geographic location information, and second ambient light intensity value information, and finally effectively generating target recommended item information based on the first recommended item information, the second recommended item information, and a comprehensive matching degree calculation function. The present application can dynamically adjust the recommendation results in combination with the user's personal scene changes, provide multiple users with personalized content recommendations, and greatly improve the user stickiness of the commercial platform.

Description

Technical Field

[0001] The present application relates to the technical field of data prediction, and in particular, to a personalized recommendation method and system based on user scenarios. Background Art

[0002] With the rapid development of the Internet, personalized recommendation systems have become increasingly important in various applications. Personalized recommendation systems can recommend products or services that meet users' needs.

[0003] At present, personalized recommendation systems usually focus on content recommendations for a single user and are unable to provide personalized content recommendations for multiple users at the same time. For example, they are unable to recommend suitable social entertainment services to a group of friends. This is not conducive to improving user stickiness on commercial platforms and needs further improvement. Summary of the invention

[0004] Based on this, the embodiments of the present application provide a personalized recommendation method and system based on user scenarios to solve the problem in the prior art that is not conducive to improving user stickiness of commercial platforms.

[0005] In a first aspect, an embodiment of the present application provides a personalized recommendation method based on user scenarios, the method comprising:

[0006] Acquire current time information, and acquire first scene information of a first user and second scene information of a second user, wherein the first scene information includes first geographic location information and first ambient light intensity value information, and the second scene information includes second geographic location information and second ambient light intensity value information;

[0007] generating first recommended item information according to the current time information, the first geographical location information, and the first ambient light intensity value information, and generating second recommended item information according to the current time information, the second geographical location information, and the second ambient light intensity value information;

[0008] Target recommended item information is generated according to the first recommended item information, the second recommended item information and a preset comprehensive matching degree calculation function.

[0009] Compared with the prior art, the beneficial effect is as follows: the personalized recommendation method based on user scenarios provided in the embodiment of the present application, the terminal device can first obtain the current time information, the first scene information of the first user and the second scene information of the second user, and then quickly generate the first recommended item information according to the current time information, the first geographic location information and the first ambient light intensity value information, and at the same time quickly generate the second recommended item information according to the current time information, the second geographic location information and the second ambient light intensity value information, and finally effectively generate the target recommended item information according to the first recommended item information and the second recommended item information and the comprehensive matching degree calculation function, so as to realize dynamic adjustment of the recommendation results in combination with the scene changes, and provide multiple users with fitting and personalized content recommendations at the same time, enhance the user's trust and dependence on the recommendation system, improve the user stickiness of the commercial platform, and to a certain extent solve the current problem that is not conducive to improving the user stickiness of the commercial platform.

[0010] In a second aspect, an embodiment of the present application provides a personalized recommendation system based on user scenarios, the system comprising:

[0011] A location scene information acquisition module: used to acquire current time information, and acquire first location scene information of a first user and second location scene information of a second user, wherein the first location scene information includes first geographic location information and first ambient light intensity value information, and the second location scene information includes second geographic location information and second ambient light intensity value information;

[0012] A recommended item information generating module: used to generate first recommended item information according to the current time information, the first geographical location information and the first ambient light intensity value information, and to generate second recommended item information according to the current time information, the second geographical location information and the second ambient light intensity value information;

[0013] Target recommendation item information generation module: used to generate target recommendation item information according to the first recommendation item information, the second recommendation item information and a preset comprehensive matching degree calculation function.

[0014] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method of the first aspect described above when executing the computer program.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method of the first aspect described above are implemented.

[0016] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0018] Figure 1 is a flowchart of a personalized recommendation method provided by an embodiment of the present application;

[0019] Figure 2 is a flowchart of step S200 in the personalized recommendation method provided in one embodiment of the present application;

[0020] Figure 3 is a flowchart of step S300 in the personalized recommendation method provided in one embodiment of the present application;

[0021] Figure 4 is a flowchart of step S360 in the personalized recommendation method provided in one embodiment of the present application;

[0022] Figure 5 It is a flowchart after step S300 in the personalized recommendation method provided in one embodiment of the present application;

[0023] Figure 6 This is a module block diagram of a personalized recommendation system provided by an embodiment of the present application;

[0024] Figure 7 It is a schematic diagram of a terminal device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0025] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0026] In the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0027] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0028] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0029] See also Figure 1 , Figure 1 : is a flowchart of a personalized recommendation method based on user scenarios provided by an embodiment of the present application. In this embodiment, the execution subject of the personalized recommendation method is a terminal device. It is understandable that the types of terminal devices include but are not limited to mobile phones, tablet computers, laptops, ultra-mobile personal computers (Ultra-Mobile Personal Computer, UMPC), netbooks, personal digital assistants (Personal Digital Assistant, PDA), etc., and the embodiments of the present application do not impose any restrictions on the specific types of terminal devices.

[0030] See also Figure 1 The personalized recommendation method provided in the embodiment of the present application includes but is not limited to the following steps:

[0031] In S100, current time information is obtained, and first scene information of a first user and second scene information of a second user are obtained.

[0032] Specifically, the terminal device can first obtain the current moment information, and obtain the first scene information of the first user, and simultaneously obtain the second scene information of the second user, wherein the current moment information is used to describe the current moment; the first user is used to describe a user to be personalized recommended, and exemplarily, the first user can be the initiator of the social activity; the second user is used to describe another user to be personalized recommended, and exemplarily, the second user can be a participant in the same social activity.

[0033] Without loss of generality, the first scene information includes first geographic location information and first ambient light intensity value information, wherein the first geographic location information is used to describe the geographic location of the scene where the first user is located, and the first ambient light intensity value information is used to describe the ambient light intensity of the scene where the first user is located; the second scene information includes second geographic location information and second ambient light intensity value information, wherein the second geographic location information is used to describe the geographic location of the scene where the second user is located, and the second ambient light intensity value information is used to describe the ambient light intensity of the scene where the second user is located.

[0034] Exemplarily, the terminal device can use a preset time sensor to obtain current time information, then use a preset light sensor to obtain first ambient light intensity value information and second ambient light intensity value information, and then use a preset GPS positioning sensor to obtain first geographic location information and second geographic location information.

[0035] It should be noted that the ambient light intensity can affect the user's emotions, and the user's emotional changes will affect the user's choices. Therefore, personalized recommendations based on the ambient light intensity can help improve the accuracy and timeliness of the recommended content.

[0036] In S200, first recommended item information is generated according to current time information, first geographical location information and first ambient light intensity value information, and second recommended item information is generated according to current time information, second geographical location information and second ambient light intensity value information.

[0037] Specifically, after the terminal device obtains the current time information, the first scene information and the second scene information, the terminal device can effectively generate the first recommended item information according to the current time information, the first geographic location information and the first ambient light intensity value information, and at the same time effectively generate the second recommended item information according to the current time information, the second geographic location information and the second ambient light intensity value information, wherein the first recommended item information is used to describe the service items obtained by personalized recommendation specifically for the first user, and the second recommended item information is used to describe the service items obtained by personalized recommendation specifically for the second user, and the service items may be cinemas or restaurants suitable for multiple social entertainments.

[0038] In some possible implementations, in order to realize the generation of the first recommended item information and the second recommended item information, please refer to Figure 2 Step S200 includes but is not limited to the following steps:

[0039] In S210, based on a preset historical database, according to the first geographic location information, multiple first historical scene information of the first user and the first historical moment information corresponding to each first historical scene information are obtained, and according to the second geographic location information, multiple second historical scene information of the second user and the second historical moment information corresponding to each second historical scene information are obtained.

[0040] Specifically, the terminal device can obtain multiple first historical scene information of the first user and the first historical moment information corresponding to each piece of first historical scene information based on the preset historical database and the first geographic location information. At the same time, the terminal device can obtain multiple second historical scene information of the second user and the second historical moment information corresponding to each piece of second historical scene information based on the second geographic location information, wherein the first historical scene information is used to describe the historical scene that the first user has selected; the first historical moment information is used to describe the moment when the first user selects the first historical scene information, such as the moment when the first user places an order and pays for the first historical scene information on a commercial platform; the second historical scene information is used to describe the historical scene that the second user has selected, and the second historical moment information is used to describe the moment when the second user selects the second historical scene information, such as the moment when the second user places an order and pays for the second historical scene information on a commercial platform.

[0041] For example, when the first user went to the first restaurant in the first area on January 1 to consume, went to the second restaurant in the first area on January 2 to consume, and went to the third restaurant in the first area on January 3 to consume, the first geographic location information may be "first area", and the multiple first historical scene information may be "first restaurant", "second restaurant" and "third restaurant", respectively. Specifically, the first historical moment information corresponding to the first historical scene information of the "first restaurant" is "January 1", the first historical moment information corresponding to the first historical scene information of the "second restaurant" is "January 2", and the first historical moment information corresponding to the first historical scene information of the "third restaurant" is "January 3".

[0042] In S220, sampling time range information is generated according to the current time information and the preset fault tolerance time value information.

[0043] Specifically, after the terminal device obtains multiple first historical scene information, multiple first historical moment information, multiple second historical scene information and multiple second historical moment information, the terminal device can generate sampling time range information based on the sum of current moment information and preset fault tolerance time value information.

[0044] For example, if the current time information is "11:05" and the fault tolerance time value information is two hours, the sampling time range information may be "11:05 to 13:05".

[0045] In S230, at least one first matching scene information is determined according to the sampling time range information and the first historical moment information, and at least one second matching scene information is determined according to the sampling time range information and the second historical moment information.

[0046] Specifically, after the terminal device generates the sampling time range information, the terminal device can quickly determine at least one first matching scene information based on the sampling time range information and the first historical moment information, and quickly determine at least one second matching scene information based on the sampling time range information and the second historical moment information, wherein the first matching scene information is used to describe the first historical scene information of the first historical moment information within the sampling time range information; the second matching scene information is used to describe the second historical scene information of the second historical moment information within the sampling time range information.

[0047] Exemplarily, when the first historical scene information specifically for the “first restaurant” corresponds to the first historical moment information of “January 1 11:30”, the first historical scene information specifically for the “second restaurant” corresponds to the first historical moment information of “January 2 13:45”, the first historical moment information specifically for the “third restaurant” corresponds to the first historical moment information of “January 3 11:45” and the sampling time range information is “11:05 to 13:05”, the first matching scene information can be the first historical scene information specifically for the “first restaurant” and the first historical scene information specifically for the “third restaurant”.

[0048] In S240, first historical light intensity value information corresponding to each first matching scene information and second historical light intensity value information corresponding to each second matching scene information are obtained according to the historical database.

[0049] Specifically, after the terminal device determines at least one first matching scene information and second matching scene information, the terminal device can obtain the first historical light intensity value information corresponding to each first matching scene information and the second historical light intensity value information corresponding to each second matching scene information based on the historical database, wherein the first historical light intensity value information is used to describe the ambient light intensity corresponding to the first matching scene information, and the second historical light intensity value information is used to describe the ambient light intensity corresponding to the second matching scene information.

[0050] In S250, it is determined whether the difference between the first historical light intensity value information and the first ambient light intensity value information is less than a preset deviation light intensity threshold information.

[0051] Specifically, after the terminal device obtains the first historical light intensity value information and the second historical light intensity value information, the terminal device can determine whether the difference between the first historical light intensity value information and the first ambient light intensity value information is less than the preset deviation light intensity threshold information, where the deviation light intensity threshold information can be a preset value.

[0052] In S260, if the difference between the first historical light intensity value information and the first ambient light intensity value information is less than the deviation light intensity threshold information, it is determined that the user-selected item corresponding to the first matching scene information is the first recommended item information.

[0053] Specifically, if the difference between the first historical light intensity value information and the first ambient light intensity value information is less than the deviation light intensity threshold information, it indicates that the ambient light intensity of the scene currently located by the first user is similar to the ambient light intensity of the scene when the first matching scene information was originally selected. Therefore, the terminal device can determine that the user selected item corresponding to the first matching scene information is the first recommended item information.

[0054] In S270, it is determined whether the difference between the second historical light intensity value information and the second ambient light intensity value information is less than the deviation light intensity threshold information.

[0055] Specifically, after the terminal device determines the first recommended item information, the terminal device may determine whether the difference between the second historical light intensity value information and the second ambient light intensity value information is less than the deviation light intensity threshold information.

[0056] In S280, if the difference between the second historical light intensity value information and the second ambient light intensity value information is less than the deviation light intensity threshold information, it is determined that the user-selected item corresponding to the second matching scene information is the second recommended item information.

[0057] Specifically, if the difference between the second historical light intensity value information and the second ambient light intensity value information is less than the deviation light intensity threshold information, it indicates that the ambient light intensity of the scene where the second user is currently located is similar to the ambient light intensity of the scene when the second matching scene information was originally selected. Therefore, the terminal device can determine that the user selected item corresponding to the second matching scene information is the second recommended item information.

[0058] In S300, target recommended item information is generated according to the first recommended item information, the second recommended item information and a preset comprehensive matching degree calculation function.

[0059] Specifically, after the terminal device generates the first recommended item information and the second recommended item information, the terminal device can generate the target recommended item information based on the first recommended item information and the second recommended item information and a preset comprehensive matching degree calculation function, thereby dynamically adjusting the recommendation results in combination with scene changes, and providing personalized content recommendations for multiple users at the same time. The recommended content can be tailored to each user at the same time, thereby enhancing the user's trust and reliance on the recommendation system, which is conducive to improving the user stickiness of the commercial platform.

[0060] In some possible implementations, in order to determine effective target recommendation item information, please refer to Figure 3 Step S300 includes but is not limited to the following steps:

[0061] In S310, the first historical average consumption amount information and the first cumulative selection number information corresponding to each first recommended item information are obtained, and the second historical average consumption amount information and the second cumulative selection number information corresponding to each second recommended item information are obtained.

[0062] Specifically, the terminal device can first obtain the first historical average consumption amount information and the first cumulative selection number information corresponding to each first recommended item information, and at the same time obtain the second historical average consumption amount information and the second cumulative selection number information corresponding to each second recommended item information, wherein the first historical average consumption amount information is used to describe the average consumption amount of the first user in the first recommended item information; the first cumulative selection number information is used to describe the cumulative selection number of the first user in the first recommended item information; the second historical average consumption amount information is used to describe the average consumption amount of the second user in the second recommended item information; and the second cumulative selection number information is used to describe the cumulative selection number of the second user in the second recommended item information.

[0063] Exemplarily, when the first user has consumed the first recommended item information twice, and the consumption amounts are 300 yuan and 500 yuan respectively, the first historical average consumption amount information may be 400 yuan, and the first cumulative number of selections information may be two times.

[0064] In S320, the first comprehensive average consumption amount information is generated based on the average value of the sum of multiple first historical average consumption amount information, and the second comprehensive average consumption amount information is generated based on the average value of the sum of multiple second historical average consumption amount information, and the first comprehensive average selection number information is generated based on the average value of the sum of multiple first cumulative selection number information, and the second comprehensive average selection number information is generated based on the average value of the sum of multiple second cumulative selection number information.

[0065] Specifically, the terminal device can quickly generate the first comprehensive average consumption amount information based on the average value of the sum of multiple first historical average consumption amount information, and efficiently generate the second comprehensive average consumption amount information based on the average value of the sum of multiple second historical average consumption amount information, and effectively generate the first comprehensive average selection number information based on the average value of the sum of multiple first cumulative selection number information, and quickly generate the second comprehensive average selection number information based on the average value of the sum of multiple second cumulative selection number information.

[0066] In S330, the third comprehensive average consumption amount information is generated based on the average value of the sum of the first comprehensive average consumption amount information and the second comprehensive average consumption amount information, and the third comprehensive average selection number information is generated based on the average value of the sum of the first comprehensive average selection number information and the second comprehensive average selection number information.

[0067] Specifically, the terminal device can effectively generate the third comprehensive average consumption amount information based on the average of the sum of the first comprehensive average consumption amount information and the second comprehensive average consumption amount information, and at the same time quickly generate the third comprehensive average selection number information based on the average of the sum of the first comprehensive average selection number information and the second comprehensive average selection number information.

[0068] In S340, for each first recommended item information: the first matching degree information is generated according to the first historical average consumption amount information, the first comprehensive average consumption amount information, the third comprehensive average consumption amount information, the first cumulative number of selections information, the first comprehensive average number of selections information, the third comprehensive average number of selections information and a preset comprehensive matching degree calculation function.

[0069] Specifically, the terminal device can perform this processing for each first recommended item information: the first historical average consumption amount information, the first comprehensive average consumption amount information, the third comprehensive average consumption amount information, the first cumulative number of selections information, the first comprehensive average number of selections information and the third comprehensive average number of selections information are all input into a preset comprehensive matching degree calculation function to effectively generate the first matching degree information, wherein the first matching degree information is used to characterize the degree to which the first recommended item information can be suitable for both the first user and the second user.

[0070] In S350, for each second recommended item information: the second matching degree information is generated according to the second historical average consumption amount information, the second comprehensive average consumption amount information, the third comprehensive average consumption amount information, the second cumulative number of selections information, the second comprehensive average number of selections information, the third comprehensive average number of selections information and the comprehensive matching degree calculation function.

[0071] Specifically, the terminal device can perform this processing for each second recommended item information: the second historical average consumption amount information, the second comprehensive average consumption amount information, the third comprehensive average consumption amount information, the second cumulative number of selections information, the second comprehensive average number of selections information and the third comprehensive average number of selections information are all input into the comprehensive matching degree calculation function to effectively generate the second matching degree information, wherein the second matching degree information is used to characterize the degree to which the second recommended item information can be suitable for both the first user and the second user.

[0072] In S360 , target recommendation item information is determined according to the first matching degree information and the second matching degree information.

[0073] Specifically, after the terminal device generates the first matching information and the second matching information, the terminal device can effectively determine the target recommendation item information based on the first matching information and the second matching information, thereby determining the service item that is most suitable for both the first user and the second user among multiple service items.

[0074] In some possible implementations, the above comprehensive matching degree calculation function may be:

[0075] ,

[0076] In the formula, Represents the first correction factor, and the value range of the first correction factor is 1.14 to 1.28. Exemplarily, when the first historical average consumption amount information is greater than three times the first comprehensive average consumption amount information, the first correction factor can be 1.28; when the first historical average consumption amount information is greater than the first historical average consumption amount information and the first historical average consumption amount information is less than 1.2 times the first comprehensive average consumption amount information, the first correction factor can be 1.14.

[0077] In the formula, Represents the second correction factor, and the value range of the second correction factor is 1.38 to 1.44. Exemplarily, when the first cumulative selection number information is greater than three times the first comprehensive average selection number information, the first correction factor can be 1.44; when the first cumulative selection number information is greater than the first comprehensive average selection number information and the first cumulative selection number information is less than 1.2 times the first comprehensive average selection number information, the first correction factor can be 1.38.

[0078] In the formula, represents the third comprehensive average consumption amount information, which is used as a benchmark value representing the first user and the second user in the dimension of consumption amount; Represents the third comprehensive average selection times information, which is used as a benchmark value that simultaneously characterizes the first user and the second user in the dimension of selection times.

[0079] In the formula, when the calculation object of the comprehensive matching degree calculation function is the first recommended item information, represents the first matching degree information, and the smaller the value of the first matching degree information is, the higher the degree of suitability of the first recommended item information for both the first user and the second user is; Indicates the first historical average consumption amount information, Indicates the first comprehensive average consumption amount information, Indicates the first cumulative selection times information, Indicates the first comprehensive average selection number information.

[0080] In the formula, when the calculation object of the comprehensive matching degree calculation function is the second recommended item information, represents the second matching degree information, and the smaller the value of the second matching degree information is, the more suitable the second recommended item information is for both the first user and the second user; Indicates the second historical average consumption amount information, Indicates the second comprehensive average consumption amount information, Indicates the second cumulative selection times information, Indicates the second comprehensive average selection number information.

[0081] It should be noted that both the first matching degree information and the second matching degree information are dimensionless values.

[0082] In some possible implementations, to further determine the target recommended item information, please refer to Figure 4 Step S360 includes but is not limited to the following steps:

[0083] In S361, the first recommended item information corresponding to the smallest first matching degree information is determined as the first preliminary selected item information, and the second recommended item information corresponding to the smallest second matching degree information is determined as the second preliminary selected item information.

[0084] Specifically, the terminal device may determine that the first recommended item information corresponding to the first matching degree information with the smallest value is the first preliminary selected item information, and simultaneously determine that the second recommended item information corresponding to the second matching degree information with the smallest value is the second preliminary selected item information.

[0085] In S362, it is determined whether the first matching degree information of the first preliminary selected item information is less than or equal to the second matching degree information of the second preliminary selected item information.

[0086] Specifically, after the terminal device determines the first preliminary selection item information and the second preliminary selection item information, the terminal device may determine whether the first matching degree information of the first preliminary selection item information is less than or equal to the second matching degree information of the second preliminary selection item information.

[0087] In S363, if the first matching degree information of the first preliminary selected item information is less than or equal to the second matching degree information of the second preliminary selected item information, the first preliminary selected item information is determined as the target recommended item information; otherwise, the second preliminary selected item information is determined as the target recommended item information.

[0088] Specifically, if the first matching degree information of the first preliminary selected item information is less than or equal to the second matching degree information of the second preliminary selected item information, the terminal device can determine that the first preliminary selected item information is the target recommended item information; otherwise, the terminal device can determine that the second preliminary selected item information is the target recommended item information.

[0089] In some possible implementations, in order to facilitate the subsequent optimization of the recommendation system by combining big data technology, please refer to Figure 5 After step S300, the method further includes but is not limited to the following steps:

[0090] In S400, first identity information of a first user and second identity information of a second user are obtained.

[0091] Specifically, the terminal device may first obtain first identity information of the first user and second identity information of the second user, wherein the first identity information is used to describe the identity of the first user, and the second identity information is used to describe the identity of the second user.

[0092] In S410, record data package information is generated according to current time information, first identity information, second identity information and target recommendation item information.

[0093] Specifically, after the terminal device obtains the first identity identification information and the second identity identification information, the terminal device can comprehensively generate record data packet information based on the current time information, the first identity identification information, the second identity identification information and the target recommended item information, thereby comprehensively recording the current time information, the first identity identification information, the second identity identification information and the target recommended item information through the record data packet information, so as to facilitate the subsequent tracing of the recommended content.

[0094] The implementation principle of the personalized recommendation method based on user scenarios in the embodiment of the present application is as follows: the terminal device can first obtain the current time information, the first scene information of the first user and the second scene information of the second user, and then quickly generate the first recommended item information according to the current time information, the first geographic location information and the first ambient light intensity value information, and at the same time quickly generate the second recommended item information according to the current time information, the second geographic location information and the second ambient light intensity value information, and finally effectively generate the target recommended item information according to the first recommended item information and the second recommended item information and the comprehensive matching degree calculation function, so as to provide multiple users with fitting and personalized content recommendations at the same time, enhance users' trust and dependence on the recommendation system, and help improve the user stickiness of the commercial platform.

[0095] It should be noted that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0096] The embodiment of the present application also provides a personalized recommendation system based on user scenarios. For ease of description, only the parts related to the present application are shown, such as Figure 6 As shown, the system 60 includes:

[0097] The scene information acquisition module 61 is used to acquire current time information, and acquire first scene information of the first user and second scene information of the second user, wherein the first scene information includes first geographic location information and first ambient light intensity value information, and the second scene information includes second geographic location information and second ambient light intensity value information;

[0098] Recommended item information generating module 62: used to generate first recommended item information according to current time information, first geographical location information and first ambient light intensity value information, and to generate second recommended item information according to current time information, second geographical location information and second ambient light intensity value information;

[0099] The target recommended item information generating module 63 is used to generate the target recommended item information according to the first recommended item information, the second recommended item information and a preset comprehensive matching degree calculation function.

[0100] Optionally, the recommended item information generating module 62 includes:

[0101] The historical scene information acquisition submodule is used to acquire, based on a preset historical database and according to the first geographic location information, a plurality of first historical scene information of a first user and first historical moment information corresponding to each first historical scene information, and to acquire, based on the second geographic location information, a plurality of second historical scene information of a second user and second historical moment information corresponding to each second historical scene information;

[0102] Sampling time range information generation submodule: used to generate sampling time range information according to current time information and preset fault tolerance time value information;

[0103] A matching scene information determination submodule: used to determine at least one first matching scene information according to the sampling time range information and the first historical moment information, and to determine at least one second matching scene information according to the sampling time range information and the second historical moment information, wherein the first matching scene information is used to describe the first historical scene information of the first historical moment information within the sampling time range information, and the second matching scene information is used to describe the second historical scene information of the second historical moment information within the sampling time range information;

[0104] A historical light intensity value information acquisition submodule: used to acquire, according to a historical database, first historical light intensity value information corresponding to each first matching scene information and second historical light intensity value information corresponding to each second matching scene information;

[0105] Deviation light intensity threshold information first judgment submodule: used to judge whether the difference between the first historical light intensity value information and the first ambient light intensity value information is less than the preset deviation light intensity threshold information;

[0106] A first recommended item information determination submodule: for determining that the user-selected item corresponding to the first matching scene information is the first recommended item information if the difference between the first historical light intensity value information and the first ambient light intensity value information is less than the deviation light intensity threshold information;

[0107] Deviation light intensity threshold information second judgment submodule: used to judge whether the difference between the second historical light intensity value information and the second ambient light intensity value information is less than the deviation light intensity threshold information;

[0108] The second recommended item information determination submodule is used to determine that the user-selected item corresponding to the second matching scene information is the second recommended item information if the difference between the second historical light intensity value information and the second ambient light intensity value information is less than the deviation light intensity threshold information.

[0109] Optionally, the target recommendation item information generating module 63 includes:

[0110] The historical average consumption amount information acquisition submodule is used to acquire the first historical average consumption amount information and the first cumulative selection number information corresponding to each first recommended item information, and acquire the second historical average consumption amount information and the second cumulative selection number information corresponding to each second recommended item information;

[0111] Comprehensive average consumption amount information generation submodule: used to generate first comprehensive average consumption amount information according to the average value of the sum of multiple first historical average consumption amount information, and to generate second comprehensive average consumption amount information according to the average value of the sum of multiple second historical average consumption amount information, and to generate first comprehensive average selection times information according to the average value of the sum of multiple first cumulative selection times information, and to generate second comprehensive average selection times information according to the average value of the sum of multiple second cumulative selection times information;

[0112] Comprehensive average selection times information generation submodule: used to generate the third comprehensive average consumption amount information according to the average of the sum of the first comprehensive average consumption amount information and the second comprehensive average consumption amount information, and to generate the third comprehensive average selection times information according to the average of the sum of the first comprehensive average selection times information and the second comprehensive average selection times information;

[0113] The first matching degree information generating submodule is used to generate the first matching degree information for each first recommended item information according to the first historical average consumption amount information, the first comprehensive average consumption amount information, the third comprehensive average consumption amount information, the first cumulative number of selections information, the first comprehensive average number of selections information, the third comprehensive average number of selections information and a preset comprehensive matching degree calculation function;

[0114] Second matching degree information submodule: for each second recommended item information: generating second matching degree information according to the second historical average consumption amount information, the second comprehensive average consumption amount information, the third comprehensive average consumption amount information, the second cumulative number of selections information, the second comprehensive average number of selections information, the third comprehensive average number of selections information and the comprehensive matching degree calculation function;

[0115] Target recommendation item information determination submodule: used to determine target recommendation item information according to the first matching degree information and the second matching degree information;

[0116] Optionally, the above-mentioned target recommendation item information determination submodule includes:

[0117] A preliminary selection item information determining unit: used to determine the first recommended item information corresponding to the smallest first matching degree information as the first preliminary selection item information, and determine the second recommended item information corresponding to the smallest second matching degree information as the second preliminary selection item information;

[0118] A matching degree information judging unit: used to judge whether the first matching degree information of the first preliminary selected item information is less than or equal to the second matching degree information of the second preliminary selected item information;

[0119] Target recommendation item information determination unit: used to determine the first preliminary item information as the target recommendation item information if the first matching degree information of the first preliminary item information is less than or equal to the second matching degree information of the second preliminary item information, and otherwise determine the second preliminary item information as the target recommendation item information.

[0120] Optionally, the system 60 further includes:

[0121] An identity information acquisition module: used to acquire first identity information of a first user and second identity information of a second user;

[0122] Record data packet information generation module: used to generate record data packet information according to current time information, first identity identification information, second identity identification information and target recommended item information.

[0123] It should be noted that the information interaction, execution process and other contents between the above-mentioned modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0124] The present application also provides a terminal device, such as Figure 7 As shown, the terminal device 70 of this embodiment includes: a processor 71, a memory 72, and a computer program 73 stored in the memory 72 and executable on the processor 71. When the processor 71 executes the computer program 73, the steps in the above-mentioned personalized recommendation method embodiment are implemented, for example Figure 1 Steps S100 to S300 shown; or, when the processor 71 executes the computer program 73, the functions of each module in the above device are realized, for example Figure 6 The functions of modules 61 to 63 are shown.

[0125] The terminal device 70 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server, and the terminal device 70 includes but is not limited to a processor 71 and a memory 72. Those skilled in the art will appreciate that Figure 7 It is only an example of the terminal device 70 and does not constitute a limitation of the terminal device 70. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device 70 may also include input and output devices, network access devices, buses, etc.

[0126] Among them, the processor 71 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.; the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0127] The memory 72 may be an internal storage unit of the terminal device 70, such as a hard disk or memory of the terminal device 70, or the memory 72 may be an external storage device of the terminal device 70, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 70; further, the memory 72 may include both an internal storage unit and an external storage device of the terminal device 70, and the memory 72 may also store a computer program 73 and other programs and data required by the terminal device 70, and the memory 72 may also be used to temporarily store data that has been output or is to be output.

[0128] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps of each of the above method embodiments can be implemented. Among them, the computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form, etc.; the computer-readable medium may include: any entity or device that can carry computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0129] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, all equivalent changes made according to the methods, principles, and structures of the present application should be included in the protection scope of the present application.

Claims

1. A personalized recommendation method based on user scenarios, characterized in that: The method comprises: Acquire current time information, and acquire first scene information of a first user and second scene information of a second user, wherein the first scene information includes first geographic location information and first ambient light intensity value information, and the second scene information includes second geographic location information and second ambient light intensity value information; generating first recommended item information according to the current time information, the first geographical location information, and the first ambient light intensity value information, and generating second recommended item information according to the current time information, the second geographical location information, and the second ambient light intensity value information; Generate target recommended item information according to the first recommended item information, the second recommended item information and a preset comprehensive matching degree calculation function; The step of generating first recommended item information according to the current time information, the first geographical location information, and the first ambient light intensity value information, and generating second recommended item information according to the current time information, the second geographical location information, and the second ambient light intensity value information includes: Based on a preset historical database, obtaining, according to the first geographic location information, a plurality of first historical scene information of the first user and first historical moment information corresponding to each of the first historical scene information, and, according to the second geographic location information, obtaining a plurality of second historical scene information of the second user and second historical moment information corresponding to each of the second historical scene information; Generate sampling time range information according to the current time information and preset fault tolerance time value information; Determine at least one first matching scene information according to the sampling time range information and the first historical moment information, and determine at least one second matching scene information according to the sampling time range information and the second historical moment information, wherein the first matching scene information is used to describe the first historical scene information of the first historical moment information within the sampling time range information, and the second matching scene information is used to describe the second historical scene information of the second historical moment information within the sampling time range information; According to the historical database, obtaining first historical light intensity value information corresponding to each of the first matching scene information and second historical light intensity value information corresponding to each of the second matching scene information; Determine whether the difference between the first historical light intensity value information and the first ambient light intensity value information is less than a preset deviation light intensity threshold information; If the difference between the first historical light intensity value information and the first ambient light intensity value information is less than the deviation light intensity threshold information, determining that the user-selected item corresponding to the first matching scene information is the first recommended item information; Determine whether the difference between the second historical light intensity value information and the second ambient light intensity value information is less than the deviation light intensity threshold information; If the difference between the second historical light intensity value information and the second ambient light intensity value information is less than the deviation light intensity threshold information, determining that the user selected item corresponding to the second matching scene information is the second recommended item information; The step of generating target recommended item information according to the first recommended item information, the second recommended item information and a preset comprehensive matching degree calculation function includes: Acquire the first historical average consumption amount information and the first cumulative selection number information corresponding to each of the first recommended item information, and acquire the second historical average consumption amount information and the second cumulative selection number information corresponding to each of the second recommended item information; Generate first comprehensive average consumption amount information based on the average of the sum of the plurality of first historical average consumption amount information, generate second comprehensive average consumption amount information based on the average of the sum of the plurality of second historical average consumption amount information, generate first comprehensive average selection times information based on the average of the sum of the plurality of first cumulative selection times information, and generate second comprehensive average selection times information based on the average of the sum of the plurality of second cumulative selection times information; Generating third comprehensive average consumption amount information according to the average value of the sum of the first comprehensive average consumption amount information and the second comprehensive average consumption amount information, and generating third comprehensive average selection number information according to the average value of the sum of the first comprehensive average selection number information and the second comprehensive average selection number information; For each of the first recommended item information: generating first matching degree information according to the first historical average consumption amount information, the first comprehensive average consumption amount information, the third comprehensive average consumption amount information, the first cumulative number of selections information, the first comprehensive average number of selections information, the third comprehensive average number of selections information and a preset comprehensive matching degree calculation function; For each of the second recommended item information: generating second matching degree information according to the second historical average consumption amount information, the second comprehensive average consumption amount information, the third comprehensive average consumption amount information, the second cumulative number of selections information, the second comprehensive average number of selections information, the third comprehensive average number of selections information and the comprehensive matching degree calculation function; Determining the target recommended item information according to the first matching degree information and the second matching degree information; Wherein, the comprehensive matching degree calculation function is: ， In the formula, is a first correction factor, the value range of the first correction factor is 1.14 to 1.28, is the second correction factor, the value range of the second correction factor is 1.38 to 1.44, is the third comprehensive average consumption amount information, is the third comprehensive average selection times information, when the calculation object is the first recommended item information, is the first matching degree information, is the first historical average consumption amount information, is the first comprehensive average consumption amount information, is the first cumulative selection times information, is the first comprehensive average selection times information, when the calculation object is the second recommended item information, is the second matching degree information, is the second historical average consumption amount information, The second comprehensive average consumption amount information is: is the second cumulative selection times information, This is the second comprehensive average selection times information.

2. The method according to claim 1, characterized in that The determining the target recommended item information according to the first matching degree information and the second matching degree information includes: Determine that the first recommended item information corresponding to the smallest first matching degree information is the first preliminary selected item information, and determine that the second recommended item information corresponding to the smallest second matching degree information is the second preliminary selected item information; Determining whether the first matching degree information of the first preliminary selected item information is less than or equal to the second matching degree information of the second preliminary selected item information; If the first matching degree information of the first preliminary selected item information is less than or equal to the second matching degree information of the second preliminary selected item information, the first preliminary selected item information is determined to be the target recommended item information; otherwise, the second preliminary selected item information is determined to be the target recommended item information.

3. The method according to claim 1, characterized in that After generating target recommended item information according to the first recommended item information, the second recommended item information and a preset comprehensive matching degree calculation function, the method further includes: Acquire first identity information of the first user and second identity information of the second user; Generate record data packet information according to the current time information, the first identity identification information, the second identity identification information and the target recommended item information.

4. A personalized recommendation system based on user scenarios, characterized in that: The system comprises: A location scene information acquisition module: used to acquire current time information, and acquire first location scene information of a first user and second location scene information of a second user, wherein the first location scene information includes first geographic location information and first ambient light intensity value information, and the second location scene information includes second geographic location information and second ambient light intensity value information; A recommended item information generating module: used to generate first recommended item information according to the current time information, the first geographical location information and the first ambient light intensity value information, and to generate second recommended item information according to the current time information, the second geographical location information and the second ambient light intensity value information; Target recommendation item information generation module: used to generate target recommendation item information according to the first recommendation item information, the second recommendation item information and a preset comprehensive matching degree calculation function; Wherein, the recommended item information generation module includes: A historical scene information acquisition submodule: used to acquire, based on a preset historical database and according to the first geographic location information, a plurality of first historical scene information of the first user and first historical moment information corresponding to each of the first historical scene information, and to acquire, based on the second geographic location information, a plurality of second historical scene information of the second user and second historical moment information corresponding to each of the second historical scene information; Sampling time range information generation submodule: used to generate sampling time range information according to the current time information and preset fault tolerance time value information; A matching scene information determination submodule: used to determine at least one first matching scene information according to the sampling time range information and the first historical moment information, and to determine at least one second matching scene information according to the sampling time range information and the second historical moment information, wherein the first matching scene information is used to describe the first historical scene information of the first historical moment information within the sampling time range information, and the second matching scene information is used to describe the second historical scene information of the second historical moment information within the sampling time range information; A historical light intensity value information acquisition submodule: used to acquire, according to the historical database, first historical light intensity value information corresponding to each of the first matching scene information and second historical light intensity value information corresponding to each of the second matching scene information; Deviation light intensity threshold information first judgment submodule: used to judge whether the difference between the first historical light intensity value information and the first ambient light intensity value information is less than the preset deviation light intensity threshold information; A first recommended item information determination submodule: configured to determine that the user-selected item corresponding to the first matching scene information is the first recommended item information if the difference between the first historical light intensity value information and the first ambient light intensity value information is less than the deviation light intensity threshold information; Deviation light intensity threshold information second judgment submodule: used to judge whether the difference between the second historical light intensity value information and the second ambient light intensity value information is less than the deviation light intensity threshold information; A second recommended item information determination submodule: configured to determine that the user-selected item corresponding to the second matching scene information is the second recommended item information if the difference between the second historical light intensity value information and the second ambient light intensity value information is less than the deviation light intensity threshold information; Wherein, the target recommendation item information generation module includes: The historical average consumption amount information acquisition submodule is used to acquire the first historical average consumption amount information and the first cumulative selection number information corresponding to each of the first recommended item information, and acquire the second historical average consumption amount information and the second cumulative selection number information corresponding to each of the second recommended item information; A comprehensive average consumption amount information generating submodule: used to generate first comprehensive average consumption amount information according to the average value of the sum of the plurality of first historical average consumption amount information, and to generate second comprehensive average consumption amount information according to the average value of the sum of the plurality of second historical average consumption amount information, and to generate first comprehensive average selection times information according to the average value of the sum of the plurality of first cumulative selection times information, and to generate second comprehensive average selection times information according to the average value of the sum of the plurality of second cumulative selection times information; A comprehensive average selection times information generating submodule: used to generate the third comprehensive average consumption amount information according to the average value of the sum of the first comprehensive average consumption amount information and the second comprehensive average consumption amount information, and to generate the third comprehensive average selection times information according to the average value of the sum of the first comprehensive average selection times information and the second comprehensive average selection times information; The first matching degree information generating submodule is used to generate the first matching degree information for each of the first recommended item information according to the first historical average consumption amount information, the first comprehensive average consumption amount information, the third comprehensive average consumption amount information, the first cumulative number of selections information, the first comprehensive average number of selections information, the third comprehensive average number of selections information and a preset comprehensive matching degree calculation function; The second matching degree information submodule is used to generate the second matching degree information for each of the second recommended item information according to the second historical average consumption amount information, the second comprehensive average consumption amount information, the third comprehensive average consumption amount information, the second cumulative number of selections information, the second comprehensive average number of selections information, the third comprehensive average number of selections information and the comprehensive matching degree calculation function; A target recommendation item information determination submodule: configured to determine the target recommendation item information according to the first matching degree information and the second matching degree information; Wherein, the comprehensive matching degree calculation function is: ， In the formula, is a first correction factor, the value range of the first correction factor is 1.14 to 1.28, is the second correction factor, the value range of the second correction factor is 1.38 to 1.44, is the third comprehensive average consumption amount information, is the third comprehensive average selection times information, when the calculation object is the first recommended item information, is the first matching degree information, is the first historical average consumption amount information, is the first comprehensive average consumption amount information, is the first cumulative selection times information, is the first comprehensive average selection times information, when the calculation object is the second recommended item information, is the second matching degree information, is the second historical average consumption amount information, The second comprehensive average consumption amount information is: is the second accumulated selection times information, This is the second comprehensive average selection times information.

5. The system according to claim 4, characterized in that The system further comprises: An identity information acquisition module: used to acquire the first identity information of the first user and the second identity information of the second user; Record data packet information generation module: used to generate record data packet information according to the current time information, the first identity identification information, the second identity identification information and the target recommended item information.

6. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images