A recommendation method and device based on user usage trajectory

Abstract

The purpose of the present application is to provide a recommendation method and device based on user usage track. Specifically, the historical usage track of one or more historical users is first obtained; then the current usage track of the current user is obtained; the current usage track is matched in the historical usage track to obtain a matching result about a recommendation object; then a weight score is assigned to the corresponding recommendation object based on the path depth of the matching result, and the multiple recommendation objects are prioritized according to the weight score of the recommendation object. Compared with the prior art, the present application solves the problem of recommending a camera when a user calls a monitoring camera. Further, the weight score of the recommendation object and the path depth of the corresponding matching result are positively correlated. The present application can achieve better recommendation effect in the scene of user calling a monitoring camera.

Description

Technical Field

[0001] The present application relates to the field of information technology, and in particular to a recommendation technology based on user usage trajectory. Background Art

[0002] In recent years, recommendation algorithms have been increasingly used, for example, in e-commerce product recommendations, music and film content recommendations, and social networking recommendations. Existing recommendation solutions primarily collect data, train models, input user data into the models, and then output recommendations. However, these solutions are not suitable for all scenarios. For example, in the case of users accessing surveillance cameras, a city may have over 100,000, or even hundreds of thousands, of cameras. Helping users quickly find the desired camera remains an unresolved problem. Summary of the Invention

[0003] One purpose of the present application is to provide a recommendation method and device based on user usage trajectory to solve the problem of recommending cameras when a user calls a surveillance camera.

[0004] According to one aspect of the present application, a recommendation method based on user usage trajectory is provided, wherein the method includes:

[0005] Obtain the historical usage traces of one or more historical users;

[0006] Get the current user's current usage track;

[0007] Matching the current usage trajectory with the historical usage trajectory to obtain a matching result for the recommended object;

[0008] Based on the path depth of the matching result, a weight score is assigned to the corresponding recommended object, and the plurality of recommended objects are prioritized according to the weight score of the recommended object.

[0009] Furthermore, the weight score of the recommended object is positively correlated with the path depth of the corresponding matching result.

[0010] Furthermore, if the path depth of the matching result is n, the weight of the corresponding recommended object is divided into 2 n-1 .

[0011] Furthermore, the priority order of the recommended objects is positively correlated with their weight scores.

[0012] Furthermore, the current usage trajectory of the current user includes:

[0013] Tracing back from the current usage record of the current user, several consecutive usage records of the current user.

[0014] Furthermore, matching is performed on the historical usage trajectory according to the current usage trajectory to obtain a matching result for the recommended object, including:

[0015] Several consecutive usage records of the current user are respectively used as preconditions, and matching is performed in the historical usage trajectory to obtain matching results for recommended objects.

[0016] Furthermore, the method further comprises:

[0017] According to the priority ranking of the plurality of recommended objects, a target number of recommended objects are selected from the plurality of recommended objects as target recommended objects.

[0018] According to another aspect of the present application, a recommendation device based on user usage trajectory is also provided, wherein the device includes:

[0019] A history track module is used to obtain the history usage tracks of one or more historical users;

[0020] The current track module is used to obtain the current usage track of the current user;

[0021] A matching module, configured to perform matching on the historical usage trajectory according to the current usage trajectory to obtain a matching result on a recommended object;

[0022] The recommendation module is used to assign weight scores to the corresponding recommended objects based on the path depths of the matching results, and to prioritize the multiple recommended objects according to the weight scores of the recommended objects.

[0023] According to another aspect of the present application, a computing device is also provided, wherein the device includes a memory for storing computer program instructions and a processor for executing the computer program instructions, wherein when the computer program instructions are executed by the processor, the device is triggered to execute the recommendation method based on user usage trajectory.

[0024] According to another aspect of the present application, a computer-readable medium is provided, on which computer program instructions are stored. The computer-readable instructions can be executed by a processor to implement the recommendation method based on user usage trajectory.

[0025] In the scheme provided in the application, the historical use trajectories of one or more historical users are acquired first; the current use trajectory of a current user is acquired; the current use trajectory is matched in the historical use trajectories to obtain a matching result about a recommended object; then a weight score is assigned to the corresponding recommended object based on the path depth of the matching result, and the multiple recommended objects are prioritized according to the weight scores of the recommended objects. Compared with the prior art, the application solves the problem of recommending a camera when a user calls a monitoring camera. Further, the weight score of the recommended object is in a positive correlation with the path depth of the corresponding matching result. The application can achieve better recommendation effect in the scene of a user calling a monitoring camera. BRIEF DESCRIPTION OF DRAWINGS

[0026] Other features, objects and advantages of the application will become more apparent from the following detailed description of non-limiting embodiments made with reference to the drawings:

[0027] Figure 1 is a flow chart of a recommendation method based on user use trajectories according to an embodiment of the application;

[0028] Figure 2 is a schematic diagram of a recommendation device based on user use trajectories according to an embodiment of the application.

[0029] The same or similar reference signs in the drawings represent the same or similar components. DETAILED DESCRIPTION

[0030] The application will be further described in detail below with reference to the drawings.

[0031] In a typical configuration of the application, the terminal, the device of the service network and the trusted party each include one or more processors (CPU), input / output interfaces, network interfaces and memories.

[0032] The memory can include a non-permanent memory in a computer readable medium, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of the computer readable medium.

[0033] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology for information storage. The information can be a device that can store computer-readable instructions, data structures, programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc-read only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0034] The embodiment of the present application provides a recommendation method based on user usage trajectory, which can achieve better recommendation effects by combining the characteristics of fixed access paths in scenarios where users call surveillance cameras.

[0035] In practical scenarios, the device implementing this method can be a user device, a network device, or a device formed by integrating a user device and a network device via a network. The user device includes, but is not limited to, terminal devices such as smartphones, tablet computers, and personal computers, and the network device includes, but is not limited to, a network host, a single network server, a set of multiple network servers, or a collection of computers based on cloud computing. Here, the cloud is composed of a large number of hosts or network servers based on cloud computing. Cloud computing is a type of distributed computing, consisting of a group of loosely coupled computers forming a virtual computer.

[0036] Figure 1 This is a flow chart of a recommendation method based on user usage trajectory according to an embodiment of the present application, the method comprising step S101, step S102, step S103 and step S104.

[0037] Step S101: Obtain historical usage traces of one or more historical users.

[0038] For example, in a scenario where a user calls a surveillance camera, the historical usage trajectory includes the path that the corresponding historical user has taken to call the camera; the path that each historical user has taken to call the camera can be recorded when each historical user uses the surveillance system. For example:

[0039] The path for user a to access the camera is: Da1→Da2→Da3→Da4;

[0040] The path for user b to access the camera is: Db1→Db2→Db3→Db4→Db5→Db6;

[0041] The path for user c to access the camera is: Dc1→Dc2→Dc3→Dc4→Dc5→Dc6→Dc7;

[0042] The path for user d to access the camera is: Dd1→Dd2→Dd3→Dd4→Dd5;

[0043] The path for user e to access the camera is: De1→De2→De3→De4→De5→De6→De7→De8;

[0044] The path for user f to call the camera is: Df1→Df2→Df3→Df4→Df5.

[0045] Step S102: Obtain the current usage track of the current user.

[0046] For example, in a scenario where a user calls a surveillance camera, the current usage trajectory includes the path taken by the current user to call the camera; after the current user logs into the surveillance system, the path taken by the current user to call the camera can be recorded.

[0047] In some embodiments, the current user's current usage trajectory includes: tracing back from the current user's current usage record, a number of consecutive usage records of the current user. For example, assuming that the current user's current camera usage path is: Dn1→Dn2→Dn3; then the current user's current usage trajectory includes: Dn1→Dn2→Dn3, Dn2→Dn3, Dn3.

[0048] Step S103 : matching the historical usage trajectory according to the current usage trajectory to obtain a matching result for a recommended object.

[0049] In some embodiments, the step S103 includes: using several consecutive usage records of the current user as preconditions, performing matching in the historical usage trajectory, and obtaining matching results for recommended objects.

[0050] For example, in the scenario where a user accesses a surveillance camera, assume that the path the current user uses to access the camera is: Dn1→Dn2→Dn3; with Dn1→Dn2→Dn3, Dn2→Dn3, and Dn3 as preconditions, matching is performed on all historical users' historical usage trajectories. Assume that the following matching results are obtained for the recommended objects:

[0051] Dn1→Dn2→Dn3→Dx1;

[0052] Dn1→Dn2→Dn3→Dx2;

[0053] Dn2→Dn3→Dx3;

[0054] Dn2→Dn3→Dx4;

[0055] Dn2→Dn3→Dx5;

[0056] Dn3→Dx6;

[0057] Dn3→Dx7;

[0058] Dn3→Dx8;

[0059] Dn3→Dx9.

[0060] Step S104 : assigning weight scores to the corresponding recommended objects based on the path depths of the matching results, and prioritizing the plurality of recommended objects according to the weight scores of the recommended objects.

[0061] In some embodiments, the weight score of the recommended object is positively correlated with the path depth of the corresponding matching result. For example, different weight scores can be set for matching results of different path depths, with the deeper the path depth, the higher the weight score.

[0062] In some embodiments, if the path depth of the matching result is n, the weight of the corresponding recommended object is divided into 2 n-1 For example, continuing the previous example, in 2 n-1 Under the weight coefficient, the weights of the recommended objects Dx1 and Dx2 are 4, the weights of the recommended objects Dx3, Dx4, and Dx5 are 2, and the weights of the recommended objects Dx6, Dx7, Dx8, and Dx9 are 1.

[0063] Of course, those skilled in the art should understand that the above n-1 The weight coefficient is only an example. Other weight coefficients, such as 3n-2, n 2 Etc., if applicable to the present application, should also be included in the scope of protection of the present application and are incorporated herein by reference.

[0064] In some embodiments, the priority order of the recommended objects is positively correlated with their weight scores. For example, continuing with the previous example, assuming that there are duplicates among the recommended objects Dx1 to Dx9, the weight scores of the duplicate recommended objects can be accumulated to obtain a final weight score for each recommended object. These recommended objects can then be prioritized based on their weight scores, with higher weight scores indicating higher priorities.

[0065] In some embodiments, the method for recommending based on user usage trajectory further includes: selecting a target number of recommended objects from the plurality of recommended objects as target recommended objects based on their priority ranking. For example, assuming the target number is m, where m can be a configuration item and can be configured to any natural number as needed, the m recommended objects with the highest priority are selected from the plurality of recommended objects as target recommended objects, and the target recommended objects can then be output to the current user.

[0066] Figure 2 2 is a schematic diagram of a recommendation device based on user usage trajectory according to an embodiment of the present application. The device includes a history trajectory module 201 , a current trajectory module 202 , a matching module 203 and a recommendation module 204 .

[0067] The history track module 201 obtains the history usage tracks of one or more historical users.

[0068] For example, in a scenario where a user calls a surveillance camera, the historical usage trajectory includes the path that the corresponding historical user has taken to call the camera; the path that each historical user has taken to call the camera can be recorded when each historical user uses the surveillance system. For example:

[0069] The path for user a to access the camera is: Da1→Da2→Da3→Da4;

[0070] The path for user b to access the camera is: Db1→Db2→Db3→Db4→Db5→Db6;

[0071] The path for user c to access the camera is: Dc1→Dc2→Dc3→Dc4→Dc5→Dc6→Dc7;

[0072] The path for user d to access the camera is: Dd1→Dd2→Dd3→Dd4→Dd5;

[0073] The path for user e to access the camera is: De1→De2→De3→De4→De5→De6→De7→De8;

[0074] The path for user f to call the camera is: Df1→Df2→Df3→Df4→Df5.

[0075] The current track module 202 obtains the current usage track of the current user.

[0076] For example, in a scenario where a user calls a surveillance camera, the current usage trajectory includes the path taken by the current user to call the camera; after the current user logs into the surveillance system, the path taken by the current user to call the camera can be recorded.

[0077] In some embodiments, the current user's current usage trajectory includes: tracing back from the current user's current usage record, a number of consecutive usage records of the current user. For example, assuming the current user's current camera usage path is: Dn1 → Dn2 → Dn3; then the current user's current usage trajectory includes: Dn1 → Dn2 → Dn3, Dn2 → Dn3, Dn3.

[0078] The matching module 203 performs matching in the historical usage trajectory according to the current usage trajectory to obtain a matching result for the recommended object.

[0079] In some embodiments, the matching module 203 is configured to use a plurality of consecutive usage records of the current user as preconditions, perform matching in the historical usage trajectory, and obtain matching results for recommended objects.

[0080] For example, in the scenario where a user accesses a surveillance camera, assume that the path the current user uses to access the camera is: Dn1→Dn2→Dn3; with Dn1→Dn2→Dn3, Dn2→Dn3, and Dn3 as preconditions, matching is performed on all historical users' historical usage trajectories. Assume that the following matching results are obtained for the recommended objects:

[0081] Dn1→Dn2→Dn3→Dx1;

[0082] Dn1→Dn2→Dn3→Dx2;

[0083] Dn2→Dn3→Dx3;

[0084] Dn2→Dn3→Dx4;

[0085] Dn2→Dn3→Dx5;

[0086] Dn3→Dx6;

[0087] Dn3→Dx7;

[0088] Dn3→Dx8;

[0089] Dn3→Dx9.

[0090] The recommendation module 204 assigns a weight score to the corresponding recommended object based on the path depth of the matching result, and prioritizes the multiple recommended objects according to the weight score of the recommended object.

[0091] In some embodiments, the weight score of the recommended object is positively correlated with the path depth of the corresponding matching result. For example, different weight scores can be set for matching results of different path depths, with the deeper the path depth, the higher the weight score.

[0092] In some embodiments, if the path depth of the matching result is n, the weight of the corresponding recommended object is divided into 2 n-1 For example, continuing the previous example, in 2 n-1 Under the weight coefficient, the weights of the recommended objects Dx1 and Dx2 are 4, the weights of the recommended objects Dx3, Dx4, and Dx5 are 2, and the weights of the recommended objects Dx6, Dx7, Dx8, and Dx9 are 1.

[0093] Of course, those skilled in the art should understand that the above n-1 The weight coefficient is only an example. Other weight coefficients, such as 3n-2, n 2 Etc., if applicable to the present application, should also be included in the scope of protection of the present application and are incorporated herein by reference.

[0094] In some embodiments, the priority order of the recommended objects is positively correlated with their weight scores. For example, continuing with the previous example, assuming that there are duplicates among the recommended objects Dx1 to Dx9, the weight scores of the duplicate recommended objects can be accumulated to obtain a final weight score for each recommended object. These recommended objects can then be prioritized based on their weight scores, with higher weight scores indicating higher priorities.

[0095] In some embodiments, the recommendation module 204 is further configured to select a target number of recommended objects from the plurality of recommended objects as target recommended objects based on the priority ranking of the plurality of recommended objects. For example, assuming the target number is m, where m can be a configuration item and can be configured to any natural number according to actual needs, the m recommended objects with the highest priority are selected from the plurality of recommended objects as target recommended objects, and the target recommended objects can then be output to the current user.

[0096] In addition, a part of the present application may be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can call or provide the method and / or technical solution according to the present application through the operation of the computer. The program instructions for calling the method of the present application may be stored in a fixed or removable recording medium, and / or transmitted through a data stream in a broadcast or other signal-carrying medium, and / or stored in a working memory of a computer device that runs according to the program instructions. Here, some embodiments of the present application provide a computing device, which includes a memory for storing computer program instructions and a processor for executing computer program instructions, wherein, when the computer program instructions are executed by the processor, the device is triggered to execute the methods and / or technical solutions of the aforementioned multiple embodiments of the present application.

[0097] In addition, some embodiments of the present application further provide a computer-readable medium on which computer program instructions are stored. The computer-readable instructions can be executed by a processor to implement the methods and / or technical solutions of the aforementioned multiple embodiments of the present application.

[0098] It should be noted that the present application can be implemented in a combination of software and / or software and hardware, for example, can be implemented using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In certain embodiments, the software program of the present application can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present application (including relevant data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the present application can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0099] It is obvious to those skilled in the art that the present application is not limited to the details of the above-mentioned exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic characteristics of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims are included in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by one unit or device through software or hardware. Words such as first and second are used to indicate names and do not indicate any particular order.

Claims

1. A recommendation method based on user usage trajectory, wherein: The method comprises: Obtaining historical usage traces of one or more historical users, wherein the historical usage traces include paths of the corresponding historical users calling the camera; Obtain the current user's current usage trajectory, which includes the path of the current user calling the camera, and trace back from the current user's current usage record to obtain several consecutive usage records of the current user; Using several consecutive usage records of the current user as preconditions, matching is performed on the historical usage trajectory to obtain matching results for recommended objects; Based on the path depth of the matching result, a weight score is assigned to the corresponding recommended object, and multiple recommended objects are prioritized according to the weight score of the recommended object. The weight score of the recommended object is positively correlated with the path depth of the corresponding matching result.

2. The method according to claim 1, wherein If the path depth of the matching result is n, the weight of the corresponding recommended object is divided into 2 n-1 .

3. The method according to claim 1, wherein The priority order of the recommended objects is positively correlated with their weight scores.

4. The method according to any one of claims 1 to 3, wherein The method further comprises: According to the priority ranking of the plurality of recommended objects, a target number of recommended objects are selected from the plurality of recommended objects as target recommended objects.

5. A recommendation device based on user usage trajectory, wherein: The device comprises: A history track module is used to obtain the history usage track of one or more history users, where the history usage track is the path of the corresponding history user calling the camera; A current track module is used to obtain the current usage track of the current user. The current usage track is the path of the current user calling the camera, including several consecutive usage records of the current user obtained by tracing back the current usage record of the current user; A matching module, configured to use a plurality of consecutive usage records of the current user as preconditions, perform matching in the historical usage trajectory, and obtain matching results for recommended objects; The recommendation module is used to assign weight scores to the corresponding recommended objects based on the path depth of the matching results, and to prioritize the multiple recommended objects according to the weight scores of the recommended objects, wherein the weight scores of the recommended objects are positively correlated with the path depth of the corresponding matching results.

6. A computing device, wherein: The device comprises a memory for storing computer program instructions and a processor for executing the computer program instructions, wherein when the computer program instructions are executed by the processor, the device is triggered to execute the method according to any one of claims 1 to 4.

7. A computer-readable medium having computer program instructions stored thereon, wherein the computer-readable instructions can be executed by a processor to implement the method according to any one of claims 1 to 4.

Images