Point resource recommendation method, device, and electronic device

Abstract

The embodiments of the present application are applicable to the field of data processing technology, and provide a method, device, and electronic device for recommending point resources. The method includes: obtaining historical behavior data; the historical behavior data includes behavior information related to each account and point resources; for a target account among the accounts, determining a characteristic account of the target account based on the historical behavior data; and determining first point resource recommendation data based on the behavior information of the characteristic account. Based on the first point resource recommendation data, target recommendation data for the target account is generated. The embodiments of the present application can improve the degree of adaptation between the target recommendation data output by the video platform in the security field and the target account, and improve the accuracy of point resource recommendation.

Description

Technical Field

[0001] The embodiments of the present application belong to the field of data processing technology, and in particular, relate to a method, device, and electronic device for recommending point resources. Background Art

[0002] On some security video platforms, users can view video data from different locations after logging into the platform with authorization. In order to improve the user experience, the platform needs to recommend video data to users.

[0003] In the content recommendation methods of platforms in other fields, a promotional content database is usually set up first and the user is profiled. When the user logs in to the platform, the product demand information is obtained based on the user's behavioral characteristic information and profile, and several products in the promotional content database that are highly similar to the product demand information are recommended to the user.

[0004] However, the security video platform does not have a promotional content database, and the user's operation characteristics are relatively simple, so it is impossible to distinguish different users by profiling them. The current content recommendation method is not suitable for the security video platform, and a point resource recommendation method suitable for the security video platform is urgently needed. Summary of the invention

[0005] In view of this, the embodiments of the present application provide a method, device, electronic device and computer program product for recommending point resources, so as to improve the degree of adaptation between target recommendation data and target account and improve the accuracy of point resource recommendation.

[0006] A first aspect of an embodiment of the present application provides a method for recommending point resources, including:

[0007] Obtaining historical behavior data; the historical behavior data includes behavior information related to each account and point resources;

[0008] For a target account among the accounts, determining a characteristic account of the target account according to the historical behavior data;

[0009] Determining first point resource recommendation data based on the behavior information of the characteristic account;

[0010] Based on the first point resource recommendation data, target recommendation data of the target account is generated.

[0011] A second aspect of an embodiment of the present application provides a point resource recommendation device, including:

[0012] A historical behavior data acquisition module is used to acquire historical behavior data; the historical behavior data includes behavior information related to each account and point resources;

[0013] A characteristic account determination module, configured to determine, for a target account among the accounts, a characteristic account of the target account according to the historical behavior data;

[0014] A first point resource recommendation data generation module, configured to determine first point resource recommendation data based on the behavior information of the characteristic account;

[0015] The target recommendation data generating module is used to generate the target recommendation data of the target account based on the first point resource recommendation data.

[0016] A third aspect of an embodiment of the present application provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device implements the point resource recommendation method as described in the first aspect above.

[0017] A fourth aspect of the embodiments of the present application provides a computer program product, including a computer program. When the computer program is executed, the method for recommending point resources as described in the first aspect above is executed.

[0018] A fifth aspect of 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 method for recommending point resources as described in the first aspect above is implemented.

[0019] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0020] In an embodiment of the present application, historical behavior data is obtained; the historical behavior data includes behavior information related to each account and point resources; for a target account among the various accounts, a characteristic account of the target account is determined based on the historical behavior data; based on the behavior information of the characteristic account, first point resource recommendation data is determined; based on the first point resource recommendation data, target recommendation data of the target account is generated. The embodiment of the present application aims to determine a characteristic account similar to the target account through the behavior information of each account, and generate the first point resource recommendation data based on the behavior information of the characteristic account, and generate the target recommendation data displayed to the user of the target account based on the first point resource recommendation data, so as to improve the degree of adaptation of the target recommendation data and the target account and improve the accuracy of point resource recommendation. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or prior art descriptions. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a schematic diagram of a point resource recommendation method provided in an embodiment of the present application;

[0023] Figure 2 This is a schematic diagram of interaction between a user and a platform provided in an embodiment of the present application;

[0024] Figure 3 It is a schematic diagram of a first point resource data generation method provided in an embodiment of the present application;

[0025] Figure 4 This is a schematic diagram of a point resource recommendation process provided by an embodiment of the present application;

[0026] Figure 5 is a schematic diagram of a point resource recommendation device provided in an embodiment of the present application;

[0027] Figure 6 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] 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.

[0029] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0030] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0031] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0032] In addition, 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.

[0033] 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.

[0034] On some video platforms in the security field (hereinafter referred to as the platform), users can use their accounts to log in to the platform to view video data collected by points (cameras) deployed at one or more locations. In order to improve the user experience of using the above platform, the platform can recommend point resources to users, that is, it can recommend video data collected at points in different deployment locations to users. Through the embodiments of the present application, the accuracy of recommending point resources to users can be improved. The technical solution of the present application is explained below through specific embodiments.

[0035] Reference Figure 1 , shows a schematic diagram of a point resource recommendation method provided in an embodiment of the present application, which may specifically include the following steps:

[0036] Step 101, obtaining historical behavior data;

[0037] The historical behavior data includes behavior information related to each account and point resources;

[0038] After logging into the platform with an account, users can perform operations on different points, such as viewing video data at different points, or modifying relevant information at points, etc. The platform can retain the operations of each user on the platform through logs to obtain relevant behavior information.

[0039] In a specific implementation, a thread may be deployed in the platform to obtain the behavior information of the account. As an example, the behavior information may include the account identifier, operation action, point identifier, and operation time.

[0040] Step 102, for a target account among the accounts, determining a characteristic account of the target account according to the historical behavior data;

[0041] The platform can determine the target accounts in a preset manner, for example, all accounts as target accounts, or accounts that have been confirmed by users to be allowed to be recommended as target accounts. The platform determines the characteristic accounts corresponding to each target account based on the recorded behavior data. The characteristic accounts are accounts similar to the target accounts.

[0042] Behavioral information can reflect account preferences. Generally, the behavioral information of different accounts is different, but the preferences of different accounts have certain similarities. Through the behavioral information of each account, several accounts with high similarity corresponding to each account can be determined as feature accounts.

[0043] Step 103, determining first point resource recommendation data based on the behavior information of the characteristic account;

[0044] After determining the characteristic account of the target account, one or more points can be determined as the first point resource recommendation data corresponding to the target account through the behavior information of the characteristic account. It is understandable that the same target account can correspond to one or more characteristic accounts, that is, the first point resource recommendation data can be determined based on the behavior information of one or more characteristic accounts corresponding to the account.

[0045] For example, through the behavior information of accounts A, B, and C, it is obtained that account A prefers to view video data of points in area X, account B prefers to view video data of points in area Y, and account C prefers to view video data of points in areas X and Z. Since accounts A and C have the same preferred viewing area X, account C has more similar preferences to account A than account B, so account C can be used as a characteristic account of account A instead of account B as a characteristic account of account A. After determining that account C is a characteristic account of account A, the first point resource recommendation data corresponding to account A can be determined based on the behavior information of account C.

[0046] Step 104: Generate target recommendation data for the target account based on the first point resource recommendation data.

[0047] The target recommendation data is the point resource that is finally output to the target account, and the target recommendation data may include but is not limited to the first point resource recommendation data. For example, after adding or deleting point resources based on the first point resource recommendation data, the target recommendation data is obtained.

[0048] In actual applications, since determining characteristic accounts involves a large amount of behavioral information that needs to be processed, in order to avoid the situation where users need to wait when displaying target recommendation data to users, the first point resource recommendation data can be generated and stored offline, and then read and called when the target recommendation data needs to be output to the target account. The first point resource recommendation data can be updated at a certain time. For example: the first point resource recommendation data corresponding to each target account is updated every day.

[0049] The platform can output resource recommendation data to the target account when the target account is authorized or when the target account enters a designated page provided by the platform. As an example, the platform can display a pop-up window during the target account login to prompt the user who logged into the target account whether point resource recommendation is required. When confirmation is received that point resource recommendation is required, the target recommendation data is displayed to the user. As another example, the platform provides a designated page for displaying point resources recommended to users. When the target account enters the designated page, the corresponding target recommendation data is displayed to the user.

[0050] In an embodiment of the present application, historical behavior data is obtained; the historical behavior data includes behavior information related to each account and point resources; for a target account among the each account, a characteristic account of the target account is determined based on the historical behavior data; based on the behavior information of the characteristic account, first point resource recommendation data is determined; based on the first point resource recommendation data, target recommendation data of the target account is generated. The embodiment of the present application determines a characteristic account similar to the target account through the behavior information of each account, and generates the first point resource recommendation data based on the behavior information of the characteristic account, and generates the target recommendation data displayed to the user of the target account based on the first point resource recommendation data, thereby improving the degree of adaptation of the target recommendation data to the target account and improving the accuracy of point resource recommendation.

[0051] In an optional embodiment of the present application, determining the characteristic account of the target account based on the historical behavior data includes: determining the similarity between the target account and other accounts based on the historical behavior data; determining the characteristic account of the target account among the other accounts based on the similarity; wherein the other accounts are accounts among the various accounts except the target account.

[0052] The similarity calculation is performed for the behavior information of all accounts included in the historical behavior data, the similarity between each target account and other accounts is calculated, and the similarity is sorted. For each target account, several other accounts with high similarity are used as the characteristic accounts of the target account.

[0053] As the platform usage time increases and the number of accounts using the platform increases, more behavioral information is involved in determining the characteristic accounts, and the characteristic accounts are more accurate, which further makes the first point resource data obtained subsequently more compatible with the target account, and the point resource recommendations to the target account are more accurate.

[0054] In an optional embodiment of the present application, determining the similarity between the target account and other accounts based on the historical behavior data includes: determining the behavior category and its corresponding calculation rule information; calculating the similarity between the target account and the other accounts according to the calculation rule information, the behavior information of the target account, and the behavior information of the other accounts.

[0055] Since users can perform different point operations after logging into the platform, and different point operations may have different characteristics, in order to improve the accuracy of similarity calculation, corresponding similarity calculation rules, i.e., calculation rule information, can be set in advance for different types of point operations. When calculating the similarity between the target account and other accounts, different calculation rule information is called according to the corresponding point operations in the behavior information to perform similarity calculation.

[0056] In an optional embodiment of the present application, the behavior category includes a first category with a frequency characteristic, and the first category includes at least one first point operation (for example: preview, detail view, control, search, etc.); the similarity between the target account and the other accounts is calculated according to the calculation rule information, the behavior information of the target account, and the behavior information of the other accounts, including: determining the first frequency information corresponding to the behavior information of the target account; determining the second frequency information corresponding to the behavior information of the other accounts; for various first point operations, the similarity between the target account and the other accounts is calculated according to the first calculation rule corresponding to the first category, the first frequency information, and the second frequency information.

[0057] Frequency information is information related to the frequency of the user performing the first point operation (for example, frequency level, frequency value within a certain period of time, etc.). The first frequency information is the frequency information of one or more first point operations corresponding to the target account, and the second frequency information is the frequency information of one or more first point operations corresponding to other accounts.

[0058] Some of the user's point operations are repeatable operations, that is, they have frequency characteristics. The repeatable point operations are taken as first point operations, and different first point operations are divided into the first category. Therefore, the similarity between the target account and other accounts can be evaluated based on the frequency characteristics of each first point operation.

[0059] The frequency information may be a pre-divided frequency level, for example: if the frequency of a first point operation is less than a first threshold, then the frequency information of the first point operation is a low frequency; if the frequency of a first point operation is greater than the first threshold and less than a second threshold, then the frequency information of the first point operation is a medium frequency; if the frequency of a first point operation is greater than the second threshold, then the frequency information of the first point operation is a high frequency, wherein the second threshold is greater than the first threshold.

[0060] The similarity is calculated for the frequency information of each first-position operation in the behavior information of the target account and the frequency information of each first-position operation in the behavior information of other accounts. Since different first-position operations can also represent the user's preference, the similarity between the target account and other accounts can be calculated for each first-position operation.

[0061] For example, the first point operation with frequency characteristics includes preview and detail viewing. The preview frequency and detail viewing frequency of the target account are determined based on the behavior information of the target account, and the preview frequency and detail viewing frequency of other accounts are determined based on the behavior information of other accounts. The preview similarity is calculated based on the preview frequency of the target account and the preview frequency of other accounts; the detail viewing similarity is calculated based on the detail viewing frequency of the target account and the detail viewing frequency of other accounts.

[0062] The first calculation rule corresponding to the first category is the Pearson Correlation Coefficient calculation formula, that is, for the same first-point operation, the Pearson Correlation Coefficient calculation formula can be called to calculate the first frequency information of the target account and the second frequency information of other accounts, and the value determined by the Pearson Correlation Coefficient calculation formula is used as the similarity between the other accounts and the target account under the first-point operation.

[0063] In an optional embodiment of the present application, the behavior category includes a second category without a frequency characteristic; the second category includes at least one second point operation (for example, favorite, follow); the similarity between the target account and the other accounts is calculated according to the calculation rule information, the behavior information of the target account, and the behavior information of the other accounts, including: determining a first point identifier corresponding to the second point operation in the behavior information of the target account; determining a second point identifier corresponding to the second point operation in the behavior information of the other accounts; for various second point operations, the similarity between the target account and the other accounts is calculated according to the second calculation rule corresponding to the second category, the first point identifier, and the second point identifier.

[0064] The point identifier is one or more codes used to distinguish the points. The first point identifier is one or more point identifiers corresponding to any second point operation of the target account, and the second point identifier is one or more point identifiers corresponding to any second point operation of other accounts.

[0065] Some of the user's point operations do not have frequency characteristics. The point operations without frequency characteristics are determined as second point operations. Different second point operations are divided into second categories, and corresponding calculation rule information can be set for the second category. In the case that the second point operation does not have a frequency characteristic, the point identifier corresponding to the second point operation is determined, and then the degree of overlap between the target account and other accounts for the same second point operation is determined, so as to determine the similarity between the target account and other accounts. For example: for the same second point operation, the first point identifier contains the codes of 4 points, and the second point identifier contains the codes of 6 points. The similarity between the target account and other accounts can be determined by determining the degree of overlap between the first point identifier and the second point identifier (for example: the number of the same points contained in the two).

[0066] For example, the second point operation includes: collection. The first point identifier (including one or more point codes) corresponding to the collection point operation of the target account is determined based on the behavior information of the target account, and the second point identifier (including one or more point codes) corresponding to the collection point operation of other accounts is determined based on the behavior information of other accounts. The collection similarity is calculated based on the first point identifier of the target account and the second point identifier of other accounts.

[0067] The second calculation rule corresponding to the second category is the Jaccard coefficient calculation formula, that is, for the same second-point operation, the Jaccard coefficient calculation formula can be called to calculate the first-point identifier of the target account and the second-point identifiers of other accounts, and the value determined by the Jaccard coefficient calculation formula is used as the similarity between the other accounts and the target account under the second-point operation.

[0068] In an optional embodiment of the present application, determining the characteristic account of the target account in the other accounts according to the similarity includes: determining the target accounts corresponding to various point operations in the other accounts according to the similarity.

[0069] Since the target account may include multiple first-point operations and multiple second-point operations, the characteristic accounts of the target account may be determined for different point operations to make the characteristic accounts more refined. For example, after calculating the preview similarity, detail viewing similarity, and favorite similarity between the target account and other accounts, at least one characteristic account may be determined for the preview similarity, detail viewing similarity, and favorite similarity, and the preview similarity, detail viewing similarity, and favorite similarity may correspond to different characteristic accounts, thereby improving the accuracy of determining the characteristic accounts of the target account at different point operations.

[0070] In an optional embodiment of the present application, step 104 includes: determining second point resource recommendation data based on the behavior information of the target account within a preset time interval; and generating target recommendation data based on the first point resource recommendation data and the second point resource recommendation data.

[0071] The preset time interval can be the time between the current moment and the update of the first point location data. Since the first point location resource recommendation data is generated offline, it is updated at a fixed frequency. When the target recommendation data needs to be output to the target account, there is a certain time difference from the update time of the last update of the first point location resource recommendation data, resulting in the user's recent change in usage habits. Characteristics cannot be reflected in the recommendation results. Therefore, based on the behavioral information within the preset time interval of the target account, the second point location resource recommendation data can be determined, and the first point location resource recommendation data and the second point location resource recommendation data can be combined to generate the target recommendation data, so that the user's overall preference calculated based on all operation records of the user since using the platform, as well as the user's recent preferences are reflected in the target recommendation data, making the target recommendation data more accurate.

[0072] In an optional embodiment of the present application, generating target recommendation data according to the first point resource recommendation data and the second point resource recommendation data includes:

[0073] Determine recommendation parameters; the recommendation parameters include: a first ratio value between the first point resource recommendation data and the second point resource recommendation data, and / or, a corresponding second ratio value for different point operations; generate target recommendation data based on the recommendation parameters, the first point resource recommendation data and the second point resource recommendation data.

[0074] The first ratio value refers to the ratio between the number of points included in the first point recommendation data and the number of points included in the second point recommendation data in the target recommendation data. For example, if the first ratio value is 1:2, the number of points included in the first point resource recommendation data accounts for 1 / 3 of the number of points included in the target recommendation data, and the number of points included in the second point resource recommendation data accounts for 2 / 3 of the number of points included in the target recommendation data.

[0075] The second ratio value is the ratio of the number of points corresponding to each different point operation to the number of points included in the target recommendation data. For example, the second ratio value includes "Collection: 1:4", "Details View: 1:2", and "Preview 1:4". In the target recommendation data, the number of points selected by the feature account determined by the collection similarity accounts 1 / 4 of the number of points in the target recommendation data, the number of points selected by the feature account determined by the details view similarity accounts 1 / 2 of the number of points in the target recommendation data, and the number of points selected by the feature account determined by the preview similarity accounts 1 / 4 of the number of points in the target recommendation data.

[0076] A first ratio value of the first point resource recommendation data and the second point resource recommendation data, and / or a corresponding second ratio value of different point operations can be pre-set as a recommendation parameter. After obtaining the first point resource data and the second point resource data, the ratio of the first point resource recommendation data and the second point resource recommendation data is adjusted in combination with the recommended parameters, and / or the corresponding ratios of different point operations are adjusted to obtain the target recommended data. As an example, the first ratio value and the second ratio value are both adjustable values, and the embodiment of the present application does not limit the adjustment method of the first ratio value and the second ratio value.

[0077] In addition, the target recommendation data can be optimized, for example, by removing duplicates and sorting.

[0078] The following is a further description of the embodiments of the present application using different examples:

[0079] Reference Figure 2, showing a schematic diagram of the interaction between a user and a platform provided in an embodiment of the present application. The platform performs log monitoring by setting a thread, and stores the monitored log data (historical behavior data) in the first database. By using the historical behavior data stored in the first database to perform a scheduled task, first point resource recommendation data is generated, and the generated first point resource recommendation data is stored in the second database (Redis database). In response to the point resource recommendation triggered by the user, the platform generates second point resource recommendation data, and generates target recommendation data in combination with the second point resource recommendation data and the first point resource recommendation data read from the second database, and uses the target recommendation data to make real-time recommendations to users.

[0080] Reference Figure 3 , showing a schematic diagram of a first point resource data generation method provided by an embodiment of the present application. In a specific implementation, the first point operations include preview, detail viewing, and control (for example, arming and disarming, pan / tilt rotation, zooming, and other remote control of the camera through signaling), and the second point operations include favorites. For each first point operation, a score value corresponding to each frequency is determined, and the Pearson coefficient between accounts is calculated based on the score value, and the Jaccard coefficient is calculated for the second point operation. For each point operation, the TopN account (several characteristic users with the highest similarity) is determined, and the point recommendation resource corresponding to each point operation is determined based on the behavior information of the TopN account, and the point recommendation resources corresponding to each point operation are combined to generate the first point resource recommendation data.

[0081] For points, attribute items (such as latitude and longitude, name, visual field angle, visual field direction, visual field distance, etc.) and attribute parameters corresponding to the attribute items can be preset. When adding points, the attribute parameters can be empty or preset information, and the corresponding attribute parameters can be modified through point management. The more attribute items with modified attribute parameters, the more complete the point is.

[0082] Reference Figure 4 , showing a schematic diagram of a point resource recommendation process provided in an embodiment of the present application.

[0083] The platform can identify the account logged in by each user and determine whether the current account is the target account. If it is not the target account, the platform will recommend points in a preset manner, including: obtaining the point governance status (the degree of perfection of the point), sorting according to the point governance status, obtaining the point resources with the best governance, and displaying the points with the best governance (highest degree of perfection) as real-time recommended point resources to users. If the current account is the target account, the first point resource recommendation data is read, and the second point resource recommendation data is generated after obtaining the behavior information of the target account within a preset time interval. After obtaining the recommendation parameters, the target recommendation data is generated based on the first point resource recommendation data, the second point resource recommendation data and the recommendation parameters, and the target recommendation data is displayed to the user to make real-time recommendations for the target account.

[0084] 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.

[0085] Reference Figure 5 , shows a schematic diagram of a point resource recommendation device provided in an embodiment of the present application, which may specifically include a historical behavior data acquisition module 501, a feature account determination module 502, a first point resource recommendation data generation module 503, and a target recommendation data generation module 504, wherein:

[0086] The historical behavior data acquisition module 501 is used to acquire historical behavior data; the historical behavior data includes behavior information related to each account and point resources;

[0087] A characteristic account determination module 502 is used to determine a characteristic account of a target account among the accounts according to the historical behavior data;

[0088] A first point resource recommendation data generation module 503, configured to determine first point resource recommendation data based on the behavior information of the characteristic account;

[0089] The target recommendation data generating module 504 is configured to generate the target recommendation data of the target account based on the first point resource recommendation data.

[0090] In an optional embodiment of the present application, the characteristic account determination module 502 includes:

[0091] A similarity determination submodule, used to determine the similarity between the target account and other accounts based on the historical behavior data;

[0092] A characteristic account determination submodule, used to determine the characteristic account of the target account among the other accounts according to the similarity;

[0093] The other accounts are accounts other than the target account among the accounts.

[0094] In an optional embodiment of the present application, the similarity determination submodule includes:

[0095] A calculation rule determination unit, used to determine the behavior category and its corresponding calculation rule information;

[0096] The similarity determination unit is used to calculate the similarity between the target account and the other accounts according to the calculation rule information, the behavior information of the target account, and the behavior information of the other accounts.

[0097] In an optional embodiment of the present application, the behavior category includes a first category with a frequency feature, the first category includes at least one first point operation; the similarity determination unit includes:

[0098] A first frequency information determining subunit, configured to determine first frequency information corresponding to the behavior information of the target account;

[0099] A second frequency information determining subunit, configured to determine the second frequency information corresponding to the behavior information of the other account;

[0100] The similarity determination first subunit is used to calculate the similarity between the target account and the other accounts according to the first calculation rule corresponding to the first category, the first frequency information, and the second frequency information for various first point operations.

[0101] In an optional embodiment of the present application, the behavior category includes a second category without a frequency feature; the second category includes at least one second point operation; and the similarity determination unit includes:

[0102] A first quantity information determination subunit is used to determine a first point position identifier corresponding to the second point position operation in the behavior information of the target account;

[0103] A second quantity information determination subunit, configured to determine a second point position identifier corresponding to the second point position operation in the behavior information of the other account;

[0104] The similarity determination second subunit is used to calculate the similarity between the target account and the other accounts according to the second calculation rule corresponding to the second category, the first point identifier, and the second point identifier for various second point operations.

[0105] In an optional embodiment of the present application, the feature account determination submodule is used to determine the target accounts corresponding to various point operations in the other accounts based on the similarity.

[0106] In an optional embodiment of the present application, the target recommendation data generating module 504 includes:

[0107] A second point resource recommendation data determination submodule, configured to determine the second point resource recommendation data based on the behavior information of the target account within a preset time interval;

[0108] The target recommendation data generation submodule is used to generate target recommendation data according to the first point resource recommendation data and the second point resource recommendation data.

[0109] In an optional embodiment of the present application, the target recommendation data generation submodule includes:

[0110] A recommended parameter determination unit, configured to determine recommended parameters; the recommended parameters include: a first ratio value between the first point resource recommended data and the second point resource recommended data, and / or a second ratio value corresponding to different point operations;

[0111] The target recommendation data generating unit is configured to generate target recommendation data according to the recommendation parameter, the first point resource recommendation data and the second point resource recommendation data.

[0112] An embodiment of the present application provides a device for recommending point resources. By using the device, each step in the aforementioned method embodiments can be implemented.

[0113] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment part.

[0114] Reference Figure 6 , shows a schematic diagram of an electronic device provided by an embodiment of the present application. Figure 6 As shown, the electronic device 600 in the embodiment of the present application includes: a processor 610, a memory 620, and a computer program 621 stored in the memory 620 and executable on the processor 610. When the processor 610 executes the computer program 621, the steps in each embodiment of the above-mentioned point resource recommendation method are implemented, for example Figure 1 Alternatively, when the processor 610 executes the computer program 621, the functions of each module / unit in the above-mentioned device embodiments are realized, for example Figure 4 Functions of modules 401 to 404 are shown.

[0115] Exemplarily, the computer program 621 may be divided into one or more modules / units, which are stored in the memory 620 and executed by the processor 610 to complete the present application. The one or more modules / units may be a series of computer program instruction segments that can perform specific functions, and the instruction segments may be used to describe the execution process of the computer program 621 in the electronic device 600. For example, the computer program 621 may be divided into a historical behavior data acquisition module, a feature account determination module, a first point resource recommendation data generation module, and a target recommendation data generation module, and the specific functions of each module are as follows:

[0116] A historical behavior data acquisition module is used to acquire historical behavior data; the historical behavior data includes behavior information related to each account and point resources;

[0117] A characteristic account determination module, configured to determine, for a target account among the accounts, a characteristic account of the target account according to the historical behavior data;

[0118] A first point resource recommendation data generation module, configured to determine first point resource recommendation data based on the behavior information of the characteristic account;

[0119] The target recommendation data generating module is used to generate the target recommendation data of the target account based on the first point resource recommendation data.

[0120] The electronic device 600 may be a computing device such as a desktop computer or a cloud server. The electronic device 600 may include, but is not limited to, a processor 610 and a memory 620. Those skilled in the art will appreciate that Figure 6 It is only an example of the electronic device 600 and does not constitute a limitation of the electronic device 600. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 600 may also include input and output devices, network access devices, buses, etc.

[0121] The processor 610 may 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. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0122] The memory 620 may be an internal storage unit of the electronic device 600, such as a hard disk or memory of the electronic device 600. The memory 620 may also be an external storage device of the electronic device 600, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 600. Further, the memory 620 may also include both an internal storage unit of the electronic device 600 and an external storage device. The memory 620 is used to store the computer program 621 and other programs and data required by the electronic device 600. The memory 620 may also be used to temporarily store data that has been output or is to be output.

[0123] An embodiment of the present application also discloses an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device implements the point resource recommendation method as described in the aforementioned embodiments.

[0124] The embodiment of the present application further discloses 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 point resource recommendation method as described in the above-mentioned embodiments is implemented.

[0125] The embodiment of the present application further discloses a computer program product, including a computer program. When the computer program is executed, the point resource recommendation method as described in the above embodiments is executed.

[0126] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application is described in detail with reference to the above-mentioned embodiments, a person skilled in the art should understand that the technical solutions described in the above-mentioned embodiments can still be modified, or some of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for recommending point resources, characterized in that: include: Get historical behavior data; The historical behavior data includes behavior information related to each account and point resources; The behavior information is the point operations performed by each account on the point resources; For a target account among the accounts, determining a characteristic account of the target account according to the historical behavior data; Determining first point resource recommendation data based on the behavior information of the characteristic account; Based on the first point resource recommendation data, generating target recommendation data for the target account; The target recommendation data is the point resources output to the target account; The determining the characteristic account of the target account according to the historical behavior data includes: Determine the similarity between the target account and other accounts based on the historical behavior data; Determining a characteristic account of the target account among the other accounts according to the similarity; The other accounts are accounts other than the target account among the accounts; Determining the similarity between the target account and other accounts based on the historical behavior data includes: Determine the behavior category and its corresponding calculation rule information; Calculate the similarity between the target account and the other accounts according to the calculation rule information, the behavior information of the target account, and the behavior information of the other accounts; The behavior category includes a second category without a frequency feature; the second category includes at least one second point operation; and the similarity between the target account and the other accounts is calculated according to the calculation rule information, the behavior information of the target account, and the behavior information of the other accounts, including: Determine the first point identifier corresponding to each second point operation in the behavior information of the target account; Determine the second point identifier corresponding to each second point operation in the behavior information of the other account; For the same second point operation, determining the overlap degree between the first point identifier and the second point identifier to determine the overlap degree between the target account and the other accounts, and determining the similarity between the target account and the other accounts based on the overlap degree; The behavior category includes a first category with a frequency feature, the first category includes at least one first point operation; the first point operation includes at least one of point image preview, point attribute detail view, point control, and point search; the similarity between the target account and the other accounts is calculated according to the calculation rule information, the behavior information of the target account, and the behavior information of the other accounts, including: Determine first frequency information corresponding to the first point operation of the target account; Determine second frequency information corresponding to the first point operation of the other account; For various first point operations, calculate the similarity between the target account and the other accounts according to the first frequency information and the second frequency information; Determining the characteristic account of the target account from the other accounts according to the similarity includes: Determining characteristic accounts corresponding to various point operations in the other accounts according to the similarity; The generating the target recommendation data of the target account based on the first point resource recommendation data includes: Determining second point resource recommendation data based on the behavior information of the target account within a preset time interval; Generate target recommendation data according to the first point resource recommendation data and the second point resource recommendation data; The generating target recommendation data according to the first point resource recommendation data and the second point resource recommendation data comprises: Determine recommendation parameters; the recommendation parameters include a first ratio value between the first point resource recommendation data and the second point resource recommendation data, and second ratio values ​​corresponding to different point operations; the first ratio value is the ratio between the number of points included in the first point resource recommendation data and the number of points included in the second point resource recommendation data in the target recommendation data, and the second ratio value is the ratio of the number of points corresponding to each different point operation in the target recommendation data to the number of points included in the target recommendation data; Generate target recommendation data according to the recommendation parameter, the first point resource recommendation data and the second point resource recommendation data; The method further comprises: For non-target accounts, perform the following steps: Obtaining the completeness of the point resources; Outputting the point resources to the non-target account in descending order of the perfection; The point resource is provided with attribute parameters, and the perfection is used to characterize the number of modified attribute parameters of a single point resource.

2. A point resource recommendation device, characterized in that: include: A historical behavior data acquisition module is used to acquire historical behavior data; the historical behavior data includes behavior information related to each account and point resources; The behavior information is the point operations performed by each account on the point resources; A characteristic account determination module, configured to determine, for a target account among the accounts, a characteristic account of the target account according to the historical behavior data; A first point resource recommendation data generation module, configured to determine first point resource recommendation data based on the behavior information of the characteristic account; A target recommendation data generating module, configured to generate target recommendation data of the target account based on the first point resource recommendation data; The target recommendation data is the point resources output to the target account; The characteristic account determination module includes: A similarity determination submodule, used to determine the similarity between the target account and other accounts based on the historical behavior data; A characteristic account determination submodule, used to determine the characteristic account of the target account among the other accounts according to the similarity; The other accounts are accounts other than the target account among the accounts; The similarity determination submodule includes: A calculation rule determination unit, used to determine the behavior category and its corresponding calculation rule information; a similarity determination unit, configured to calculate the similarity between the target account and the other accounts according to the calculation rule information, the behavior information of the target account, and the behavior information of the other accounts; The behavior category includes a second category without frequency characteristics; the second category includes at least one second point operation; the similarity determination unit includes: A first quantity information determination subunit is used to determine a first point identifier corresponding to each second point operation in the behavior information of the target account; A second quantity information determination subunit, configured to determine a second point identifier corresponding to each second point operation in the behavior information of the other account; a second similarity determination subunit, configured to determine, for the same second point operation, a degree of overlap between the first point identifier and the second point identifier, so as to determine a degree of overlap between the target account and the other accounts, and determine a degree of similarity between the target account and the other accounts based on the degree of overlap; The behavior category includes a first category with a frequency feature, the first category includes at least one first point operation; the first point operation includes at least one of point image preview, point attribute detail view, point control, and point search; the similarity determination unit includes: A first frequency information determining subunit, configured to determine first frequency information corresponding to the first point operation of the target account; A second frequency information determining subunit, configured to determine the second frequency information corresponding to the first point operation of the other account; A first similarity determination subunit is used to calculate the similarity between the target account and the other accounts according to the first frequency information and the second frequency information for various first point operations; Determining the characteristic account of the target account from the other accounts according to the similarity includes: Determining characteristic accounts corresponding to various point operations in the other accounts according to the similarity; The target recommendation data generation module includes: A second point resource recommendation data determination submodule, configured to determine the second point resource recommendation data based on the behavior information of the target account within a preset time interval; A target recommendation data generation submodule, configured to generate target recommendation data according to the first point resource recommendation data and the second point resource recommendation data; The target recommendation data generation submodule includes: A recommended parameter determination unit, used to determine recommended parameters; the recommended parameters include: a first ratio value between the first point resource recommended data and the second point resource recommended data, and second ratio values ​​corresponding to different point operations; the first ratio value is the ratio between the number of points included in the first point resource recommended data and the number of points included in the second point resource recommended data in the target recommended data, and the second ratio value is the ratio of the number of points corresponding to each different point operation in the target recommended data to the number of points included in the target recommended data; A target recommendation data generating unit, configured to generate target recommendation data according to the recommendation parameter, the first point resource recommendation data and the second point resource recommendation data; The device also includes: a module for performing the following steps for non-target accounts; The steps include: obtaining the perfection of the point resources; outputting the point resources to the non-target account in descending order of the perfection; The point resource is provided with attribute parameters, and the perfection is used to characterize the number of modified attribute parameters of a single point resource.

3. An electronic device, characterized in that: The electronic device comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device implements the method according to claim 1.

4. A computer program product, characterized in that The invention comprises a computer program which, when executed, causes the method as claimed in claim 1 to be performed.

Images