Application recommendation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention relates to the technical field of application programs, and discloses an application recommendation method and device, electronic equipment and a storage medium. The method comprises the steps that a current application use sequence is obtained, and the current application use sequence comprises one or more first applications; application use sequence data corresponding to the first applications are obtained, and the application use sequence data are used for representing application use conditions corresponding to the target use step number after the first applications are used; application use habit data are obtained, and the application use habit data comprise use frequencies corresponding to the one or more second applications in the first historical time period; and according to the current application use sequence, the application use sequence data and the application use habit data, determining a recommended application set. By implementing the embodiment of the invention, the reference of the determined recommended application set can be improved, so that the user can quickly search the application through the recommended application set, and the use experience of the user is further improved.

Description

Technical Field

[0001] The present application relates to the field of application technology, and in particular to an application recommendation method and device, an electronic device, and a storage medium. Background Art

[0002] With the rapid development of electronic equipment technology and application development technology, today's electronic devices are usually installed with a large number of applications to meet various usage needs of users.

[0003] Since there are too many installed applications, when users want to open a certain application, they need to search among a large number of application icons. This process is rather cumbersome, thereby reducing the user experience. Summary of the invention

[0004] The embodiments of the present application disclose an application recommendation method and device, an electronic device, and a storage medium, which can improve the referenceability of a determined recommended application set, so that users can quickly find applications through the recommended application set, thereby improving the user's usage experience.

[0005] The first aspect of the present application embodiment discloses an application recommendation method, the method comprising:

[0006] Acquire a current application usage sequence, where the current application usage sequence includes one or more first applications;

[0007] Acquire application usage sequence data corresponding to each of the first applications, wherein the application usage sequence data is used to characterize application usage conditions corresponding to target usage steps after using the first application;

[0008] Acquire application usage habit data, wherein the application usage habit data includes usage frequencies corresponding to one or more second applications in a first historical time period;

[0009] A recommended application set is determined according to the current application usage sequence, the application usage order data, and the application usage habit data.

[0010] A second aspect of an embodiment of the present application discloses an application recommendation device, the device comprising:

[0011] A first acquisition unit, configured to acquire a current application usage sequence, where the current application usage sequence includes one or more first applications;

[0012] A second acquisition unit is used to acquire application usage sequence data corresponding to each of the first applications, wherein the application usage sequence data is used to characterize application usage conditions corresponding to target usage steps after using the first application;

[0013] A third acquisition unit, configured to acquire application usage habit data, wherein the application usage habit data includes usage frequencies corresponding to one or more second applications in a first historical time period;

[0014] A determination unit is used to determine a recommended application set according to the current application usage sequence, the application usage order data and the application usage habit data.

[0015] A third aspect of the present application discloses an electronic device, including:

[0016] A memory storing executable program code;

[0017] a processor coupled to the memory;

[0018] The processor calls the executable program code stored in the memory to execute the application recommendation method disclosed in the first aspect of the embodiment of the present application.

[0019] A fourth aspect of an embodiment of the present application discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the application recommendation method disclosed in the first aspect of an embodiment of the present application.

[0020] The fifth aspect of the embodiments of the present application discloses a computer program product. When the computer program product runs on a computer, the computer executes part or all of the steps of any one of the methods of the first aspect of the embodiments of the present application.

[0021] A sixth aspect of an embodiment of the present application discloses an application publishing platform, which is used to publish a computer program product. When the computer program product runs on a computer, the computer executes part or all of the steps of any one of the methods of the first aspect of the embodiment of the present application.

[0022] Compared with the related art, the embodiments of the present application have the following beneficial effects:

[0023] In the embodiment of the present application, the current application usage sequence can be obtained, and the current application usage sequence includes one or more first applications; then the application usage sequence data corresponding to each first application can be obtained, and the application usage sequence data is used to characterize the application usage corresponding to the target number of steps after using the first application; and the application usage habit data is obtained, and the application usage habit data includes the usage frequency corresponding to one or more second applications in the first historical time period; then, the recommended application set can be determined according to the current application usage sequence, the application usage sequence data and the application usage habit data. It can be seen that the application recommendation method disclosed in the embodiment of the present application combines the application usage data of the three dimensions of the current application usage sequence, the application usage sequence data and the application usage habit data, that is, it takes into account the historical application usage and the current application usage, so that a more accurate recommended application set can be predicted, so that the user can quickly find the application through the recommended application set to meet the user's application recommendation needs at the current moment, thereby improving the user's usage experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 It is a flowchart of an application recommendation method disclosed in an embodiment of the present application;

[0026] Figure 2 It is a flowchart of another application recommendation method disclosed in an embodiment of the present application;

[0027] Figure 3 is a schematic diagram of a process for determining a first application set disclosed in an embodiment of the present application;

[0028] Figure 4 It is a schematic diagram of a process of determining a recommended application set disclosed in an embodiment of the present application;

[0029] Figure 5 It is a flowchart of another application recommendation method disclosed in the embodiment of the present application;

[0030] Figure 6 is a flow chart of counting application usage sequence data corresponding to a fourth application disclosed in an embodiment of the present application;

[0031] Figure 7 is a structural schematic diagram of an application recommendation device disclosed in an embodiment of the present application;

[0032] Figure 8 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0034] It should be noted that the terms "first", "second", "third" and "fourth" in the specification and claims of the present application are used to distinguish different objects rather than to describe a specific order. The terms "including" and "having" in the embodiments of the present application and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device including a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] The embodiments of the present application disclose an application recommendation method and device, an electronic device, and a storage medium, which can improve the referenceability of a determined recommended application set, so that users can quickly find applications through the recommended application set, thereby improving the user's usage experience.

[0036] The technical solution of the present application will be described in detail below in conjunction with specific embodiments.

[0037] In order to more clearly introduce the application recommendation method disclosed in the embodiment of the present application. First, the application scenario applicable to the method is introduced. Optionally, the method can be applied to various electronic devices, including but not limited to portable electronic devices such as mobile phones and tablet computers, wearable devices such as smart watches and smart bracelets, or desktop devices such as desktop computers and desktop TVs, which are not limited here.

[0038] With the rapid development of electronic equipment technology and application development technology, today's electronic devices are usually installed with a large number of applications to meet various usage needs of users.

[0039] However, when users actually use electronic devices, due to the large number of installed applications, when users want to open an application, they need to find the icon of the target application among a large number of application icons and then open it. This process is rather cumbersome.

[0040] In practice, it is found that the application recommendation method in the related art can consider the user's historical usage data and obtain the applications that the user has frequently used in the past, but this cannot meet the user's current application search needs. That is, the recommended applications predicted in the related art are relatively single and not accurate enough to meet the user's needs, thereby reducing the user's usage experience.

[0041] In this regard, the present application embodiment provides an application recommendation method to solve the technical defects in the related art. Optionally, the application recommendation method provided by the present application embodiment can be applied to various electronic devices or other execution entities (such as cloud servers) introduced above, which is not limited here.

[0042] Optionally, the electronic device can obtain the current application usage sequence, which includes one or more first applications; and then obtain application usage sequence data corresponding to each first application, the application usage sequence data is used to characterize the application usage corresponding to the target number of steps after using the first application; and obtain application usage habit data, the application usage habit data includes the usage frequency corresponding to one or more second applications in the first historical time period; and then, the electronic device can determine the recommended application set according to the current application usage sequence, the application usage sequence data and the application usage habit data. It can be seen that the application recommendation method disclosed in the embodiment of the present application combines the application usage data of three dimensions, namely, the current application usage and the historical application usage are taken into account, so that a more accurate recommended application set can be predicted, so that the user can quickly find the application through the recommended application set to meet the user's application recommendation needs, thereby improving the user's usage experience.

[0043] Based on this, the application recommendation method and device, electronic device, and storage medium disclosed in the embodiments of the present application are introduced below.

[0044] See also Figure 1 , Figure 1 1 is a flowchart of an application recommendation method disclosed in an embodiment of the present application. Optionally, the method can be applied to various electronic devices or other execution entities introduced above, which are not limited here. Optionally, the method can include the following steps:

[0045] 102. Obtain a current application usage sequence, where the current application usage sequence includes one or more first applications.

[0046] In the embodiment of the present application, the electronic device can obtain the current application usage sequence by checking the application running log or by setting a data collection script in various applications.

[0047] In one embodiment, the current application usage sequence may represent the first application used by the electronic device within the last first time period, that is, the current application usage sequence may reflect the most recent application usage of the electronic device.

[0048] Optionally, the current application usage sequence may include: the first application used by the electronic device within a first time period before and at the current moment. The first time period may be set by a developer based on a large amount of development experience, or by a user based on actual usage requirements, and typical values ​​may include: one day, three days, five days, or one week, etc., which are not limited here.

[0049] Optionally, the first application may be an application that has been installed by the electronic device. In another embodiment, the first application may not include an application that has been installed by the electronic device but has been uninstalled, thereby avoiding the subsequent recommendation of the uninstalled application to the user, thereby improving the intelligence of the method and the accuracy of the recommendation.

[0050] Optionally, the first application may include: system applications and / or third-party applications. Among them: system applications may include various applications installed by default in the electronic device system, including: photo applications, address book applications, calendar applications, email applications, or memo applications, etc., which are not limited here.

[0051] The third method application may include applications downloaded by the electronic device from a third-party application store or the Internet, including: short video applications, music applications or game applications, etc., which are not limited here.

[0052] In an optional embodiment, the current application usage sequence may also include usage moments corresponding to one or more first applications. Optionally, the one or more first applications may be sorted according to usage moments, for example, sorted in order from recent to most recent usage moments, etc., which is not limited here. This facilitates the subsequent sorting and statistics of the current application usage sequence.

[0053] 104. Obtain application usage sequence data corresponding to each first application, where the application usage sequence data is used to characterize application usage situations corresponding to target usage steps after using the first application.

[0054] In the embodiment of the present application, each first application may correspond to an application usage sequence data, and the application usage sequence data is used to characterize the application usage corresponding to the target usage steps after using the first application.

[0055] In one embodiment, the application usage sequence data corresponding to the first application includes: application usage probability data corresponding to the target number of usage steps after using the first application, wherein the application usage probability data corresponding to the Nth step includes the usage probabilities corresponding to one or more third applications in the Nth step after using the first application, and N is a positive integer.

[0056] For example, assuming that after using the first application A: the application usage probability data corresponding to the first step may include: "third application A (30%), third application B (60%) and third application C (10%)";

[0057] The application usage probability data corresponding to the second step may include: "third application D (60%), third application B (20%), and third application E (20%)";

[0058] …Step N… is not limited here.

[0059] In the embodiment of the present application, N can be a positive integer, and N can be set by a developer based on a large amount of development experience, or by a user based on actual usage requirements, and is not limited here.

[0060] It can be seen that the application usage probability data corresponding to each step can reflect the probability of each third application that may be used by the electronic device in the corresponding number of usage steps.

[0061] In summary, the application usage sequence data corresponding to the first application can reflect the usage sequence of the third application that the electronic device may use after using the first application. For example, suppose that after using the first application A, the third application B is used in the first step, the third application D is used in the second step, and so on.

[0062] In an optional embodiment, the electronic device may collect statistics of application usage sequence data corresponding to each first application according to the corresponding historical application usage sequence in the second historical time period.

[0063] Among them, multiple fourth applications may include one or more first applications introduced above; the historical application usage sequence includes multiple fourth applications arranged in order of usage; the historical second time period can be set by developers based on a large amount of development experience, or by users based on actual usage needs. Typical values ​​may include: the past month, the past six months, etc., which are not limited here.

[0064] In another optional embodiment, the electronic device may count application usage sequence data corresponding to each fourth application in advance based on the corresponding historical application usage sequence within the second historical time period; and then subsequently may determine application usage sequence data corresponding to the corresponding first application based on the application usage sequence data corresponding to multiple fourth applications.

[0065] Exemplarily, the electronic device has previously counted the application usage sequence data corresponding to the fourth application A and the fourth application B, respectively, and the fourth application A corresponds to the first application A (that is, the two are the same application), and the fourth application B corresponds to the first application C, then the electronic device can directly determine the application usage sequence data corresponding to the fourth application A as the application usage sequence data corresponding to the first application A; and determine the application usage sequence data corresponding to the fourth application B as the application usage sequence data corresponding to the first application C, without limitation herein.

[0066] By implementing the above method, the electronic device can count in advance the application usage sequence data corresponding to the applications included in the electronic device, and then can directly determine the application usage sequence data corresponding to each first application included in the current application usage sequence based on the data counted in advance, thereby improving the efficiency of obtaining the application usage sequence data corresponding to each first application.

[0067] 106. Obtain application usage habit data, where the application usage habit data includes usage frequencies corresponding to one or more second applications in a first historical time period.

[0068] In the embodiment of the present application, the first historical time period can be set by the developer based on a large amount of development experience, or by the user based on actual usage requirements, and a typical value can include the past week, the past month, etc., which is not limited here. Optionally, the first historical time period and the second historical time period described above can be the same or different, which is not limited here.

[0069] Optionally, the electronic device may obtain the usage counts of one or more second applications respectively within the first historical time period, and the total usage counts of the applications within the first historical time period; wherein the total usage counts of the applications may include the total usage counts of all second applications within the first historical time period.

[0070] Then, the electronic device may calculate the ratio between the usage count of each second application and the total usage count of the application as the usage frequency of the corresponding second application.

[0071] For example, assuming that the total number of application uses is 100 times, among which the number of times the second application A is used is 16, then the corresponding usage frequency of the second application A is 16%; assuming that the number of times the second application B is used is 36, then the corresponding usage frequency of the second application B is 36%, which is not limited here.

[0072] Optionally, the electronic device may sort the second applications according to usage frequency (eg, sort them in descending order of usage frequency) to obtain application usage habit data. Optionally, the application usage habit data may include usage frequencies corresponding to the second applications.

[0073] In summary, the application usage habit data can reflect the application usage habits of the electronic device in the first historical time period, that is, which applications the user frequently uses.

[0074] 108. Determine a recommended application set based on the current application usage sequence, application usage order data, and application usage habit data.

[0075] In an embodiment of the present application, the electronic device may perform statistical calculations based on the current application usage sequence, application usage order data, and application usage habit data introduced above to determine a recommended application set from multiple dimensions.

[0076] In an optional embodiment, the electronic device may merge the applications respectively included in the current application usage sequence, the application usage order data, and the application usage habit data, and sort them according to the usage frequency to obtain a recommended application set.

[0077] By implementing the methods disclosed in the above embodiments, it is possible to obtain the current application usage sequence, which includes one or more first applications; further, it is possible to obtain application usage sequence data corresponding to each first application, and the application usage sequence data is used to characterize the application usage corresponding to the target number of steps after using the first application; and further, to obtain application usage habit data, and the application usage habit data includes the usage frequency corresponding to one or more second applications in the first historical time period; further, it is possible to determine a recommended application set based on the current application usage sequence, the application usage sequence data, and the application usage habit data. It can be seen that the application recommendation method disclosed in the embodiments of the present application combines application usage data of three dimensions: the current application usage sequence, the application usage sequence data, and the application usage habit data, that is, it takes into account the historical application usage and the current application usage, so that a more accurate recommended application set can be predicted to meet the user's application recommendation needs at the current moment, thereby improving the user's usage experience.

[0078] See also Figure 2 , Figure 2 1 is a flowchart of another application recommendation method disclosed in an embodiment of the present application. Optionally, the method can be applied to various electronic devices or other execution entities introduced above, which are not limited here. Optionally, the method can include the following steps:

[0079] 202. Obtain a current application usage sequence, where the current application usage sequence includes one or more first applications.

[0080] 204. Obtain application usage sequence data corresponding to each first application, where the application usage sequence data is used to characterize application usage situations corresponding to target usage steps after using the first application.

[0081] 206. Obtain application usage habit data, where the application usage habit data includes usage frequencies corresponding to one or more second applications in the first historical time period.

[0082] 208. Determine a first application set according to the current application usage sequence and the application usage order data.

[0083] In the embodiment of the present application, the electronic device may predict an initial recommended application set as the first application set based on the current application usage sequence and application usage order data.

[0084] As an optional implementation, the electronic device may determine the first score corresponding to the target third application relative to the target first application based on the target usage probability corresponding to the target third application and the step number sequence corresponding to the target third application in the application usage sequence data corresponding to the target first application;

[0085] Furthermore, the second score corresponding to the target third application can be determined based on the first scores corresponding to the target third application relative to each first application; and the second scores corresponding to each third application included in the application usage sequence data corresponding to one or more first applications are sorted to obtain a first application set.

[0086] The target first application is any first application included in the current application usage sequence, and the target third application is any third application included in the application usage sequence data corresponding to the target first application. The step number sequence corresponding to the target third application refers to the step number after the target first application is used.

[0087] By implementing the above method, the electronic device can comprehensively consider multi-dimensional factors such as the probability of use of the target third application in each step sequence and the probability of use of the target third application relative to different first applications, and determine the second score corresponding to the target third application, so that the second score can more accurately reflect the probability of use of the target third application, thereby improving the reference for subsequent determination of the first application set.

[0088] The following first introduces an optional implementation method of determining a first score corresponding to the target third application relative to the target first application:

[0089] As an optional implementation, the electronic device may determine the sub-scores corresponding to the target third application relative to each step order according to the target usage probability corresponding to the target third application and the corresponding step order;

[0090] Furthermore, the sub-scores corresponding to the target third application with respect to each step sequence are accumulated to obtain a first score corresponding to the target third application with respect to the target first application.

[0091] As described above, the application usage sequence data corresponding to the target first application includes: application usage probability data corresponding to the target usage steps after using the target first application. It should be noted that the application usage probability data corresponding to the target usage steps may include the same third application.

[0092] For example, assuming that after using the first application A: the application usage probability data corresponding to the first step may include: "third application A (30%), third application B (60%) and third application C (10%)";

[0093] The application usage probability data corresponding to the second step may include: “third application D (60%), third application B (20%) and third application E (20%)”….

[0094] It can be seen that the application usage probability data corresponding to the first step and the second step respectively include the third application B, and the usage probabilities corresponding to the third application B are different.

[0095] In order to comprehensively consider the usage probability of the target third application in each step order, the electronic device can determine the sub-scores corresponding to the target third application relative to each step order according to the target usage probability and the corresponding step order corresponding to the target third application.

[0096] Exemplarily, the electronic device can determine the sub-score of the third application B relative to the first step based on the step number sequence "1" of the first step and the usage probability of 60% of the third application B in the first step; and can determine the sub-score of the third application B relative to the second step based on the second step number sequence "2" and the usage probability of 30% of the third application B in the second step, and accumulate the sub-scores of the third application B corresponding to each step number sequence to obtain the first score of the third application B relative to the first application A.

[0097] It should be noted that if the application usage probability data corresponding to a certain step sequence of the target first application does not include the target third application, the sub-score corresponding to the step sequence of the target third application can be determined as the default score. Optionally, the default score can be set by the developer based on a large amount of development experience, and typical values ​​can include: 0, 1, etc., which are not limited here.

[0098] By implementing the above method, the electronic device can comprehensively consider the usage probability of the target third application in each step sequence, first determine the sub-scores corresponding to the target third application relative to each step sequence, and then accumulate the sub-scores to obtain the first score, so that the first score can more accurately reflect the usage probability of the target third application relative to the target first application, thereby improving the reference for subsequent determination of the first application set.

[0099] As another optional implementation, the electronic device may obtain a first time difference between the current time and the start time of use of the target first application;

[0100] Furthermore, a first score corresponding to the target third application relative to the target first application may be determined according to the first time difference, the target usage probability corresponding to the target third application, and the corresponding step order.

[0101] Optionally, the electronic device may calculate the product of the first time difference, the target usage probability corresponding to the target third application, and the corresponding step order as the first score corresponding to the target third application relative to the target first application.

[0102] When implementing the above method, the first time difference between the start time of use of the target first application and the current time can be considered, and the first score corresponding to the target third application can be attenuated according to the first time difference, wherein the larger the first time difference is, the more serious the score attenuation is, thereby improving the first score of the third application that the electronic device has recently used, thereby improving the reference for subsequently determining the first application set.

[0103] In another optional embodiment, the electronic device may determine the first score corresponding to the target third application relative to the target first application according to the preset weight, the target usage probability corresponding to the target third application, and the corresponding step order. The preset weight is determined according to the application information of the target third application, and the application information may include application functions, application attributes, application developers, etc., which are not limited here.

[0104] By implementing the above method, the electronic device can also comprehensively consider the application information of the target third application when determining the first score corresponding to the target third application, thereby improving the referenceability of subsequent determination of the first application set.

[0105] Furthermore, an optional implementation manner of determining the second score corresponding to the target third application is introduced below:

[0106] As described above, the application usage sequence data corresponding to the first application includes: the usage probabilities corresponding to one or more third applications in the Nth step after the first application is used. It should be noted that the application usage sequence data corresponding to different first applications may include the same third application, but the usage probabilities of the third application in the application usage sequence data corresponding to different first applications are different.

[0107] For example, assuming that in the application usage sequence data corresponding to the first application A, the application usage probability data corresponding to the first step includes the third application A, and the corresponding usage probability is 30%; in the application usage sequence data corresponding to the first application B, the application usage probability data corresponding to the second step also includes the third application A, but the corresponding usage probability is 60%; then, through the method introduced in the previous article, the first score of the third application A relative to the first application A is calculated, which is different from the first score of the third application A relative to the first application B.

[0108] Optionally, the electronic device may comprehensively consider the usage probability of the target third application relative to different first applications, and determine the second score corresponding to the target third application according to the first scores corresponding to the target third application relative to each first application, so that the second score can more accurately reflect the usage probability of the target third application, thereby improving the reference for subsequent determination of the first application set.

[0109] In an optional embodiment, the electronic device may calculate an average value according to the first scores respectively corresponding to the target third application with respect to each first application, to obtain the second score corresponding to the target third application.

[0110] Optionally, the electronic device may accumulate the first scores of the target third application corresponding to each first application to obtain a first accumulation result, and then divide the first accumulation result by the target number corresponding to the first application to obtain an average value.

[0111] In an optional embodiment, after each time the electronic device determines the first score corresponding to a target third application relative to the target first application, it can add one to the processing quantity, and after completing the determination of the first scores corresponding to the target third application relative to each first application, the electronic device can use the current processing quantity as the target quantity corresponding to the first application.

[0112] In another optional embodiment, the electronic device can determine the first scores corresponding to the target third application relative to each first application in the order of decay of usage time, and when it is determined that the processing quantity is greater than the quantity threshold, it can end the calculation of the first score and use the current processing quantity as the target quantity corresponding to the first application.

[0113] By implementing the above method, the electronic device can control the number of first applications to be processed, thereby improving the controllability of the method.

[0114] For example, see Figure 3 , Figure 3 This is a schematic diagram of a process for determining a first application set disclosed in an embodiment of the present application; wherein:

[0115] The electronic device may obtain the current application usage sequence and application usage order data; and then traverse the first applications included in the current application usage sequence in the decaying order of the start of use time; wherein the manner of traversing each first application includes: traversing the usage probabilities corresponding to one or more third applications in the Nth step after the first application; determining the scores corresponding to each step sequence according to the first time difference, the usage probabilities of the third applications and the step sequence, and accumulating the scores corresponding to each step number to obtain the first scores corresponding to each third application;

[0116] Obtain the processing quantity of the currently processed first application. If the processing quantity is greater than the quantity threshold, the loop ends. If the processing quantity is not greater than the quantity threshold, the processing quantity increases by one and the next first application is processed.

[0117] After the loop ends, the scores are normalized according to the scores and processing quantities corresponding to each third application to obtain the second scores corresponding to the third application; and then the first application set is determined according to the second day scores corresponding to each third application.

[0118] 210. Determine a second application set according to the current application usage sequence and application usage habit data.

[0119] As described above, the application usage habit data includes: usage frequencies corresponding to one or more second applications in a first historical time period.

[0120] In this regard, as an optional implementation, the electronic device can select the second application whose usage frequency ranks in the top M from the application usage habit data; and then obtain the second application set based on the current application usage sequence and the second application whose usage frequency ranks in the top M, where M is a positive integer.

[0121] For example, assume that the current application usage sequence is "first application A, first application B, and first application C"; the second applications ranked in the first two in terms of usage frequency in the application usage habit data are "second application D and second application E". The electronic device can add "second application D and second application E" to "first application A, first application B, and first application C" to obtain a second application set: "first application A, first application B, first application C, second application D, and second application E", which is not limited here.

[0122] By implementing the above method, the electronic device can predict the second application set by combining the current application usage sequence, historical application usage habit data and other factors of multiple dimensions, thereby improving the referenceability of the subsequent determination of the recommended application set.

[0123] 212. Determine a recommended application set according to the first application set and the second application set.

[0124] In an optional embodiment, the electronic device may merge the first application set and the second application set to obtain a third application set, wherein the third application set includes a plurality of fifth applications, and each fifth application corresponds to a target score.

[0125] Optionally, after the electronic device fuses the first application set and the second application set to obtain the third application set, it can set target scores for multiple fifth applications included in the first application set. Optionally, the target scores can be set by the developer based on a large amount of development experience, and typical values ​​may include 1, 5 or 10, etc., which are not limited here. Optionally, the target scores corresponding to the multiple fifth applications can be the same or different, which are not limited here.

[0126] In an optional embodiment, before the electronic device merges the first application set and the second application set to obtain the third application set, it can obtain a second time difference between the current time and the start time of use of the sixth application, where the sixth application is any application included in the second application set;

[0127] Then, a decay operation is performed on the target score corresponding to the sixth application according to the second time difference, wherein the decay amplitude corresponding to the decay operation may be positively correlated with the second time difference.

[0128] For example, assuming that the second application set includes five sixth applications, namely, "first application A, first application B, first application C, second application D, and second application E", and the default target scores are all 1, the electronic device can attenuate the target scores corresponding to each sixth application according to the second time difference between the current moment and the start time of use of each sixth application.

[0129] By implementing the above method, the electronic device can perform an attenuation operation on the target score corresponding to each sixth application according to the second time difference between the current moment and the start time of use of each sixth application included in the second application set, so as to reduce the target score of the sixth application whose use time is too far away from the current moment, thereby allowing the second application set to more accurately reflect the user's recent application usage habits.

[0130] In one embodiment, the electronic device may perform a score adjustment operation on target scores corresponding to a plurality of fifth applications included in the third application set according to the first application set, the second application set, and the current application usage sequence.

[0131] Optionally, the electronic device may perform a first score adjustment operation on target scores respectively corresponding to a plurality of fifth applications included in the third application set according to the first application set and the second application set, to obtain an adjusted third application set;

[0132] Then, according to the first application set and the current application usage sequence, a second score adjustment operation is performed on the target scores respectively corresponding to the plurality of fifth applications included in the adjusted third application set.

[0133] Optionally, the score adjustment operation may include one or more of the following:

[0134] increasing the target score of a fifth application that exists in both the first application set and the second application set;

[0135] Lowering the target score of the fifth application that exists only in the first application set or only in the second application set;

[0136] Improving the target score of the fifth application that exists in both the current application usage sequence and the third application set;

[0137] The target score of the fifth application that exists only in the current application usage sequence but not in the third application set is lowered.

[0138] Optionally, the electronic device may also maintain a target score for a fifth application that exists only in the current application usage sequence but not in the first application set.

[0139] Exemplarily, assume that the current application usage sequence includes "application A, application B, and application C"; the first application set includes "application B, application C, and application R"; and the second application set includes "application A, application B, application C, application E, and application K".

[0140] Then the electronic device can merge the first application set and the second application set to obtain a third application set "application A, application B, application C, application R, application E and application K";

[0141] Then, the electronic device can increase the target score of the fifth application that exists in both the first application set and the second application set according to the first application set and the second application set; and reduce the target score of the fifth application that exists only in the first application set or only in the second application set, so as to obtain an adjusted third application set. For example, if both the first application set and the second application set include "application B and application C", the target scores corresponding to "application B and application C" are increased; if "application R" exists only in the first application set, the target score corresponding to "application R" can be reduced.

[0142] Furthermore, the electronic device may perform a second score adjustment operation on the adjusted third application set based on the first application set and the current application usage sequence. The second score adjustment operation may include: increasing the target score of the fifth application that exists in both the current application usage sequence and the third application set; and, decreasing the target score of the fifth application that only exists in the current application usage sequence but not in the third application set. Exemplarily, if the current application usage sequence and the third application set both include "application B and application C", then the target scores corresponding to "application B and application C" are increased respectively; and, the target score of "application A" is maintained.

[0143] Furthermore, the electronic device may sort the plurality of fifth applications according to the adjusted target scores corresponding to the respective fifth applications to obtain a set of recommended applications.

[0144] By implementing the above method, the electronic device can obtain the third application set by fusion, and improve the score of the fifth application included in multiple application sets through multiple rounds of score adjustment operations, thereby making the probability of the fifth application included in multiple application sets being recommended subsequently increased, thereby improving the referenceability of the subsequently determined application recommendation set.

[0145] In addition, by implementing the above method, the electronic device can comprehensively consider the second application set that reflects current and historical application usage habits and the first application set that predicts future application usage to determine a recommendation reason set, thereby being able to predict a more accurate recommended application set to meet the user's application recommendation needs at the current moment, thereby improving the user's usage experience.

[0146] In order to more clearly introduce how to determine the recommended application set, the following Figure 4 Provide explanation. Figure 4 This is a schematic diagram of a process for determining a recommended application set disclosed in an embodiment of the present application, wherein:

[0147] Obtain the current application usage sequence, and construct a second application set according to the current application usage sequence and the application usage habit data described above;

[0148] performing a decay operation on a target score corresponding to a sixth application included in the second application set according to the second time difference;

[0149] Determine a target score corresponding to each application included in the first application set;

[0150] whether the application in the first application set exists in the second application set; if so, raising the target score of the application that exists in both the first application set and the second application set; if not, lowering the target score of the fifth application that exists only in the first application set or only in the second application set;

[0151] whether the application in the current application usage sequence exists in the third application set; if so, increasing the target score of the fifth application that exists in both the current application usage sequence and the third application set; if not, decreasing the target score of the fifth application that only exists in the current application usage sequence but not in the third application set;

[0152] According to the scores corresponding to the respective fifth applications included in the third application set, the plurality of fifth applications are sorted to obtain a recommended application set.

[0153] The method disclosed in the above embodiments is implemented, combining application usage data of three dimensions, namely, current application usage sequence, application usage order data and application usage habit data, that is, considering the historical application usage and the current application usage, so that a more accurate recommended application set can be predicted to meet the user's application recommendation needs at the current moment, thereby improving the user's usage experience; and, comprehensively considering the use probability of the target third application in each step sequence, and the use probability of the target third application relative to different first applications and other multi-dimensional factors, to determine the second score corresponding to the target third application, so that the second score can more accurately reflect the use probability of the target third application, thereby improving the reference for the subsequent determination of the first application set; and, The use probability of the target third application in each step sequence can be comprehensively considered, and the sub-scores corresponding to the target third application relative to each step sequence can be determined respectively, and then the sub-scores are accumulated to obtain the first score, so that the first score can more accurately reflect the use probability of the target third application relative to the target first application, thereby improving the reference for the subsequent determination of the first application set; and, the first time difference between the corresponding start time of the target first application and the current time can be considered, and the first score corresponding to the target third application can be attenuated according to the first time difference, wherein the larger the first time difference is, the more serious the score attenuation is, thereby improving the first score of the third application that is most frequently used by the electronic device recently, thereby improving the reference for the subsequent determination of the first application set;

[0154] Furthermore, the second application set can be predicted by combining factors of multiple dimensions such as the current application usage sequence and historical application usage habit data, thereby improving the reference for subsequently determining the recommended application set; and, the third application set can be obtained by fusion, and through multiple rounds of score adjustment operations, the score of the fifth application included in multiple application sets can be improved, so that the probability of the fifth application included in multiple application sets being recommended later can be made, thereby improving the reference for subsequently determined application recommendation sets; and, the second application set that reflects current and historical application usage habits and the first application set that predicts future application usage can be comprehensively considered to determine the recommendation reason set, so that a more accurate recommended application set can be predicted to meet the user's application recommendation needs at the current moment, thereby improving the user's usage experience.

[0155] See also Figure 5 , Figure 5 This is a flowchart of another application recommendation method disclosed in an embodiment of the present application. Optionally, the method can be applied to various electronic devices or other execution entities introduced above, which are not limited here. Optionally, the method can include the following steps:

[0156] 502. Obtain a current application usage sequence, where the current application usage sequence includes one or more first applications.

[0157] 504. Acquire a plurality of historical application usage sequences corresponding to the second historical time period, where the historical application usage sequences include a plurality of fourth applications arranged in a usage order.

[0158] In an embodiment of the present application, the electronic device can classify the multiple fourth applications included in the multiple historical application usage sequences corresponding to the second historical time period according to unit time length, and sort the multiple fourth applications according to the order of usage, thereby facilitating subsequent electronic devices to process the multiple historical application usage sequences corresponding to the second historical time period.

[0159] In an optional embodiment, the electronic device may preprocess multiple historical application usage sequences corresponding to the second historical time period, and count application usage order data corresponding to each fourth application based on the preprocessed multiple historical application usage sequences.

[0160] Optionally, the preprocessing may include: removing abnormal usage data and / or non-user-triggered usage data from multiple historical application usage sequences; wherein the abnormal usage data includes usage data for abnormal applications, and the abnormal applications are blacklisted applications.

[0161] By implementing the above method, the electronic device can eliminate abnormal usage data and / or non-user-triggered usage data in multiple historical application usage sequences to simplify multiple historical application usage sequences, thereby facilitating subsequent electronic devices to process multiple historical application usage sequences corresponding to the second historical time period.

[0162] 506. According to the plurality of historical application usage sequences, statistics are collected on application usage sequence data corresponding to each fourth application.

[0163] Among them, the application usage sequence data corresponding to the target fourth application includes: application usage probability data corresponding to the target usage steps after using the target fourth application, the application usage probability data corresponding to the Nth step includes the usage probabilities corresponding to one or more fourth applications in the Nth step after using the target fourth application, and the target fourth application is any fourth application included in the multiple historical application usage sequences corresponding to the second historical time period.

[0164] Among them, in the Nth step after using the target fourth application, the usage probability corresponding to another fourth application used can be determined according to the first number of times another fourth application is used in the Nth step; and, after using the target fourth application, the total number of times all fourth applications are used in the Nth step.

[0165] For example, assuming that in the third step after using the fourth application A, the total number of times all fourth applications have been used is 10 times, among which the first number of times fourth application B is used is 3 times, then it can be determined that in the third step after using the fourth application A, the probability of using the fourth application B is 30%, which is not limited here.

[0166] See also Figure 6 , Figure 6 This is a flow chart of a method for collecting statistics of application usage sequence data corresponding to a fourth application disclosed in an embodiment of the present application. Optionally, the electronic device may first perform the aforementioned sorting, classification and preprocessing on multiple historical application usage sequences including the fourth application;

[0167] Furthermore, the electronic device can obtain, from multiple historical application usage sequences, the first number of times another fourth application is used in step N after using the target fourth application; and the total number of times all fourth applications are used in step N after using the target fourth application as record data corresponding to step N.

[0168] The electronic device can traverse the loop in the above manner to obtain the recorded data corresponding to the target usage steps after using the target fourth application, and then the electronic device can count the application usage sequence data corresponding to the target fourth application based on the recorded data corresponding to the target usage steps.

[0169] 508. Obtain application usage sequence data corresponding to each first application according to the application usage sequence data corresponding to each fourth application, where the application usage sequence data is used to characterize application usage situations corresponding to the target number of usage steps after using the first application.

[0170] In an embodiment of the present application, the electronic device has already determined in advance the application usage sequence data corresponding to each fourth application. The electronic device can determine the application usage sequence data corresponding to the fourth application that matches the target first application as the application usage sequence data corresponding to the target first application, thereby improving the efficiency of obtaining the application usage sequence data corresponding to each first application.

[0171] 510. Obtain application usage habit data, where the application usage habit data includes usage frequencies corresponding to one or more second applications in a first historical time period.

[0172] 512. Determine a recommended application set based on the current application usage sequence, application usage order data, and application usage habit data.

[0173] The method disclosed in the above embodiments combines application usage data in three dimensions: current application usage sequence, application usage sequence data, and application usage habit data. That is, it takes into account both historical application usage and current application usage, so that a more accurate set of recommended applications can be predicted to meet the user's application recommendation needs at the current moment, thereby improving the user's usage experience; and, the application usage sequence data corresponding to each fourth application can be determined in advance. For this purpose, the electronic device can determine the application usage sequence data corresponding to the fourth application matching the target first application as the application usage sequence data corresponding to the target first application, thereby improving the efficiency of obtaining the application usage sequence data corresponding to each first application.

[0174] See also Figure 7 , Figure 7 is a schematic diagram of the structure of an application recommendation device disclosed in an embodiment of the present application. Optionally, the device can be applied to various electronic devices or other execution entities introduced above, which are not limited here. Optionally, the device may include a first acquisition unit 702, a second acquisition unit 704, a third acquisition unit 706 and a determination unit 708, wherein:

[0175] A first acquisition unit 702 is used to acquire a current application usage sequence, where the current application usage sequence includes one or more first applications;

[0176] The second acquisition unit 704 is used to acquire application usage sequence data corresponding to each first application, where the application usage sequence data is used to characterize application usage conditions corresponding to the target usage steps after using the first application;

[0177] The third acquisition unit 706 is used to acquire application usage habit data, where the application usage habit data includes usage frequencies corresponding to one or more second applications in the first historical time period;

[0178] The determination unit 708 is used to determine a recommended application set according to the current application usage sequence, application usage order data and application usage habit data.

[0179] By implementing the above-mentioned device, it is possible to obtain the current application usage sequence, which includes one or more first applications; further, it is possible to obtain application usage sequence data corresponding to each first application, and the application usage sequence data is used to characterize the application usage corresponding to the target number of steps after using the first application; and further, it is possible to obtain application usage habit data, and the application usage habit data includes the usage frequency corresponding to one or more second applications in the first historical time period; further, it is possible to determine a recommended application set based on the current application usage sequence, the application usage sequence data, and the application usage habit data. It can be seen that the application recommendation method disclosed in the embodiment of the present application combines application usage data of three dimensions, namely, the current application usage, and the current application usage, so that a more accurate recommended application set can be predicted to meet the user's application recommendation needs at the current moment, thereby improving the user's usage experience.

[0180] As an optional implementation, the determination unit 708 is also used to determine a first application set based on the current application usage sequence and application usage order data; and, to determine a second application set based on the current application usage sequence and application usage habit data; and, to determine a recommended application set based on the first application set and the second application set.

[0181] By implementing the above-mentioned device, the application usage data of three dimensions, namely, the current application usage sequence, the application usage order data and the application usage habit data, can be combined to first predict the first application set and the second application set respectively, and then a more accurate recommended application set can be obtained based on the predictions of the two sets to meet the user's application recommendation needs at the current moment, thereby improving the user's usage experience.

[0182] As an optional implementation manner, the application usage sequence data corresponding to the first application includes: application usage probability data corresponding to the target number of usage steps after using the first application, wherein the application usage probability data corresponding to the Nth step includes the usage probabilities corresponding to one or more third applications in the Nth step after using the first application, and N is a positive integer;

[0183] The determination unit 708 is further used to determine a first score corresponding to the target third application relative to the target first application based on the target usage probability and the corresponding step order corresponding to the target third application in the application usage sequence data corresponding to the target first application; the target first application is any first application included in the current application usage sequence, and the target third application is any third application included in the application usage sequence data corresponding to the target first application; and, based on the first scores corresponding to the target third application relative to each first application, determine a second score corresponding to the target third application; and, sort the second scores corresponding to each third application included in the application usage sequence data corresponding to one or more first applications to obtain a first application set.

[0184] By implementing the above device, the electronic device can comprehensively consider multi-dimensional factors such as the probability of use of the target third application in each step sequence and the probability of use of the target third application relative to different first applications, and determine the second score corresponding to the target third application, so that the second score can more accurately reflect the probability of use of the target third application, thereby improving the reference for subsequent determination of the first application set.

[0185] As an optional implementation, the determination unit 708 is further used to determine the sub-scores corresponding to the target third application relative to each step order based on the target usage probability corresponding to the target third application and the corresponding step order; and to accumulate the sub-scores corresponding to the target third application relative to each step order to obtain the first score corresponding to the target third application relative to the target first application.

[0186] By implementing the above device, the electronic device can comprehensively consider the usage probability of the target third application in each step sequence, first determine the sub-scores corresponding to the target third application relative to each step sequence, and then accumulate the sub-scores to obtain the first score, so that the first score can more accurately reflect the usage probability of the target third application relative to the target first application, thereby improving the reference for subsequent determination of the first application set.

[0187] As an optional implementation, the determination unit 708 is also used to obtain a first time difference between the current moment and the start time of use corresponding to the target first application; and, based on the first time difference, the target usage probability corresponding to the target third application, and the corresponding step order, determine the first score corresponding to the target third application relative to the target first application.

[0188] When implementing the above-mentioned device, the first time difference between the start time of use of the target first application and the current time can be considered, and the first score corresponding to the target third application can be attenuated according to the first time difference, wherein the larger the first time difference is, the more serious the score attenuation is, thereby improving the first score of the third application that the electronic device has recently used, thereby improving the reference for subsequently determining the first application set.

[0189] As an optional implementation, the determination unit 708 is further configured to calculate an average value according to the first scores respectively corresponding to the target third application relative to each first application, so as to obtain a second score corresponding to the target third application.

[0190] By implementing the above device, the electronic device can comprehensively consider the usage probability of the target third application relative to different first applications, and determine the second score corresponding to the target third application according to the first scores corresponding to the target third application relative to each first application, so that the second score can more accurately reflect the usage probability of the target third application, thereby improving the reference for subsequent determination of the first application set.

[0191] As an optional implementation, the determination unit 708 is further used to select the second application whose usage frequency ranks in the top M from the application usage habit data; and obtain a second application set based on the current application usage sequence and the top M second applications, where M is a positive integer.

[0192] By implementing the above device, the electronic device can predict the second application set by combining the current application usage sequence, historical application usage habit data and other factors of multiple dimensions, thereby improving the referenceability of the subsequent determination of the recommended application set.

[0193] As an optional implementation, the determination unit 708 is also used to fuse the first application set and the second application set to obtain a third application set, wherein the third application set includes multiple fifth applications, and each fifth application corresponds to a target score; and, based on the first application set, the second application set and the current application usage sequence, perform a score adjustment operation on the target scores corresponding to the multiple fifth applications included in the third application set; and, based on the adjusted target scores corresponding to each fifth application, sort the multiple fifth applications to obtain a recommended application set.

[0194] By implementing the above-mentioned device, the electronic device can comprehensively consider the second application set that reflects the current and historical application usage habits and the first application set that predicts future application usage to determine the recommendation reason set, so as to predict a more accurate recommended application set to meet the user's application recommendation needs at the current moment, thereby improving the user's usage experience.

[0195] As an optional implementation, the score adjustment operation includes one or more of the following:

[0196] increasing the target score of a fifth application that exists in both the first application set and the second application set;

[0197] Lowering the target score of the fifth application that exists only in the first application set or only in the second application set;

[0198] Improving the target score of the fifth application that exists in both the current application usage sequence and the third application set;

[0199] The target score of the fifth application that exists only in the current application usage sequence but not in the third application set is lowered.

[0200] By implementing the above-mentioned device, the electronic device can obtain the third application set by fusion, and improve the score of the fifth application included in multiple application sets through multiple rounds of score adjustment operations, thereby making the probability of the fifth application included in multiple application sets being recommended subsequently increased, thereby improving the referenceability of the subsequently determined application recommendation set.

[0201] As an optional implementation, Figure 7 The device shown may also include an attenuation unit (not shown), wherein:

[0202] The attenuation unit is used to obtain a second time difference between the current moment and the start time of use of a sixth application before fusing the first application set and the second application set to obtain the third application set, where the sixth application is any application included in the second application set; and perform an attenuation operation on the target score corresponding to the sixth application according to the second time difference, wherein the attenuation amplitude corresponding to the attenuation operation is positively correlated with the second time difference.

[0203] By implementing the above device, the electronic device can perform an attenuation operation on the target score corresponding to each sixth application according to the second time difference between the current moment and the start time of use of each sixth application included in the second application set, so as to reduce the target score of the sixth application whose use time is too far away from the current moment, thereby allowing the second application set to more accurately reflect the user's recent application usage habits.

[0204] As an optional implementation, Figure 7 The device shown may also include a statistical unit not shown, wherein:

[0205] a statistical unit, configured to obtain a plurality of historical application usage sequences corresponding to the second historical time period before obtaining the application usage sequence data corresponding to each first application, the historical application usage sequence including a plurality of fourth applications arranged in a usage order; and, based on the plurality of historical application usage sequences, to count the application usage sequence data corresponding to each fourth application; wherein the application usage sequence data corresponding to the target fourth application includes application usage probability data corresponding to the target number of usage steps after the target fourth application is used, the application usage probability data corresponding to the Nth step includes usage probabilities corresponding to one or more fourth applications in the Nth step after the target fourth application is used, and the target fourth application is any fourth application;

[0206] Furthermore, the second acquisition unit 704 is further configured to acquire the application usage sequence data corresponding to each first application according to the application usage sequence data corresponding to each fourth application.

[0207] By implementing the above-mentioned device, the application usage sequence data corresponding to each fourth application can be determined in advance. The electronic device can determine the application usage sequence data corresponding to the fourth application matching the target first application as the application usage sequence data corresponding to the target first application, thereby improving the efficiency of obtaining the application usage sequence data corresponding to each first application.

[0208] See also Figure 8 , Figure 8 Schematic diagram of the structure of an electronic device disclosed in the embodiment of the present application. Figure 8 As shown, the electronic device may include:

[0209] A memory 801 storing executable program codes;

[0210] a processor 802 coupled to the memory 801;

[0211] The processor 802 calls the executable program code stored in the memory 801 to execute the application recommendation method disclosed in the above embodiments.

[0212] The embodiments of the present application disclose a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the application recommendation method disclosed in the above embodiments.

[0213] The embodiments of the present application also disclose an application publishing platform, wherein the application publishing platform is used to publish a computer program product, wherein when the computer program product runs on a computer, the computer executes part or all of the steps of the method in the above method embodiments.

[0214] It should be understood that the "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. Those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required for the present application.

[0215] In the various embodiments of the present application, it should be understood that the size of the serial numbers of the above-mentioned processes does not necessarily 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.

[0216] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0217] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0218] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for a computer device (which can be a personal computer, a server or a network device, etc., specifically a processor in a computer device) to perform some or all of the steps of the above-mentioned methods of various embodiments of the present application.

[0219] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0220] The above is a detailed introduction to the recommended application methods and devices, electronic devices, and storage media disclosed in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the methods and core ideas of the present application. At the same time, for general technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An application recommendation method, characterized in that: The method comprises: Acquire a current application usage sequence, where the current application usage sequence includes one or more first applications; Acquire application usage sequence data corresponding to each of the first applications, wherein the application usage sequence data is used to characterize application usage conditions corresponding to target usage steps after using the first application; Acquire application usage habit data, wherein the application usage habit data includes usage frequencies corresponding to one or more second applications in a first historical time period; A recommended application set is determined according to the current application usage sequence, the application usage order data, and the application usage habit data.

2. The method according to claim 1, characterized in that The determining of a recommended application set according to the current application usage sequence, the application usage order data, and the application usage habit data includes: Determining a first application set according to the current application usage sequence and the application usage order data; Determining a second application set according to the current application usage sequence and the application usage habit data; A recommended application set is determined according to the first application set and the second application set.

3. The method according to claim 2, characterized in that The application usage sequence data corresponding to the first application includes: application usage probability data corresponding to the target number of usage steps after using the first application, wherein the application usage probability data corresponding to the Nth step includes the usage probabilities corresponding to one or more third applications in the Nth step after using the first application, where N is a positive integer; determining the first application set according to the current application usage sequence and the application usage sequence data includes: Determine a first score corresponding to the target third application relative to the target first application according to the target usage probability and the corresponding step order of the target third application in the application usage sequence data corresponding to the target first application; the target first application is any first application included in the current application usage sequence, and the target third application is any third application included in the application usage sequence data corresponding to the target first application; determining a second score corresponding to the target third application according to the first scores respectively corresponding to the target third application relative to each of the first applications; The second scores corresponding to the third applications included in the application usage sequence data corresponding to the one or more first applications are sorted to obtain a first application set.

4. The method according to claim 3, characterized in that The determining, according to the target usage probability and the corresponding step order of the target third application in the application usage sequence data corresponding to the target first application, a first score corresponding to the target third application relative to the target first application comprises: According to the target usage probability and the corresponding step order corresponding to the target third application, respectively determine the sub-scores corresponding to the target third application relative to each of the step orders; The sub-scores corresponding to the target third application relative to each of the step orders are accumulated to obtain a first score corresponding to the target third application relative to the target first application.

5. The method according to claim 3, characterized in that: The determining, according to the target usage probability and the corresponding step order of the target third application in the application usage sequence data corresponding to the target first application, a first score corresponding to the target third application relative to the target first application comprises: Obtaining a first time difference between the current time and the start time of use of the target first application; A first score corresponding to the target third application relative to the target first application is determined according to the first time difference, the target usage probability corresponding to the target third application, and the corresponding step order.

6. The method according to claim 3, characterized in that The determining, according to the first scores respectively corresponding to the target third application relative to each of the first applications, the second score corresponding to the target third application includes: An average value is calculated according to the first scores respectively corresponding to the target third application with respect to each of the first applications to obtain a second score corresponding to the target third application.

7. The method according to claim 2, characterized in that The determining the second application set according to the current application usage sequence and the application usage habit data includes: Selecting a second application ranked in the top M in terms of usage frequency from the application usage habit data; A second application set is acquired according to the current application usage sequence and the first M second applications, where M is a positive integer.

8. The method according to claim 2, characterized in that: The determining a recommended application set according to the first application set and the second application set includes: Merging the first application set and the second application set to obtain a third application set, wherein the third application set includes a plurality of fifth applications, and each of the fifth applications corresponds to a target score; According to the first application set, the second application set, and the current application usage sequence, adjusting the target scores respectively corresponding to the plurality of fifth applications included in the third application set; The plurality of fifth applications are sorted according to the adjusted target scores corresponding to the respective fifth applications to obtain a recommended application set.

9. The method according to claim 8, characterized in that The score adjustment operation includes one or more of the following: increasing the target score of a fifth application that exists in both the first application set and the second application set; reducing a target score of a fifth application that exists only in the first application set or only in the second application set; increasing the target score of the fifth application that exists in both the current application usage sequence and the third application set; The target score of a fifth application that exists only in the current application usage sequence but not in the third application set is lowered.

10. The method according to claim 8 or 9, characterized in that: Before fusing the first application set and the second application set to obtain a third application set, the method further includes: Obtaining a second time difference between the current time and a start time of use of a sixth application, where the sixth application is any application included in the second application set; A decay operation is performed on the target score corresponding to the sixth application according to the second time difference, and a decay amplitude corresponding to the decay operation is positively correlated with the second time difference.

11. The method according to claim 1, characterized in that: Before obtaining the application usage sequence data corresponding to each of the first applications, the method further includes: Acquire a plurality of historical application usage sequences corresponding to the second historical time period, wherein the historical application usage sequences include a plurality of fourth applications arranged in a usage order; According to the multiple historical application usage sequences, the application usage sequence data corresponding to each of the fourth applications are counted; wherein the application usage sequence data corresponding to the target fourth application includes application usage probability data corresponding to the target number of usage steps after the target fourth application is used, and the application usage probability data corresponding to the Nth step includes the usage probabilities corresponding to one or more fourth applications in the Nth step after the target fourth application is used, and the target fourth application is any of the fourth applications; And, the obtaining of application usage sequence data corresponding to each of the first applications includes: The application usage sequence data corresponding to each of the first applications is obtained according to the application usage sequence data corresponding to each of the fourth applications.

12. An application recommendation device, characterized in that: The device comprises: A first acquisition unit, configured to acquire a current application usage sequence, where the current application usage sequence includes one or more first applications; A second acquisition unit is used to acquire application usage sequence data corresponding to each of the first applications, wherein the application usage sequence data is used to characterize application usage conditions corresponding to target usage steps after using the first application; A third acquisition unit, configured to acquire application usage habit data, wherein the application usage habit data includes usage frequencies corresponding to one or more second applications in a first historical time period; The determination unit is used to determine a recommended application set according to the current application usage sequence, the application usage order data and the application usage habit data.

13. An electronic device, characterized in that: It comprises a memory storing executable program code and a processor coupled to the memory; wherein the processor calls the executable program code stored in the memory to execute the method according to any one of claims 1 to 11.

14. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images