Relevance analysis method and device for intelligent cabin application program

Abstract

The invention relates to a correlation analysis method and device for an intelligent cabin application program. The method comprises the following steps: acquiring historical usage data of a plurality of application programs, and determining a transaction data set based on the historical usage data of each application program; and determining a first frequent item set from the transaction data set, and determining a second frequent item set based on a preset associated parameter, the transaction data set and the first frequent item set. And determining an application program association set based on the first frequent item set, the second frequent item set and the historical use data of each application program so as to mine the association among the application programs. Besides, the association position of each application program is determined based on the application program association set and the historical use data of each application program, so that a scientific and reliable basis is provided for application program setting of the intelligent cockpit system by using the association position of each application program; therefore, the mode of displaying each application program to the driver and passengers by the intelligent cabin system can better meet personalized requirements, and the application program use experience of the driver and passengers is improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present specification belong to the technical field of automobile cabin design, and in particular relate to a correlation analysis method and device for intelligent cabin application programs. BACKGROUND

[0002] The intelligent cabin system of an automobile generally refers to the cockpit inside the automobile and its integrated technical system, including the instrument panel, infotainment system, navigation system, and air conditioning control system, etc. In recent years, with the continuous development of automobile intelligence, the intelligent cabin system integrates more and more application programs to meet the needs of drivers and passengers in navigation, entertainment, communication, and vehicle control, etc.

[0003] Drivers and passengers often have corresponding use habits for each application program, however, the current intelligent cabin system exhibits application programs to drivers and passengers in a relatively fixed manner, which affects the application program use experience of drivers and passengers. SUMMARY

[0004] Embodiments of the present disclosure provide a correlation analysis method and device for intelligent cabin application programs.

[0005] In a first aspect of the present disclosure, a correlation analysis method for intelligent cabin application programs is provided. The method includes obtaining historical use data of a plurality of application programs, and determining a transaction data set based on the historical use data of each application program, the transaction data set including a plurality of transaction periods and at least one application program corresponding to each transaction period. The method further includes determining a first frequent item set from the transaction data set, and determining a second frequent item set based on a preset correlation parameter, the transaction data set, and the first frequent item set. The method further includes determining an application program correlation set based on the first frequent item set, the second frequent item set, and the historical use data of each application program. In addition, the method further includes determining the correlation position of each application program based on the application program correlation set and the historical use data of each application program.

[0006] In a second aspect of the present disclosure, an association analysis apparatus for intelligent cockpit applications is provided. The apparatus comprises a data determination module configured to acquire historical usage data of a plurality of applications, and determine a transaction data set based on the historical usage data of each application, the transaction data set comprising a plurality of transaction periods and at least one application corresponding to each transaction period. The apparatus further comprises an item set generation module configured to determine a first frequent item set from the transaction data set, and determine a second frequent item set based on a preset association parameter, the transaction data set and the first frequent item set. The apparatus further comprises an application association module configured to determine an application association set based on the first frequent item set, the second frequent item set and the historical usage data of each application. In addition, the apparatus further comprises a location association module configured to determine an association location of each application based on the application association set and the historical usage data of each application.

[0007] In a third aspect of the present disclosure, a computer program product is provided, comprising a computer program executable by a processor to implement the method according to the first aspect.

[0008] In a fourth aspect of the present disclosure, a machine readable storage medium is provided. The machine readable storage medium has stored thereon machine executable instructions, wherein the machine executable instructions are executable by a processor to implement the method provided by the first aspect of the present disclosure.

[0009] It should be understood that the description in the summary is not intended to identify key or essential features of embodiments of the present disclosure or limit the scope of the present disclosure. Other features of the present disclosure will be apparent from review of the description below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0010] The above and other features, aspects and advantages of embodiments of the present disclosure will become more apparent from the following detailed description in conjunction with the accompanying drawings. In the drawings: Figure 1 a schematic diagram illustrating an example environment in which some embodiments of the present disclosure can be implemented is shown; Figure 2 a flowchart of a method for association analysis of intelligent cockpit applications according to some embodiments of the present disclosure is shown; Figure 3 a schematic diagram illustrating a process of determining a frequent item set according to some embodiments of the present disclosure is shown; Figure 4 a schematic diagram illustrating a process of determining an association location of an application according to some embodiments of the present disclosure is shown; Figure 5 a block diagram of an association analysis apparatus for intelligent cockpit applications according to some embodiments of the present disclosure is shown; and Figure 6 A block diagram of an electronic device in which a plurality of embodiments of the present disclosure can be implemented is shown. DETAILED DESCRIPTION

[0011] In order to make the purposes, technical solutions, and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the embodiments of the present application and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0012] The terms “comprise” and “have” and any variations thereof in the specification and claims and above drawings are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but can optionally further include steps or units not listed, or can optionally further include other steps or units inherent to such processes, methods, products, or devices. Depending on the context, the word “if’ as used herein can be interpreted as “when” or “upon” or “in response to determining” or “in response to detecting”.

[0013] As described above, the intelligent cockpit system of the automobile displays a plurality of application programs to the driver and passenger through the display screen, so that the driver and passenger can use each application program according to the needs. However, the driver and passenger often have corresponding use habits for each application program, and the current intelligent cockpit system displays each application program to the driver and passenger in a relatively fixed manner, without considering the relevance between the application programs used by the driver and passenger, resulting in the problem of affecting the application program use experience of the driver and passenger.

[0014] To this end, an embodiment of the present disclosure proposes an association analysis method for an intelligent cockpit application program. The method includes obtaining historical use data of a plurality of application programs, and determining a transaction data set based on the historical use data of each application program, the transaction data set including a plurality of transaction time periods and at least one application program corresponding to each transaction time period. The method further includes determining a first frequent item set from the transaction data set, and determining a second frequent item set based on a preset association parameter, the transaction data set, and the first frequent item set. The method further includes determining an application program association set based on the first frequent item set, the second frequent item set, and the historical use data of each application program. In addition, the method further includes determining an association position of each application program based on the application program association set and the historical use data of each application program.

[0015] In this way, an application association set can be obtained based on the frequent itemsets determined by the historical usage data of multiple applications, so as to explore the correlation between the applications used by drivers and passengers. In addition, based on the application association set and the historical usage data of each application, the association position of each application can be determined. This provides a scientific and reliable basis for the application settings of the intelligent cockpit system, thereby enabling the intelligent cockpit system to present each application to drivers and passengers in a more personalized way, greatly improving the application user experience of drivers and passengers and the comfort of using the intelligent cockpit system.

[0016] Figure 1 Schematic diagrams are shown illustrating example environments in which some embodiments of this disclosure can be implemented. For example... Figure 1 As shown, the example environment 100 may include a smart cockpit system 101 for a vehicle. This smart cockpit system 101 can display multiple applications to the driver and passengers via a screen, allowing the drivers and passengers to use one or more applications as needed. The historical usage data of each application can be collected by the built-in sensors, system logs, or user behavior monitoring module of the smart cockpit system 101. Here, the historical usage data of each application may include one or more of the following: at least one historical usage period, the historical start time corresponding to each historical usage period, the historical end time, the historical usage time, and the usage frequency. It is understood that the methods by which the built-in sensors, system logs, or user behavior monitoring module of the smart cockpit system 101 collect the historical usage data of each application are conventional techniques in the art and will not be elaborated upon here.

[0017] The intelligent cockpit system 101 of some embodiments of this disclosure can also collect historical usage data of different drivers and passengers for each application. For example, it can collect historical usage data of each application according to the ID information of different drivers and passengers, and can store and process the historical usage data of each application separately based on the ID information of different drivers and passengers, but is not limited thereto.

[0018] The example environment 100 further includes a processing terminal 102 that is communicatively coupled to the intelligent cockpit system 101 to obtain historical usage data of the applications by the driver or passenger collected by the intelligent cockpit system 101. In addition, after obtaining the historical usage data of the applications by the driver or passenger, the processing terminal 102 can determine a transaction data set based on the historical usage data of the applications, the transaction data set including a plurality of transaction time periods and at least one application corresponding to each transaction time period. Here, the plurality of transaction time periods included in the transaction data set can be determined based on all historical usage time periods in the historical usage data of the applications, and the at least one application corresponding to each transaction time period can be determined based on at least one application corresponding to each historical usage time period within each transaction time period.

[0019] In addition, the processing terminal 102 can determine a first frequent item set and a second frequent item set based on the transaction data set and a preset association parameter, determine an application association set in combination with the first frequent item set, the second frequent item set, and the historical usage data of the applications, and determine an association position of each application based on the application association set and the historical usage data of the applications. It can be understood that, after obtaining the association position of each application, the processing terminal 102 can feed back the association position of each application to the intelligent cockpit system 101, so that the intelligent cockpit system 101 optimizes and adjusts the way of displaying each application in combination with the association position of each application. Here, the way of optimizing and adjusting the way of displaying each application by the intelligent cockpit system 101 is a routine technical means in the art, and will not be described in detail here.

[0020] In this way, the application association set can be obtained based on the frequent item sets determined based on the historical usage data of the plurality of applications, so as to mine the association between the applications used by the driver or passenger. In addition, the association position of each application is determined based on the application association set and the historical usage data of the applications, so as to provide a scientific and reliable basis for the application setting of the intelligent cockpit system by using the association position of each application, and thus the way of displaying each application by the intelligent cockpit system to the driver or passenger can be more in line with the individual needs, greatly improving the application usage experience of the driver or passenger and the use comfort of the intelligent cockpit system.

[0021] The processing terminal 102 involved in some embodiments of the present disclosure can be a smart phone, a tablet computer, a desktop computer, a laptop computer, a notebook computer, an Ultra-mobile Personal Computer (UMPC), a handheld computer, a PC device, a Personal Digital Assistant (PDA), a routing device, a virtual reality device, etc., and of course can also be a hardware server, a virtual server, a cloud server, a routing device, a gateway device, etc.

[0022] It should be understood that the architecture and functions in the example environment 100 are described for the purpose of illustration only, without implying any limitation on the scope of the present disclosure. Embodiments of the present disclosure can also be applied to other environments with different structures and / or functions.

[0023] Figure 2 A flowchart of a relevance analysis method for smart cockpit applications is shown according to some embodiments of the present disclosure. The method 200 may, for example, be performed by the processing terminal 102 in the example environment 100 shown. Figure 1 As shown in the example environment 100, the processing terminal 102 can be a smart phone, a tablet computer, a desktop computer, a laptop computer, a notebook computer, an Ultra-mobile Personal Computer (UMPC), a handheld computer, a PC device, a Personal Digital Assistant (PDA), a routing device, a virtual reality device, etc., and of course can also be a hardware server, a virtual server, a cloud server, a routing device, a gateway device, etc. Figure 2 As shown in the example environment 100, the processing terminal 102 can be a smart phone, a tablet computer, a desktop computer, a laptop computer, a notebook computer, an Ultra-mobile Personal Computer (UMPC), a handheld computer, a PC device, a Personal Digital Assistant (PDA), a routing device, a virtual reality device, etc., and of course can also be a hardware server, a virtual server, a cloud server, a routing device, a gateway device, etc.

[0024] In some embodiments, when determining the transaction data set based on the historical usage data of each application, the processing terminal can determine a plurality of transaction periods based on all the historical usage periods in the historical usage data of each application. In an example, the earliest historical start time and the latest historical end time can be identified based on all the historical usage periods in the historical usage data of each application, and the period corresponding to the earliest historical start time and the latest historical end time can be evenly divided to obtain a plurality of transaction periods with consistent time lengths.

[0025] Afterwards, the processing terminal can determine at least one application corresponding to each historical usage period in each transaction period as at least one application corresponding to the corresponding transaction period. In an example, one or more transaction moments in each transaction period can be identified to determine each historical usage period containing at least one transaction moment in the historical usage data of each application, and at least one application corresponding to each historical usage period containing at least one transaction moment can be determined as at least one application corresponding to the corresponding transaction period. For example, a historical usage period of application A contains a transaction moment in a transaction period, and a historical usage period of application B also contains a transaction moment in the transaction period, and at least one application corresponding to the transaction period includes application A and application B.

[0026] Afterwards, the processing terminal can integrate each transaction period and at least one application corresponding to the corresponding transaction period into a transaction data set. In an example, each transaction period can be sorted in chronological order, and each transaction period after sorting and at least one application corresponding to the corresponding transaction period can be summarized to obtain a transaction data set.

[0027] In block 204, the method 200 can determine a first frequent item set from the transaction data set, and determine a second frequent item set based on a preset association parameter, the transaction data set and the first frequent item set. Here, the first frequent item set can include single-item frequent items composed of each application and a support degree corresponding to each single-item frequent item, the preset association parameter can include at least one of a preset support degree threshold and a preset confidence threshold, and the second frequent item set can include multiple multi-item frequent items composed of at least two applications and a support degree corresponding to each multi-item frequent item, for example, the second frequent item set can include multiple two-item frequent items composed of two applications and multiple three-item frequent items composed of three applications.

[0028] The way of determining the first frequent item set and the second frequent item set of some embodiments of the present disclosure can be obtained by processing the transaction data set and the preset association parameter based on an association rule algorithm such as the Apriori algorithm or the FP-Growth algorithm, and is not limited thereto.

[0029] In some embodiments, when determining the first frequent item set from the transaction data set, the processing terminal can count the support degree corresponding to each application from the transaction data set. Here, the support degree corresponding to each application can be the ratio between the number of transaction periods corresponding to each application and the number of all transaction periods.

[0030] Afterwards, the processing terminal can integrate each support degree and the corresponding application program which is not less than the preset support degree threshold into the first frequent item set based on the preset support degree threshold. In an example, each support degree which is not less than the preset support degree threshold can be sorted in descending order, and each support degree and the corresponding application program after sorting can be summarized to obtain the first frequent item set. Here, the preset support degree threshold can be 0.2, and is not limited thereto.

[0031] In some embodiments, when the processing terminal determines the second frequent item set based on the preset association parameter, the transaction data set and the first frequent item set, the processing terminal can determine a plurality of candidate frequent items based on each application program in the first frequent item set. Here, each candidate frequent item includes any two application programs in the first frequent item set and the support degrees corresponding to the two application programs. In an example, each application program in the first frequent item set can be combined to obtain a plurality of application program combinations, each application program combination including any two application programs in the first frequent item set, and then the support degrees corresponding to each application program combination can be counted from the transaction data set, and the two application programs included in each application program and the corresponding support degrees can be used as candidate frequent items. It can be understood that the support degree corresponding to each application program combination can be the ratio between the number of transaction periods corresponding to the two application programs included in each application program combination and the number of all transaction periods in the transaction data set.

[0032] Afterwards, the processing terminal can eliminate each candidate frequent item corresponding to each support degree which is less than the preset support degree threshold based on the preset support degree threshold in the preset association parameter, and can determine the confidence degrees corresponding to each remaining candidate frequent item based on the transaction data set after completing the elimination of the corresponding candidate frequent item. It can be understood that the confidence degree corresponding to each candidate frequent item can be the ratio between the support degree corresponding to each candidate frequent item and the support degree corresponding to any one application program in the corresponding candidate frequent item (counted based on the transaction data set).

[0033] Afterwards, the processing terminal can eliminate each candidate frequent item corresponding to each confidence degree which is less than the preset confidence degree threshold based on the preset confidence degree threshold in the preset association parameter, and integrate each remaining candidate frequent item into the second frequent item set. It can be understood that the support degree corresponding to each candidate frequent item in the second frequent item set is greater than or equal to the preset support degree threshold, and the confidence degree corresponding to each candidate frequent item is greater than or equal to the preset confidence degree threshold. Here, the preset confidence degree threshold can be 0.2, and is not limited thereto.

[0034] It should be noted that the application programs corresponding to each of the alternative frequent items in the second frequent item set are two, and some embodiments of the present disclosure can further determine a plurality of three-item alternative frequent items based on each of the alternative frequent items and the transaction data set after determining the second frequent item set, and perform elimination processing on the plurality of three-item alternative frequent items in combination with the preset support threshold and the preset confidence threshold, and then the remaining three-item alternative frequent items can be used as the third frequent item set (of course, they can also be used as the second frequent item set together with the above-mentioned alternative frequent items, without being limited thereto), and the manner of determining the third frequent item set can be referred to above, but will not be described herein again.

[0035] Referring to Figure 3 , Figure 3 A schematic diagram of a frequent item set determination process according to some embodiments of the present disclosure is shown. As Figure 3 indicated, the frequent item set determination process 300 can determine a single-item alternative frequent item set based on the transaction data set, and the single-item alternative frequent item set includes a plurality of single-item frequent items and the support corresponding to each of the single-item frequent items. Then, taking the preset support threshold as 0.2 for example, the first frequent item set can be determined based on the single-item alternative frequent item set, and the first frequent item set includes five single-item frequent items with a support greater than or equal to the preset support threshold, and are represented as [a], [b], [c], [d] and [e] respectively. Then, the two-item alternative frequent item set can be determined based on the first frequent item set and the transaction data set, and the two-item alternative frequent item set includes a plurality of two-item frequent items and the support corresponding to each of the two-item frequent items. Then, taking the preset support threshold as 0.2 and the confidence threshold as 0.2 for example, the second frequent item set can be determined based on the two-item alternative frequent item set, and the second frequent item set includes six two-item frequent items with a support greater than or equal to the preset support threshold and a confidence greater than or equal to the confidence threshold, and are represented as [a, b], [a, c], [a, e], [b, c], [b, d] and [c, e] respectively. Then, the third frequent item set can also be determined based on the second frequent item set and the transaction data set, and the third frequent item set includes two three-item frequent items with a support greater than or equal to the preset support threshold and a confidence greater than or equal to the confidence threshold, and are represented as [a, b, e] and [a, c, e] respectively.

[0036] If some embodiments of the present disclosure do not determine the first frequent item set and the second frequent item set based on the transaction data set and the preset association parameters, it indicates that the preset association parameters need to be adjusted, for example, the preset support threshold and the preset confidence threshold in the preset association parameters can be reduced, and the first frequent item set and the second frequent item set can be determined based on the transaction data set and the adjusted preset association parameters.

[0037] At block 206, the method 200 can determine an application association set based on the first frequent item set, the second frequent item set, and the historical usage data of the applications. Here, the application association set can include one or more application combinations corresponding to at least one of the one or more application combinations corresponding to the first application relationship, the one or more application combinations corresponding to the second application relationship, and the one or more application combinations corresponding to the third application relationship, the first application relationship can be a complementary relationship, the second application relationship can be a substitution relationship, and the third application relationship can be a cause-effect relationship.

[0038] In some embodiments, when determining the application association set based on the first frequent item set, the second frequent item set, and the historical usage data of the applications, the processing terminal can determine a lift degree corresponding to each alternative frequent item in the second frequent item set based on a support degree corresponding to each application in the first frequent item set and a confidence degree corresponding to each alternative frequent item in the second frequent item set. In an example, the lift degree corresponding to each alternative frequent item in the second frequent item set can be a ratio of the confidence degree corresponding to the alternative frequent item to a support degree corresponding to the remaining applications in the alternative frequent item. For example, when the alternative frequent item includes an application A and an application B, the lift degree corresponding to the alternative frequent item can be a ratio of the confidence degree corresponding to the alternative frequent item to a support degree corresponding to the application B, when the confidence degree corresponding to the alternative frequent item is a ratio of the support degrees corresponding to the application A and the application B to the support degree corresponding to the application A.

[0039] Subsequently, the processing terminal can determine a time overlap rate corresponding to each alternative frequent item in the second frequent item set based on the historical usage data of the applications. In an example, based on each application included in each alternative frequent item in the second frequent item set, the processing terminal can determine all historical usage periods in the corresponding historical usage data, and determine a time overlap rate corresponding to each alternative frequent item based on all historical usage periods corresponding to each application included in the alternative frequent item, as a ratio of a length of an intersection period corresponding to all historical usage periods to a length of a union period corresponding to all historical usage periods.

[0040] Afterwards, the processing terminal can determine the candidate frequent items corresponding to the first application relationship based on the lift and time overlap rate corresponding to each candidate frequent item in the second frequent item set, and determine the application association set based on the candidate frequent items corresponding to the first application relationship. In an example, the lift and time overlap rate corresponding to each candidate frequent item in the second frequent item set can be multiplied to obtain a corresponding association strength value, and the candidate frequent item corresponding to each association strength value greater than or equal to a preset first application relationship threshold value can be determined as the candidate frequent item corresponding to the first application relationship. Here, the first application relationship can be a complementary relationship.

[0041] It can be understood that after obtaining the candidate frequent items corresponding to the first application relationship, the candidate frequent items can be sorted in descending order of the association strength value corresponding to each candidate frequent item based on the association strength value corresponding to each candidate frequent item, and a corresponding relationship between the two application programs included in each candidate frequent item and the first application relationship can be established after the sorting processing, and then the application association set is obtained.

[0042] In some embodiments, when determining the application association set based on the candidate frequent items corresponding to the first application relationship, the processing terminal can also determine the semantic information similarity between each two application programs in the first frequent item set based on the semantic information corresponding to each application program in the first frequent item set. Here, the semantic information corresponding to each application program can be understood as the representation information of the function that can be executed by each application program. In an example, each application program in the first frequent item set can be combined to obtain a plurality of application program combinations, each application program combination including any two application programs in the first frequent item set, and the semantic information corresponding to the two application programs in each application program combination can be converted to obtain a corresponding feature vector, and the semantic information similarity between the corresponding two application programs in the first frequent item set can be obtained by calculating the similarity between the two feature vectors.

[0043] Afterwards, the processing terminal can determine the confidence corresponding to each two applications in the first frequent item set based on the transaction data set, and determine the two applications corresponding to the second application relationship based on the confidence corresponding to each two applications in the first frequent item set and the semantic information similarity. Here, the second application relationship can be a substitution relationship, and the manner of determining the confidence corresponding to each two applications in the first frequent item set can refer to the above, but will not be described here in detail. In an example, the confidence corresponding to each two applications in the first frequent item set and the semantic information similarity can be substituted into a preset association strength value calculation formula to obtain the corresponding association strength value, and the two applications corresponding to each association strength value greater than or equal to a preset second application relationship threshold value can be regarded as the two applications corresponding to the second application relationship. The preset association strength value calculation formula can refer to the expression shown as follows: Association strength value = (1-confidence) x semantic information similarity It can be understood that after obtaining the alternative frequent items corresponding to the second application relationship, the two applications can be sorted in descending order of the association strength value corresponding to the alternative frequent items, so as to establish a corresponding relationship between the sorted two applications and the second application relationship, and combine the corresponding relationship between the two applications included in the sorted alternative frequent items and the first application relationship to obtain the application association set.

[0044] Some embodiments of the present disclosure can also determine the timing result between each two applications in the first frequent item set based on the historical use time periods corresponding to the applications in the first frequent item set. Here, the timing result can be the ratio between the number of carrying historical use time periods corresponding to each two applications and the number of all historical use time periods corresponding to the two applications. The carrying historical use time period can be understood as two historical use time periods being regarded as carrying historical use time periods when the interval between the historical start time of a historical use time period and the historical end time of a historical use time period is less than a preset interval threshold value.

[0045] Afterwards, the two applications corresponding to the third application relationship can also be determined based on the timing result between each two applications in the first frequent item set, and the application association set can be determined in combination with the alternative frequent items corresponding to the first application relationship and the two applications corresponding to the second application relationship. Here, the third application relationship can be a cause-effect relationship, and the manner of determining the application association set can refer to the above, but will not be described here in detail.

[0046] At block 208, the method 200 can determine the associated positions of the applications based on the application association set and the historical usage data of the applications. Here, the associated position of each application can be understood as the position of the application that has the association in the preset display interface of the smart cockpit system for displaying the applications, which can be represented by the position coordinates in the preset display interface, and the associated position of each application can be fed back to the smart cockpit system by the processing terminal, so that the smart cockpit system can optimize and adjust the preset display interface for displaying the applications in combination with the associated positions of the applications. For example, two applications that have a complementary relationship can be arranged at adjacent positions or in the same classification directory, and of course, two applications that have a causal relationship can also be arranged at adjacent positions or in the same classification directory, so as to enable the driver or passenger to quickly know the applications that have the association, and reduce the time and energy consumption of the driver or passenger for searching for the related applications in the preset display interface.

[0047] In some embodiments, when the processing terminal determines the associated positions of the applications based on the application association set and the historical usage data of the applications, the processing terminal can count the sum of the usage frequencies corresponding to each candidate frequent item in the application association set based on the usage frequencies in the historical usage data of the applications. It can be understood that each candidate frequent item in the application association set has a corresponding relationship with the first application, that is, the sum of the usage frequencies corresponding to each two applications that have a complementary relationship is counted, and the greater the sum of the usage frequencies, the higher the frequency of using the corresponding two applications by the driver or passenger while the two applications have a complementary relationship.

[0048] Then, the processing terminal can sort each candidate frequent item based on the sum of the usage frequencies corresponding to each candidate frequent item in the application association set. Here, the sorting manner can be to sort the two applications corresponding to each candidate frequent item in descending order of the sum of the usage frequencies, so as to arrange the applications that have a complementary relationship and are used more frequently by the driver or passenger at the front position.

[0049] Afterwards, the processing terminal can adjust the positions of the application programs corresponding to the preset display interface based on the processed each candidate frequent item, and determine the adjusted positions of the application programs as the associated positions of the corresponding application programs. In an example, based on the number of all application programs corresponding to the processed all candidate frequent items, the region where all the application programs with complementary relationship exist in the preset display interface can be determined, and based on the application programs corresponding to the processed each candidate frequent item, the positions of the application programs are adjusted to the specified positions arranged in a specified order in the region where all the application programs with complementary relationship exist, for example, the positions of the two application programs corresponding to the candidate frequent item ranked first can be adjusted to the application program position in the first row and the first column and the application program position in the first row and the second column in the region where all the application programs with complementary relationship exist, and the position coordinates of each specified position in the region where all the application programs with complementary relationship exist are represented as the positions of the corresponding application programs after the adjustment processing. It can be understood that for all the application programs without complementary relationship, if the positions of all the application programs without complementary relationship are not adjusted, the positions of all the application programs without complementary relationship can remain unchanged; if the positions of all the application programs without complementary relationship are occupied, the positions of all the application programs without complementary relationship can be adjusted according to the arrangement mode set in the preset display interface, but not limited thereto.

[0050] Referring to Figure 4 , Figure 4 A schematic diagram of a determination process of the associated positions of the application programs according to some embodiments of the present disclosure is shown. As Figure 4As shown, the determination process 400 of the associated position of the application program can determine the region where all the application programs with complementary relationship exist (including the region where the first two rows of application programs in the preset display interface exist) based on the preset display interface (including the application programs arranged in three rows and three columns) and the number of all the application programs corresponding to all the candidate frequent items after the sorting processing, and adjust the positions of the application programs corresponding to the candidate frequent items after the sorting processing to the specified positions arranged in the specified order in the region where all the application programs with complementary relationship exist in sequence. Here, taking the application programs corresponding to the candidate frequent items after the sorting processing as application program A, application program F, application program B, application program D, application program E and application program C in sequence as an example, the associated position of the application program A can be represented as the application program position coordinates in the first row and the first column of the preset display interface, the associated position of the application program F can be represented as the application program position coordinates in the first row and the second column of the preset display interface, the associated position of the application program B can be represented as the application program position coordinates in the first row and the last column of the preset display interface, the associated position of the application program D can be represented as the application program position coordinates in the second row and the first column of the preset display interface, the associated position of the application program E can be represented as the application program position coordinates in the second row and the second column of the preset display interface, and the associated position of the application program C can be represented as the application program position coordinates in the second row and the last column of the preset display interface.

[0051] Some embodiments of the present disclosure can further acquire the current use data of an application program (for example, the current starting time of an application program) collected by the intelligent cockpit system in real time after determining the application program association set, and can determine the associated application programs with complementary relationship based on the application program association set, and can feed back the associated application programs to the intelligent cockpit system, so as to recommend the associated application programs to the driver and passenger in the preset display interface by the intelligent cockpit system, thereby improving the use convenience of the driver and passenger for the application program.

[0052] Some embodiments of the present disclosure can further generate the corresponding application program linkage demand based on the application programs with complementary relationship in the application program association set after determining the application program association set, for example, for the car navigation application program and the car air conditioner control application program with complementary relationship, the processing terminal can generate the linkage demand of adjusting the in-vehicle air conditioner setting temperature based on the external environment temperature of the navigation route, the linkage demand can be the corresponding list of the external environment temperature and the air conditioner setting temperature, and the linkage demand can be fed back to the intelligent cockpit system, so as to automatically adjust the in-vehicle air conditioner setting temperature according to the linkage demand by the intelligent cockpit system, thereby realizing the more intelligent and personalized intelligent cockpit system control. Of course, the application programs with complementary relationship also include the car air conditioner control application program and the car seat heating control application program, etc., which are not limited thereto.

[0053] Figure 5 A block diagram of an association analysis apparatus for intelligent cockpit applications is shown in accordance with some embodiments of the present disclosure. As shown Figure 5 The association analysis apparatus 500 for intelligent cockpit applications includes a data determination module 502 configured to acquire historical usage data of a plurality of applications, and determine a transaction data set based on the historical usage data of each application, the transaction data set including a plurality of transaction periods and at least one application corresponding to each transaction period. The association analysis apparatus 500 for intelligent cockpit applications also includes an item set generation module 504 configured to determine a first frequent item set from the transaction data set, and determine a second frequent item set based on a preset association parameter, the transaction data set, and the first frequent item set. The association analysis apparatus 500 for intelligent cockpit applications further includes a program association module 506 configured to determine an application association set based on the first frequent item set, the second frequent item set, and the historical usage data of each application. In addition, the association analysis apparatus 500 for intelligent cockpit applications also includes a location association module 508 configured to determine an association location of each application based on the application association set and the historical usage data of each application.

[0054] Figure 6 A block diagram of an electronic device in which a number of embodiments of the present disclosure can be implemented is shown. As shown Figure 6 The electronic device 600 includes a processor 601 that can perform various appropriate actions and processes in accordance with computer program instructions loaded into a random access memory (RAM) 603 from computer program instructions stored in a read-only memory (ROM) 602. Various programs and data required for operation of the electronic device 600 can also be stored in the RAM 603. The processor 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0055] The various processes and processes described above, such as the method 200, can be performed by the processor 601. For example, in some embodiments, the method 200 can be implemented as a software program tangibly embodied in a machine-readable medium. In some embodiments, part or all of the software program can be loaded and / or installed on the electronic device 600 via the ROM 602. When the software program is loaded into the RAM 603 and executed by the processor 601, one or more actions of the method 200 described above can be performed.

[0056] The functionality described herein above can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, illustrative types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Program- specific Integrated Circuits (ASICs), Program- specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0057] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / operations specified in the flowchart and / or block diagram block or blocks. The program code can be retrieved from a machine-readable storage medium, loaded onto the machine, and executed by the machine. The machine can be any suitable combination of hardware and / or software.

[0058] The present disclosure can be a method, apparatus, system, and / or program product. Program products can include machine-readable storage media with machine- readable program instructions stored therein to perform various aspects of the present disclosure. The machine-readable program instructions described herein can be downloaded to various computing / processing devices from a machine-readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network, and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives machine-readable program instructions from the network and forwards the machine-readable program instructions to a machine-readable storage medium within the respective computing / processing device for execution by the computing device.

[0059] Machine program instructions for performing operations of the present disclosure can be assembly instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The machine readable program instructions may, in entirety, be executed on the user's computer, executed partially on the user's computer, executed as a standalone software package, executed partially on the user's computer and partially on a remote computer, or executed entirely on a remote computer or server. In situations

[0060] In the context of the present disclosure, a machine readable medium can be a tangible medium that can contain or store program for use by or in connection with an instruction execution system, apparatus, or device. The machine readable medium can be a machine readable signal medium or a machine readable storage medium. Machine readable medium can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine readable storage medium would include one or more lines of electrical wire, portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing. Further, while operations are depicted in a particular order, this should not be understood as requiring such order or sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing can be advantageous. Likewise, while specific implementations are discussed herein, these should not be construed as limiting the scope of the present disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable sub-combination.

[0061] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

1. A correlation analysis method for smart cockpit applications, characterized in that, include: Historical usage data of multiple applications are obtained, and a transaction dataset is determined based on the historical usage data of each application. The transaction dataset includes multiple transaction periods and at least one application corresponding to each transaction period. A first frequent itemset is determined from the transaction dataset, and a second frequent itemset is determined based on preset association parameters, the transaction dataset, and the first frequent itemset; Based on the first frequent itemset, the second frequent itemset, and the historical usage data of each application, an application association set is determined; as well as Based on the application association set and the historical usage data of each application, the association location of each application is determined.

2. The method according to claim 1, characterized in that, The historical usage data for each of the aforementioned applications includes at least one historical usage period; The determination of the transaction dataset based on the historical usage data of each of the applications includes: Based on all the historical usage periods in the historical usage data of each of the aforementioned applications, multiple transaction periods are determined; At least one application corresponding to each of the historical usage periods within each of the aforementioned transaction periods is identified as at least one application corresponding to the corresponding transaction period; and Each of the aforementioned transaction periods and at least one of the aforementioned applications corresponding to the respective transaction periods are integrated into a transaction dataset.

3. The method according to claim 1, characterized in that, Determining the first frequent itemset from the transaction dataset includes: The support level of each application is statistically analyzed from the transaction dataset; and Each support level not less than a preset support threshold and the corresponding application are integrated into a first frequent itemset.

4. The method according to claim 3, characterized in that, The preset association parameters include the preset support threshold and the preset confidence threshold; The step of determining the second frequent itemset based on preset association parameters, the transaction dataset, and the first frequent itemset includes: Based on each of the applications in the first frequent itemset, a plurality of candidate frequent items are determined, each candidate frequent item including any two applications in the first frequent itemset and the support corresponding to the two applications. The candidate frequent items corresponding to each support level less than the preset support threshold are eliminated; and Based on the transaction dataset, the confidence level corresponding to each of the candidate frequent items is determined. Candidate frequent items corresponding to each confidence level that is less than the preset confidence level threshold are eliminated, and the remaining candidate frequent items are integrated into the second frequent itemset.

5. The method according to claim 4, characterized in that, The step of determining the application association set based on the first frequent itemset, the second frequent itemset, and the historical usage data of each application includes: Based on the support corresponding to each application in the first frequent itemset and the confidence corresponding to each candidate frequent item in the second frequent itemset, the lift corresponding to each candidate frequent item in the second frequent itemset is determined. Based on the historical usage data of each of the aforementioned applications, determine the time overlap rate corresponding to each of the candidate frequent items in the second frequent item set; and Based on the lift and time overlap rate corresponding to each of the candidate frequent items in the second frequent itemset, each of the candidate frequent items corresponding to the first application relationship is determined, and an application association set is determined based on each of the candidate frequent items corresponding to the first application relationship.

6. The method according to claim 5, characterized in that, The step of determining the application association set based on each of the candidate frequent items corresponding to the first application relationship further includes: Based on the semantic information corresponding to each application in the first frequent itemset, the semantic information similarity between every two applications in the first frequent itemset is determined; Based on the transaction dataset, determine the confidence level corresponding to each pair of applications in the first frequent itemset; and Based on the confidence level and semantic information similarity of each pair of applications in the first frequent itemset, the two applications corresponding to the second application relationship are determined, and based on each of the candidate frequent items corresponding to the first application relationship and each of the two applications corresponding to the second application relationship, an application association set is determined.

7. The method according to claim 5, characterized in that, Historical usage data for each application also includes usage frequency; The step of determining the association location of each application based on the application association set and the historical usage data of each application includes: Based on the usage frequency in the historical usage data of each application, the sum of the usage frequencies corresponding to each of the candidate frequent items in the application association set is calculated; Based on the sum of the usage frequencies corresponding to each of the candidate frequent items in the application association set, the candidate frequent items are sorted; and Based on the sorted and selected frequent items, the positions of each application in the preset display interface are adjusted, and the adjusted positions of each application are determined as the associated positions of the corresponding applications.

8. A correlation analysis device for a smart cockpit application, characterized in that, include: The data determination module is configured to acquire historical usage data of multiple applications and determine a transaction dataset based on the historical usage data of each application. The transaction dataset includes multiple transaction periods and at least one application corresponding to each transaction period. The itemset generation module is configured to determine a first frequent itemset from the transaction dataset, and to determine a second frequent itemset based on preset association parameters, the transaction dataset, and the first frequent itemset; The application association module is configured to determine the application association set based on the first frequent itemset, the second frequent itemset, and the historical usage data of each application. as well as The location association module is configured to determine the associated location of each application based on the application association set and the historical usage data of each application.

9. A computer-readable storage medium having a computer program stored thereon, the computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform the steps of the method as claimed in any one of claims 1-7.

10. An electronic device, characterized in that, include: One or more processors, and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method according to any one of claims 1-7.

Images