Information processing methods, behavior recommendation methods and devices, electronic devices and media
By constructing and updating the frequent set of user behavior sequence sets, the accuracy and universality issues of user behavior habit mining in existing technologies are solved, resulting in more accurate behavior recommendations and improved user experience.
Patent Information
- Application Number
- CN202211399209.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-11-09
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2042-11-09
AI Technical Summary
Existing methods for mining user behavior habits have low accuracy and poor universality, which affects the accuracy of behavior recommendations and leads to a poor user experience.
By constructing a set of original behavioral sequences of users' historical interaction information, and using association mining algorithms to generate a current frequent set and update the historical frequent set, a relationship between triggering behavior and response behavior is formed, reflecting users' operating habits.
Without human intervention, it improves the accuracy and universality of user behavior habit mining, simplifies user operations, and enhances the accuracy of behavior recommendations.
Smart Images

Figure CN118051663B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of computer technology, specifically to an information processing method, an information processing apparatus, a behavior recommendation method, a behavior recommendation apparatus, an electronic device, and a computer-readable storage medium. Background Technology
[0002] With the rapid development of computer and internet technologies, users increasingly expect convenient operation and higher efficiency in human-computer interaction. Therefore, by analyzing and processing user interaction behavior information, it is possible to predict user operation needs in advance and make behavioral recommendations.
[0003] Currently, methods for mining user behavior habits in related technologies still suffer from low accuracy and poor universality, which in turn affects the accuracy of recommendation behavior and, to some extent, the user experience. Summary of the Invention
[0004] The purpose of this disclosure is to provide an information processing method and apparatus, a behavior recommendation method and apparatus, an electronic device, and a computer-readable storage medium, thereby improving the accuracy and universality of methods for mining user behavior habits to at least a certain extent, so as to improve the accuracy of behavior recommendations.
[0005] According to a first aspect of this disclosure, an information processing method is provided, comprising: determining an original behavior sequence set based on user historical interaction information; performing correlation sequence analysis processing on the original behavior sequence set to obtain a current frequent set, wherein frequent items in the current frequent set include behavior rules and occurrence attribute information corresponding to the behavior rules, the behavior rules including triggering behaviors and response behaviors of the triggering behaviors; and updating a historical frequent set using the current frequent set based on the triggering behaviors, the response behaviors of the triggering behaviors, and the occurrence attribute information.
[0006] According to a second aspect of this disclosure, a behavior recommendation method is provided, comprising: determining an original behavior sequence set based on user historical interaction information; performing association sequence analysis on the original behavior sequence set to obtain a current frequent set, wherein frequent items in the current frequent set include behavior rules and occurrence attribute information corresponding to the behavior rules, the behavior rules including triggering behaviors and response behaviors of the triggering behaviors; updating the historical frequent set using the current frequent set based on the triggering behaviors, the response behaviors of the triggering behaviors, and the occurrence attribute information to obtain an updated frequent set; and recommending target operation behaviors to the user based on the updated frequent set and the user's current interaction information.
[0007] According to a third aspect of this disclosure, an information processing apparatus is provided, comprising: a determining module, configured to determine an original behavior sequence set based on user historical interaction information; a processing module, configured to perform correlation sequence analysis processing on the original behavior sequence set to obtain a current frequent set, wherein frequent items in the current frequent set include behavior rules and occurrence attribute information corresponding to the behavior rules, the behavior rules including triggering behavior and response behavior of the triggering behavior; and an updating module, configured to update a historical frequent set using the current frequent set based on the triggering behavior, the response behavior of the triggering behavior, and the occurrence attribute information.
[0008] According to a fourth aspect of this disclosure, a behavior recommendation device is provided, comprising: a determining module, configured to determine an original behavior sequence set based on user historical interaction information; a processing module, configured to perform correlation sequence analysis processing on the original behavior sequence set to obtain a current frequent set, wherein frequent items in the current frequent set include behavior rules and occurrence attribute information corresponding to the behavior rules, and the behavior rules include triggering behaviors and response behaviors of the triggering behaviors; an updating module, configured to update the historical frequent set using the current frequent set based on the triggering behaviors, the response behaviors of the triggering behaviors, and the occurrence attribute information to obtain an updated frequent set; and a recommending module, configured to recommend target operation behaviors to the user based on the updated frequent set and the user's current interaction information.
[0009] According to a fifth aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to perform the method described above.
[0010] According to a sixth aspect of this disclosure, a computer-readable storage medium is provided that stores a computer program thereon, which, when executed by a processor, implements the method described above.
[0011] The information processing scheme provided in this disclosure constructs an original behavior sequence set through user historical interaction information, and obtains a current frequent set by mining the associated sequences in the original behavior sequence set. This current frequent set is then used to update the historical frequent set, thereby realizing the mining of user operation behavior habits. On the one hand, without human intervention, by learning the original behavior sequences, frequent items including triggering behaviors and corresponding response behaviors are assembled using user interaction behaviors. The frequent items in the current frequent set are then used to update the frequent items in the historical frequent set, enabling the frequent items in the updated frequent set to correlate triggering behaviors with response behaviors, accurately representing the user's operation habits. On the other hand, based on the correlation between the triggering and response behaviors of frequent items, corresponding response behaviors can be quickly provided when a user triggers a behavior, which has practical significance for the further application of products related to user perception and simplified user operations.
[0012] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description
[0013] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:
[0014] Figure 1 A schematic diagram illustrates an exemplary application environment in which an information processing method and apparatus according to embodiments of the present disclosure can be applied;
[0015] Figure 2 This schematically illustrates a flowchart of an information processing method according to an exemplary embodiment of the present disclosure;
[0016] Figure 3 A flowchart illustrating an implementation of determining an original set of behavioral sequences in an exemplary embodiment of this disclosure is shown schematically.
[0017] Figure 4 This diagram schematically illustrates a historical interaction behavior and the timing of the occurrence of the historical interaction behavior in an exemplary embodiment of this disclosure;
[0018] Figure 5 This illustration schematically depicts a time range extension in an exemplary embodiment of the present disclosure;
[0019] Figure 6 The flowchart schematically illustrates an implementation of obtaining the current frequent set in an exemplary embodiment of this disclosure;
[0020] Figure 7 A flowchart illustrating another information processing method according to an exemplary embodiment of the present disclosure is shown schematically.
[0021] Figure 8 This illustration schematically depicts a frequently updated history set in an exemplary embodiment of the present disclosure;
[0022] Figure 9 A flowchart illustrating an exemplary embodiment of the present disclosure is shown schematically.
[0023] Figure 10 This schematically illustrates a flowchart of an exemplary embodiment of the present disclosure that recommends a target operation behavior to a user based on a frequently updated set and the user's current interaction information;
[0024] Figure 11 This schematic diagram illustrates the composition of an information processing apparatus according to an exemplary embodiment of the present disclosure.
[0025] Figure 12 This schematic diagram illustrates the composition of a behavior recommendation device in an exemplary embodiment of the present disclosure;
[0026] Figure 13 A schematic diagram of an electronic device to which embodiments of the present disclosure may be applied is shown. Detailed Implementation
[0027] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
[0028] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.
[0029] Figure 1 A schematic diagram illustrates an exemplary application environment in which an information processing scheme applicable to embodiments of the present disclosure can be applied.
[0030] like Figure 1As shown, the terminal device can be an intelligent device with information processing function, such as a smartphone, computer, tablet, smartwatch, in-vehicle device, wearable device, monitoring device, etc. The terminal device can also be called a mobile terminal, terminal, mobile device, etc. This disclosure does not limit the type of terminal device.
[0031] In this embodiment of the present disclosure, the information processing device of the terminal device can determine the original behavior sequence set based on the information processing method of this embodiment of the present disclosure according to the user's historical interaction information; perform correlation sequence analysis processing on the original behavior sequence set to obtain the current frequent set, the frequent items in the current frequent set include behavior rules and occurrence attribute information corresponding to the behavior rules, the behavior rules include triggering behavior and response behavior of triggering behavior; based on the triggering behavior, the response behavior of triggering behavior and occurrence attribute information, use the current frequent set to update the historical frequent set to obtain the updated frequent set.
[0032] It should be noted that the information processing method provided in this disclosure can be executed by a terminal device. The information processing method provided in this disclosure can also be executed by a server, and correspondingly, the information processing device can also be located in the server. The server can be a backend system providing information processing-related services in this disclosure, and may include a single electronic device with computing capabilities, such as a portable computer, desktop computer, or smartphone, or a cluster of multiple electronic devices. In this disclosure, the information processing method is described using an example of execution by a terminal device.
[0033] refer to Figure 2 As shown, the information processing method of this disclosure embodiment may include the following steps S210 to S230:
[0034] In step S210, the original behavior sequence set is determined based on the user's historical interaction information.
[0035] In the exemplary embodiments of this disclosure, user historical interaction information refers to interaction information generated by the user using the terminal device, including but not limited to latitude and longitude information, Bluetooth connection information, Wi-Fi connection information, application usage information, settings information, screen on / off information, etc. The original behavior sequence set includes original behavior sequences, which are generated based on the user's historical interaction behaviors and the corresponding time ranges.
[0036] The extraction time range for user historical interaction information can be 1 day, 3 days, 1 week, etc., and there are no special requirements for this. For example, the data dimension of the previous day can be extracted as the user historical interaction data for the current day.
[0037] For example, the original behavior sequence is "(timestamp interval - Bluetooth connection), (timestamp interval - Bluetooth connection - using application A), (timestamp interval - Bluetooth connection - using application B), (timestamp interval - using application B)", where "Bluetooth connection", "Bluetooth connection - using application A" and "Bluetooth connection - using application B" are interactive behaviors extracted from the user's historical interaction information, and the timestamp interval is the time range corresponding to the original behavior sequence.
[0038] In some possible embodiments, after obtaining the user's historical interaction information, further processing such as filtering, deduplication, and clustering labeling can be performed.
[0039] For example, for application usage information, the package name and corresponding timestamp of each application used by the user are recorded. The processing involved is to filter short-term data, such as data whose usage time does not exceed a set time, such as 2 seconds, to avoid accidental touches or misoperations.
[0040] For example, for screen on / off information, the screen states such as on / off, off, and unlock are recorded along with their corresponding timestamps. The processing involves filtering short-duration screen on / off times and extracting the first screen on after a screen off time greater than a set threshold, such as a threshold range of (2h-12h), which can be set according to specific circumstances.
[0041] For example, for latitude and longitude information, the latitude and longitude points generated by the user can be recorded; such as longitude: 113.91884, latitude: 22.570468, and the corresponding timestamp 1624700288270ms. By clustering the location data, the mobile device's permanent location is learned, and the latitude and longitude within the permanent location range are marked with the corresponding permanent location (if there are permanent location clustering results). For example, when the cluster center of the user's home is longitude: 113.918447, latitude: 22.570477, and the cluster radius is 12.89 meters, the current data is within the range of the permanent home, and the current latitude and longitude is marked as the permanent home.
[0042] For example, for device connection information, the system records the user's device connection status, including connection status, device name, and corresponding timestamp, and performs deduplication on the data. Additionally, for settings information, the system records the relevant device settings status, such as entering / exiting airplane mode and the corresponding timestamp, and performs deduplication on the data.
[0043] The above examples are for illustrative purposes only, and the embodiments disclosed herein include, but are not limited to, the above data preprocessing methods.
[0044] The embodiments of this disclosure can mine user interaction behavior habits based on user historical interaction information, generate original behavior sequences, and form an original behavior sequence set based on each original behavior sequence.
[0045] In step S220, the original behavior sequence set is subjected to association sequence analysis to obtain the current frequent set. The frequent items in the current frequent set include behavior rules and the occurrence attribute information corresponding to the behavior rules. The behavior rules include triggering behaviors and response behaviors of triggering behaviors.
[0046] In the exemplary embodiments of this disclosure, association mining algorithms can be used to perform association sequence analysis on the original behavior sequence set. These algorithms include, but are not limited to, April (association rule algorithm) and Prefix Span (Prefix-Projected Pattern Growth), and no special requirements are specified. For example, taking the PrefixSpan algorithm, a support threshold α = 1 can be set, meaning that as many original behavior sequences as possible are retained. This algorithm is then used to perform association sequence mining on the original behavior sequence set to obtain the current frequent set.
[0047] The currently frequently occurring items include behavioral rules (triggered behaviors and their response behaviors) and the occurrence attribute information corresponding to the behavioral rules. Occurrence attribute information includes, but is not limited to, the number of occurrences and the time since the last occurrence. A triggered behavior is a user interaction that can serve as a triggering event, such as connecting to Bluetooth or connecting to Wi-Fi. The corresponding response behavior is the response event to the triggering event; for example, connecting to Bluetooth uses application A, and connecting to Wi-Fi uses application B.
[0048] By performing correlation sequence analysis on the original behavior sequence set, a correspondence between triggering behavior and response behavior can be constructed. By combining triggering behavior and response behavior, a scenario can be formed without human intervention to preset the scenario. This avoids the shortcomings of manually setting thresholds, which cannot adapt to all users. It is beneficial to improve the universality of mining user habit behavior, and thus improves the accuracy of behavior recommendation based on the information processing method of this disclosure embodiment.
[0049] In step S230, based on the triggering behavior, the response behavior of the triggering behavior, and the occurrence attribute information, the historical frequent set is updated using the current frequent set to obtain the updated frequent set.
[0050] In an exemplary embodiment of this disclosure, the historical frequent set is a frequent set that existed prior to obtaining the current user's historical interaction information. The frequent items in the historical frequent set also include behavioral rules and the occurrence attribute information corresponding to the behavioral rules. Furthermore, the behavioral rules include triggering behaviors and the corresponding response behaviors. In other words, the information processing method in this embodiment is a process of continuously updating the historical frequent set incrementally using the current frequent set, to ensure that the updated historical frequent set (also called the updated frequent set) conforms as closely as possible to the user's latest operating habits.
[0051] In one exemplary embodiment, an implementation for determining an original set of behavioral sequences is provided. For example... Figure 3 As shown, determining the original behavior sequence set based on user historical interaction information may include steps S310 to S340:
[0052] Step S310: Extract historical interaction behaviors and the corresponding occurrence times from the user's historical interaction information.
[0053] Historical interaction behavior includes user interaction behavior across different dimensions, and any dimension of historical interaction behavior can further include different types of interaction events. For example, see Figure 4 The diagram illustrates a historical interaction behavior and the occurrence time of the historical interaction behavior according to an exemplary embodiment of the present disclosure. The historical interaction behavior may include application dimension, Bluetooth dimension, Wi-Fi dimension and location dimension. The application dimension may also include different types of application A, application B and application C, etc., and each interaction event has a corresponding occurrence time.
[0054] Step S320: Determine the timestamp interval, and expand the range of the occurrence time of the historical interaction behavior based on the timestamp interval to obtain the time range of the historical interaction behavior.
[0055] The timestamp interval is set according to actual needs, and historical interaction information can be divided into multiple time periods according to the timestamp interval. For example, if the historical interaction information is the interaction data generated by the user in one day (24 hours), and the timestamp interval is 0.5 hours, then the day is divided into 48 time periods, such as 0:00 to 0:30 as one time period, 0:30 to 1:00 as another time period, and so on, to get 48 time periods.
[0056] Since user interaction behaviors have a time difference in sequence, it is usually impossible to manually set the effective time range of the historical interaction behaviors for each dimension. The range of the occurrence time of historical interaction behaviors can be expanded based on the timestamp interval.
[0057] When expanding the range of historical interaction times based on timestamp intervals, the range of historical interaction times within each timestamp interval (time period) is expanded. The historical interaction times between each timestamp interval are independent of each other and do not interfere with each other.
[0058] In one exemplary embodiment, an implementation method for extending the time range is provided. Extending the time range of historical interaction behaviors based on timestamp intervals to obtain the time range of historical interaction behaviors may include:
[0059] Determine the effective duration of historical interaction behaviors;
[0060] Within each timestamp interval, starting from the time of occurrence of the historical interaction, the time range of the occurrence of the historical interaction is expanded according to the effective time length to obtain the time range of the historical interaction.
[0061] Among them, the historical interaction behaviors of different dimensions have their own corresponding effective time lengths. That is, the effective time lengths corresponding to the historical interaction behaviors of each dimension can be the same or different, and can be set according to the actual situation. No special restrictions are imposed on this.
[0062] Figure 5 A schematic diagram illustrating a time range extension according to an exemplary embodiment of the present disclosure is shown, such as... Figure 5 As shown, if the effective time length of historical interaction behavior for each dimension is set to 5 minutes, in timestamp interval 1, for the Bluetooth dimension, the occurrence time will be extended from 8:01 to "8:01-8:06"; in timestamp interval 2, for the Wi-Fi dimension, the occurrence time will be extended from 8:51 to "8:51-8:56", and so on.
[0063] It is worth noting that, for any dimension of historical interaction behavior, if the time difference between the starting points of the occurrence times of the first and second interaction events of different types is less than the effective time length, the occurrence time of the second interaction event that occurred later is taken as the starting point, and the range of the occurrence time of the second interaction event is expanded according to the effective time length.
[0064] See also Figure 5 As shown, for the application dimension, if the time difference between the starting points of the occurrence time of application A and application B is less than 5 minutes, then the occurrence time of application B is expanded by 5 minutes from the starting point.
[0065] Furthermore, the occurrence times of historical interactions belonging to the same dimension between timestamp interval 1 and timestamp interval 2 do not affect each other.
[0066] By expanding the range of historical interaction times according to a preset effective time length, the time difference between sequential historical interactions can be compensated for. The determination of the effective time length for different dimensions can also be obtained through learning and analysis of user historical interaction information, thereby allowing for targeted expansion of the range of historical interaction times. For example, if a user typically spends a relatively long time at their usual residence, the effective time length for that dimension can be increased.
[0067] Step S330: Based on the relationship between the time ranges of historical interaction behaviors within the timestamp interval, determine the original behavior sequence corresponding to the historical interaction behaviors within the timestamp region.
[0068] Within the same timestamp interval, historical interaction behaviors can be generated across multiple dimensions. Therefore, within the same timestamp interval, the original behavior sequence corresponding to historical interaction behaviors within the same timestamp interval can be determined based on historical interaction behaviors that overlap in time ranges. The sequence items in the original behavior sequence carry information about the timestamp interval.
[0069] For example, see [link to example]. Figure 5 As shown, within timestamp interval 1, a Bluetooth connection occurs between 8:01 and 8:02. Between 8:02 and 8:06, the time ranges for connecting via Bluetooth and using application A overlap, as do the time ranges for connecting via Bluetooth and using application B. Application B is used after 8:06. Based on timestamp interval 1, the original behavior sequence can be obtained as: (8:00-8:30 Bluetooth connection), (8:00-8:30-Bluetooth connection-Application A), (8:00-8:30-Bluetooth connection-Application B), (8:00-8:30-Application B). Correspondingly, the original sequence for timestamp interval 2 can be obtained as: (8:30-9:00-Residential Location 1), (8:30-9:00-Residential Location 1-wifi1 connection), (8:30-9:00-Residential Location 1-wifi1 connection-Using Application C), (8:30-9:00-wifi1 connection-Using Application C), (8:30-9:00-Using Application C).
[0070] By forming the original behavior sequence corresponding to each timestamp interval, the historical interaction behaviors in each timestamp interval are combined according to the occurrence time. The resulting original behavior sequence can accurately reflect the user interaction behaviors within that timestamp interval.
[0071] Step S340: Form an original behavior sequence set based on the original behavior sequences corresponding to each timestamp interval.
[0072] After obtaining the original behavior sequences corresponding to each timestamp interval, an original behavior sequence set can be formed based on the original behavior sequences corresponding to each timestamp interval.
[0073] In an exemplary embodiment, to further improve the accuracy of the original behavior sequence set in reflecting user operating habits, post-processing operations can be performed on the original behavior sequence set. The sequence items in the original behavior sequence set include triggering behaviors and response behaviors.
[0074] In some possible embodiments, the original behavioral sequence can be deduplicated to remove sequence repetitions caused by time range expansion.
[0075] In some possible embodiments, the order of sequence items in the original behavior sequence can be adjusted based on preset interaction state change information. That is, the order of sequence items in the original behavior sequence can be adjusted according to the normal order of event state changes to avoid the occurrence of behavior that should happen later occurring before behavior that should happen first.
[0076] Based on this, the problem of incorrect subsequent behavior recommendations caused by the order in which behaviors occur can be avoided.
[0077] In some possible embodiments, the order of triggering behaviors in a sequence item can be adjusted based on preset interaction state change information.
[0078] For example, if the sequence "Bluetooth connection → Wi-Fi connection → Use application A" already exists, then the adjusted sequence "Wi-Fi connection → Bluetooth connection → Use application A" is also considered reasonable, and the two sequences are considered to be the same sequence.
[0079] Based on this, the order in which triggering behaviors occur can be avoided from affecting the occurrence of the final response behavior, thus improving the accuracy of the original behavior sequence.
[0080] In one exemplary embodiment, an implementation for obtaining the current frequent set is provided. For example... Figure 6 As shown, performing association sequence analysis on the original set of behavioral sequences to obtain the current frequent set may include steps S610 to S630:
[0081] Step S610: Perform association sequence analysis on the original behavior sequence set to determine the historical interaction behavior that serves as the triggering behavior and the historical interaction behavior that serves as the response behavior corresponding to the triggering behavior from the historical interaction behavior in each original behavior sequence, so as to obtain the behavior rules.
[0082] Association mining algorithms are used to perform association analysis on the original set of behavior sequences, thereby obtaining behavior rules, which include triggering behaviors and response behaviors.
[0083] In the sequence “Bluetooth connection → Wi-Fi connection → Use application A”, “Bluetooth connection → Wi-Fi connection” is the triggering behavior, and “Use application A” is the response behavior.
[0084] Step S620: Based on the user's historical interaction information, determine the occurrence attribute information corresponding to the behavior rule.
[0085] Occurrence attribute information includes, but is not limited to, the number of occurrences and the time since the last occurrence. Occurrence attribute information for various dimensions of behavioral rules can be obtained based on the user's historical interaction information.
[0086] Taking the number of occurrences as an example, if the timestamp interval is 0.5h, and the time dimension for obtaining user historical interaction information is 1 day, then 1 day is divided into 48 time periods. If "Bluetooth connection" exists in each time period, then the number of occurrences corresponding to Bluetooth connection is 48.
[0087] Step S630: Determine frequent items based on the behavior rules and the occurrence attribute information corresponding to the behavior rules, and form the current frequent set based on all the obtained frequent items.
[0088] After obtaining the behavior rules and their occurrence attribute information, i.e., obtaining a frequent item, the current frequent set is formed based on all the frequent items.
[0089] The frequent items in the current frequent set include behavioral rules and their corresponding occurrence attribute information. Behavioral rules include triggering behaviors and their response behaviors. For example, one frequent item in the current frequent set might be "Bluetooth connection → Wi-Fi connection → Using application A (days since last occurrence: 1; number of occurrences: 1)". Of course, the specific format can be adjusted according to the implementation, and no special limitations are imposed.
[0090] In one exemplary embodiment, an implementation method for updating a historical frequent set is provided. The occurrence attribute information further includes the occurrence weight of the behavior rule and the time since the behavior rule last appeared. The occurrence weight is determined based on the number of times the behavior rule appears. For example, if the behavior rule appears 48 times, the corresponding occurrence weight can be log(48+1). This smooths out the occurrence count of the behavior rule to obtain the corresponding occurrence weight, thus avoiding the impact of abnormal data caused by a sharp increase in the occurrence count due to multiple clicks or occurrences within the same time period on the overall result.
[0091] Based on the triggering behavior, the response behavior of the triggering behavior, and the occurrence attribute information, updating the historical frequent set using the current frequent set can include the following cases:
[0092] In some possible embodiments, in response to the fact that the frequent items in the current frequent cluster have the same behavior rule as the frequent items in the historical frequent cluster, the occurrence weight corresponding to the same behavior rule in the historical frequent cluster and the time since the last occurrence of the same behavior rule are updated.
[0093] For example, if a historical frequent set includes the frequent item "Bluetooth connection -> using application A" - (days since last occurrence: 4, weight: 3)", and the current frequent set only includes "Bluetooth connection -> using application A" - (days since last occurrence: 1, weight: 1)", then the frequent item in the historical frequent set is updated to "Bluetooth connection -> using application A" - (days since last occurrence: 1, weight: 3 + log(m + 1)). Here, m is obtained based on the number of days since the frequent item appeared in the current frequent set. In other words, when the behavior rules of frequent items in the historical frequent set and frequent items in the current frequent set are the same, the number of days since last occurrence is updated, and the weight is also updated.
[0094] It is worth noting that, in order to avoid the impact of abnormal data on the overall result caused by multiple clicks or multiple occurrences within the same time period, the example uses the log(m+1) method for processing. Other methods can also be used for data smoothing in this embodiment of the disclosure, and no special restrictions are placed on this.
[0095] In some possible embodiments, in response to the fact that the first frequent item in the current frequent set and the second frequent item in the historical frequent set have the same triggering behavior and the response behavior of the same behavior scenario is different, the occurrence weight of the behavior rule corresponding to the second frequent item can be reduced, and the time since the last occurrence of the behavior rule corresponding to the second frequent item can be accumulated.
[0096] For example, if a historical frequent set includes the frequent item "Bluetooth connection -> using application A" - (days since last occurrence: 4, weight: 3), and the current frequent set only includes "Bluetooth connection -> using application B" - (days since last occurrence: 1, weight: 1), then the frequent item in the historical frequent set is updated to "Bluetooth connection -> using application A" - (days since last occurrence: 5, weight: 3 - penaltyP). Here, penaltyP is a pre-set value, such as (0, 1), which can be set according to the actual situation. That is, when the triggering behavior in the behavior rules of a frequent item in the historical frequent set and a frequent item in the current frequent set is the same, but the response behavior is different, the days since last occurrence are accumulated, while the weight is decayed.
[0097] In some possible embodiments, if the first frequent item in the current frequent set and the second frequent item in the historical frequent set have response behaviors belonging to the same behavioral dimension, but the corresponding trigger behaviors are different, then the first frequent item is updated to the historical frequent set; and the trigger behaviors in the second frequent item and the occurrence weights corresponding to the second frequent item are updated using the trigger behaviors in the first frequent item.
[0098] For example, if the historical frequent cluster does not include the frequent item "Bluetooth connection -> using application B - (days since last occurrence: 1, weight: 1)", and the current frequent cluster only includes "Bluetooth connection -> using application B" - (days since last occurrence: 1, weight: 1)", then the historical frequent cluster will add the frequent item "Bluetooth connection -> using application B - (days since last occurrence: 1, weight: 1)", and the frequent item "Wi-Fi connection -> using application A - (days since last occurrence: 1, weight: 1)" in the historical frequent cluster will be updated to "Bluetooth connection -> using application A - (days since last occurrence: 1, weight: log(1+1))".
[0099] In other words, if the scenarios of frequent items in the current frequent set are different from those of frequent items in the historical frequent set, and there are response behaviors belonging to the same behavioral dimension, then the frequent items in the current frequent set are added to the historical frequent set, and the triggering behavior of the second frequent item and the occurrence weight of the second frequent item are updated according to the triggering behavior of the first frequent item.
[0100] In some possible implementations, if none of the above conditions exist, the occurrence of frequent items that are historically concentrated will be attenuated, i.e., the number of days since the last occurrence will be increased by 1.
[0101] For example, if a frequent item "Bluetooth connection -> using application A" exists in the historical frequent set - (days since last occurrence: 4, weight: 3)", but there is no frequent item "Bluetooth connection" in the current frequent set, then the frequent item in the historical frequent set will be updated to "Bluetooth connection -> using application A" - (days since last occurrence: 5, weight: 3)".
[0102] Through the above methods, based on the triggering behavior, the response behavior of the triggering behavior, and the occurrence attribute information, the current frequent set can be used to update the historical frequent set, so that the obtained historical frequent set can reflect the user's latest operating habits, improve the accuracy of the historical frequent set, and thus improve the accuracy of subsequent behavior recommendations for users based on the historical frequent set.
[0103] In some possible embodiments, the target behavior rule can also be deleted from the historical frequent set if the ratio of the time elapsed since the last occurrence of the target behavior rule to the number of days since the occurrence of the target behavior rule is greater than a set threshold. This is to avoid storing too many randomly occurring behavior rules in the historical frequent set, which would not be enough to generate habitual data. This would reduce the amount of data in the historical frequent set and help improve information processing efficiency.
[0104] In some possible embodiments, in order to further improve information processing efficiency and the accuracy of behavior recommendations based on historical frequent sets, after updating the historical frequent sets using the current frequent sets based on the triggering behavior, the response behavior of the triggering behavior, and the occurrence attribute information, the frequent items in the updated historical frequent sets can be filtered according to the occurrence weights of the frequent items in the updated historical frequent sets to obtain a target frequent set, so as to use the target frequent set to recommend user operation behaviors.
[0105] In this embodiment, a weight threshold can be set according to actual needs to filter out frequent items whose weights are greater than the weight threshold, and a target frequent set is formed based on the filtered frequent items. This disclosure does not specify the specific data for the weight threshold.
[0106] Figure 7 A flowchart of an information processing method according to an exemplary embodiment of this disclosure is shown below, in conjunction with... Figure 7 The information processing method of the present disclosure embodiments will be fully described.
[0107] First, you can specify the time dimension for obtaining historical interaction information, such as the time range, to meet information processing needs for a specific time range.
[0108] Secondly, the obtained historical interaction information is preprocessed, including but not limited to deduplication, recording, and tagging.
[0109] Next, the original behavior sequence set is determined based on the user's historical interaction information, and the original behavior sequence set is processed by association sequence analysis to obtain the current frequent set.
[0110] Furthermore, based on the triggering behavior of the current frequent set, the response behavior of the triggering behavior, and the occurrence attribute information, the historical frequent set is updated using the current frequent set.
[0111] Then, based on the occurrence weights of the frequent items in the updated historical frequent set, the frequent items in the updated historical frequent set are filtered to obtain the target frequent set, i.e., the intent library.
[0112] This involves obtaining user historical interaction information based on a set update time and executing the above process for frequently updated historical data. Figure 8 A schematic diagram of a frequently updated history set according to an exemplary embodiment of the present disclosure is shown, such as... Figure 8 As shown, taking 1 day as the dimension, the user's historical interaction information of the previous day is obtained, and the historical frequent set is updated based on the above process of updating the historical frequent set, so that the historical frequent set that is closest to the user's operating habits can be obtained every day, so as to be used for behavior recommendation.
[0113] certainly, Figure 8 The 1 day mentioned is merely an example. This disclosure embodiment can select any update frequency according to actual needs, and no special limitation is made in this regard.
[0114] It should be noted that, Figure 7 and Figure 8 The details of the information processing involved have been described in the above embodiments and will not be repeated here.
[0115] As shown above, without human intervention, by learning the original behavior sequence, frequent items including triggering behaviors and corresponding response behaviors are assembled using user interaction behaviors. The frequent items in the current frequent set are then used to update the frequent items in the historical frequent set, enabling the obtained updated frequent set to correlate triggering behaviors with response behaviors, accurately representing the user's operating habits. Based on the correlation between the triggering and response behaviors of frequent items, corresponding response behaviors can be quickly provided when a user triggers a behavior. This has practical significance for the further application of products related to user perception and simplified user operations.
[0116] Further reference Figure 9 As shown in the exemplary embodiments of this disclosure, a behavior recommendation method is also provided. For example... Figure 9 The behavior recommendation method of this disclosure embodiment may include steps S910 to S940:
[0117] Step S910: Determine the original behavior sequence set based on the user's historical interaction information.
[0118] Step S920: Perform association sequence analysis on the original behavior sequence set to obtain the current frequent set. The frequent items in the current frequent set include behavior rules and the occurrence attribute information corresponding to the behavior rules. The behavior rules include triggering behaviors and response behaviors of triggering behaviors.
[0119] Step S930: Based on the triggering behavior, the response behavior of the triggering behavior, and the occurrence attribute information, update the historical frequent set using the current frequent set to obtain the updated frequent set;
[0120] Step S940: Based on the frequently updated set and the user's current interaction information, recommend the target operation behavior to the user.
[0121] The specific implementation details of steps S910 to S920 are described in detail in the embodiments of the above information processing method, and will not be repeated here.
[0122] The occurrence attribute information in this embodiment includes the occurrence weight of the behavior rule. In step S940, after obtaining the frequently updated set, the user's current interaction information can be perceived, and based on the user's current interaction information and the frequently updated set, the target operation behavior can be recommended to the user.
[0123] like Figure 10 As shown, recommending a target action to the user based on the frequently updated set and the user's current interaction information may include steps S1010 to S1050:
[0124] Step S1010: Extract interactive behaviors of different dimensions from the user's current interaction information, and generate a behavior set with interactive behaviors of different dimensions and combinations of interactive behaviors of different dimensions as set elements.
[0125] After obtaining the user's current interaction information, the interaction behaviors of different dimensions within the current timestamp interval can be obtained according to the timestamp interval when the frequently updated set was generated. For example, during the period of 8:00-8:30, the interaction behaviors of different dimensions can be extracted, including Wi-Fi connection and Bluetooth connection; then, the behavior set "Wi-Fi connection, Bluetooth connection and Wi-Fi connection-Bluetooth connection" is obtained by using Wi-Fi connection, Bluetooth connection and the combination of the two "Wi-Fi connection-Bluetooth connection" as set elements.
[0126] Step S1020: Obtain frequently matching items from the set of elements of the behavior set corresponding to the time when the user's current interaction information occurs.
[0127] After obtaining the behavior set, it is matched with the frequently updated set to retrieve the frequently matching items of the behavior set elements corresponding to the time of the user's current interaction. Specifically, if the triggering behavior of a frequently matched item is the same as that of a set element, then that frequently matched item is considered a frequently matched item of that set element.
[0128] For example, if the set element is "Wi-Fi connection", the corresponding frequent items could be "Wi-Fi connection, using application A", "Wi-Fi connection, using application B", etc. Similarly, if the set element is "Bluetooth connection", the corresponding frequent items could be "Bluetooth connection, using application A", "Bluetooth connection, using application B", etc.
[0129] The above methods can be used to obtain the frequently matched items of each set element. Table 1 schematically shows the set elements and their corresponding frequently matched items during the period of 8:00-8:30.
[0130] Table 1
[0131]
[0132] If the collection element "Wi-Fi connection" does not have a corresponding frequently matched item, then a frequently matched item can be added to Wi-Fi connection based on pre-defined frequently matched items, such as adding "Wi-Fi connection - using application A" and assigning corresponding occurrence attribute information (such as weight). The pre-defined frequently matched items can be set based on historical experience, and there are no special restrictions on them.
[0133] Step S1030: For any set element, sort the frequently matched items in descending order according to their occurrence weights to determine the first value of the frequently matched item.
[0134] As shown in Table 1, for the set element "Wi-Fi Connection", the frequently matched items are sorted according to their corresponding occurrence weights as follows: Wi-Fi Connection - Using Application A (1,3), Wi-Fi Connection - Using Application B (1,2). The first occurrence value of Wi-Fi Connection - Using Application A (1,3) is 1, and the first occurrence value of Wi-Fi Connection - Using Application B (1,2) is 2. The processing method for other set elements is the same. For the set element "Bluetooth Connection", the first occurrence value of Bluetooth Connection - Using Application B (1,3) is 1, and the first occurrence value of Bluetooth Connection - Using Application A (1,2) is 2; for the set element "Wi-Fi Connection - Bluetooth Connection", the first occurrence value of Wi-Fi Connection - Bluetooth Connection - Using Application A (1,3) is 1, and the first occurrence value of Wi-Fi Connection - Bluetooth Connection - Using Application B (1,2) is 2. Further details are omitted.
[0135] Step S1040: Merge the first secondary values of frequently matched items with the same response behavior to obtain the second secondary value with the same response behavior.
[0136] As can be seen in Table 1, for the frequent items corresponding to the same response behavior "Use application A", including: Wi-Fi connection - Use application A (1,3), Bluetooth connection - Use application A (1,2), Wi-Fi connection - Bluetooth connection - Use application A (1,3), the first value of these frequent items is merged to obtain the second value of "Use application A".
[0137] If the fusion weight is set to 1, then the second position value of "using application A" = 1×1 + 2×1 + 1×1 = 4, and the corresponding second position value of "using application B" = 2×1 + 1×1×2 = 5.
[0138] Step S1050: Based on the second position value of each identical response behavior, determine the target operation behavior from each identical response behavior.
[0139] As shown in Table 1, after obtaining the second-order values of "Use Application A" and "Use Application B", the target operation behavior is determined from each identical response behavior according to the second-order value.
[0140] In one exemplary embodiment, the identical response behaviors can be sorted in ascending order according to the second rank value, so as to determine the target operation behavior from the identical response behaviors based on the ascending order sorting result; wherein, if there are target response behaviors with the same second rank value, they are sorted in descending order according to the time since the last occurrence of the target response behavior.
[0141] As shown in Table 1, the ascending sorting result obtained by sorting the same response behaviors in ascending order according to the second position value is: using application A, using application B. Application A can be recommended first, that is, user A is determined as the target operation behavior.
[0142] It is worth noting that the above sorting process is based on frequent items with the same triggering behavior. For example, "Bluetooth connection -> using application A" and "Bluetooth connection - Wi-Fi connection -> using application B" are not compared.
[0143] In addition, after the above sorting process, the results can be truncated according to a pre-set truncation threshold, and the results at the top of the sorting results can be selected as the final result, while other results are temporarily ignored. This process selects the results with a higher probability of being recommended and improves the efficiency of subsequent processing.
[0144] In one exemplary embodiment, in response to a behavior type selection operation, the second rank value of target response behaviors with the target behavior type can be compared among the same response behaviors to determine the target operation behavior from the target response behaviors with the target behavior type. That is, the recommended behavior type can be specified according to actual needs, improving both recommendation accuracy and processing efficiency.
[0145] In one exemplary embodiment, before recommending a target operation to the user based on the frequently updated set and the user's current interaction information, the frequent items in the frequently updated set can be filtered according to the occurrence attribute information corresponding to the frequent items in the frequently updated set to obtain a target frequent set, so as to recommend the operation using the target frequent set. The process of determining the target frequent set has been described in the above embodiments and will not be repeated here. In addition, the process of recommending operation based on the target frequent set is the same as the specific details of recommending operation based on the frequently updated set described above, and will not be repeated here either.
[0146] In summary, without human intervention, by learning the original behavior sequence, frequent items including triggering behaviors and corresponding response behaviors are assembled using user interaction behaviors. The frequent items in the current frequent set are then used to update the frequent items in the historical frequent set, enabling the obtained updated frequent set to correlate triggering behaviors with response behaviors, accurately representing the user's operating habits. Based on the correlation between the triggering and response behaviors of frequent items, corresponding response behaviors can be quickly provided when a user triggers a behavior. This has practical significance for the further application of products related to user perception and simplified user operations.
[0147] It should be noted that the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.
[0148] Further reference Figure 11 As shown, an exemplary embodiment of this disclosure provides an information processing apparatus 1100, including a determining module 1110, a processing module 1120, and an updating module 1130.
[0149] in:
[0150] Module 1110 is used to determine the original behavior sequence set based on the user's historical interaction information;
[0151] Processing module 1120 is used to perform correlation sequence analysis processing on the original behavior sequence set to obtain the current frequent set. The frequent items in the current frequent set include behavior rules and occurrence attribute information corresponding to the behavior rules. The behavior rules include triggering behaviors and response behaviors of the triggering behaviors.
[0152] The update module 1130 is used to update the historical frequent set using the current frequent set based on the triggering behavior, the response behavior of the triggering behavior, and the occurrence attribute information.
[0153] In an exemplary embodiment, the determining module 1110 is configured to: extract historical interaction behaviors and the occurrence times corresponding to the historical interaction behaviors from the user's historical interaction information; determine timestamp intervals, expand the range of occurrence times of the historical interaction behaviors based on the timestamp intervals to obtain the time range of the historical interaction behaviors; determine the original behavior sequences corresponding to the historical interaction behaviors within the timestamp intervals based on the relationship between the time ranges of the historical interaction behaviors within the timestamp intervals; and form the original behavior sequence set according to the original behavior sequences corresponding to each timestamp interval.
[0154] In an exemplary embodiment, the determining module 1110 is configured to: determine the effective time length of the historical interaction behavior; within each timestamp interval, starting from the occurrence time of the historical interaction behavior, expand the range of the occurrence time of the historical interaction behavior according to the effective time length to obtain the time range of the historical interaction behavior.
[0155] In an exemplary embodiment, the historical interaction behaviors of different dimensions have their own corresponding effective time lengths; the determining module 1110 is configured to: for any dimension of the historical interaction behavior, if there is a time difference between the starting points of the occurrence times of a first interaction event and a second interaction event of different types that is less than the effective time length, take the occurrence time of the second interaction event that occurred later as the starting point, and expand the range of the occurrence time of the second interaction event according to the effective time length.
[0156] In an exemplary embodiment, the determining module 1110 is configured to: determine the original behavior sequence corresponding to the historical interaction behavior within the timestamp interval based on the historical interaction behavior that has an overlapping relationship between time ranges within the timestamp interval; wherein, the sequence items in the original behavior sequence carry information about the timestamp interval.
[0157] In an exemplary embodiment, the sequence items include triggering behaviors and response behaviors. The information processing device 1100 further includes: a preprocessing module configured to adjust the order of sequence items in the original behavior sequence based on preset interaction state change information; and / or configured to adjust the order of triggering behaviors in the sequence items based on the preset interaction state change information.
[0158] In an exemplary embodiment, the processing module 1120 is configured to: perform correlation sequence analysis on the original behavior sequence set to determine historical interaction behaviors that serve as triggering behaviors and historical interaction behaviors that serve as response behaviors corresponding to the triggering behaviors from the historical interaction behaviors in each of the original behavior sequences, so as to obtain the behavior rules; determine occurrence attribute information corresponding to the behavior rules based on the user's historical interaction information; determine the frequent items according to the behavior rules and the occurrence attribute information corresponding to the behavior rules, and form the current frequent set according to all the obtained frequent items.
[0159] In an exemplary embodiment, the occurrence attribute information includes the occurrence weight of the behavior rule and the time since the last occurrence of the behavior rule, wherein the occurrence weight is determined based on the number of occurrences of the behavior rule; the update module 1130 is configured to: in response to the fact that the frequent items in the current frequent set and the frequent items in the historical frequent set have the same behavior rule, update the occurrence weight corresponding to the same behavior rule in the historical frequent set and the time since the last occurrence of the same behavior rule.
[0160] In an exemplary embodiment, the update module 1130 is configured to: in response to the fact that the first frequent item in the current frequent set and the second frequent item in the historical frequent set have the same triggering behavior, and the response behaviors of the same behavior scenarios are different, reduce the occurrence weight of the behavior rule corresponding to the second frequent item, and accumulate the time since the last occurrence of the behavior rule corresponding to the second frequent item.
[0161] In an exemplary embodiment, the update module 1130 is configured to: update the first frequent item in the current frequent set and the second frequent item in the historical frequent set to the historical frequent set if they have response behaviors belonging to the same behavioral dimension and the corresponding trigger behaviors are different; and update the trigger behavior in the second frequent item and the occurrence weight corresponding to the second frequent item using the trigger behavior in the first frequent item.
[0162] In an exemplary embodiment, the update module 1130 is configured to delete the target behavior rule from the historical frequent set if the ratio of the time elapsed since the last occurrence of the target behavior rule in the historical frequent set to the number of days since the occurrence of the target behavior rule is greater than a set threshold.
[0163] In one exemplary embodiment, the information processing apparatus 1100 further includes:
[0164] The filtering module is configured to filter the frequent items in the updated historical frequent set according to the occurrence weights of the frequent items in the updated historical frequent set, so as to obtain the target frequent set.
[0165] The specific details of each module in the above-mentioned device have been described in detail in the method section of the implementation. For any undisclosed details, please refer to the implementation content of the method section, and therefore will not be repeated here.
[0166] Further reference Figure 12 As shown, an exemplary embodiment of this disclosure provides a behavior recommendation processing device 1200, including a determination module 1210, a processing module 1220, an update module 1230, and a recommendation module 1240. Wherein:
[0167] The determination module 1210 is used to determine the original behavior sequence set based on the user's historical interaction information;
[0168] Processing module 1220 is used to perform correlation sequence analysis processing on the original behavior sequence set to obtain the current frequent set. The frequent items in the current frequent set include behavior rules and occurrence attribute information corresponding to the behavior rules. The behavior rules include triggering behaviors and response behaviors of the triggering behaviors.
[0169] The update module 1230 is used to update the historical frequent set based on the triggering behavior, the response behavior of the triggering behavior, and the occurrence attribute information, using the current frequent set to obtain the updated frequent set;
[0170] The recommendation module 1240 is used to recommend target operation behaviors to the user based on the frequently updated set and the user's current interaction information.
[0171] In an exemplary embodiment, the recommendation module 1240 is configured to: extract interactive behaviors of different dimensions from the user's current interaction information, and generate a behavior set using the interactive behaviors of different dimensions and combinations of interactive behaviors of different dimensions as set elements; obtain frequently matching items of the set elements of the behavior set from the frequently updated set corresponding to the occurrence time of the user's current interaction information; for any set element, sort the frequently matching items in descending order according to the occurrence weight corresponding to the frequently matching items to determine the first ranking value of the frequently matching items; merge the first ranking values of frequently matching items with the same response behavior to obtain the second ranking value of the same response behavior; and determine the target operation behavior from each of the same response behaviors based on the second ranking value of each of the same response behaviors.
[0172] In an exemplary embodiment, the recommendation module 1240 is configured to: sort the identical response behaviors in ascending order according to the second rank value, so as to determine the target operation behavior from the identical response behaviors based on the ascending order sorting result; wherein, if there are target response behaviors with the same second rank value, they are sorted in descending order according to the time since the last occurrence of the target response behavior.
[0173] In an exemplary embodiment, the recommendation module 1240 is configured to: in response to a behavior type selection operation, compare the second rank value of a target response behavior having a target behavior type among the same response behaviors, so as to determine the target operation behavior from the target response behaviors having the target behavior type.
[0174] In an exemplary embodiment, the behavior recommendation device 1200 further includes a filtering module configured to filter the frequent items in the frequent update set based on the occurrence attribute information corresponding to the frequent items in the frequent update set.
[0175] The specific details of each module in the above-mentioned device have been described in detail in the method section of the implementation. For any undisclosed details, please refer to the implementation content of the method section, and therefore will not be repeated here.
[0176] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."
[0177] An exemplary embodiment of this disclosure also provides an electronic device for the above-described method. This electronic device may be the aforementioned imaging device or a server. Generally, the electronic device includes at least a processor and a memory, the memory for storing executable instructions of the processor, and the processor configured to perform the above-described method by executing the executable instructions.
[0178] The following is based on Figure 13 Taking the mobile terminal 1300 as an example, the construction of the electronic device in this disclosure embodiment will be described by way of example. Those skilled in the art will understand that, apart from components specifically designed for mobile purposes, Figure 13 The structure shown can also be applied to fixed-type devices. In other embodiments, the mobile terminal 1300 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components can be implemented in hardware, software, or a combination of software and hardware. The interface connections between the components are only schematic and do not constitute a limitation on the structure of the mobile terminal 1300. In other embodiments, the mobile terminal may also adopt a similar design to... Figure 13 Different interface connection methods, or combinations of multiple interface connection methods.
[0179] like Figure 13As shown, the mobile terminal 1300 may specifically include: a processor 1301, a memory 1302, a bus 1303, a mobile communication module 1304, an antenna 1, a wireless communication module 1305, an antenna 2, a display screen 1306, a camera module 1307, an audio module 1308, a power supply module 1309, and a sensor module 1310. The processor 1301 may include one or more processing units, such as: an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor, and / or an NPU (Neural-Network Processing Unit), etc.
[0180] An encoder encodes (compresses) images or videos to reduce data size for easier storage or transmission. A decoder decodes (decompresses) the encoded data to restore the original image or video data. The mobile terminal 1300 can support one or more encoders and decoders, such as image formats like JPEG (Joint Photographic Experts Group), PNG (Portable Network Graphics), and BMP (Bitmap), and video formats like MPEG (Moving Picture Experts Group) 1, MPEG10, H.1063, H.1064, and HEVC (High Efficiency Video Coding).
[0181] The processor 1301 can be connected to the memory 1302 or other components via the bus 1303. The memory 1302 can be used to store executable program code, including instructions. The processor 1301 executes various functional applications and data processing of the mobile terminal 1300 by running the instructions stored in the memory 1302. The memory 1302 can also store application data, such as images, videos, and other files.
[0182] The communication function of mobile terminal 1300 can be implemented through mobile communication module 1304, antenna 1, wireless communication module 1305, antenna 2, modem processor, and baseband processor. Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Mobile communication module 1304 can provide 3G, 4G, and 5G mobile communication solutions for mobile terminal 1300. Wireless communication module 1305 can provide wireless communication solutions such as wireless LAN, Bluetooth, and near-field communication for mobile terminal 1300.
[0183] The display screen 1306 is used to implement display functions, such as displaying the user interface, images, videos, etc., and displaying abnormal prompts. The camera module 1307 is used to implement shooting functions, such as capturing images and videos to acquire scene images. The audio module 1308 is used to implement audio functions, such as playing audio and capturing voice. The power module 1309 is used to implement power management functions, such as charging the battery, supplying power to the device, and monitoring battery status. The sensor module 1310 may include one or more sensors for implementing corresponding sensing and detection functions.
[0184] Furthermore, exemplary embodiments of this disclosure also provide a computer-readable storage medium storing a program product capable of implementing the methods described above. In some possible embodiments, various aspects of this disclosure may also be implemented as a program product including program code that, when run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.
[0185] It should be noted that the computer-readable medium disclosed herein may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.
[0186] In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can transmit, propagate, or transfer a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wireline, optical fiber, RF, etc., or any suitable combination thereof.
[0187] Furthermore, program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java and C++, and conventional procedural programming languages such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).
[0188] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.
Claims
1. An information processing method characterized by comprising: include: Determine the original behavior sequence set based on the user's historical interaction information; The original set of behavior sequences is subjected to association sequence analysis to obtain the current frequent set. The frequent items in the current frequent set include behavior rules and occurrence attribute information corresponding to the behavior rules. The behavior rules include triggering behaviors and response behaviors of the triggering behaviors. The occurrence attribute information includes the occurrence weight of the behavior rule and the time since the last occurrence of the behavior rule. The occurrence weight is determined based on the number of times the behavior rule has occurred. Based on the triggering behavior, the response behavior of the triggering behavior, and the occurrence attribute information, the historical frequent set is updated using the current frequent set, including: in response to the fact that the frequent items in the current frequent set and the frequent items in the historical frequent set have the same behavior rule, the occurrence weight corresponding to the same behavior rule in the historical frequent set and the time since the last occurrence of the same behavior rule are updated. The method further includes: In response to the fact that the first frequent item in the current frequent set and the second frequent item in the historical frequent set have the same triggering behavior and the response behavior of the same triggering behavior are different, the occurrence weight of the behavior rule corresponding to the second frequent item is reduced, and the time since the last occurrence of the behavior rule corresponding to the second frequent item is accumulated. If the first frequent item in the current frequent set and the second frequent item in the historical frequent set have response behaviors belonging to the same behavioral dimension, but the corresponding trigger behaviors are different, then the first frequent item is updated to the historical frequent set; and Using the triggering behavior in the first frequent item, update the triggering behavior in the second frequent item and the occurrence weight corresponding to the second frequent item.
2. The method according to claim 1, characterized in that, The step of determining the original behavior sequence set based on user historical interaction information includes: Extract historical interaction behaviors and the corresponding occurrence times from the user's historical interaction information; Determine a timestamp interval, and expand the range of occurrence times of the historical interaction behavior based on the timestamp interval to obtain the time range of the historical interaction behavior; Based on the relationship between the time ranges of historical interaction behaviors within the timestamp intervals, the original behavior sequence corresponding to the historical interaction behaviors within the timestamp regions is determined. The original behavior sequence set is formed based on the original behavior sequence corresponding to each timestamp interval.
3. The method according to claim 2, characterized in that, The process of expanding the time range of the historical interaction behavior based on the timestamp interval to obtain the time range of the historical interaction behavior includes: Determine the effective duration of the historical interaction behavior; Within each timestamp interval, starting from the occurrence time of the historical interaction, the occurrence time of the historical interaction is expanded according to the effective time length to obtain the time range of the historical interaction.
4. The method according to claim 3, characterized in that, The historical interaction behaviors of different dimensions each have their own corresponding effective time length; Within each timestamp interval, starting from the occurrence time of the historical interaction, the occurrence time of the historical interaction is expanded according to the effective time length to obtain the time range of the historical interaction, including: For any dimension of the historical interaction behavior, if the time difference between the starting points of the occurrence times of the first and second interaction events of different types is less than the effective time length, the occurrence time of the second interaction event that occurred later is taken as the starting point, and the range of the occurrence time of the second interaction event is expanded according to the effective time length.
5. The method according to claim 2, characterized in that, The step of determining the original behavior sequence corresponding to the historical interaction behavior within the timestamp interval based on the relationship between the time ranges of the historical interaction behavior within the timestamp interval includes: Based on the historical interaction behaviors that have overlapping relationships between time ranges within the timestamp interval, determine the original behavior sequence corresponding to the historical interaction behaviors within the timestamp interval; The sequence items in the original behavior sequence carry information about the timestamp interval.
6. The method according to claim 5, characterized in that, The sequence item includes a triggering behavior and a response behavior, and the method further includes: Based on preset interaction state change information, the order of sequence items in the original behavior sequence is adjusted; and / or The order of triggering behaviors in the sequence items is adjusted based on the preset interaction state change information.
7. The method according to claim 2, characterized in that, The process of performing association sequence analysis on the original behavioral sequence set to obtain the current frequent set includes: The original behavior sequence set is subjected to association sequence analysis to determine the historical interaction behavior that serves as the triggering behavior and the historical interaction behavior that serves as the response behavior corresponding to the triggering behavior from the historical interaction behavior in each original behavior sequence, so as to obtain the behavior rule; Based on the user's historical interaction information, determine the occurrence attribute information corresponding to the behavior rule; The frequent items are determined based on the behavior rules and the occurrence attribute information corresponding to the behavior rules, and the current frequent set is formed based on all the obtained frequent items.
8. The method according to claim 1, characterized in that, The method further includes: If the ratio of the time elapsed since the last occurrence of a target behavior rule in the historical frequent set to the number of days since the occurrence of the target behavior rule is greater than a set threshold, the target behavior rule is deleted from the historical frequent set.
9. The method according to claim 8, characterized in that, After updating the historical frequent set using the current frequent set based on the triggering behavior, the response behavior of the triggering behavior, and the occurrence attribute information, the process further includes: Based on the occurrence weights of the frequent items in the updated historical frequent set, the frequent items in the updated historical frequent set are filtered to obtain the target frequent set.
10. A behavior recommendation method, characterized in that, include: Determine the original behavior sequence set based on the user's historical interaction information; The original set of behavior sequences is subjected to association sequence analysis to obtain the current frequent set. The frequent items in the current frequent set include behavior rules and occurrence attribute information corresponding to the behavior rules. The behavior rules include triggering behaviors and response behaviors of the triggering behaviors. Based on the triggering behavior, the response behavior of the triggering behavior, and the occurrence attribute information, the historical frequent set is updated using the current frequent set to obtain the updated frequent set; Based on the frequently updated set and the user's current interaction information, the system recommends target actions to the user. The occurrence attribute information includes the occurrence weight of the behavior rule; the step of recommending target operation behavior to the user based on the frequently updated set and the user's current interaction information includes: Extract interactive behaviors of different dimensions from the user's current interaction information, and generate a behavior set using the interactive behaviors of different dimensions and the combination of interactive behaviors of different dimensions as set elements; The frequently matching items of the behavior set elements are obtained from the frequently updated set corresponding to the time of occurrence of the user's current interaction information. For any of the set elements, the frequently matched items are sorted in descending order according to their occurrence weights to determine the first value of each frequently matched item. The first value of frequently matched items with the same response behavior is merged to obtain the second value of the same response behavior. The target operation behavior is determined from the identical response behaviors based on the second position value of each of the identical response behaviors.
11. The method according to claim 10, characterized in that, The step of determining the target operation behavior from the identical response behaviors based on the second rank value of each of the identical response behaviors includes: The identical response behaviors are sorted in ascending order according to the second rank value, so as to determine the target operation behavior from the identical response behaviors based on the ascending order result; If there are target response behaviors with the same second position value, they are sorted in descending order according to the time since the last occurrence of the target response behavior.
12. The method according to claim 10, characterized in that, The step of determining the target operation behavior from the identical response behaviors based on the second rank value of each of the identical response behaviors includes: In response to the behavior type selection operation, the second position value of the target response behavior with the target behavior type among the same response behaviors is compared to determine the target operation behavior from the target response behaviors with the target behavior type.
13. The method according to any one of claims 10 to 12, characterized in that, Before recommending the target operation behavior to the user based on the frequently updated set and the user's current interaction information, the method further includes: Based on the occurrence attribute information corresponding to the frequent items in the frequent update set, the frequent items in the frequent update set are filtered.
14. An information processing device, characterized in that, include: The determination module is used to determine the original behavior sequence set based on the user's historical interaction information; A processing module is used to perform correlation sequence analysis on the original behavior sequence set to obtain a current frequent set. The frequent items in the current frequent set include behavior rules and occurrence attribute information corresponding to the behavior rules. The behavior rules include triggering behaviors and response behaviors of the triggering behaviors. The occurrence attribute information includes the occurrence weight of the behavior rule and the time since the last occurrence of the behavior rule. The occurrence weight is determined based on the number of occurrences of the behavior rule. An update module is used to update the historical frequent set based on the triggering behavior, the response behavior of the triggering behavior, and the occurrence attribute information using the current frequent set. This includes updating the occurrence weight of the same behavior rule in the historical frequent set and the time since the last occurrence of the same behavior rule in the historical frequent set in response to the existence of the same behavior rule in the frequent items in the current frequent set and the same behavior rule. The update module is further configured to, in response to the fact that the first frequent item in the current frequent set and the second frequent item in the historical frequent set have the same triggering behavior and the response behavior of the same triggering behavior are different, reduce the occurrence weight of the behavior rule corresponding to the second frequent item, and accumulate the time since the last occurrence of the behavior rule corresponding to the second frequent item. If the first frequent item in the current frequent set and the second frequent item in the historical frequent set have response behaviors belonging to the same behavioral dimension, and the corresponding trigger behaviors are different, then the first frequent item is updated to the historical frequent set; and the trigger behaviors in the second frequent item and the occurrence weights corresponding to the second frequent item are updated using the trigger behaviors in the first frequent item.
15. A behavior recommendation device, characterized in that, include: The determination module is used to determine the original behavior sequence set based on the user's historical interaction information; The processing module is used to perform correlation sequence analysis on the original behavior sequence set to obtain the current frequent set. The frequent items in the current frequent set include behavior rules and occurrence attribute information corresponding to the behavior rules. The behavior rules include triggering behaviors and response behaviors of the triggering behaviors. The update module is used to update the historical frequent set based on the triggering behavior, the response behavior of the triggering behavior, and the occurrence attribute information, using the current frequent set to obtain the updated frequent set; The recommendation module is used to recommend target operation behaviors to the user based on the frequently updated set and the user's current interaction information; The occurrence attribute information includes the occurrence weight of the behavior rule; the step of recommending target operation behavior to the user based on the frequently updated set and the user's current interaction information includes: Extract interactive behaviors of different dimensions from the user's current interaction information, and generate a behavior set using the interactive behaviors of different dimensions and the combination of interactive behaviors of different dimensions as set elements; The frequently matching items of the behavior set elements are obtained from the frequently updated set corresponding to the time of occurrence of the user's current interaction information. For any of the set elements, the frequently matched items are sorted in descending order according to their occurrence weights to determine the first value of each frequently matched item. The first value of frequently matched items with the same response behavior is merged to obtain the second value of the same response behavior. The target operation behavior is determined from the identical response behaviors based on the second position value of each of the identical response behaviors.
16. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 13 by executing the executable instructions.
17. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 13.
Citation Information
Patent Citations
Association rule mining method of large-scale data
CN103020256A
A frequent item set fused oilfield business service recommendation method
CN109410008A
Application analysis method and device, electronic equipment and computer readable storage medium
CN113157766A
APP recommendation method and device
CN115168691A
