CN108876284B - User behavior prompt generation method and terminal equipment - Google Patents
User behavior prompt generation method and terminal equipment Download PDFInfo
- Publication number
- CN108876284B CN108876284B CN201810457094.3A CN201810457094A CN108876284B CN 108876284 B CN108876284 B CN 108876284B CN 201810457094 A CN201810457094 A CN 201810457094A CN 108876284 B CN108876284 B CN 108876284B
- Authority
- CN
- China
- Prior art keywords
- behavior
- target
- user
- completion
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Abstract
The invention provides a user behavior prompt generation method and terminal equipment, which are suitable for the technical field of data processing, and the method comprises the following steps: acquiring a work and rest action plan of a user in a first preset time period; screening target behavior historical data corresponding to target completion behaviors from historical behavior data of a user, and performing deep learning on the target behavior historical data to obtain behavior prediction data corresponding to each target completion behavior in a first preset time period, wherein the behavior prediction data comprises prediction completion time of the target completion behaviors; and generating an error behavior warning according to the time point of the difference between the predicted completion time corresponding to each target completion behavior and the corresponding target completion time. The embodiment of the invention achieves the purpose of intelligently providing behavior suggestions for the daily work and rest of the user according to the actual situation of the user, and greatly improves the intelligent degree of the application program.
Description
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to a user behavior prompt generation method and terminal equipment.
Background
In the traditional life assistant application programs in the market, behavior prompt is performed on a user at a specific time point only according to a prompting rule set by the user, for example, the user is prompted to exercise at 9 am, and the user is prompted to sleep at 10 pm. However, these existing applications of the life assistant type are very passive to follow the setting of the user or trigger the prompt of the user state, and cannot actively give a prompt or suggestion to the user according to the actual situation of the user. Therefore, the degree of intelligence of the application programs of the life assistant class in the prior art is low, and behavior prompting suggestions cannot be intelligently provided for the daily work and rest of the user according to the actual situation of the user.
Disclosure of Invention
In view of this, embodiments of the present invention provide a user behavior prompt generating method and a terminal device, so as to solve the problem that in the prior art, the degree of intelligence of an application program is low, and a behavior prompt suggestion cannot be intelligently provided for a user's daily work and rest according to the actual situation of the user.
A first aspect of an embodiment of the present invention provides a method for generating a user behavior prompt, including:
acquiring a work and rest action plan of a user in a first preset time period, wherein the work and rest action plan stores target completion actions of the user in the first preset time period and target completion time of each target completion action in the first preset time period;
screening target behavior historical data corresponding to the target completion behaviors from the historical behavior data of the user, and performing deep learning on the target behavior historical data to obtain behavior prediction data corresponding to each target completion behavior one by one in the first preset time period, wherein the behavior prediction data comprise the predicted completion time of the target completion behaviors;
and generating an error behavior warning according to the time point of the difference between the predicted completion time corresponding to each target completion behavior and the corresponding target completion time.
A second aspect of the embodiments of the present invention provides a user behavior prompt generation terminal device, where the user behavior prompt generation terminal device includes a memory and a processor, where the memory stores a computer program that can be executed on the processor, and the processor implements the following steps when executing the computer program.
Acquiring a work and rest action plan of a user in a first preset time period, wherein the work and rest action plan stores target completion actions of the user in the first preset time period and target completion time of each target completion action in the first preset time period;
screening target behavior historical data corresponding to the target completion behaviors from the historical behavior data of the user, and performing deep learning on the target behavior historical data to obtain behavior prediction data corresponding to each target completion behavior one by one in the first preset time period, wherein the behavior prediction data comprise the predicted completion time of the target completion behaviors;
and generating an error behavior warning according to the time point of the difference between the predicted completion time corresponding to each target completion behavior and the corresponding target completion time.
A third aspect of an embodiment of the present invention provides a computer-readable storage medium, including: a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the user behavior alert generation method as described above.
Compared with the prior art, the embodiment of the invention has the following beneficial effects: considering that although a user has a work and rest behavior plan, the plan is often difficult to be effectively executed in practical situations, and due to the problem of the work and rest behavior habits of the user, the practical situations often exist where the work and rest behavior habits conflict with the work and rest behavior plan, for example, the user currently has a work and rest behavior habit of eating dinner at 10 pm every day, but the plan is that the user hopes to eat dinner at 6 pm every day on time, and although the plan is provided, the user is used to eat dinner at 10 pm, even if the user is reminded to eat dinner at 6 pm, the user still wants to eat at 10 pm, and the planned plan is possibly damaged.
Therefore, in order to realize intelligent prompting according to the actual situation of the user to ensure the normal execution of the work and rest behavior plan, the embodiment of the invention predicts the possible behaviors of the user during the work and rest plan according to the actual historical behavior data of the user, generates the corresponding prompt of behavior error warning for the time point different from the time point of the work and rest behavior plan according to the predicted behavior completion time, and informs the user that the conflicting behaviors cannot be performed at the moment, wherein the plan is that the user eats dinner at 6 pm, but the user is predicted to eat at 10 pm, and at the moment, the user needs to be warned that the user cannot eat at 10 pm to ensure the normal execution of the work and rest behavior plan. Compared with the prior art that the behavior prompt of the specific event can be performed only according to the time point set by the user, the embodiment of the invention can predict the behavior of the user according to the actual living habits of the user and timely send out the corresponding warning prompt when a certain behavior is not required to be performed, thereby realizing the purpose of intelligently providing behavior suggestions for the daily work and rest of the user according to the actual situation of the user and greatly improving the intelligent degree of the application program.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic flow chart illustrating an implementation of a user behavior prompt generation method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart illustrating an implementation of a user behavior prompt generation method according to a second embodiment of the present invention;
fig. 3 is a schematic flow chart illustrating an implementation of a user behavior prompt generating method according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a user behavior prompt generation apparatus according to a fourth embodiment of the present invention;
fig. 5 is a schematic diagram of a user behavior prompt generation terminal device according to a fifth embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
In order to explain the technical means of the present invention, the following description will be given by way of specific examples.
Fig. 1 shows a flowchart of an implementation of a user behavior prompt generation method according to an embodiment of the present invention, which is detailed as follows:
s101, obtaining a work and rest action plan of a user in a first preset time period, wherein target completion actions of the user in the first preset time period and target completion time of each target completion action in the first preset time period are stored in the work and rest action plan.
The work and rest behavior plan refers to some behaviors planned to be completed by a user in a future period of time, and includes but is not limited to exercise plans, diet plans, work and rest plans and the like, for example, the user plans to start running for half an hour at 8 am every day, sleep at 11 pm every day, and the user plans to finish the activities in 7: 30. 12:00 and 17: eating on time 30, etc. The work and rest action plan may be set and input by the user, or may be automatically generated after being analyzed according to some data of the physical condition of the user, which is not limited herein and may be determined by the actual application. In the embodiment of the present invention, the preset time period refers to a future time period after the current time, such as a future month, which is specifically selected by a user or a technician according to actual needs.
S102, screening target behavior historical data corresponding to target completion behaviors from the historical behavior data of the user, and performing deep learning on the target behavior historical data to obtain behavior prediction data corresponding to each target completion behavior one by one in a first preset time period, wherein the behavior prediction data comprises the prediction completion time of the target completion behaviors.
The target behavior history data refers to the completion condition history data of the target completion behaviors of the user before the current time, such as the time point of getting up, running and sleeping of the user every day in the history data. The data source can be input by the user or obtained from other data sources, such as wearable equipment and the like, to collect and record the daily life behaviors of the user. Since the target behavior history data is used for predicting the user behavior, but considering that the actual significance of the data with too long time to the user prediction is small, and even the accuracy of the user behavior prediction may be adversely affected, the target behavior history data in the embodiment of the present invention refers to a certain period of time before the current time, and the specific period of time selection may be set by a technician according to the actual situation.
A work and rest plan may include one or more plans, such as a running plan, a breakfast plan, and a sleeping plan, which may correspond to different goals to complete the activities. In practical situations, the regularity of the target completing behaviors in the life of the user is strong, such as the breakfast eating time, the sleeping time, the running time every week and the like, so that the analysis and prediction of the target completing behaviors can be theoretically completed by using the user behavior historical data to predict the time of the user completing the target completing behaviors in the future time and other data. Meanwhile, considering that the target completing behaviors are relatively independent, the prediction is preferably performed by taking each specific behavior as a unit, so that the independent and accurate prediction of the completing time of each target completing behavior of a user in a future period of time can be realized.
Therefore, in order to provide more personalized and intelligent behavior prompts for users, the embodiment of the invention takes the behavior history data of the users as training samples, constructs a prediction model of the target completion behavior of the users, realizes the prediction of the target completion behavior of the users in a period of time in the future, and lays a foundation for the follow-up intelligent prompt. The specific method for constructing the deep learning prediction model can be completed by selecting some existing network models.
And S103, generating an error behavior warning according to the time point of the difference between the predicted completion time corresponding to each target completion behavior and the corresponding target completion time.
The wrong behavior warning is used for prompting the user what kind of activities should not be performed at the time point, so that the user can effectively execute the work and rest behavior plan and put an end to certain living behaviors which are not consistent with the work and rest behavior plan. Because the work and rest behavior plan is only one plan, whether the user can complete the plan timely and effectively is difficult to determine in practical situations, but it can be determined that no matter how the work and rest plan is, the historical work and rest behavior habits of the user are difficult to change timely, for example, the user is accustomed to the fact that the current work and rest behavior habits of the user are that the user eats dinner at 10 pm every day, but the user expects to eat at 6 pm every day and at right time, and at this moment, although the user has a plan, the user is accustomed to eating at 10 pm, even if the user is reminded of eating at 6 pm, the user still wants to eat at 10 pm. Therefore, if the action event is directly prompted only according to the action plan, for example, the user is prompted to eat at 6 pm, but when the original action event is reached, such as 10 pm, the user may still continue to have historical behavior habits, especially for some users with weak self-control ability.
Therefore, in order to implement personalized and intelligent prompting on a user and improve the effectiveness of a daily work and rest prompting suggestion for the user, in the embodiment of the invention, the time for the user to execute the target completion behavior within a period of time in the future is identified and predicted based on the user behavior historical data, and is compared with the target completion time of the target completion behavior set in the work and rest behavior plan, if there is a difference, it is indicated that there is a time point at which the target completion behavior should not be executed by the user according to the user habits, which is a habit time point at which the user should execute the target completion behavior, but the user should not execute the target completion behavior at this time, which may greatly affect the normal work and rest behavior plan, for example, it is found that the user would eat dinner at 10 pm according to the prediction, but should eat dinner at 6 o ' clock according to the work and rest behavior plan, therefore, even if the user had been prompted by 6 o ' clock that the user should eat dinner at night, in order to prevent the user from continuing eating at 10 o ' clock at 10 o clock, the embodiment of the invention may generate a corresponding wrong warning at 10 pm at 10 o ' clock, and inform the user that the user cannot eat at 10 o ' clock.
In order to realize intelligent prompting according to the actual situation of the user and ensure the normal execution of the work and rest action plan, the embodiment of the invention predicts the possible actions of the user during the work and rest action plan according to the actual historical action data of the user, generates the corresponding action error warning prompt for the time point different from the time point of the work and rest action plan according to the predicted action completion time, and informs the user that the conflict action can not be carried out at the moment so as to ensure the normal execution of the work and rest action plan. Compared with the prior art that the behavior prompt of the specific event can be performed only according to the time point set by the user, the behavior of the user can be predicted according to the actual living habit of the user, and the corresponding warning prompt is timely sent out when a certain behavior is not required to be performed, so that the purpose of intelligently providing behavior suggestions for the daily work and rest of the user according to the actual situation of the user is achieved, and the intelligent degree of an application program is greatly improved.
As a second embodiment of the present invention, as shown in fig. 2, acquiring a work and rest action plan of a user in a first preset time period includes:
s201, acquiring personal information of a user, weather forecast data of a first preset time period and a work and rest behavior plan input by the user.
The personal information includes, but is not limited to, sex, age, weight, place of living, place of birth, preference, and hobby sports of the user. The weather forecast data refers to how the weather is in the first preset time period in the future every day.
S202, calculating executable probability of the target completion behaviors contained in the work and rest behavior plan based on the personal information and the weather forecast data, and adjusting target completion time of the target completion behaviors of which the executable probability is lower than a probability threshold.
The executable probability refers to a probability of possibility that the work and rest behavior can be executed within a period of time in the future. The work and rest action plan includes some action plans that the user wants to complete in a future period of time, but in actual situations, due to differences of personal physical conditions of the user and different weather conditions, not all actions are suitable for the user to do, for example, the user sets running at 8 points a day in a month in the future, but weather forecast data shows that the user needs to be rained day by day in a week in the future, so the user is not suitable for running in the week in the future, and the running executable probability is low at the moment. Therefore, in order to ensure that the finally obtained work and rest action plan can really meet the actual requirements of the user so as to improve the effectiveness of the life and rest prompt of the user, in the embodiment of the invention, the work and rest action plan set by the user is corrected according to the personal information of the user and the weather forecast data, so that the finally obtained really available work and rest action plan is obtained.
The specific calculation method of the executable probability can be set by a technician. As a specific implementation way of the invention for calculating the executable probability, the method comprises the following steps:
and analyzing whether an inappropriate target completion behavior exists in the work and rest behavior plan according to the personal information of the user, and setting the executable probability of the inappropriate target completion behavior to be 0. For example, the technician may set corresponding restriction information for each target completing act, such as that the pregnant woman or the user with some specific diseases is not suitable for running, and at this time, directly according to the rules, it may be determined whether the user is suitable for performing the target completing act.
And for non-inappropriate target completing behaviors, judging whether the weather forecast data corresponding to all target completing time is suitable for performing the target completing behaviors or not, and if not, setting the executable probability of the target completing behaviors to a value below a probability threshold. For example, when the rest plan is running at 8 morning hours per day in the next month, but the weather forecast data shows that it rains in the next week, and therefore, in the next week, the running is not suitable for running at 8 morning hours, the running executable probability value is set to a specific value lower than the probability threshold value, so as to inform that the target completion time of running needs to be modified subsequently.
The target completion time for which a target completion action having a probability less than a probability threshold may be performed is adjusted. And for the target completion behavior with the executable probability of 0, directly deleting the target completion behavior from the work and rest behavior plan, namely setting all target completion time of the target completion behavior to be null. And (3) corresponding to target completion behaviors which are not 0 but are smaller than the probability threshold, modifying the target completion time according to the specific conditions of weather forecast data every day in the first preset time, and if the weather forecast data is not suitable for running on a certain day, directly canceling running on a changed day, if the weather shows that the weather is rainy when the original target completion time is displayed, but running on a clear day after one hour, modifying the target completion time into the time after the original target completion time, wherein the specific modification method/rule can be set by a technician according to the actual conditions.
As an embodiment of the present invention, when deep learning is performed on target behavior history data to obtain behavior prediction data corresponding to each target completion behavior in a first preset time period, the method includes:
and performing deep learning on the historical data of each target behavior respectively to obtain behavior prediction models corresponding to the target completion behaviors one by one, and performing analysis prediction on each target completion behavior in a first preset time period by using the behavior prediction models respectively to obtain behavior prediction data corresponding to the target completion behaviors one by one.
As can be seen from the above description, the accuracy of predicting the target completion behavior can be improved by independently predicting each target completion behavior. Therefore, in the embodiment of the invention, learning modeling is respectively performed based on the target behavior historical data corresponding to each target completion behavior, for example, historical running data is used as a training sample, and independent learning training modeling is performed to obtain a prediction model corresponding to running. And predicting the target completion behaviors one by utilizing the obtained prediction modules. The specific deep learning modeling method can be set by technicians according to actual requirements, including but not limited to learning modeling by using a BP neural network.
As a third embodiment of the present invention, as shown in fig. 3, a process of constructing a behavior prediction model for a target completion behavior includes:
s301, analyzing the historical completion time of the target completion behavior in the target behavior historical data, determining a behavior repetition period corresponding to the target completion behavior, and dividing the target behavior historical data into N target behavior historical data segments with time lengths equal to the behavior repetition period according to the time sequence for storing the target behavior historical data to obtain N period sample data.
And S302, performing model training based on the N periods of sample data to obtain a behavior prediction model.
In practical situations, many work and rest behaviors are not in a single day, such as running plans and getting-up times, and are usually in a single week, so that if the behaviors are completed for each target by using one day as the cycle, the prediction accuracy may be low. Therefore, in the embodiment of the present invention, the corresponding behavior repeating cycle is firstly identified according to the target behavior history data of each target completing behavior, for example, the minimum repeating cycle of the running behavior is identified according to the history data of running of the user every day in the past year, and then the target behavior history data of the target completing behavior is divided into data segments according to the cycle to obtain the corresponding N cycle sample data. Due to the fact that the regularity of the user behaviors in the repetition period is strong, the user behaviors are used as sample data to be trained, and the obtained prediction accuracy rate is also relatively strong.
As a preferred embodiment of the present invention, when performing model construction based on N cycle sample data, data of the same day corresponding to each cycle in the cycle may be extracted separately from each cycle sample data, and if it is assumed that the running cycle is a week, data of monday, tuesday, … and sunday may be extracted separately at this time, so as to obtain 7 corresponding sets of cycle sample data. And modeling is carried out respectively based on the small period sample data to obtain a plurality of corresponding prediction models, and finally, prediction is carried out respectively by taking one day as a unit during prediction, as described above, the prediction is carried out respectively on Monday, tuesday, … and Sunday in the first preset time to obtain the prediction data corresponding to each day in the first preset time. In the embodiment of the invention, each target completion behavior corresponds to one or more behavior prediction submodels, and the behavior prediction submodels are used for predicting the behavior of each day in the repeating period so as to improve the accuracy of prediction.
As an embodiment of the present invention, after generating the hint, the method includes: and updating and training the behavior prediction model based on the behavior data of the target completion behavior of the user in the first preset time period.
After the prompt is generated, actual behavior data of the user for completing the behaviors to the targets in the first preset time are recorded, such as running data of each day in the first preset time, and the prediction model is updated and trained based on the data, so that the prediction accuracy of the prediction model is improved.
Fig. 4 shows a block diagram of a user behavior prompt generation apparatus provided in an embodiment of the present invention, which corresponds to the method in the foregoing embodiment, and for convenience of explanation, only the relevant parts to the embodiment of the present invention are shown. The user behavior prompt generation apparatus illustrated in fig. 4 may be an execution subject of the user behavior prompt generation method provided in the first embodiment.
Referring to fig. 4, the user behavior prompt generation device includes:
the plan obtaining module 41 is configured to obtain a work and rest behavior plan of a user in a first preset time period, where the work and rest behavior plan stores a target completion behavior of the user in the first preset time period and a target completion time of each target completion behavior in the first preset time period.
The behavior prediction module 42 is configured to screen target behavior historical data corresponding to the target completion behavior from the historical behavior data of the user, and perform deep learning on the target behavior historical data to obtain behavior prediction data corresponding to each target completion behavior in the first preset time period, where the behavior prediction data includes prediction completion time of the target completion behavior.
A prompt generating module 43, configured to generate an error behavior warning according to a time point, of the predicted completion time corresponding to each target completion behavior, that is different from the corresponding target completion time.
Further, the plan obtaining module 41 includes:
and acquiring personal information of the user, weather forecast data of the first preset time period and the work and rest behavior plan input by the user.
Calculating executable probability of the target completion behavior contained in the work and rest behavior plan based on the personal information and the weather forecast data, and adjusting the target completion time of the target completion behavior with the executable probability lower than a probability threshold.
Further, the behavior prediction module 42 includes:
and performing deep learning on each target behavior historical data to obtain a behavior prediction model corresponding to the target completion behaviors one by one, and performing analysis prediction on each target completion behavior in the first preset time period by using the behavior prediction model to obtain the behavior prediction data corresponding to the target completion behaviors one by one.
Further, the behavior prediction module 42 includes:
analyzing the historical finish time of the target finish behavior in the target behavior historical data, determining a behavior repetition period corresponding to the target finish behavior, dividing the target behavior historical data into N target behavior historical data segments with time lengths equal to the behavior repetition period according to the time sequence for storing the target behavior historical data, and obtaining N period sample data.
And performing model training based on the N periods of sample data to obtain the behavior prediction model.
The user behavior prompt generation device further comprises:
and updating and training the behavior prediction model based on the behavior data of the target completion behavior of the user in the first preset time period.
The process of implementing each function by each module in the user behavior prompt generating device provided in the embodiment of the present invention may specifically refer to the description of the first embodiment shown in fig. 1, and details are not repeated here.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
It will also be understood that, although the terms first, second, etc. may be used herein to describe various elements in some embodiments of the invention, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first contact may be termed a second contact, and, similarly, a second contact may be termed a first contact, without departing from the scope of the various described embodiments. The first contact and the second contact are both contacts, but they are not the same contact.
Fig. 5 is a schematic diagram of a user behavior prompt generation terminal device according to an embodiment of the present invention. As shown in fig. 5, the user behavior prompt generation terminal device 5 of this embodiment includes: a processor 50, a memory 51, said memory 51 having stored therein a computer program 52 executable on said processor 50. The processor 50, when executing the computer program 52, implements the steps in the above-described embodiments of the user behavior prompt generation method, such as the steps 101 to 103 shown in fig. 1. Alternatively, the processor 50, when executing the computer program 52, implements the functions of the modules/units in the above-mentioned device embodiments, such as the functions of the modules 41 to 43 shown in fig. 4.
The user behavior prompt generation terminal device 5 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing device. The user behavior prompt generating terminal device may include, but is not limited to, a processor 50 and a memory 51. It will be appreciated by those skilled in the art that fig. 5 is merely an example of the user behaviour cue generation terminal device 5, and does not constitute a limitation on the user behaviour cue generation terminal device 5, and may include more or fewer components than those shown, or some components may be combined, or different components, for example, the user behaviour cue generation terminal device may further include an input transmission device, a network access device, a bus, etc.
The Processor 50 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 51 may be an internal storage unit of the user behavior prompt generation terminal device 5, such as a hard disk or a memory of the user behavior prompt generation terminal device 5. The memory 51 may also be an external storage device of the user behavior prompt generation terminal device 5, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like provided on the user behavior prompt generation terminal device 5. Further, the memory 51 may also include both an internal storage unit and an external storage device of the user behavior prompt generation terminal device 5. The memory 51 is used for storing the computer program and other programs and data required by the user behavior prompt generation terminal device. The memory 51 may also be used to temporarily store data that has been transmitted or is to be transmitted.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U.S. disk, removable hard disk, magnetic diskette, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), electrical carrier wave signal, telecommunications signal, and software distribution medium, etc. It should be noted that the computer-readable medium may contain suitable additions or subtractions depending on the requirements of legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer-readable media may not include electrical carrier signals or telecommunication signals in accordance with legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (8)
1. A user behavior prompt generation method is characterized by comprising the following steps:
acquiring a work and rest action plan of a user in a first preset time period, wherein the work and rest action plan stores target completion actions of the user in the first preset time period and target completion time of each target completion action in the first preset time period;
screening target behavior historical data corresponding to the target completion behaviors from the historical behavior data of the user, and performing deep learning on the target behavior historical data to obtain behavior prediction data corresponding to each target completion behavior one by one in the first preset time period, wherein the behavior prediction data comprise the predicted completion time of the target completion behaviors;
generating a wrong behavior warning according to a time point of difference between the predicted completion time corresponding to each target completion behavior and the corresponding target completion time;
the deep learning of the target behavior historical data to obtain behavior prediction data corresponding to each target completion behavior in the first preset time period in a one-to-one manner includes:
and performing deep learning on each target behavior historical data to obtain a behavior prediction model corresponding to the target completion behaviors one by one, and performing analysis prediction on each target completion behavior in the first preset time period by using the behavior prediction model to obtain the behavior prediction data corresponding to the target completion behaviors one by one.
2. The method for generating a user behavior prompt according to claim 1, wherein the obtaining of the work and rest behavior plan of the user within the first preset time period comprises:
acquiring personal information of the user, weather forecast data of the first preset time period and the work and rest behavior plan input by the user;
calculating executable probability of the target completion behavior contained in the work and rest behavior plan based on the personal information and the weather forecast data, and adjusting the target completion time of the target completion behavior with the executable probability lower than a probability threshold.
3. The method of generating user behavior hints according to claim 1, wherein the building of the behavior prediction model process for the goal completion behavior comprises:
analyzing the historical completion time of the target completion behavior in the target behavior historical data, determining a behavior repetition period corresponding to the target completion behavior, and dividing the target behavior historical data into N target behavior historical data segments with the time length being the behavior repetition period according to the time sequence for storing the target behavior historical data to obtain N period sample data;
and performing model training based on the N periods of sample data to obtain the behavior prediction model.
4. The user behavior cue generation method of claim 1 further comprising:
and updating and training the behavior prediction model based on the behavior data of the target completion behavior of the user in the first preset time period.
5. A user behavior prompt generation terminal device, wherein the user behavior prompt generation terminal device includes a memory and a processor, the memory stores a computer program operable on the processor, and the processor executes the computer program to implement the following steps:
acquiring a work and rest action plan of a user in a first preset time period, wherein the work and rest action plan stores target completion actions of the user in the first preset time period and target completion time of each target completion action in the first preset time period;
screening target behavior historical data corresponding to the target completion behaviors from the historical behavior data of the user, and performing deep learning on the target behavior historical data to obtain behavior prediction data corresponding to each target completion behavior one by one in the first preset time period, wherein the behavior prediction data comprise the predicted completion time of the target completion behaviors;
generating an error behavior warning according to the time point of difference between the predicted completion time corresponding to each target completion behavior and the corresponding target completion time;
the deep learning of the target behavior historical data to obtain behavior prediction data corresponding to each target completion behavior in the first preset time period one to one specifically includes:
and performing deep learning on each target behavior historical data to obtain a behavior prediction model corresponding to the target completion behaviors one by one, and performing analysis prediction on each target completion behavior in the first preset time period by using the behavior prediction model to obtain the behavior prediction data corresponding to the target completion behaviors one by one.
6. The user behavior prompt generation terminal device according to claim 5, wherein the acquiring of the work and rest behavior plan of the user within the first preset time period specifically includes:
acquiring personal information of the user, weather forecast data of the first preset time period and the work and rest behavior plan input by the user;
calculating an executable probability of the target completion behavior included in the work and rest behavior plan based on the personal information and the weather forecast data, and adjusting the target completion time of the target completion behavior with the executable probability lower than a probability threshold.
7. The user behavior prompt generating terminal device according to claim 5, wherein the process of constructing the behavior prediction model for the target completion behavior specifically includes:
analyzing the historical finish time of the target finish behavior in the target behavior historical data, determining a behavior repetition period corresponding to the target finish behavior, and dividing the target behavior historical data into N target behavior historical data segments with time lengths equal to the behavior repetition period according to the time sequence for storing the target behavior historical data to obtain N periods of sample data;
and performing model training based on the N periods of sample data to obtain the behavior prediction model.
8. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of a method according to any one of claims 1 to 4.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810457094.3A CN108876284B (en) | 2018-05-14 | 2018-05-14 | User behavior prompt generation method and terminal equipment |
| PCT/CN2018/097118 WO2019218465A1 (en) | 2018-05-14 | 2018-07-25 | User behavior prompt generation method and apparatus, and terminal device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810457094.3A CN108876284B (en) | 2018-05-14 | 2018-05-14 | User behavior prompt generation method and terminal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108876284A CN108876284A (en) | 2018-11-23 |
| CN108876284B true CN108876284B (en) | 2023-04-18 |
Family
ID=64333924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810457094.3A Active CN108876284B (en) | 2018-05-14 | 2018-05-14 | User behavior prompt generation method and terminal equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108876284B (en) |
| WO (1) | WO2019218465A1 (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109684543B (en) * | 2018-12-14 | 2021-04-02 | 北京百度网讯科技有限公司 | User behavior prediction and information delivery method, device, server and storage medium |
| CN109978491B (en) * | 2019-02-12 | 2024-02-06 | 平安科技（深圳）有限公司 | Reminding prediction method, reminding prediction device, computer equipment and storage medium |
| WO2020168454A1 (en) * | 2019-02-18 | 2020-08-27 | 深圳市欢太科技有限公司 | Behavior recommendation method and apparatus, storage medium, and electronic device |
| CN110135794A (en) * | 2019-03-25 | 2019-08-16 | 阿里巴巴集团控股有限公司 | Intelligent checks based reminding method and device, electronic equipment and storage medium |
| CN110362266B (en) * | 2019-07-19 | 2020-12-18 | 北京字节跳动网络技术有限公司 | Prompt information display method, system, electronic equipment and computer readable medium |
| CN110610752B (en) * | 2019-08-23 | 2023-01-17 | 北京卡路里信息技术有限公司 | Moving object determining method and device |
| CN110719360B (en) * | 2019-09-04 | 2021-04-20 | 奇酷互联网络科技（深圳）有限公司 | Automatic generation method and device of memo event and storage device |
| CN110648115B (en) * | 2019-09-20 | 2023-09-22 | 深圳Tcl新技术有限公司 | Event reminding method, device, equipment and storage medium |
| CN111143350A (en) * | 2019-11-27 | 2020-05-12 | 深圳壹账通智能科技有限公司 | Enterprise data monitoring method and device, computer equipment and storage medium |
| CN114518797B (en) * | 2020-11-20 | 2024-02-13 | Oppo（重庆）智能科技有限公司 | Information pushing method and device, wearable device and storage medium |
| CN112488657B (en) * | 2020-12-08 | 2023-07-28 | 中国航空结算有限责任公司 | Flight information processing method, device and equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009230718A (en) * | 2008-03-25 | 2009-10-08 | Sysmex Corp | Apparatus, computer program and system for proposing lifestyle improvement |
| CN106650429A (en) * | 2016-09-30 | 2017-05-10 | 北京奇虎科技有限公司 | User behavior management method and system, and secure desktop |
| CN106683340A (en) * | 2016-12-15 | 2017-05-17 | 歌尔股份有限公司 | User behavior monitoring method and wearable equipment |
| CN107833610A (en) * | 2017-10-31 | 2018-03-23 | 咪咕互动娱乐有限公司 | A kind of based reminding method, device and computer-readable recording medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101620647A (en) * | 2008-07-03 | 2010-01-06 | 王晓毅 | Health-care management method and health-care management system for realizing method |
| CN102804238A (en) * | 2011-12-15 | 2012-11-28 | 北京英福生科技有限公司 | Exercise reminding device and system |
| CN106919776A (en) * | 2015-12-24 | 2017-07-04 | 中国移动通信集团公司 | The method and device that a kind of goal activities is reminded |
| CN107239669A (en) * | 2017-06-15 | 2017-10-10 | 重庆柚瓣家科技有限公司 | Health plan system |
| CN107609324A (en) * | 2017-10-11 | 2018-01-19 | 上海展扬通信技术有限公司 | A kind of management method and managing device of user's work and rest based on smart machine |
-
2018
- 2018-05-14 CN CN201810457094.3A patent/CN108876284B/en active Active
- 2018-07-25 WO PCT/CN2018/097118 patent/WO2019218465A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009230718A (en) * | 2008-03-25 | 2009-10-08 | Sysmex Corp | Apparatus, computer program and system for proposing lifestyle improvement |
| CN106650429A (en) * | 2016-09-30 | 2017-05-10 | 北京奇虎科技有限公司 | User behavior management method and system, and secure desktop |
| CN106683340A (en) * | 2016-12-15 | 2017-05-17 | 歌尔股份有限公司 | User behavior monitoring method and wearable equipment |
| CN107833610A (en) * | 2017-10-31 | 2018-03-23 | 咪咕互动娱乐有限公司 | A kind of based reminding method, device and computer-readable recording medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108876284A (en) | 2018-11-23 |
| WO2019218465A1 (en) | 2019-11-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108876284B (en) | User behavior prompt generation method and terminal equipment | |
| Bürkner et al. | Ordinal regression models in psychology: A tutorial | |
| CN108076224B (en) | Application program control method and device, storage medium and mobile terminal | |
| Matthiopoulos et al. | Establishing the link between habitat selection and animal population dynamics | |
| US20170316324A1 (en) | Computerized Event-Forecasting System and User Interface | |
| US11508479B2 (en) | Automated question generation and response tracking | |
| CN109324902B (en) | Method for adjusting working frequency of mobile terminal, mobile terminal and storage medium | |
| Arthur et al. | Adaptive social contact rates induce complex dynamics during epidemics | |
| US20200151627A1 (en) | Adherence monitoring through machine learning and computing model application | |
| EP3579154A1 (en) | Reinforcement learning for user behaviour | |
| CN115755564A (en) | Alarm clock control method based on sleep stage prediction, radar and storage medium | |
| US20150148616A1 (en) | Systems and methods for probability based risk prediction | |
| CN110070250B (en) | Exponentially-increased business index monitoring method and device, electronic equipment and medium | |
| CN115408696B (en) | Application identification method and electronic equipment | |
| CN117275673A (en) | Cognitive training equipment and method for improving distribution attention | |
| CN113344723B (en) | User insurance cognitive evolution path prediction method and device and computer equipment | |
| Erbas et al. | Embodied imitation-enhanced reinforcement learning in multi-agent systems | |
| CN112686690B (en) | Data processing method, device, electronic equipment and computer readable storage medium | |
| CN111930602B (en) | Performance index prediction method and device | |
| CN111046156B (en) | Method, device and server for determining rewarding data | |
| CN111340540B (en) | Advertisement recommendation model monitoring method, advertisement recommendation method and advertisement recommendation model monitoring device | |
| Esteban et al. | Supporting an autonomous social agent within a competitive environment | |
| Jarvis et al. | A computational architecture of punishment insensitivity | |
| CN111554406A (en) | Physiological data processing method and device, electronic equipment and storage medium | |
| KR102498426B1 (en) | Techniques to provide cognitive reinforcement training based on digital biomarkers |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |