CN114885016A - Service pushing method and device, storage medium and electronic device - Google Patents
Service pushing method and device, storage medium and electronic device Download PDFInfo
- Publication number
- CN114885016A CN114885016A CN202210467537.3A CN202210467537A CN114885016A CN 114885016 A CN114885016 A CN 114885016A CN 202210467537 A CN202210467537 A CN 202210467537A CN 114885016 A CN114885016 A CN 114885016A
- Authority
- CN
- China
- Prior art keywords
- control instruction
- target
- target object
- service
- occurrence probability
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000010801 machine learning Methods 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims description 41
- 238000012549 training Methods 0.000 claims description 29
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 13
- 230000003993 interaction Effects 0.000 claims description 12
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 5
- 230000004044 response Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000007635 classification algorithm Methods 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000036961 partial effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000005406 washing Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 238000004887 air purification Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
- H04L67/125—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks involving control of end-device applications over a network
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Automation & Control Theory (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Selective Calling Equipment (AREA)
Abstract
The application discloses a service pushing method and device, a storage medium and an electronic device, and relates to the technical field of smart families, wherein the service pushing method comprises the following steps: acquiring a first control instruction currently issued by a target object and a trigger condition of the first control instruction; inputting the first control instruction and the trigger condition into a prediction model to obtain a second control instruction and a target occurrence probability corresponding to the second control instruction, wherein the prediction model is trained by using multiple groups of data through machine learning, and each group of data in the multiple groups of data comprises: a control instruction set formed by the first control instruction and a second control instruction related to the first control instruction, a trigger condition corresponding to the control instruction set, and an occurrence probability of the second control instruction after the first control instruction; and under the condition that the target occurrence probability is greater than or equal to the preset threshold value, pushing the target service corresponding to the second control instruction to the target object.
Description
Technical Field
The application relates to the technical field of smart homes, in particular to a service pushing method and device, a storage medium and an electronic device.
Background
At present, intelligent household products can receive user instructions through voice and control relevant equipment to respond according to the user instructions, and the intelligent household products such as intelligent sound boxes, intelligent gateways, intelligent panels and the like can receive the voice instructions. The user can control the equipment through voice, so that the user does not need to directly walk to the equipment to perform key operation or use a remote controller to control, and the use of the user is facilitated. In addition, a user can edit the control instructions of the intelligent household equipment into scenes such as movie scenes according to the using scenes, the instructions of turning on the television, turning off the curtain and turning off the lamp can be combined, after the user edits the scenes, when the user needs to watch the television, the user only needs to execute the movie scenes to complete the execution of the instruction, and the use of the user is further facilitated. However, in the related art, when the user wakes up the smart device through a specific command, the smart device can only passively wait for the next control command of the user, and cannot form a humanized interaction with the user, and when the control command is complex, the user experience is poor because the processing time is too long when the control command is executed. For example, eight users want to turn on the light through the intelligent sound box at night, after the users awaken up the intelligent sound box, the intelligent sound box can only wait passively for the users to issue a light-on instruction at the moment, the light-on instruction is a simple device control instruction, and if the user changes to complex instructions such as scene control, and the like, because the flows such as state acquisition, instruction analysis and conversion, instruction issue and the like of a plurality of devices are involved, the time delay of instruction execution can be very high, and the user experience is poor. In addition, although many users use the functions of the smart home in daily life, the smart home system does not realize that many instructions can be combined and generate scenes according with the smart home system, and at the moment, the smart home system does not analyze the user behaviors and recommend the scenes to the users.
Therefore, the service provided by the current smart home for the user needs to depend on the instruction issued by the user in real time or a preset scene, the initiative of the service provided for the user is not provided, the instruction to be issued by the user is not estimated, interaction with the user cannot be formed or preprocessing cannot be performed in advance, and in addition, the instruction frequently used by the user cannot be combined to generate the scene to be recommended to the user.
Aiming at the problems that the target service cannot be actively pushed to the target object according to the current control instruction data issued by the target object and the like in the related technology, an effective technical scheme is not provided yet.
Disclosure of Invention
The embodiment of the invention provides a service pushing method and device, a storage medium and an electronic device, which are used for at least solving the problems that in the related art, target services cannot be actively pushed to a target object according to current control instruction data issued by the target object and the like.
According to an embodiment of the present invention, there is provided a service push method, including: acquiring a first control instruction currently issued by a target object and a trigger condition of the first control instruction; inputting the first control instruction and the trigger condition into a prediction model to obtain a second control instruction and a target occurrence probability corresponding to the second control instruction, wherein the prediction model is trained by using multiple groups of data through machine learning, and each group of data in the multiple groups of data comprises: a control instruction set formed by a first control instruction and a second control instruction related to the first control instruction, a trigger condition corresponding to the control instruction set, and an occurrence probability of the second control instruction after the first control instruction; and under the condition that the target occurrence probability is larger than or equal to a preset threshold value, pushing the target service corresponding to the second control instruction to the target object.
In an exemplary embodiment, when the target occurrence probability is greater than or equal to a preset threshold, pushing a target service corresponding to the second control instruction to the target object includes: preprocessing the second control instruction under the condition that the occurrence probability is greater than or equal to a preset threshold, wherein the preprocessing comprises at least one of the following steps: analyzing scene information corresponding to the second control instruction, and determining an analysis result of the scene information as a preprocessing result; acquiring the equipment state of the equipment to be controlled corresponding to the second control instruction, and determining the equipment state as the preprocessing result; combining the first control instruction and the second control instruction to perform instruction analysis to obtain a control operation, and determining the control operation as the preprocessing result; under the condition that the target occurrence probability is greater than or equal to a preset threshold value, pushing the target service corresponding to the second control instruction to the target object includes: and determining the target service according to the preprocessing result, and pushing the target service to the target object.
In an exemplary embodiment, after the first control instruction and the trigger condition are input into a prediction model to obtain a second control instruction and a target occurrence probability corresponding to the second control instruction, the method further includes: when the target occurrence probability is smaller than a preset threshold value, forbidding to push a target service corresponding to the second control instruction to the target object; starting to execute the service corresponding to the first control instruction; and entering a waiting state under the condition that the service execution is finished, wherein the waiting state is used for indicating that a first control instruction issued again by the target object is waited.
In an exemplary embodiment, when the target occurrence probability is greater than or equal to a preset threshold, after the target service corresponding to the second control instruction is pushed to the target object, the method further includes: under the condition that the target object refuses to execute the target service corresponding to the second control instruction, recording a third control instruction actively issued by the target object; binding the third control instruction with the trigger condition and the first control instruction to generate a training sample of the prediction model; adding the training samples to the set of control instructions to update the predictive model using the training samples.
In an exemplary embodiment, when the target occurrence probability is greater than or equal to a preset threshold, after the target service corresponding to the second control instruction is pushed to the target object, the method further includes: sending interactive information to the target object through voice equipment; receiving indication information which is fed back by the target object based on the interaction information and carries the permission of the target object to execute the target service, wherein the indication information carries a time point for executing the target service; and controlling the execution of the target service according to the indication information.
In an exemplary embodiment, when the target occurrence probability is greater than or equal to a preset threshold, after the target service corresponding to the second control instruction is pushed to the target object, the method further includes: determining an execution probability of the target object to the target service, wherein the execution probability is used for indicating the use condition of the target object to a plurality of control instructions existing in the target service; under the condition that the execution probability is larger than a second preset threshold value, generating a target scene model corresponding to the target service; adding the target scene model to a scene list of the target object.
In an exemplary embodiment, before obtaining the first control instruction currently issued by the target object, the method further includes: acquiring the interval time of at least two control instructions in a plurality of historical control instructions issued by the target object; and under the condition that the interval time is less than a third preset threshold, determining that the target object is in a state of continuously issuing control instructions, and recording a trigger condition corresponding to the control instruction issued for the first time in the continuously issuing control instructions.
According to another embodiment of the present invention, there is provided an apparatus for pushing a service, including: the acquisition module is used for acquiring a first control instruction currently issued by a target object and a trigger condition of the first control instruction; a prediction module, configured to input the first control instruction and the trigger condition into a prediction model to obtain a second control instruction and a target occurrence probability corresponding to the second control instruction, where the prediction model is trained through machine learning by using multiple sets of data, and each set of data in the multiple sets of data includes: a control instruction set formed by a first control instruction and a second control instruction related to the first control instruction, a trigger condition corresponding to the control instruction set, and an occurrence probability of the second control instruction after the first control instruction; and the pushing module is used for pushing the target service corresponding to the second control instruction to the target object under the condition that the target occurrence probability is greater than or equal to a preset threshold value.
In an exemplary embodiment, the pushing module is further configured to, when the occurrence probability is greater than or equal to a preset threshold, perform preprocessing on the second control instruction, where the preprocessing includes at least one of the following steps: analyzing scene information corresponding to the second control instruction, and determining an analysis result of the scene information as a preprocessing result; acquiring the equipment state of the equipment to be controlled corresponding to the second control instruction, and determining the equipment state as the preprocessing result; combining the first control instruction and the second control instruction to perform instruction analysis to obtain a control operation, and determining the control operation as the preprocessing result; under the condition that the target occurrence probability is greater than or equal to a preset threshold value, pushing the target service corresponding to the second control instruction to the target object includes: and determining the target service according to the preprocessing result, and pushing the target service to the target object.
In an exemplary embodiment, the above apparatus further comprises; the waiting module is used for forbidding to push the target service corresponding to the second control instruction to the target object under the condition that the target occurrence probability is smaller than a preset threshold value; starting to execute the service corresponding to the first control instruction; and entering a waiting state under the condition that the service execution is finished, wherein the waiting state is used for indicating that a first control instruction issued again by the target object is waited.
In an exemplary embodiment, the above apparatus further comprises; the updating module is used for recording a third control instruction actively issued by the target object under the condition that the target object refuses to execute the target service corresponding to the second control instruction; binding the third control instruction with the trigger condition and the first control instruction to generate a training sample of the prediction model; adding the training samples to the set of control instructions to update the predictive model using the training samples.
In an exemplary embodiment, the above apparatus further comprises; the interaction module sends interaction information to the target object through voice equipment; receiving indication information which is fed back by the target object based on the interaction information and carries the permission of the target object to execute the target service, wherein the indication information carries a time point for executing the target service; and controlling the execution of the target service according to the indication information.
In an exemplary embodiment, the above apparatus further comprises; the scene module is used for determining the execution probability of the target object on the target service, wherein the execution probability is used for indicating the use condition of the target object on a plurality of control instructions existing in the target service; under the condition that the execution probability is larger than a second preset threshold value, generating a target scene model corresponding to the target service; adding the target scene model to a scene list of the target object.
In an exemplary embodiment, the above apparatus further comprises; the determining module is used for acquiring the interval time of at least two control instructions in a plurality of historical control instructions issued by the target object; and under the condition that the interval time is less than a third preset threshold, determining that the target object is in a state of continuously issuing control instructions, and recording a trigger condition corresponding to the control instruction issued for the first time in the continuously issuing control instructions.
According to a further embodiment of the present invention, there is also provided a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
According to yet another embodiment of the present invention, there is also provided an electronic device, including a memory in which a computer program is stored and a processor configured to execute the computer program to perform the steps in any of the above method embodiments.
According to the invention, a first control instruction currently issued by a target object and a trigger condition of the first control instruction are obtained; inputting the first control instruction and the trigger condition into a prediction model to obtain a second control instruction and a target occurrence probability corresponding to the second control instruction, wherein the prediction model is trained by using multiple groups of data through machine learning, and each group of data in the multiple groups of data comprises: a control instruction set formed by the first control instruction and a second control instruction related to the first control instruction, a trigger condition corresponding to the control instruction set, and an occurrence probability of the second control instruction after the first control instruction; and under the condition that the target occurrence probability is greater than or equal to the preset threshold value, pushing the target service corresponding to the second control instruction to the target object. That is to say, a second control instruction which is possibly executed by a target object after the first control instruction is predicted through a prediction model based on a trigger condition and the first control instruction, and then a target service containing the second control instruction with a higher occurrence probability is pushed to the target object, so that active recommendation of the target object is realized, therefore, the problems that the target service cannot be actively pushed to the target object according to current control instruction data issued by the target object and the like in the prior art can be solved, when the target object wakes up an intelligent device or issues an instruction, the intelligent home system can predict a subsequent control instruction of the target object, and scene recommendation containing the target service is carried out on the target object according to the occurrence probability of a prediction result, so that the intelligence of individuation and a platform is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
Fig. 1 is a hardware environment diagram of a method for pushing a service according to an embodiment of the present application;
FIG. 2 is a flow diagram of a method of service push according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an overall system architecture for improving smart home service initiative and personalized scene recommendation using a machine learning algorithm, in accordance with an alternative embodiment of the present invention;
FIG. 4 is a flow diagram of enhancing smart home service initiative and personalized scene recommendation using a machine learning algorithm, according to an alternative embodiment of the present invention;
fig. 5 is a block diagram of a service push determination apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the accompanying drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Moreover, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
According to an aspect of an embodiment of the present application, a method for service push is provided. The service pushing method is widely applied to full-House intelligent digital control application scenes such as intelligent homes (Smart Home), intelligent homes, intelligent Home equipment ecology, intelligent House (Intelligent House) ecology and the like. Alternatively, in this embodiment, the method for pushing the service may be applied to a hardware environment formed by the terminal device 102 and the server 104 as shown in fig. 1. As shown in fig. 1, the server 104 is connected to the terminal device 102 through a network, and may be configured to provide a service (e.g., an application service) for the terminal or a client installed on the terminal, set a database on the server or independent of the server, and provide a data storage service for the server 104, and configure a cloud computing and/or edge computing service on the server or independent of the server, and provide a data operation service for the server 104.
The network may include, but is not limited to, at least one of: wired networks, wireless networks. The wired network may include, but is not limited to, at least one of: wide area networks, metropolitan area networks, local area networks, which may include, but are not limited to, at least one of the following: WIFI (Wireless Fidelity), bluetooth. Terminal equipment 102 can be but not limited to be PC, the cell-phone, the panel computer, intelligent air conditioner, intelligent cigarette machine, intelligent refrigerator, intelligent oven, intelligent kitchen range, intelligent washing machine, intelligent water heater, intelligent washing equipment, intelligent dish washer, intelligent projection equipment, intelligent TV, intelligent clothes hanger, intelligent (window) curtain, intelligence audio-visual, smart jack, intelligent stereo set, intelligent audio amplifier, intelligent new trend equipment, intelligent kitchen guarding equipment, intelligent bathroom equipment, intelligence robot of sweeping the floor, intelligence robot of wiping the window, intelligence robot of mopping the ground, intelligent air purification equipment, intelligent steam ager, intelligent microwave oven, intelligent kitchen is precious, intelligent clarifier, intelligent water dispenser, intelligent lock etc..
In this embodiment, a method for pushing a service is provided, and fig. 2 is a flowchart of the method for pushing a service according to an embodiment of the present invention, where the flowchart includes the following steps:
step S202, acquiring a first control instruction currently issued by a target object and a trigger condition of the first control instruction;
step S204, inputting the first control instruction and the trigger condition into a prediction model to obtain a second control instruction and a target occurrence probability corresponding to the second control instruction, where the prediction model is trained by machine learning using multiple sets of data, and each set of data in the multiple sets of data includes: a control instruction set formed by a first control instruction and a second control instruction related to the first control instruction, a trigger condition corresponding to the control instruction set, and an occurrence probability of the second control instruction after the first control instruction;
step S206, when the target occurrence probability is greater than or equal to a preset threshold, pushing a target service corresponding to the second control instruction to the target object.
Through the steps, a first control instruction currently issued by the target object and a trigger condition of the first control instruction are obtained; inputting the first control instruction and the trigger condition into a prediction model to obtain a second control instruction and a target occurrence probability corresponding to the second control instruction, wherein the prediction model is trained by using multiple groups of data through machine learning, and each group of data in the multiple groups of data comprises: a control instruction set formed by the first control instruction and a second control instruction related to the first control instruction, a trigger condition corresponding to the control instruction set, and an occurrence probability of the second control instruction after the first control instruction; and under the condition that the target occurrence probability is greater than or equal to the preset threshold value, pushing the target service corresponding to the second control instruction to the target object. That is to say, a second control instruction which is possibly executed by a target object after the first control instruction is predicted through a prediction model based on a trigger condition and the first control instruction, and then a target service containing the second control instruction with a higher occurrence probability is pushed to the target object, so that active recommendation of the target object is realized, therefore, the problems that the target service cannot be actively pushed to the target object according to current control instruction data issued by the target object and the like in the prior art can be solved, when the target object wakes up an intelligent device or issues an instruction, the intelligent home system can predict a subsequent control instruction of the target object, and scene recommendation containing the target service is carried out on the target object according to the occurrence probability of a prediction result, so that the intelligence of individuation and a platform is improved.
It should be noted that the method can be applied to an intelligent home system at the cloud end of the internet of things, and can also be applied to other suitable systems or software, which is not limited in this application.
In an exemplary embodiment, when the target occurrence probability is greater than or equal to a preset threshold, pushing a target service corresponding to the second control instruction to the target object includes: preprocessing the second control instruction under the condition that the occurrence probability is greater than or equal to a preset threshold, wherein the preprocessing comprises at least one of the following steps: analyzing scene information corresponding to the second control instruction, and determining an analysis result of the scene information as a preprocessing result; acquiring the equipment state of the equipment to be controlled corresponding to the second control instruction, and determining the equipment state as the preprocessing result; combining the first control instruction and the second control instruction to perform instruction analysis to obtain a control operation, and determining the control operation as the preprocessing result; under the condition that the target occurrence probability is greater than or equal to a preset threshold value, pushing the target service corresponding to the second control instruction to the target object includes: and determining the target service according to the preprocessing result, and pushing the target service to the target object. Optionally, the target service at least includes a first control instruction and a second control instruction that completes the preprocessing, and the second control instruction is executed after the first control instruction.
For example, after a user (equivalent to a target object in the embodiment of the present invention) wakes up an intelligent device or issues an instruction, the intelligent home system may predict a subsequent control instruction of the user, and for a prediction result, the intelligent device may actively inquire whether the user needs a predicted service, and interact with the user to improve intelligence and user experience, or may pre-process a complex instruction, obtain a device state in advance, and complete instruction analysis and conversion, thereby greatly reducing an execution time of the complex instruction, and improving response efficiency of the complex instruction under a condition that the user determines to execute the complex instruction.
In an exemplary embodiment, after the first control instruction and the trigger condition are input into a prediction model to obtain a second control instruction and a target occurrence probability corresponding to the second control instruction, the method further includes: when the target occurrence probability is smaller than a preset threshold value, forbidding to push a target service corresponding to the second control instruction to the target object; starting to execute the service corresponding to the first control instruction; and entering a waiting state under the condition that the service execution is finished, wherein the waiting state is used for indicating that a first control instruction issued again by the target object is waited.
It is understood that, in order to ensure the accuracy of the prediction, a preset threshold value is set correspondingly, and a second control instruction which is likely to occur or has a greater probability of occurring is selected as an instruction after the first control instruction is executed, for example, the probability of occurrence of a plurality of second control instructions which are likely to be executed after the first control instruction is determined according to the triggering condition is respectively: 76%, 90%, 85% and 65% of the preset threshold, at this time, only the second control instructions with the occurrence probabilities of 90% and 85% are recommended to the target object, and when the determined plurality of second control instructions which are possibly executed are all lower than the preset threshold, it is indicated that the operation of the target object at this time does not exist in the system cannot be accurately predicted, the target service which at least comprises the first control instruction and the second control instruction which completes the preprocessing is prohibited from being recommended to the target object, and then the prediction flow is performed again when the target object issues the first control instruction at the next time.
In an exemplary embodiment, when the target occurrence probability is greater than or equal to a preset threshold, after the target service corresponding to the second control instruction is pushed to the target object, the method further includes: under the condition that the target object refuses to execute the target service corresponding to the second control instruction, recording a third control instruction actively issued by the target object; binding the third control instruction with the trigger condition and the first control instruction to generate a training sample of the prediction model; adding the training samples to the set of control instructions to update the predictive model using the training samples.
In an exemplary embodiment, when the target occurrence probability is greater than or equal to a preset threshold, after the target service corresponding to the second control instruction is pushed to the target object, the method further includes: sending interactive information to the target object through voice equipment; receiving indication information which is fed back by the target object based on the interaction information and carries the permission of the target object to execute the target service, wherein the indication information carries a time point for executing the target service; and controlling the execution of the target service according to the indication information.
For example, when a user controls the smart home device through voice, the smart home system platform at the cloud of the internet of things records instructions continuously issued by the user and trigger conditions thereof as samples, each sample is composed of a feature and a label, the trigger conditions and the leading instructions serve as the features, and the last instruction serves as the label. Wherein the definition of the continuous issue is: the issuing time interval of the two instructions does not exceed a certain time range, such as 10 seconds. Specifically, when the user wakes up the sound box in the living room at nine nights, the light-off instruction is issued, and then the television-on instruction is issued, the time (nine nights), the position (the living room), the equipment (the sound box) and the front instruction (the light-off instruction) at the moment form the characteristics of the sample, and the last television-on instruction serves as the label. In order to avoid the situation that the classification algorithm cannot calculate due to the fact that the time granularity is too small, time can be segmented according to hours. And collecting user instruction information samples for multiple times according to the rules to form a set which is used as a training set of a subsequent training model.
In an exemplary embodiment, when the target occurrence probability is greater than or equal to a preset threshold, after the target service corresponding to the second control instruction is pushed to the target object, the method further includes: determining an execution probability of the target object to the target service, wherein the execution probability is used for indicating the use condition of the target object to a plurality of control instructions existing in the target service; under the condition that the execution probability is larger than a second preset threshold value, generating a target scene model corresponding to the target service; adding the target scene model to a scene list of the target object.
Optionally, if the target object confirms that the prediction instruction is executed and the instruction prediction occurrence probability is high, a scene is automatically generated and the target object is asked whether to set the combination as the scene, and when the target object confirms that the scene needs to be generated, the scene is saved in the scene list of the target object. The process of automatically generating the scene is as follows: and taking the trigger condition as a precondition of the scene, and taking the precondition instruction, the final instruction and the like as scene execution contents according to the sequence. The scenario is a continuous operation flow formed by combining a plurality of control commands having an association relationship.
In an exemplary embodiment, before obtaining the first control instruction currently issued by the target object, the method further includes: acquiring the interval time of at least two control instructions in a plurality of historical control instructions issued by the target object; and under the condition that the interval time is less than a third preset threshold, determining that the target object is in a state of continuously issuing control instructions, and recording a trigger condition corresponding to the control instruction issued for the first time in the continuously issuing control instructions.
In order to better understand the process of the service push method, the following describes a flow of the service push method with reference to several alternative embodiments.
As an optional embodiment, a method for improving the initiative of the smart home service and recommending personalized scenes by using a machine learning algorithm is provided, when a user wakes up the smart device or issues an instruction, the smart home system can predict a subsequent control instruction of the user, and according to a prediction result, the smart device can actively inquire whether the user needs the predicted service or not to interact with the user to improve the intelligence and user experience, and can also perform preprocessing on a complex instruction to obtain the state of the device in advance and finish the analysis and conversion of the instruction, so that the execution time of the complex instruction is greatly reduced. In addition, the user scene can be recommended according to the occurrence probability of the prediction result, and the user individuation and the platform intelligence are improved.
Optionally, fig. 3 is a schematic diagram of an overall system architecture for improving the initiative of the smart home service and the personalized scene recommendation by using a machine learning algorithm according to an optional embodiment of the present invention.
Optionally, the user may edit the architecture map of the overall system, thereby making some personalized settings. For example, naming the device itself, or setting parameters, etc., so that the constructed architecture map of the system interacts with the user, and the architecture map of the personalized system suitable for the user is adjusted.
Optionally, fig. 4 is a flowchart illustrating a method for improving the initiative of the smart home service and recommending personalized scenes by using a machine learning algorithm according to an alternative embodiment of the present invention; the method specifically comprises the following steps:
step 1, recording user instruction information as a sample; in an optional embodiment of the present invention, when a user controls an intelligent home device through voice, an AIOT (Artificial Intelligence and Internet of Things, AIOT for short) platform records instructions continuously issued by the user and trigger conditions thereof as samples, each sample is composed of a feature and a tag, the trigger conditions and a pre-instruction are used as the features, and the last instruction is used as the tag. Wherein the definition of the continuous issue is: the issuing time interval of the two instructions does not exceed a certain time range, such as 10 seconds.
For example, if the user wakes up the sound box in the living room at nine nights, and then reaches the light-off command, and then reaches the television-on command, the time (nine nights), the location (living room), the device (sound box), and the front command (light-off command) at this time constitute the characteristics of the sample, and the last television-on command serves as the tag. In order to avoid the situation that the classification algorithm cannot calculate due to the fact that the time granularity is too small, time can be segmented according to hours. And collecting user instruction information samples for multiple times according to the rules to form a set which is used as a training set of a subsequent training model.
Step 2, training the model according to the training set; predicting the last instruction through a trigger condition and a preposed instruction, wherein the value range of the last instruction is the existing function set of all equipment, and performing model training of multi-classification results;
as an alternative, a Softmax regression classification model in machine learning is used for training. And (3) the last instruction has m value conditions, and when the classification labels corresponding to the Softmax regression classification model are m, the training samples obtained in the step (1) are as follows:
A＝{(x (1) ，y (i) )，(x (2) ，y (i) )，...，(x (n) ，y (i) )}；
wherein, a is a training sample set, x (1), x (2.) x (n) is feature data composed of trigger conditions and preposed instructions, n is the number of user operation records stored by AIOT, y (i) is a classification label, namely the last instruction of a user, and y (i) is epsilon {1, 2.. multidot.m }.
The calculation formula of the probability that each sample estimates the class label to which it belongs is:
P(y＝j|x)(j＝1,2,...,m)
wherein x represents characteristic data and y represents the last instruction of the user; p represents the probability of calculation; j is a counting factor;
according to the generalized linear model theory, the prediction function of the sample can be obtained as follows:
wherein the content of the first and second substances,
h w (x (i) ) Representing the prediction function of the ith sample, estimating the probability of occurrence of each classification result of x, x (i) For the input feature data, h w (x (i) ) This m-dimensional vector of outputs represents the probability values estimated for the m classification labels (i.e. for each possible user instruction);
the effect of (1) is to normalize the probability distribution so that x (i) The sum of the probabilities belonging to each category is 1; w is a i Is x (i) The classification weight, W, is an m × k matrix.
And (3) solving the maximum likelihood estimation by using a loss function of a Softmax regression model, wherein the formula of the loss function J (W) is as follows:
wherein, I (y) (i) ) j To indicate the function, when y (i) Class j time I (y) (i) ) j 1, otherwise 0;
The solution to the loss is as follows:
retaining all weight parameters (w) 1 ，w 2 ，...，w m ) In the case of (2), a weighted attenuation term is added to the loss function
Then the loss function becomes:
at this time, the loss function becomes a convex function, a unique solution is provided, the Hessian matrix is reversible, and the partial derivative of J (W) is obtained by adopting a gradient descent method, which is as follows:
the weights wj are updated in conjunction with the training data to find the optimal solution for wj as followsShown in the figure:
wherein α is the learning rate; after training is finished, forward propagation is carried out on the test data by using W, each test data obtains m values, and an instruction corresponding to the maximum value is selected as a most likely instruction predicted by the model.
Step 3, when the user wakes up the equipment or issues the instruction, predicting the next instruction and the probability thereof through the model; optionally, when the user wakes up the device or issues an instruction, a sample x composed of user operations (time, location, device, etc.) is substituted into the model obtained by calculation in step 2 to perform Softmax regression prediction. The probability of all instructions in the functional set can be predicted through Softmax regression, the instruction with the highest occurrence probability is found, if the predicted occurrence probability exceeds a certain value, such as 80%, the step 4 is carried out, and if not, the step 5 is skipped.
Step 4, preprocessing according to the prediction result and interacting with the user; the AIOT platform carries out certain preprocessing aiming at predicting an impending instruction, such as scene analysis, related equipment state acquisition, control instruction analysis and conversion and the like, when a user confirms that the instruction needs to be executed, the instruction can be directly issued, the response speed of the instruction is improved, especially when the instruction is a complex instruction such as a scene and the like, the state acquisition of a plurality of pieces of equipment, the multi-control instruction analysis and conversion and the like can be preprocessed, and the scene type instruction response speed is obviously improved. And during preprocessing, the equipment intelligence can be improved by interacting with the user through front-end equipment, for example, front-end equipment capable of voice interaction such as an intelligent sound box and a gateway can actively inquire whether the user needs to provide a service corresponding to the prediction instruction, if the user needs the service, the step 6 is skipped, and if not, the step 5 is skipped.
Step 5, waiting for a user instruction; if the instruction wanted by the user is not the same as the predicted instruction, the user denies the service when the front end interacts, the user waits for the input of the user instruction at the moment, the processing is carried out according to the user instruction, the triggering condition and the pre-instruction are used as characteristics, the instruction given by the user finally is used as a label, a new sample is generated and stored in the set in the step 1 for the model training in the step 2.
Step 6, executing according to the prediction result; if the front-end user confirms that the service corresponding to the instruction is needed, namely the instruction desired by the user is the same as the predicted instruction, the next step of instruction execution is carried out according to the preprocessing performed in the step 4, and the step 7 is continued.
Step 7, generating a scene and recommending the scene to a user; if the user confirms that the prediction instruction is executed and the prediction occurrence probability of the instruction is high, if the prediction result occurrence probability is higher than 90%, a scene is automatically generated, whether the user needs to set the combination as the scene or not is inquired, and when the user confirms that the scene needs to be generated, the scene is stored in a scene list of the user. The process of automatically generating the scene is as follows: and taking the trigger condition as a precondition of the scene, and taking the precondition (if any) and the final instruction and the like as scene execution contents according to the sequence.
According to the scheme, the user instruction information is recorded through the AIOT cloud end, a Softmax regression model is adopted to train according to the user record to generate a model, the next instruction is predicted after the user wakes up the equipment or issues the instruction, and the probability of the instruction occurrence is calculated; and when the user wakes up the equipment or issues an instruction, predicting the next instruction and the probability thereof through the model, judging whether preprocessing is needed or not according to the probability and actively providing service for the user. And when the predicted instruction is the same as the service desired by the user, judging whether to generate a scene for the user record according to the probability of the predicted instruction and recommending the scene to the user.
In summary, according to the method, when the user performs the smart home operation, the user can predict the next step of the instruction, and perform the preprocessing according to the prediction result and provide the service to the user actively, compared with the case that the conventional smart home can only receive the user instruction passively, the method can provide more intelligent and humanized smart home experience for the user, greatly shorten the response time of the complex instruction due to the preprocessing, and improve the user experience; in addition, if the user instruction is consistent with the prediction result and the occurrence probability of the prediction instruction is high, a scene is generated according to the trigger condition and the user instruction and recommended to the user, and the scene is generated according to different user operation habits through the algorithm, so that remarkable individuation is achieved.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk), and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method for pushing the service according to the embodiments of the present invention.
In this embodiment, a device for pushing a service is further provided, where the device is used to implement the foregoing embodiment and the preferred embodiment, and details of the description already made are omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 5 is a block diagram of a structure of a service push determination apparatus according to an embodiment of the present invention, and as shown in fig. 5, the apparatus includes:
(1) an obtaining module 52, configured to obtain a first control instruction currently issued by a target object, and a trigger condition of the first control instruction;
(2) a prediction module 54, configured to input the first control instruction and the trigger condition into a prediction model to obtain a second control instruction and a target occurrence probability corresponding to the second control instruction, where the prediction model is trained through machine learning by using multiple sets of data, and each set of data in the multiple sets of data includes: a control instruction set formed by a first control instruction and a second control instruction related to the first control instruction, a trigger condition corresponding to the control instruction set, and an occurrence probability of the second control instruction after the first control instruction;
(3) a pushing module 56, configured to push, to the target object, the target service corresponding to the second control instruction when the target occurrence probability is greater than or equal to a preset threshold.
Acquiring a first control instruction currently issued by a target object and a trigger condition of the first control instruction by the device; inputting the first control instruction and the trigger condition into a prediction model to obtain a second control instruction and a target occurrence probability corresponding to the second control instruction, wherein the prediction model is trained by using multiple groups of data through machine learning, and each group of data in the multiple groups of data comprises: a control instruction set formed by the first control instruction and a second control instruction related to the first control instruction, a trigger condition corresponding to the control instruction set, and an occurrence probability of the second control instruction after the first control instruction; and under the condition that the target occurrence probability is greater than or equal to the preset threshold value, pushing the target service corresponding to the second control instruction to the target object. That is to say, a second control instruction which is possibly executed by a target object after the first control instruction is predicted through a prediction model based on a trigger condition and the first control instruction, and then a target service containing the second control instruction with a higher occurrence probability is pushed to the target object, so that active recommendation of the target object is realized, therefore, the problems that the target service cannot be actively pushed to the target object according to current control instruction data issued by the target object and the like in the prior art can be solved, when the target object wakes up an intelligent device or issues an instruction, the intelligent home system can predict a subsequent control instruction of the target object, and scene recommendation containing the target service is carried out on the target object according to the occurrence probability of a prediction result, so that the intelligence of individuation and a platform is improved.
In an exemplary embodiment, the pushing module is further configured to, when the occurrence probability is greater than or equal to a preset threshold, perform preprocessing on the second control instruction, where the preprocessing includes at least one of the following steps: analyzing scene information corresponding to the second control instruction, and determining an analysis result of the scene information as a preprocessing result; acquiring the equipment state of the equipment to be controlled corresponding to the second control instruction, and determining the equipment state as the preprocessing result; combining the first control instruction and the second control instruction to perform instruction analysis to obtain a control operation, and determining the control operation as the preprocessing result; under the condition that the target occurrence probability is greater than or equal to a preset threshold value, pushing the target service corresponding to the second control instruction to the target object includes: and determining the target service according to the preprocessing result, and pushing the target service to the target object.
In an exemplary embodiment, the above apparatus further comprises; the waiting module is used for forbidding to push the target service corresponding to the second control instruction to the target object under the condition that the target occurrence probability is smaller than a preset threshold value; starting to execute the service corresponding to the first control instruction; and entering a waiting state under the condition that the service execution is finished, wherein the waiting state is used for indicating that a first control instruction issued again by the target object is waited.
In an exemplary embodiment, the above apparatus further comprises; the updating module is used for recording a third control instruction actively issued by the target object under the condition that the target object refuses to execute the target service corresponding to the second control instruction; binding the third control instruction with the trigger condition and the first control instruction to generate a training sample of the prediction model; adding the training samples to the set of control instructions to update the predictive model using the training samples.
In an exemplary embodiment, the above apparatus further comprises; the interaction module sends interaction information to the target object through voice equipment; receiving indication information which is fed back by the target object based on the interaction information and carries the permission of the target object to execute the target service, wherein the indication information carries a time point for executing the target service; and controlling the execution of the target service according to the indication information.
In an exemplary embodiment, the above apparatus further comprises; the scene module is used for determining the execution probability of the target object on the target service, wherein the execution probability is used for indicating the use condition of the target object on a plurality of control instructions existing in the target service; under the condition that the execution probability is larger than a second preset threshold value, generating a target scene model corresponding to the target service; adding the target scene model to a scene list of the target object.
In an exemplary embodiment, the above apparatus further comprises; the determining module is used for acquiring the interval time of at least two control instructions in a plurality of historical control instructions issued by the target object; and under the condition that the interval time is less than a third preset threshold, determining that the target object is in a state of continuously issuing control instructions, and recording a trigger condition corresponding to the control instruction issued for the first time in the continuously issuing control instructions.
In the description of the present invention, it is to be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience in describing the present invention and simplifying the description, but do not indicate or imply that the device or assembly referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; the two components can be directly connected or indirectly connected through an intermediate medium, and the two components can be communicated with each other. When an element is referred to as being "secured to" or "disposed on" another element, it can be directly on the other element or intervening elements may also be present. When a component is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The specific meaning of the above terms in the present invention can be understood in specific cases to those skilled in the art.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.
An embodiment of the present invention further provides a storage medium having a computer program stored therein, wherein the computer program is configured to perform the steps in any of the method embodiments described above when executed.
In an exemplary embodiment, in the present embodiment, the storage medium may be configured to store a computer program for executing the steps of:
s1, acquiring a first control instruction currently issued by a target object and a trigger condition of the first control instruction;
s2, inputting the first control instruction and the trigger condition into a prediction model to obtain a second control instruction and a target occurrence probability corresponding to the second control instruction, where the prediction model is trained by machine learning using multiple sets of data, and each set of data in the multiple sets of data includes: a control instruction set formed by a first control instruction and a second control instruction related to the first control instruction, a trigger condition corresponding to the control instruction set, and an occurrence probability of the second control instruction after the first control instruction;
and S3, pushing the target service corresponding to the second control instruction to the target object under the condition that the target occurrence probability is greater than or equal to a preset threshold value.
In an exemplary embodiment, in the present embodiment, the storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
In an exemplary embodiment, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
In an exemplary embodiment, in the present embodiment, the processor may be configured to execute the following steps by a computer program:
s1, acquiring a first control instruction currently issued by a target object and a trigger condition of the first control instruction;
s2, inputting the first control instruction and the trigger condition into a prediction model to obtain a second control instruction and a target occurrence probability corresponding to the second control instruction, where the prediction model is trained by machine learning using multiple sets of data, and each set of data in the multiple sets of data includes: a control instruction set formed by a first control instruction and a second control instruction related to the first control instruction, a trigger condition corresponding to the control instruction set, and an occurrence probability of the second control instruction after the first control instruction;
and S3, pushing the target service corresponding to the second control instruction to the target object under the condition that the target occurrence probability is greater than or equal to a preset threshold value.
In an exemplary embodiment, for specific examples in this embodiment, reference may be made to the examples described in the above embodiments and optional implementations, and details of this embodiment are not described herein again.
It will be apparent to those skilled in the art that the various modules or steps of the invention described above may be implemented using a general purpose computing device, which may be centralized on a single computing device or distributed across a network of computing devices, and in one exemplary embodiment may be implemented using program code executable by a computing device, such that the steps shown and described may be executed by a computing device stored in a memory device and, in some cases, executed in a sequence different from that shown and described herein, or separately fabricated into individual integrated circuit modules, or multiple ones of them fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.
Claims (10)
1. A method of service push, comprising:
acquiring a first control instruction currently issued by a target object and a trigger condition of the first control instruction;
inputting the first control instruction and the trigger condition into a prediction model to obtain a second control instruction and a target occurrence probability corresponding to the second control instruction, wherein the prediction model is trained by using multiple groups of data through machine learning, and each group of data in the multiple groups of data comprises: a control instruction set formed by a first control instruction and a second control instruction related to the first control instruction, a trigger condition corresponding to the control instruction set, and an occurrence probability of the second control instruction after the first control instruction;
and under the condition that the target occurrence probability is greater than or equal to a preset threshold value, pushing the target service corresponding to the second control instruction to the target object.
2. The service pushing method according to claim 1, wherein when the target occurrence probability is greater than or equal to a preset threshold, pushing a target service corresponding to the second control instruction to the target object includes:
preprocessing the second control instruction under the condition that the occurrence probability is greater than or equal to a preset threshold, wherein the preprocessing comprises at least one of the following steps:
analyzing scene information corresponding to the second control instruction, and determining an analysis result of the scene information as a preprocessing result;
acquiring the equipment state of the equipment to be controlled corresponding to the second control instruction, and determining the equipment state as the preprocessing result;
combining the first control instruction and the second control instruction to perform instruction analysis to obtain a control operation, and determining the control operation as the preprocessing result;
when the target occurrence probability is greater than or equal to a preset threshold, pushing a target service corresponding to the second control instruction to the target object includes:
and determining the target service according to the preprocessing result, and pushing the target service to the target object.
3. The service push method according to claim 1, wherein after the first control instruction and the trigger condition are input into a prediction model to obtain a second control instruction and a target occurrence probability corresponding to the second control instruction, the method further comprises:
when the target occurrence probability is smaller than a preset threshold value, forbidding to push a target service corresponding to the second control instruction to the target object; starting and executing the service corresponding to the first control instruction;
and entering a waiting state under the condition that the service execution is finished, wherein the waiting state is used for indicating that a first control instruction issued again by the target object is waited.
4. The service pushing method according to claim 1 or 2, wherein after the target service corresponding to the second control instruction is pushed to the target object when the target occurrence probability is greater than or equal to a preset threshold, the method further comprises:
under the condition that the target object refuses to execute the target service corresponding to the second control instruction, recording a third control instruction actively issued by the target object;
binding the third control instruction with the trigger condition and the first control instruction to generate a training sample of the prediction model;
adding the training samples to the set of control instructions to update the predictive model using the training samples.
5. The service pushing method according to any one of claims 1 to 4, wherein after pushing the target service corresponding to the second control instruction to the target object when the target occurrence probability is greater than or equal to a preset threshold, the method further comprises:
sending interactive information to the target object through voice equipment;
receiving indication information which is fed back by the target object based on the interaction information and carries the permission of the target object to execute the target service, wherein the indication information carries a time point for executing the target service;
and controlling the execution of the target service according to the indication information.
6. The service pushing method according to any one of claims 1 to 4, wherein after pushing the target service corresponding to the second control instruction to the target object when the target occurrence probability is greater than or equal to a preset threshold, the method further comprises:
determining an execution probability of the target object to the target service, wherein the execution probability is used for indicating the use condition of the target object to a plurality of control instructions existing in the target service;
under the condition that the execution probability is larger than a second preset threshold value, generating a target scene model corresponding to the target service;
adding the target scene model to a scene list of the target object.
7. The service push method according to any one of claims 1 to 6, wherein before acquiring the first control instruction currently issued by the target object, the method further comprises:
acquiring the interval time of at least two control instructions in a plurality of historical control instructions issued by the target object;
and under the condition that the interval time is less than a third preset threshold, determining that the target object is in a state of continuously issuing control instructions, and recording a trigger condition corresponding to the control instruction issued for the first time in the continuously issuing control instructions.
8. An apparatus for service push, comprising:
the acquisition module is used for acquiring a first control instruction currently issued by a target object and a trigger condition of the first control instruction;
a prediction module, configured to input the first control instruction and the trigger condition into a prediction model to obtain a second control instruction and a target occurrence probability corresponding to the second control instruction, where the prediction model is trained through machine learning by using multiple sets of data, and each set of data in the multiple sets of data includes: a control instruction set formed by a first control instruction and a second control instruction related to the first control instruction, a trigger condition corresponding to the control instruction set, and an occurrence probability of the second control instruction after the first control instruction;
and the pushing module is used for pushing the target service corresponding to the second control instruction to the target object under the condition that the target occurrence probability is greater than or equal to a preset threshold value.
9. A computer-readable storage medium, comprising a stored program, wherein the program when executed performs the method of any of claims 1 to 7.
10. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to execute the method of any of claims 1 to 7 by means of the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210467537.3A CN114885016A (en) | 2022-04-29 | 2022-04-29 | Service pushing method and device, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210467537.3A CN114885016A (en) | 2022-04-29 | 2022-04-29 | Service pushing method and device, storage medium and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114885016A true CN114885016A (en) | 2022-08-09 |
Family
ID=82672853
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210467537.3A Pending CN114885016A (en) | 2022-04-29 | 2022-04-29 | Service pushing method and device, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114885016A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104832418A (en) * | 2015-05-07 | 2015-08-12 | 北京航空航天大学 | Hydraulic pump fault diagnosis method based on local mean conversion and Softmax |
| CN108063701A (en) * | 2016-11-08 | 2018-05-22 | 华为技术有限公司 | A kind of method and device for controlling smart machine |
| CN108733825A (en) * | 2018-05-23 | 2018-11-02 | 阿里巴巴集团控股有限公司 | A kind of objects trigger event prediction method and device |
| CN108919669A (en) * | 2018-09-11 | 2018-11-30 | 深圳和而泰数据资源与云技术有限公司 | A kind of smart home dynamic decision method, apparatus and service terminal |
| CN109818839A (en) * | 2019-02-03 | 2019-05-28 | 三星电子（中国）研发中心 | Personalized behavior prediction methods, devices and systems applied to smart home |
| CN110619423A (en) * | 2019-08-06 | 2019-12-27 | 平安科技（深圳）有限公司 | Multitask prediction method and device, electronic equipment and storage medium |
| CN111079006A (en) * | 2019-12-09 | 2020-04-28 | 腾讯科技（深圳）有限公司 | Message pushing method and device, electronic equipment and medium |
| CN112001565A (en) * | 2020-09-08 | 2020-11-27 | 清华大学合肥公共安全研究院 | Earthquake disaster loss prediction and evaluation method and system based on Softmax regression model |
-
2022
- 2022-04-29 CN CN202210467537.3A patent/CN114885016A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104832418A (en) * | 2015-05-07 | 2015-08-12 | 北京航空航天大学 | Hydraulic pump fault diagnosis method based on local mean conversion and Softmax |
| CN108063701A (en) * | 2016-11-08 | 2018-05-22 | 华为技术有限公司 | A kind of method and device for controlling smart machine |
| CN108733825A (en) * | 2018-05-23 | 2018-11-02 | 阿里巴巴集团控股有限公司 | A kind of objects trigger event prediction method and device |
| CN108919669A (en) * | 2018-09-11 | 2018-11-30 | 深圳和而泰数据资源与云技术有限公司 | A kind of smart home dynamic decision method, apparatus and service terminal |
| CN109818839A (en) * | 2019-02-03 | 2019-05-28 | 三星电子（中国）研发中心 | Personalized behavior prediction methods, devices and systems applied to smart home |
| CN110619423A (en) * | 2019-08-06 | 2019-12-27 | 平安科技（深圳）有限公司 | Multitask prediction method and device, electronic equipment and storage medium |
| CN111079006A (en) * | 2019-12-09 | 2020-04-28 | 腾讯科技（深圳）有限公司 | Message pushing method and device, electronic equipment and medium |
| CN112001565A (en) * | 2020-09-08 | 2020-11-27 | 清华大学合肥公共安全研究院 | Earthquake disaster loss prediction and evaluation method and system based on Softmax regression model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11050577B2 (en) | Automatically learning and controlling connected devices | |
| US11587320B2 (en) | Methods and systems for person detection in a video feed | |
| CN109445848B (en) | Equipment linkage method and device | |
| CN106842972A (en) | The forecast Control Algorithm and system of a kind of intelligent home device | |
| US10605470B1 (en) | Controlling connected devices using an optimization function | |
| US20200380968A1 (en) | Voice response interfacing with multiple smart devices of different types | |
| CN115826428A (en) | Control method and device of household equipment, storage medium and electronic device | |
| CN114755931A (en) | Control instruction prediction method and device, storage medium and electronic device | |
| CN113934926A (en) | Recommendation method and device for interactive scene and electronic equipment | |
| CN115327934A (en) | Intelligent household scene recommendation method and system, storage medium and electronic device | |
| CN114855416A (en) | Recommendation method and device of washing program, storage medium and electronic device | |
| CN114915514B (en) | Method and device for processing intention, storage medium and electronic device | |
| CN114885016A (en) | Service pushing method and device, storage medium and electronic device | |
| CN116165931A (en) | Control method and system of intelligent equipment, device, storage medium and electronic device | |
| CN115494737A (en) | Control method of intelligent household appliance, storage medium and electronic device | |
| CN114691752A (en) | Usage intention prediction method and apparatus, storage medium, and electronic apparatus | |
| CN114925158A (en) | Sentence text intention recognition method and device, storage medium and electronic device | |
| CN114691731A (en) | Usage preference determination method and apparatus, storage medium, and electronic apparatus | |
| CN115309063A (en) | Method and device for updating device scene, storage medium and electronic device | |
| Hansen et al. | A home energy management system with focus on energy optimization | |
| CN110598916A (en) | Method and system for constructing user behavior model | |
| CN114397826B (en) | Smart home control method, system and device | |
| CN118158012A (en) | Method and device for determining combined command, storage medium and electronic device | |
| CN117706954B (en) | Method and device for generating scene, storage medium and electronic device | |
| CN116007028A (en) | Gear adjusting method and device, storage medium and electronic device |
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 |