Generation method of target intention event, storage medium and electronic device

Abstract

The invention discloses a target intention event generation method, a storage medium and an electronic device, and relates to the technical field of smart home, and the target intention event generation method comprises the following steps: when it is determined that received first sensing data is triggering data used for triggering a target intention event, generating a target intention event; acquiring second sensing data from an event list corresponding to the first sensing data; wherein the event list comprises a target intention event and all perception data used for generating the target intention event; determining whether third sensing data allowed to be reported to the decision-making equipment contains the second sensing data or not; and generating a target intention event according to all the perception data under the condition of determining that the third perception data contains the second perception data and all the perception data accord with a preset time sequence, the preset time sequence being a time sequence set for all the perception data in the event list.

Description

Technical Field

[0001] The present application relates to the technical field of smart homes. Specifically, it relates to a method for generating target intent events, a storage medium, and an electronic device. Background Art

[0002] With the wide application of advanced technologies such as artificial intelligence and big data, the control methods of smart home devices have become increasingly intelligent, aiming to obtain the status data of elements such as users, devices, items, and environments within the home through real-time perception, predict user needs or action intentions, and then actively call smart home devices to provide intelligent and personalized services for users.

[0003] In existing smart home solutions, the perception data of devices, environments, users, and items are independently reported to a smart home gateway or a cloud platform. The smart home gateway or cloud platform lacks a necessary data fusion mechanism and can only make decisions based on fragmented perception data, unable to restore real user behaviors and / or actions, and thus unable to accurately identify user intentions and actively provide further services for users.

[0004] In view of the problems in the related art, such as the lack of a data fusion mechanism for perception data, resulting in the inability to accurately identify user behavior intentions, no effective solution has been proposed yet.

[0005] Therefore, it is necessary to improve the related technology to overcome the above-mentioned defects in the related technology. Summary of the Invention

[0006] Embodiments of the present application provide a method for generating target intent events, a storage medium, and an electronic device, so as to at least solve the problem in the related technology that the lack of a data fusion mechanism for perception data leads to the inability to accurately identify user behavior intentions.

[0007] According to one aspect of the embodiments of the present application, a method for generating target intent events is provided, including: when it is determined that the received first perception data is trigger data for triggering a target intent event, obtaining second perception data from the event list corresponding to the first perception data; wherein, the event list includes: the target intent event and all perception data used to generate the target intent event; wherein, the second perception data is the perception data other than the first perception data among all the perception data; determining whether the second perception data is included in the third perception data allowed to be reported to the decision device; when it is determined that the third perception data includes the second perception data and all the perception data conforms to a preset time sequence, generating the target intent event according to all the perception data, wherein the preset time sequence is the time sequence set for all the perception data in the event list.

[0008] In an exemplary embodiment, obtaining the second sensing data from the event list corresponding to the first sensing data includes: when there are multiple event lists, traversing the multiple event lists and determining the target event list among the multiple event lists as the event list corresponding to the first sensing data; wherein, there is fourth sensing data in the target event list whose data name is the same as that of the first sensing data and whose trigger identification bit is an identification field, and the identification field is used to indicate that the fourth sensing data is the trigger data of the target intention event corresponding to the fourth sensing data; obtaining the second sensing data from the traversed event list.

[0009] In an exemplary embodiment, determining whether the second sensing data is included in the third sensing data allowed to be reported to the decision device includes: determining the first time identifier and the space identifier in the first sensing data, where the first time identifier is used to indicate the acquisition time of the first sensing data, and the space identifier is used to indicate the space identifier of the space where the source end of the first sensing data is located; obtaining fifth sensing data with the space identifier from the third sensing data; screening the fifth sensing data according to the first time identifier to determine whether the second sensing data is included in the third sensing data.

[0010] In an exemplary embodiment, screening the fifth sensing data according to the first time identifier to determine whether the second sensing data is included in the third sensing data includes: determining the sequence relationship between the first time sequence and the second time sequence; wherein, the first time sequence is the time sequence corresponding to the first sensing data in the event list, and the second time sequence is the time sequence corresponding to the second sensing data in the event list; when the sequence relationship indicates that the second time sequence is before the first time sequence, screening the sixth sensing data according to the first time identifier to determine whether the second sensing data is included in the third sensing data; wherein, the sixth sensing data is the sensing data in the fifth sensing data whose second time identifier is less than the first time identifier, and the second time identifier is the time identifier corresponding to the fifth sensing data.

[0011] In an exemplary embodiment, screening the fifth perception data according to the first time identifier to determine whether the second perception data is included in the third perception data includes: determining whether there is seventh perception data in the fifth perception data; wherein, a first data name of the seventh perception data is the same as a second data name of the first perception data; in a case where the seventh perception data exists and there is a preset time relationship between a third time identifier of the seventh perception data and the first time identifier, determining the seventh perception data as the second perception data included in the third perception data; wherein, the preset time relationship includes one of the following: a time interval between the third time identifier and the first time identifier is less than a threshold duration, the third time identifier is the time identifier closest to the first time identifier.

[0012] In an exemplary embodiment, before determining whether the second perception data is included in the third perception data allowed to be reported to the decision device, the method further includes: determining a data type and a reporting method of the second perception data from the event list; in a case where the reporting method is active reporting, determining the perception data that has been reported to the decision device as the third perception data; in a case where the reporting method is periodic reporting and the data type is a user type, determining the perception data included in a source end of the second perception data as the third perception data; in a case where the reporting method is periodic reporting and the data type is a non-user type, determining the perception data that has been reported to the decision device as the third perception data, or determining the perception data included in a source end of the second perception data as the third perception data.

[0013] In an exemplary embodiment, before generating the target intent event according to all the perception data, the method further includes: in a case where it is determined that the third perception data includes the second perception data and the second perception data is user perception data, determining a quantity M of the second perception data included in the third perception data, and determining a quantity N of the second perception data included in all the perception data; in a case where the M is greater than or equal to the N, screening out N pieces of the second perception data from the M pieces of the second perception data according to user characteristics; wherein, the user characteristics include at least one of the following: user physical signs, user habits.

[0014] In an exemplary embodiment, generating the target intent event according to all the sensed data includes: determining an event template corresponding to the target intent event, and determining a first field to be replaced in the event template, where the first field is used to indicate a first data type of the sensed data to which the replacement field of the first field belongs in all the sensed data; for any sensed data among all the sensed data, extracting a second field from an extraction position of the any sensed data; where the extraction position is determined according to a second data type of the any sensed data; in a case where the first data type is the same as the second data type, using the second field as the replacement field to replace the first field, and determining the event template after replacement as the target intent event.

[0015] According to another aspect of the embodiments of the present application, there is also provided a generating device for a target intent event, including: an obtaining module, configured to obtain second sensed data from an event list corresponding to the first sensed data in a case where it is determined that the received first sensed data is trigger data for triggering a target intent event; where the event list includes: the target intent event and all the sensed data for generating the target intent event; where the second sensed data is the sensed data other than the first sensed data among all the sensed data; a determining module, configured to determine whether the second sensed data is included in third sensed data allowed to be reported to a decision device; a generating module, configured to generate the target intent event according to all the sensed data in a case where it is determined that the third sensed data includes the second sensed data and all the sensed data conforms to a preset time sequence, where the preset time sequence is the time sequence set for all the sensed data in the event list.

[0016] According to still another aspect of the embodiments of the present application, there is also provided a computer-readable storage medium, in which a computer program is stored, where the computer program is configured to execute the above-mentioned generating method for a target intent event when running.

[0017] According to still another aspect of the embodiments of the present application, there is also provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the above-mentioned processor executes the above-mentioned generating method for a target intent event through the computer program.

[0018] Through this application, when it is determined that the received first perception data is trigger data for triggering a target intent event, second perception data is obtained from the event list corresponding to the first perception data; wherein, the event list includes: the target intent event and all perception data used to generate the target intent event; wherein, the second perception data is the perception data other than the first perception data among all the perception data; determine whether the second perception data is included in the third perception data allowed to be reported to the decision device; when it is determined that the third perception data includes the second perception data and all the perception data conforms to a preset time sequence, the target intent event is generated according to all the perception data, wherein the preset time sequence is the time sequence set for all the perception data in the event list. By adopting the above technical solution, the problem in the related art that the lack of a data fusion mechanism for perception data leads to the inability to accurately identify the user's behavior intention is solved; the technical effect of accurately identifying the user's behavior intention is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application and used together with the specification to explain the principles of the present application.

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 It is a schematic diagram of the hardware environment of an optional method for generating a target intent event according to an embodiment of the present application;

[0022] Figure 2 It is a flowchart of an optional method for generating a target intent event according to an embodiment of the present application;

[0023] Figure 3 It is another flowchart of an optional method for generating a target intent event according to an embodiment of the present application;

[0024] Figure 4 It is a structural block diagram of an optional device for generating a target intent event according to an embodiment of the present application;

[0025] Figure 5 It is another structural block diagram of an optional device for generating a target intent event according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] To enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0027] It should be noted that the terms "first", "second", etc. in the description and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0028] According to one aspect of the embodiments of this application, a method for generating a target intention event is provided. The method for generating the target intention event is widely applied to whole-house intelligent digital control application scenarios such as Smart Home, smart home, smart home appliance ecosystem, and IntelligenceHouse ecosystem. Optionally, in this embodiment, the above method for generating a target intention event can be applied to, for example, Figure 1 the hardware environment composed of multiple terminal devices 102 and a server 104 as shown. As Figure 1 shown, the server 104 is connected to multiple terminal devices 102 through a network, and can be used to provide services (such as application services, etc.) for the terminal or the client installed on the terminal. A database can be set on the server or independently of the server to provide data storage services for the server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data operation services for the server 104.

[0029] The above network may include, but is not limited to, at least one of the following: a wired network, a wireless network. The above wired network may include, but is not limited to, at least one of the following: a wide area network, a metropolitan area network, a local area network. The above wireless network may include, but is not limited to, at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal device 102 is not limited to a PC, mobile phone, tablet computer, smart air conditioner, smart range hood, smart refrigerator, smart oven, smart stove, smart washing machine, smart water heater, smart washing equipment, smart dishwasher, smart projection device, smart TV, smart clothes hanger, smart curtain, smart audio and video, smart socket, smart speaker, smart sound box, smart fresh air device, smart kitchen and bathroom equipment, smart bathroom equipment, smart floor sweeping robot, smart window cleaning robot, smart mopping robot, smart air purification device, smart steam box, smart microwave oven, smart kitchen water heater, smart purifier, smart water dispenser, smart door lock, etc.

[0030] In this embodiment, a method for generating a target intention event is provided, including but not limited to being applied to a computer terminal. Figure 2 It is a flowchart of an optional method for generating a target intention event according to an embodiment of the present application. The process includes the following steps:

[0031] Step S202: When it is determined that the first perception data received is trigger data for triggering a target intention event, obtain second perception data from the event list corresponding to the first perception data; wherein, the event list includes: the target intention event and all perception data for generating the target intention event.

[0032] Wherein, the second perception data is the perception data other than the first perception data among all the perception data.

[0033] Step S204: Determine whether the second perception data is included in the third perception data allowed to be reported to the decision device.

[0034] Step S206: When it is determined that the third perception data includes the second perception data and all the perception data conforms to a preset time sequence, generate the target intention event according to all the perception data, where the preset time sequence is the time sequence set for all the perception data in the event list.

[0035] Optionally, the method for generating the target time provided in the embodiment of the present application may also run on a decision device, and the decision device includes a gateway device, a cloud platform, etc.

[0036] Through the above steps, when it is determined that the first sensed data received is trigger data for triggering a target intent event, obtain second sensed data from the event list corresponding to the first sensed data; wherein, the event list includes: the target intent event and all sensed data used to generate the target intent event; wherein, the second sensed data is the sensed data other than the first sensed data among all the sensed data; determine whether the second sensed data is included in the third sensed data allowed to be reported to the decision device; when it is determined that the third sensed data includes the second sensed data and all the sensed data conforms to a preset time sequence, generate the target intent event according to all the sensed data, wherein the preset time sequence is the time sequence set for all the sensed data in the event list. By adopting the above technical solution, the problem in the related art that the lack of a data fusion mechanism for sensed data leads to the inability to accurately identify the user's behavior intention is solved; the technical effect of accurately identifying the user's behavior intention is achieved.

[0037] Regarding the above step S202, in an exemplary embodiment, it includes: when there are multiple event lists, traverse the multiple event lists, and determine the target event list among the multiple event lists as the event list corresponding to the first sensed data; wherein, there is fourth sensed data in the target event list whose data name is the same as the first sensed data and the trigger identification bit is an identification field, and the identification field is used to indicate that the fourth sensed data is the trigger data of the target intent event corresponding to the fourth sensed data; obtain the second sensed data from the traversed event list.

[0038] It can be understood that multiple event lists can be deployed on the decision device in the embodiments of the present application, and each event list among the multiple event lists is responsible for a different home area. Exemplarily, if there is a living room and multiple bedrooms in a home, the living room can correspond to event list A, which is identified by the space number "A" corresponding to the living room; the multiple bedrooms can correspond to event list B, which is identified by the space number "B" corresponding to the bedrooms; further, each of the multiple bedrooms can also correspond to an event list respectively, and the identification can be "B-1, B-2", etc.

[0039] Furthermore, in the case of receiving the first sensed data as trigger data, multiple event lists can be traversed by the name of the first sensed data. For example, if the data name of the first sensed data is "ingredient reduction", and there is a fourth sensed data with the data name "ingredient reduction" in the target event list, and the identification field of the fourth sensed data is "Y", then the target event list is the said event list. Herein, "Y" represents "Yes", which is used to indicate that the fourth sensed data with the data name "ingredient reduction" is the trigger data in the target event list; furthermore, "N" is used to identify "No", which is used to indicate that the fourth sensed data with the data name "ingredient reduction" is not the trigger data in the target event list. Optionally, the identification field can also use "ture" to indicate that the fourth sensed data is the trigger data and "false" to indicate that the fourth sensed data is not the trigger data.

[0040] In an exemplary embodiment, determining whether the second sensed data is included in the third sensed data allowed to be reported to the decision device includes: determining the first time identifier and the space identifier in the first sensed data, where the first time identifier is used to indicate the acquisition time of the first sensed data, and the space identifier is used to indicate the space identifier of the space where the source end of the first sensed data is located; obtaining the fifth sensed data with the space identifier from the third sensed data; and screening the fifth sensed data according to the first time identifier to determine whether the second sensed data is included in the third sensed data.

[0041] It should be noted that the acquisition time includes the collection time or the generation time. The collection time refers to the collection time of the first sensed data by the sensing device, and the generation time refers to the generation time of the first sensed data by the sensing device; the source end includes the generation end of the first sensed data or the reporting end of the first sensed data.

[0042] Exemplarily, when the received first sensed data is: "ingredient reduction", and the data collection time is 22:00, and the space identifier of the source end indicates that the source end is in the kitchen: all the sensed data with the kitchen identifier are obtained from the third sensed data as the fifth sensed data, and the second sensed data is screened from the fifth sensed data by the collection time 22:00.

[0043] Further, screening the fifth perception data according to the first time identifier to determine whether the second perception data is included in the third perception data includes: determining the sequence relationship between a first time sequence and a second time sequence; wherein, the first time sequence is the time sequence corresponding to the first perception data in the event list, and the second time sequence is the time sequence corresponding to the second perception data in the event list; in the case where the sequence relationship indicates that the second time sequence is before the first time sequence, screening the sixth perception data according to the first time identifier to determine whether the second perception data is included in the third perception data; wherein, the sixth perception data is the perception data in the fifth perception data with a second time identifier less than the first time identifier, and the second time identifier is the time identifier corresponding to the fifth perception data.

[0044] If the second perception data is "the refrigerator door is opened", and the second time sequence in the event list is before the first time sequence corresponding to "the ingredients are reduced", then all the fifth perception data in the fifth perception data with a second time identifier before 22:00 can be determined as the sixth perception data for screening the second perception data.

[0045] Conversely, if the second time sequence of the second perception data is after the first time sequence, then the sixth perception data is determined as the perception data in the fifth perception data with a second time identifier greater than or equal to the first time identifier.

[0046] In an exemplary embodiment, screening the fifth perception data according to the first time identifier to determine whether the second perception data is included in the third perception data includes: determining whether there is a seventh perception data in the fifth perception data; wherein, the first data name of the seventh perception data is the same as the second data name of the first perception data; in the case where the seventh perception data exists and there is a preset time relationship between the third time identifier of the seventh perception data and the first time identifier, the seventh perception data is determined as the second perception data included in the third perception data; wherein, the preset time relationship includes one of the following: the time interval between the third time identifier and the first time identifier is less than a threshold duration, the third time identifier is the time identifier closest to the first time identifier.

[0047] It can be understood that if a seventh perception data with the same name as the first perception data and satisfying the preset time relationship is determined in the fifth perception data, it can be determined that the second perception data is included in the third perception data. Optionally, the preset time relationship can also specify that the third time identifier should have a fixed time interval from the first time identifier.

[0048] In an exemplary embodiment, before determining whether the second sensing data is included in the third sensing data allowed to be reported to the decision-making device, the method further includes: determining the data type and reporting method of the second sensing data from the event list; when the reporting method is active reporting, determining the sensing data that has been reported to the decision-making device as the third sensing data; when the reporting method is periodic reporting and the data type is user type, determining the sensing data included in the source end of the second sensing data as the third sensing data; when the reporting method is periodic reporting and the data type is non-user type, determining the sensing data that has been reported to the decision-making device as the third sensing data, or determining the sensing data included in the source end of the second sensing data as the third sensing data.

[0049] It should be noted that in the smart home scenario, typical sensing data includes: 1) Device sensing data: including data such as the operating mode, software and hardware operating status, operating time, and energy consumption of smart home devices; 2) Environmental sensing data: including the current status data of the air environment, water environment, light environment, sound environment, and security environment that can be obtained through sensing; 3) User sensing data (equivalent to user type): including data such as user identity characteristics, vital signs, posture / actions, and location that can be obtained through sensing; 4) Item sensing data: including the status data of non-device items such as food ingredients and clothing that can be obtained through sensing.

[0050] The specific acquisition methods of sensing data include: 1) During the operation of smart home devices, the devices themselves collect device sensing data; 2) Data such as home environment and user vital signs are collected through sensors, sensing units of smart home devices, etc.; 3) User identity characteristics and other data are obtained through voice sensing; 4) User posture / actions, item status, etc. are obtained through image sensing; 5) User vital signs, posture / actions, location, etc. are obtained through wireless sensing (Wi-Fi sensing, millimeter-wave radar, etc.).

[0051] The reporting methods of sensing devices include the following two types: 1) Periodic reporting: For the normal status data of devices, environments, users, and items, periodic and timed reporting is usually adopted, for example, reporting once every few minutes. The disadvantage of this reporting method is that the reported data may not accurately reflect the status of the sensed object at the current moment. 2) Real-time reporting (which can be understood as a type of active reporting): For some data that needs to notify users in a timely manner, the data is usually reported immediately after it is obtained, such as device failures, security alarms, and abnormal user vital signs.

[0052] That is to say, the determination method of the third perception data is different in combination with the data type and reporting method of the second perception data. The reporting methods include: active reporting and periodic reporting. When the second perception data is actively reported, the perception data that has been reported to the decision-making device, that is, the local data of the decision-making device, can be determined as the third perception data; when the second perception data is periodically reported and is of the user type, the perception data included in the source end of the second perception data is determined as the third perception data. For the case where the second perception data is periodic and non-user type, the above two cases are selected as the range of the third perception data according to actual requirements. For example, if the actual requirement is high efficiency, the perception data of the source end can be preferably determined as the third perception data.

[0053] When the perception data included in the source end of the second perception data is determined as the third perception data, if the second perception data cannot be searched for multiple times (K times, K is a positive integer), the range of the third perception data in this case can be updated to include: the local data of the decision-making device (range 1), the perception data included in the source end of the second perception data (range 2). Further, search for range 1 and range 2 separately. If the second perception data is searched for in range 2 continuously for K times, the range of the third perception data is updated back to include: the perception data included in the source end of the second perception data.

[0054] In an exemplary embodiment, before determining the target intent event generated according to all the perception data, the method further includes: when it is determined that the third perception data includes the second perception data and the second perception data is user perception data, determining the number M of the second perception data included in the third perception data, and determining the number N of the second perception data included in all the perception data; when M is greater than or equal to N, screening out N second perception data from the M second perception data according to user characteristics; where the user characteristics include at least one of the following: user physical signs, user habits.

[0055] If 3 second perception data that meet the conditions are screened out, and there is only one second perception data recorded in the event list, specific analysis is carried out according to user characteristics. For example, "ingredients reduced" corresponds to the reduction of "beer", and the 3 second perception data are respectively "the child is in the kitchen", "dad is in the kitchen", and "mom is in the kitchen". Then, first, according to the user body type data collected by the wireless perception device, the child can be excluded; second, according to the user's living habits, mom can be excluded (does not drink).

[0056] In an exemplary embodiment, determining the generation of the target intent event based on all the perception data includes: determining an event template corresponding to the target intent event and determining a first field to be replaced in the event template, where the first field is used to indicate a first data type of the perception data to which the replacement field of the first field belongs in all the perception data; for any perception data in all the perception data, extracting a second field from an extraction position of the any perception data; where the extraction position is determined according to a second data type of the any perception data; when the first data type is the same as the second data type, using the second field as the replacement field to replace the first field, and determining the event template after replacement as the target intent event.

[0057] That is, when the trigger data is "ingredient reduction", the trigger data specifically includes that the included ingredient type is "beer", and the perception data finally screened by the decision device is: "refrigerator door opened" and "dad is in the kitchen", and the event template is "user takes out an item from the device":

[0058] "Ingredient reduction" belongs to item perception data, and the corresponding second field extracted is "ingredient", and then corresponding to "beer"; "refrigerator door opened" belongs to device perception data, and the corresponding second field extracted is "refrigerator", and "dad is in the kitchen" belongs to user perception data, and the corresponding second field extracted is "dad". Thus, the finally generated target intent event is "dad takes out 1 bottle of beer from the refrigerator".

[0059] Obviously, the above-described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. To better understand the above method for generating the target intent event, the following describes the above process in conjunction with embodiments, but is not used to limit the technical solutions of the embodiments of the present application. Specifically:

[0060] An optional embodiment of the present application designs a mechanism for fusing and generating user behavior events based on state perception data such as users, devices, items, and environments, laying a foundation for actively providing smart home services to users. After receiving the reported perception data (equivalent to the first perception data), the smart home decision device or cloud platform can actively obtain relevant perception data (equivalent to the second perception data) by means of local acquisition or querying the reporting end according to key information such as time and space, and perform screening according to user characteristic data (physical signs, habits, etc.) as required; on this basis, according to the screened data, fuse and generate user behavior events (equivalent to target intent events).

[0061] It should be noted that the "user behavior event" proposed in the optional embodiment of this application is used to describe a specific behavior / action of the user. For example, "the user takes out ingredients from the refrigerator". However, as mentioned above, the perception data related to the user behavior event may be obtained and reported in different ways. For example, the smart refrigerator reports that "the refrigerator door is opened", and the wireless perception device perceives and obtains that "user A is in the kitchen". Therefore, this application proposes a method for generating user behavior events based on the fusion of perception data.

[0062] This method needs to pre-define and maintain a user behavior event list (equivalent to an event list) to record the perception data related to each user behavior event, specifically including:

[0063] 1) The name of the user behavior event;

[0064] 2) The list of perception data: The perception data related to the user behavior event, and each perception data is described by the following fields:

[0065] Name: The name of the perception data, such as "the refrigerator door is opened", "the ingredients are reduced";

[0066] Type: Includes 4 categories: device, environment, user, and item;

[0067] Reporting method: Includes periodic reporting and active reporting;

[0068] 3) Trigger flag: Identifies whether the perception data will trigger the fusion generation of the associated user behavior event; usually, the perception data with the reporting method of "active reporting" is selected as the trigger.

[0069] 4) Timing: When there are multiple perception data in the perception data list of the same user behavior event, it is used to mark the order of appearance of the data. For example, the occurrence time of "the refrigerator door is opened" should be earlier than that of "the ingredients are reduced".

[0070] Table 1 below gives an example of the user behavior event list.

[0071] Table 1 Example of the user behavior event list

[0072]

[0073]

[0074] In the technical solution proposed in the optional embodiment of this application, when a certain perception data (denoted as data_0, equivalent to the first perception data) triggers the fusion generation process of the associated user behavior event (denoted as UE_0, equivalent to the target intention event), the cloud platform or the smart home gateway needs to obtain the perception data related to UE_0. According to the different types and reporting methods of the perception data, two acquisition methods can be adopted:

[0075] Obtaining method 1: For the sensed data reported in the "active reporting" manner, the cloud platform or the smart home gateway can directly obtain it from the received sensed data.

[0076] Obtaining method 2: For the sensed data reported in the "periodic reporting" manner, if the type is "user", to ensure data accuracy, the cloud platform or the smart home gateway actively initiates a query to the sensed data reporting end; for the sensed data of non-"user" type, local acquisition or query to the reporting end can be selected according to actual requirements.

[0077] During the process of the cloud platform or the smart home gateway obtaining / querying the sensed data related to UE_0, it is also necessary to screen the sensed data according to the space and time (including time sequence) where the data data_0 occurs.

[0078] Space: The data that occurs in the same home space as data_0 should be selected, and usually the space where the data_0 acquisition end (or reporting end) is located is used for substitution.

[0079] Time: Taking the acquisition (or reporting) time t_0 of data_0 as a reference point, screen the data whose relative time sequence (before or after) with data_0 meets the requirements. According to actual requirements, the screening principle can be to select the data closest to t_0, or all the data within the threshold duration ΔT.

[0080] Furthermore, the user behavior event fusion generation scheme proposed in the optional embodiment of the present application has the following specific process Figure 3 as shown, including the following steps:

[0081] S31: Based on the smart home scenario, pre-define user behavior events; and establish a user behavior event list in the cloud platform or the smart home gateway.

[0082] S32: When the cloud platform or the smart home gateway receives the reported sensed data data_i, query the user behavior event list to determine whether the data can trigger the fusion generation process of the user behavior event. If it can trigger, for each triggerable user behavior event UE_i, execute steps S33 to S36 respectively; otherwise, no further operation is required.

[0083] S33: The cloud platform or the smart home gateway traverses the sensed data list of event UE_i, and obtains the sensed data related to UE_i by local acquisition or querying the sensed data reporting end in the manner described above.

[0084] S34: If all the sensed data required for fusing and generating UE_i are selected in Step 3, continue to execute Step S35 below; otherwise, end the fusing and generating process of the current event UE_i and directly jump to Step S37.

[0085] S35: If there are multiple users who meet the requirements in the spatial and temporal (including time sequence) dimensions among the data selected in Step S33, further screening should be carried out in combination with the characteristic data of the users (such as physical signs, user habits, etc.). If the user who performs this behavior can be determined, continue to execute Step S36 below; otherwise, end the fusing and generating process of UE_i and directly jump to Step S37; if the only user who meets the conditions is selected in Step S33, directly execute Step S36 below.

[0086] S36: The cloud platform or the smart home gateway completes the fusing and generation of the current user behavior event UE_i according to the sensed data selected in S33 - S35.

[0087] S37: If there is a user behavior event UE_j that can be triggered by data_i and has not been processed yet, repeat Step S33 to Step S36 for UE_j; otherwise, the overall process ends.

[0088] Specific embodiments are provided below to introduce in detail the fusing and generating process of the user behavior event proposed in the optional embodiments of the present application, as specifically shown in Step 1 to Step 6. The list of user behavior events used in the specific embodiments is as shown in Table 1 above.

[0089] Step 1: Based on the smart home scenario, pre - define user behavior events; and establish a list of user behavior events on the cloud platform or the smart home gateway (see Table 1 for specific content).

[0090] Step 2: The smart home gateway receives the sensed data "ingredients reduced" collected and reported by the smart refrigerator at 22:00. The type of ingredients included in the data is "beer", the quantity is "1", and the data collection time is 22:00.

[0091] Step 3: The smart home gateway queries the list of user behavior events to determine that this data is sufficient to trigger the fusing and generating process of the user behavior event "the user takes out ingredients from the refrigerator".

[0092] Step 4: The smart home gateway queries and obtains that the space where the smart refrigerator is located is the kitchen. Then, according to Table 1, relevant sensed data is obtained through local acquisition or active query to the sensed data reporting end, including:

[0093] Locally acquire a set of "refrigerator door opened" data with a reporting time before 22:00 and closest to 22:00;

[0094] Query the user perception device deployed in the kitchen for users who entered the kitchen within 0.5 hours (system preset time threshold) before 22:00. Suppose 3 users are queried, namely Dad, Mom, and Xiaoming.

[0095] Step 5: For the 3 eligible users screened out in Step 4, further screening is carried out in combination with the user's characteristic data (such as physical signs, user habits, etc.) - First, according to the user body type data collected by the wireless perception device, Xiaoming can be excluded; Second, according to the user's living habits, Mom (who doesn't drink) can be excluded.

[0096] Step 6: The smart home gateway generates the user behavior event "Dad took out 1 bottle of beer from the refrigerator" by fusing the finally screened perception data "refrigerator door opened" and "Dad is in the kitchen", and the process ends.

[0097] In summary, the optional embodiment of the present application proposes a method for generating user behavior events based on perception data fusion. First, a "user behavior event list" is introduced to record the user behaviors and related perception data that need to be concerned in the smart home scenario, as the basis for fusing and generating user behavior events; Second, after receiving the reported perception data, the smart home gateway or cloud platform can actively obtain relevant perception data from dimensions such as time and space based on the "user behavior event list"; In particular, when multiple eligible users are obtained, screening can also be carried out according to the user characteristic data (physical signs, habits, etc.).

[0098] Furthermore, the method for generating user behavior events proposed in the optional embodiment of the present application can fuse the perception data of devices, environment, users, and items, restore the real user behaviors / actions, thus laying a decision-making basis for accurately identifying the user's intention and further actively providing the required services to the user, and improving the user experience.

[0099] Through the description of the above implementation manners, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation manner. Based on such an understanding, the technical solution of the present application, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc), and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of the various embodiments of the present application.

[0100] In this embodiment, a generating device for target intention events is further provided. This device is used to implement the above-mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated here. As used hereinafter, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0101] Figure 4 FIG. is a structural block diagram of an optional generating device for target intention events according to an embodiment of the present application. The device includes:

[0102] An obtaining module 42, configured to obtain second perception data from an event list corresponding to the first perception data when it is determined that the received first perception data is trigger data for triggering a target intention event; wherein, the event list includes: the target intention event and all perception data for generating the target intention event;

[0103] wherein, the second perception data is the perception data other than the first perception data among all the perception data;

[0104] A determining module 44, configured to determine whether the second perception data is included in the third perception data allowed to be reported to the decision-making device;

[0105] A generating module 46, configured to generate the target intention event according to all the perception data when it is determined that the third perception data includes the second perception data and all the perception data conforms to a preset time sequence, wherein the preset time sequence is the time sequence set for all the perception data in the event list.

[0106] With the above device, when it is determined that the received first perception data is trigger data for triggering a target intention event, second perception data is obtained from an event list corresponding to the first perception data; wherein, the event list includes: the target intention event and all perception data for generating the target intention event; wherein, the second perception data is the perception data other than the first perception data among all the perception data; determine whether the second perception data is included in the third perception data allowed to be reported to the decision-making device; when it is determined that the third perception data includes the second perception data and all the perception data conforms to a preset time sequence, generate the target intention event according to all the perception data, wherein the preset time sequence is the time sequence set for all the perception data in the event list. By adopting the above technical solution, the problem in the related art that the lack of a data fusion mechanism for perception data leads to the inability to accurately identify the user's behavior intention is solved; the technical effect of accurately identifying the user's behavior intention is achieved.

[0107] In an exemplary embodiment, the obtaining module 42 is further configured to, when there are multiple event lists, traverse the multiple event lists, and determine the target event list in the multiple event lists as the event list corresponding to the first sensed data; wherein, in the target event list, there is fourth sensed data whose data name is the same as that of the first sensed data and whose trigger identification bit is an identification field, and the identification field is used to indicate that the fourth sensed data is the trigger data of the target intention event corresponding to the fourth sensed data; obtain the second sensed data from the traversed event lists.

[0108] In an exemplary embodiment, the determining module 44 is further configured to determine a first time identifier and a space identifier in the first sensed data, wherein the first time identifier is used to indicate the acquisition time of the first sensed data, and the space identifier is used to indicate the space identifier of the space where the source end of the first sensed data is located; obtain fifth sensed data with the space identifier from the third sensed data; screen the fifth sensed data according to the first time identifier to determine whether the third sensed data includes the second sensed data.

[0109] In an exemplary embodiment, the determining module 44 is further configured to determine the sequence relationship between a first time sequence and a second time sequence; wherein, the first time sequence is the time sequence corresponding to the first sensed data in the event list, and the second time sequence is the time sequence corresponding to the second sensed data in the event list; when the sequence relationship indicates that the second time sequence is before the first time sequence, screen the sixth sensed data according to the first time identifier to determine whether the third sensed data includes the second sensed data; wherein, the sixth sensed data is the sensed data in the fifth sensed data whose second time identifier is less than the first time identifier, and the second time identifier is the time identifier corresponding to the fifth sensed data.

[0110] In an exemplary embodiment, the determining module 44 is further configured to determine whether there is seventh sensed data in the fifth sensed data; wherein, a first data name of the seventh sensed data is the same as a second data name of the first sensed data; when the seventh sensed data exists and there is a preset time relationship between a third time identifier of the seventh sensed data and the first time identifier, determine the seventh sensed data as the second sensed data included in the third sensed data; wherein, the preset time relationship includes one of the following: the time interval between the third time identifier and the first time identifier is less than a threshold duration, and the third time identifier is the time identifier closest to the first time identifier.

[0111] In an exemplary embodiment, the determining module 44 is further configured to determine the data type and reporting method of the second sensed data from the event list; when the reporting method is active reporting, determine the sensed data that has been reported to the decision-making device as the third sensed data; when the reporting method is periodic reporting and the data type is user type, determine the sensed data included in the source end of the second sensed data as the third sensed data; when the reporting method is periodic reporting and the data type is non-user type, determine the sensed data that has been reported to the decision-making device as the third sensed data, or determine the sensed data included in the source end of the second sensed data as the third sensed data.

[0112] In an exemplary embodiment, as Figure 5 shown, the device further includes a screening module 48, configured to determine the quantity M of the second sensed data included in the third sensed data and the quantity N of the second sensed data included in all the sensed data when it is determined that the third sensed data includes the second sensed data and the second sensed data is user sensed data; when M is greater than or equal to N, screen out N pieces of the second sensed data from the M pieces of the second sensed data according to user characteristics; where the user characteristics include at least one of the following: user physical signs, user habits.

[0113] In an exemplary embodiment, the generating module 46 is further configured to determine an event template corresponding to the target intent event and determine a first field to be replaced in the event template, where the first field is used to indicate the first data type of the sensed data to which the replacement field of the first field belongs in all the sensed data; for any sensed data in all the sensed data, extract a second field from the extraction position of the any sensed data; where the extraction position is determined according to the second data type of the any sensed data; when the first data type is the same as the second data type, use the second field as the replacement field to replace the first field, and determine the event template after replacement as the target intent event.

[0114] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, where the computer program is configured to execute the steps in any one of the above method embodiments when running.

[0115] Optionally, in this embodiment, the above storage medium may be configured to store a computer program for executing the following steps:

[0116] S1. When it is determined that the received first perception data is trigger data for triggering a target intent event, obtain second perception data from the event list corresponding to the first perception data; wherein, the event list includes: the target intent event and all perception data used to generate the target intent event;

[0117] S2. Determine whether the second perception data is included in the third perception data allowed to be reported to the decision-making device;

[0118] S3. When it is determined that the third perception data includes the second perception data and all the perception data conforms to a preset time sequence, generate the target intent event according to all the perception data, where the preset time sequence is the time sequence set for all the perception data in the event list.

[0119] In an exemplary embodiment, the above computer-readable storage medium may include, but is not limited to: USB flash drives, read-only memories (ROM for short), random access memories (RAM for short), mobile hard disks, magnetic disks, or optical discs and other various media that can store computer programs.

[0120] Specific examples in this embodiment may refer to the examples described in the above embodiments and exemplary embodiments, and will not be repeated here.

[0121] An embodiment of the present application further provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0122] Optionally, in this embodiment, the above processor may be configured to execute the following steps through a computer program:

[0123] S1. When it is determined that the received first perception data is trigger data for triggering a target intent event, obtain second perception data from the event list corresponding to the first perception data; wherein, the event list includes: the target intent event and all perception data used to generate the target intent event;

[0124] S2. Determine whether the second perception data is included in the third perception data allowed to be reported to the decision-making device;

[0125] S3. When it is determined that the third perception data includes the second perception data and all the perception data conforms to a preset time sequence, generate the target intent event according to all the perception data, where the preset time sequence is the time sequence set for all the perception data in the event list.

[0126] In an exemplary embodiment, the above electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0127] Specific examples in this embodiment may refer to the examples described in the above embodiments and exemplary embodiments, and will not be elaborated herein.

[0128] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present application can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. They can be implemented by program codes executable by the computing device. Thus, they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described can be executed in a different order from here, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module to implement. In this way, the present application is not limited to any specific combination of hardware and software.

[0129] The above is only the preferred embodiment of the present application. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present application, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. A method for generating a target intention event, characterized in that Including: In the case where it is determined that the received first perception data is trigger data for triggering a target intent event, obtaining second perception data from the event list corresponding to the first perception data; wherein, the event list includes: the target intent event and all perception data for generating the target intent event; Determining whether the second perception data is included in the third perception data allowed to be reported to the decision device; In the case where it is determined that the third perception data includes the second perception data and all the perception data conforms to a preset time sequence, generating the target intent event according to all the perception data, wherein the preset time sequence is the time sequence set for all the perception data in the event list.

2. The method for generating the target intention event according to claim 1, wherein Obtaining second perception data from the event list corresponding to the first perception data includes: In the case where there are multiple event lists, traversing the multiple event lists and determining the target event list among the multiple event lists as the event list corresponding to the first perception data; wherein, in the target event list, there is fourth perception data with a data name the same as that of the first perception data and a trigger identification bit as an identification field, and the identification field is used to indicate that the fourth perception data is trigger data for the target intent event corresponding to the fourth perception data; Obtaining the second perception data from the traversed event list.

3. The method for generating the target intention event according to claim 1, wherein, Determining whether the second perception data is included in the third perception data allowed to be reported to the decision device includes: Determining a first time identifier and a space identifier in the first perception data, wherein the first time identifier is used to indicate the acquisition time of the first perception data, and the space identifier is used to indicate the space identifier of the space where the source end of the first perception data is located; Obtaining fifth perception data with the space identifier from the third perception data; Screening the fifth perception data according to the first time identifier to determine whether the second perception data is included in the third perception data.

4. The method for generating a target intention event according to claim 3, characterized in that, Screening the fifth perception data according to the first time identifier to determine whether the second perception data is included in the third perception data includes: Determining the sequence relationship between a first time sequence and a second time sequence; wherein, the first time sequence is the time sequence corresponding to the first perception data in the event list, and the second time sequence is the time sequence corresponding to the second perception data in the event list; In the case where the sequence relationship indicates that the second time sequence is before the first time sequence, screening sixth perception data according to the first time identifier to determine whether the second perception data is included in the third perception data; wherein, the sixth perception data is perception data in the fifth perception data with a second time identifier less than the first time identifier, and the second time identifier is the time identifier corresponding to the fifth perception data.

5. The method for generating the target intention event according to claim 3, characterized in that, Screening the fifth perception data according to the first time identifier to determine whether the second perception data is included in the third perception data includes: Determine whether there is seventh perception data in the fifth perception data; wherein, the first data name of the seventh perception data is the same as the second data name of the first perception data; When the seventh perception data exists and there is a preset time relationship between the third time identifier of the seventh perception data and the first time identifier, determine the seventh perception data as the second perception data included in the third perception data; wherein, the preset time relationship includes one of the following: the time interval between the third time identifier and the first time identifier is less than a threshold duration, the third time identifier is the time identifier closest to the first time identifier.

6. The method for generating the target intention event according to claim 1, wherein Before determining whether the second perception data is included in the third perception data allowed to be reported to the decision device, the method further includes: Determine the data type and reporting method of the second perception data from the event list; When the reporting method is active reporting, determine the perception data that has been reported to the decision device as the third perception data; When the reporting method is periodic reporting and the data type is user type, determine the perception data included in the source end of the second perception data as the third perception data; When the reporting method is periodic reporting and the data type is non-user type, determine the perception data that has been reported to the decision device as the third perception data, or determine the perception data included in the source end of the second perception data as the third perception data.

7. The method for generating the target intention event according to claim 1, wherein Before generating the target intent event according to all the perception data, the method further includes: When it is determined that the third perception data includes the second perception data and the second perception data is user perception data, determine the number M of the second perception data included in the third perception data, and determine the number N of the second perception data included in all the perception data; When M is greater than or equal to N, screen out N of the second perception data from the M second perception data according to user characteristics; wherein, the user characteristics include at least one of the following: user physical signs, user habits.

8. The method for generating the target intention event according to claim 1, wherein Generating the target intent event according to all the perception data includes: Determine the event template corresponding to the target intent event, and determine the first field to be replaced in the event template, wherein the first field is used to indicate the first data type of the perception data to which the replacement field of the first field belongs in all the perception data; For any perception data in all the perception data, extract a second field from the extraction position of the any perception data; wherein, the extraction position is determined according to the second data type of the any perception data; When the first data type and the second data type are the same, use the second field as the replacement field to replace the first field, and determine the replaced event template as the target intent event.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when running, executes the method according to any one of claims 1 to 8.

10. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 8 through the computer program.

Images