CN116701775B

CN116701775B - Service recommendation method, electronic device and computer program product

Info

Publication number: CN116701775B
Application number: CN202310981162.7A
Authority: CN
Inventors: 厉孙德
Original assignee: Beijing Jidu Technology Co Ltd
Current assignee: Beijing Jidu Technology Co Ltd
Priority date: 2023-08-04
Filing date: 2023-08-04
Publication date: 2023-10-31
Anticipated expiration: 2043-08-04
Also published as: CN116701775A

Abstract

The disclosure relates to the technical field of recommendation, and provides a service recommendation method, electronic equipment and a computer program product, in order to solve the technical problem that batch recommendation of a plurality of services cannot be performed on a vehicle, wherein the service recommendation method executed by a server comprises the following steps: receiving state data of the electronic equipment, which is sent by the electronic equipment; determining a plurality of recommended services which accord with set recommended conditions according to the state data and a pre-trained recommended model; constructing a behavior tree according to the recommended service, wherein the behavior tree comprises first action nodes which are in one-to-one correspondence with the recommended service; converting the action tree into an action tree file, wherein the action tree file is a file representing the structure of the action tree; and sending the behavior tree file to the electronic equipment to conduct service recommendation. Thus, by combining a plurality of recommended services with the behavior tree, flexible configuration of the plurality of recommended services can be realized, and different execution modes of the plurality of recommended services can be satisfied.

Description

Service recommendation method, electronic device and computer program product

Technical Field

The present disclosure relates to the field of recommendation technology, and more particularly, to a service recommendation method, an electronic device, and a computer program product.

Background

With the rapid development of new energy automobiles and automatic driving technologies, richer driving scenes and better driving experience are provided for vehicle users.

In a car networking scenario, the cloud may recommend different services to the user at the appropriate time. For example, in the running process of the vehicle, the normal running service such as route planning, road condition broadcasting, weather broadcasting, electric quantity prompting, or charging prompting can be recommended for the user; the system can also provide the service for improving the driving comfort, such as in-car temperature adjustment, seat adjustment and the like for users; and playing audio and video and entertainment life services such as delicious food, movie tickets and the like can be recommended to the user. However, the prior art only relates to a single service recommendation scenario, if a plurality of services need to be recommended, the plurality of services need to be sequentially recommended to the user, which results in a longer recommendation process and poor user experience.

Therefore, in the use process of the vehicle, batch recommendation of a plurality of services is an urgent problem to be solved.

Disclosure of Invention

It is an object of the present disclosure to provide a new technical solution for recommending services.

According to a first aspect of the present disclosure, there is provided a service recommendation method, applied to a server, the method including:

Receiving state data of the electronic equipment, which is sent by the electronic equipment;

determining a plurality of recommended services which accord with set recommended conditions according to the state data and a pre-trained recommended model;

constructing a behavior tree according to the recommended service, wherein the behavior tree comprises first action nodes which are in one-to-one correspondence with the recommended service, and the first action nodes are used for executing the corresponding recommended service when being executed;

converting the action tree into an action tree file, wherein the action tree file is a file representing the structure of the action tree;

and sending the behavior tree file to the electronic equipment to conduct service recommendation.

Optionally, the method further comprises:

receiving scene information sent by electronic equipment;

determining a target service corresponding to the scene information;

the determining a plurality of recommended services meeting the set recommended conditions according to the state data and a pre-trained recommended model comprises the following steps:

and screening a plurality of recommended services which accord with the set recommended conditions from the target services according to the state data and the recommended model.

Optionally, the behavior tree further includes a root node and at least one first sequence node, the first sequence node is a child node of the root node, and the first action node is a child node of the corresponding first sequence node.

Optionally, the method further comprises:

acquiring a device state corresponding to the recommended service, and constructing the behavior tree according to the device state;

the behavior tree further comprises first condition nodes, wherein the first sequence nodes are in one-to-one correspondence with the equipment states, the first condition nodes are first child nodes of the corresponding first sequence nodes, and the first condition nodes are used for judging whether the electronic equipment accords with the equipment states corresponding to the recommended service or not when executed.

Optionally, the behavior tree further includes a second sequence node, a third sequence node, a second condition node and a second action node, where the first sequence node and the second sequence node are all child nodes of the third sequence node, and the third sequence node is a child node of the root node; the second condition node and the second action node are child nodes of the second sequence node, the second condition node is used for judging whether the user adds the action tree into a specified mode or not when executing, and the second action node is used for storing the action tree and the specified mode correspondingly when executing.

Optionally, the method further comprises:

receiving feedback information of the user on the recommended service, wherein the feedback information is sent by the electronic equipment;

and updating the recommendation model according to the feedback information.

According to a second aspect of the present disclosure, there is provided a service recommendation method, applied to an electronic device, the method including:

acquiring state data of the electronic equipment;

determining whether the electronic equipment is in a specified scene according to the state data;

transmitting the state data to a server and receiving a behavior tree file transmitted by the server under the condition that the electronic equipment is in the appointed scene, wherein the behavior tree file is a file representing the structure of a behavior tree; the behavior tree comprises first action nodes which are in one-to-one correspondence with a plurality of recommended services, wherein the recommended services are services which are determined according to the state data and meet set recommended conditions, and the first action nodes are used for executing the corresponding recommended services when executing;

analyzing the behavior tree file to obtain the behavior tree;

and executing the action tree to conduct service recommendation.

Optionally, the method further comprises:

responding to an instruction added as a specified mode, and correspondingly storing the behavior tree file and the specified mode;

And executing the behavior tree in response to an instruction for starting the specified mode.

Optionally, the behavior tree further includes a root node and at least one first sequence node, where the first sequence node is a child node of the root node, and the first action node is a child node of the corresponding first sequence node;

the performing the behavior tree to make service recommendation includes:

traversing the first sequence node;

traversing child nodes of a first sequence node currently traversed;

and recommending or executing the recommendation service corresponding to the currently traversed first action node under the condition that the currently traversed child node is the first action node.

Optionally, the first sequence node corresponds to the equipment state corresponding to the recommended service one by one, the behavior tree further includes a first condition node corresponding to the equipment state corresponding to the recommended service one by one, the first sequence node is a child node of the root node, and the first condition node is a first child node of the corresponding first sequence node, where the first condition node is used to determine whether the electronic equipment accords with the equipment state corresponding to the recommended service when executing;

the performing the action tree to make service recommendation further comprises:

Judging whether the electronic equipment accords with the corresponding equipment state or not under the condition that the currently traversed child node is a first condition node; under the condition that the electronic equipment accords with the corresponding equipment state, continuously traversing the child nodes of the first sequence node traversed currently; otherwise, continuing to traverse the first sequence node.

Optionally, the method further comprises:

and sending scene information for indicating the specified scene to the server so that the server can determine the recommended service according to the scene information.

Optionally, the method further comprises:

acquiring feedback information of a user on the recommended service;

and sending the feedback information to the server to update a recommendation model, wherein the recommendation model is used for determining the recommendation service according to the state data.

According to a third aspect of the present disclosure there is provided an electronic device comprising a processor and a memory for storing a computer program for controlling the processor to perform the method according to the first aspect of the present disclosure or for controlling the processor to perform the method according to the second aspect of the present disclosure.

According to a fourth aspect of the present disclosure there is provided a computer program product comprising a computer program/instruction, characterized in that the computer program/instruction processor, when executed, implements the method according to the first or second aspect of the present disclosure.

According to the embodiment of the disclosure, a plurality of recommended services conforming to the operation habits of the user are determined according to the state data of the electronic equipment, and the recommended services are sent to the electronic equipment in a behavior tree file mode to be analyzed and executed so as to recommend services, so that a plurality of personalized services can be recommended to the user based on the operation habits of the user. In addition, by combining a plurality of recommended services with the behavior tree, flexible configuration of the plurality of recommended services can be realized, and different execution modes of the plurality of recommended services, such as concurrent execution, precondition sequential execution and the like, are satisfied.

Other driving features of the present disclosure and its advantages will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description, serve to explain the principles of the disclosure.

Fig. 1 is a block diagram of a service recommendation system provided by one embodiment of the present disclosure.

Fig. 2 is a flowchart of a service recommendation method provided by an embodiment of the present disclosure.

FIG. 3 is a schematic diagram of one example of a behavior tree in an embodiment of the present disclosure.

Fig. 4 is a schematic diagram of another example of a behavior tree in an embodiment of the present disclosure.

Fig. 5 is a schematic diagram of yet another example of a behavior tree in an embodiment of the present disclosure.

Fig. 6 is a flowchart of a service recommendation method provided in another embodiment of the present disclosure.

Fig. 7 is a block diagram of an electronic device provided by one embodiment of the present disclosure.

Detailed Description

Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless it is specifically stated otherwise.

The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.

Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.

In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of exemplary embodiments may have different values.

It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.

The server may recommend various services to the electronic device, which in turn may further recommend such services to the user. Alternatively, the electronic device may be a vehicle (e.g., vehicle, airplane, ship), intelligent robot, intelligent home product, etc. capable of providing different services to the user. The presentation form of each service can comprise prompt information and a control instruction generated after the user triggers the execution operation of the prompt information, and the electronic equipment executes the control instruction to realize the execution of the recommended service. The manifestation of each service can also be to open the recommended service directly for the user without the user triggering the execution operation.

In order to ensure the user experience, accurate services need to be recommended to the user, the systems and methods provided by the embodiments of the present invention can be used. In the invention, the accuracy of the service recommended by the electronic device to the user can be reflected by whether the service has executable performance for the electronic device, and the executable performance of the service can be specifically regarded as whether the electronic device is necessary to execute the service.

Based on the above description, before describing embodiments of the present invention in detail, the service executability may also be described in conjunction with the following examples:

assuming that the electronic device is specifically a vehicle or an in-vehicle electronic device mounted on the vehicle, for an in-vehicle temperature adjustment service (hereinafter, simply referred to as a temperature adjustment service), when a temperature exceeds a preset comfort temperature at a certain time in the vehicle, the server may determine that the vehicle is in an environment adjustment scene, and send the temperature adjustment service corresponding to the environment adjustment scene to the vehicle.

After this, the following may occur: under the condition, the electronic equipment receives and displays prompt information corresponding to the temperature regulation service issued by the server to the user. Then, the user can directly operate the received prompt information to generate a control instruction for adjusting the temperature in the vehicle, and the temperature in the vehicle is adjusted by executing the control instruction, namely, the user generates positive response to the recommended temperature adjusting service of the server. In this case, there is a time difference between the delivery and the reception of the temperature adjustment service.

In another case, the user automatically adjusts the temperature in the vehicle during the process of receiving the prompt information by the electronic device. At this time, it can be considered that the temperature adjustment service has no executability. If the electronic device continues to recommend the temperature regulating service to the user, the user will typically not respond to this temperature regulating service, and the recommendation of this service will also affect the user's driving experience.

Similarly, for audio and video playing service (hereinafter, simply referred to as playing service), after the server sends the playing service, the electronic device may receive and recommend the playing service to the user. The playing service may specifically be presented with prompt information for playing audio and video and a control instruction for automatically playing audio and video. If the audio/video playing function of the vehicle is started by the user independently in the process of receiving and recommending the playing service to the user by the electronic device, at this time, the playing service has no executable, and if the playing service issued by the recommending server for the user is obviously unsuitable, the driving experience of the user is affected.

From the above description, it is known that the behavior of a user affects the performability of a service during the service delivery process. In order to improve the influence of the user behavior on the service executable performance and ensure the accuracy of service recommendation, the system and the method provided by the following embodiments of the present invention can be used.

Some embodiments of the present invention are described in detail below with reference to the accompanying drawings. In the case where there is no conflict between the embodiments, the following embodiments and features in the embodiments may be combined with each other. The sequence of steps in the method embodiments described below is only an example and is not strictly limiting.

For ease of understanding, the service recommendation process may be described first from the perspective of the overall service recommendation system. Fig. 1 is a block diagram of a service recommendation system provided in the first embodiment of the present disclosure. The service recommendation system 1000 includes: a server 1100 and an electronic device 1200.

The electronic device may have various devices mounted thereon, or the electronic device may be connected to various devices to acquire related data, such as an image sensor, a temperature sensor, an acceleration sensor, a position sensor, a torque sensor, a force sensor, a power detection device, and the like. These devices may be used to collect status data. The status data may specifically include status data of the electronic device itself, or status data of other devices in which the electronic device is installed, and may also include user status data of a user using the electronic device. The state data may specifically include vehicle state data (such as a running speed, an engine speed, a gear mode, a vehicle electric quantity, whether a window is opened, a current position of the vehicle, and the like), in-vehicle environment data (such as air quality, temperature, humidity, and the like), a current time, and the like, assuming that the electronic device is an electronic device mounted on the vehicle. The user status data may include a user age distribution, a user status, a driving duration of the user, a number of live persons of the vehicle, a number of changes of the driver during driving from the start point to the end point, and the like.

The electronic equipment determines whether the scene where the electronic equipment is located is a designated scene according to the collected state data, and when the scene where the electronic equipment is located is the designated scene, the state data and scene information indicating the designated scene can be sent to a cloud server by means of a gateway, so that a target service corresponding to the designated scene is determined by the server according to a preset corresponding relation between the scene and the service, a plurality of recommended services meeting set recommended conditions are screened out from the target services corresponding to the designated scene according to the state data and a pre-trained recommended model, a behavior tree is built according to the plurality of recommended services, and the behavior tree is sent to the electronic equipment to be executed, so that service recommendation is performed. The recommended service may include prompt information related to the service content and control instructions related to the service content. Alternatively, the correspondence between the scene and the service may be stored in the memory of the server.

Taking the electronic device as an example of a vehicle, the recommended service may alternatively include an in-vehicle environment adjustment service, a driving state adjustment service, a multimedia data playing service, and the like. More specifically, in-vehicle environment adjustment services may include in-vehicle temperature adjustment services, seat position adjustment services, and the like. The driving state adjustment service may include a route planning service, a charging prompt service, and the like. The multimedia data playing service may include a music playing service, a broadcast playing service, a video playing service, and the like. Further, the specified scenes may include an in-vehicle temperature adjustment scene, a seat adjustment scene, a route planning scene, a charging prompt scene, a music playing scene, and the like.

The electronic device may be configured with a corresponding preset rule for each scene, and the scene where the electronic device is located may be determined according to whether the state data collected by the electronic device meets the preset rule. Optionally, the preset rules may also be stored in the memory of the electronic device. And continuing to take over the examples of the vehicles according to the preset rule, wherein the preset rule of the temperature regulation service corresponding to the temperature regulation scene is that the temperature in the vehicle exceeds the preset comfortable temperature. The preset rule of the charging prompt service corresponding to the charging prompt scene is that the electric quantity is lower than a preset threshold value, or the vehicle cannot travel to the destination based on the current electric quantity. The preset rule of the seat position adjustment service corresponding to the seat position adjustment scene is that the duration that the vehicle is detected to be in the P gear and the user sits in the driving position reaches the preset duration.

Then, after the electronic device receives the behavior tree issued by the server, by executing the condition node in the behavior tree, according to the latest state data collected currently by the electronic device, determining whether the scene in which the electronic device is currently located is matched with the recommended service recommended by the server, that is, determining whether the scene in which the electronic device is currently located is suitable for executing the recommended service.

If the electronic equipment determines that the scene where the electronic equipment is currently located is matched with the recommended service according to the state data which is currently and latest collected, and the recommended service recommended by the server for the electronic equipment is indicated to have the executable performance, the electronic equipment can directly recommend the recommended service to the user. If the electronic equipment determines that the current scene of the electronic equipment is not matched with the recommended service, and the recommended service issued by the server is not executable, the electronic equipment does not recommend the recommended service to the user, and therefore the use experience of the user is not affected.

After receiving the recommended service issued by the server, the electronic device can perform secondary verification on the scene where the electronic device is located according to the latest acquired state data to determine whether the current scene where the electronic device is located is matched with the recommended service recommended by the server, namely, whether the recommended service has the executable performance currently, so that the service which is not matched with the current scene where the electronic device is located is prevented from being recommended to the user.

In addition, for the effect of being able to improve service recommendation accuracy, the following can be also understood:

in the case that a certain transmission time is required for the server to issue the recommended service to the electronic device, the scene in which the electronic device is located may be changed due to user operation or other reasons. Therefore, after receiving the recommended service, the electronic device also verifies whether the scene where the electronic device is located changes or not so as to determine whether the scene where the electronic device is located currently matches with the recommended service or not. If the scene of the electronic equipment is not changed, the current scene is matched with the recommended service, the recommended service can be directly recommended to the user, otherwise, the recommended service is not recommended to the user. The electronic equipment verifies whether the current scene is matched with the recommended service or not according to the mode, can judge whether the recommended service issued by the server has the executable performance or not, and determines whether to recommend the recommended service to the user or not according to the judging result, so that the fact that the recommended service of the server for the user has the executable performance is ensured.

It should be noted that, in the above and the following embodiments of the present invention, various services and status data suitable for a vehicle are exemplified, but the embodiments of the present invention are not limited to services, status data and electronic devices, and any device capable of providing different services to a user and status data collected by the device are within the coverage range of the embodiments of the present invention.

The present disclosure provides a service recommendation method, which may be implemented by a server. In particular, the server may be the server 1100 described in the foregoing embodiments.

Fig. 2 is a flowchart of a service recommendation method according to an embodiment of the present disclosure. As shown in fig. 2, the service recommendation method may include steps S2100 to S2500 as follows:

in step S2100, status data of the electronic device sent by the electronic device is received.

In one embodiment, the status data may specifically include status data of the electronic device itself, or status data of other devices in which the electronic device is installed, and may also include user status data of a user using the electronic device. The electronic device is an electronic device installed on a vehicle, or the electronic device is a vehicle, and the state data may specifically include vehicle state data (such as a running speed, an engine speed, a gear mode, a vehicle electric quantity, whether a window is opened, a current position of the vehicle, etc.), in-vehicle environment data (such as air quality, temperature, humidity, etc.), current time, etc. The user status data may include a user age distribution, a user status (e.g., may indicate whether the user is driving tired, etc.), a driving duration of the user, an actual number of people in the vehicle, a number of changes of the driver during driving from the start point to the end point, and so on.

In one embodiment, the electronic device may send the state data to the server according to the set first frequency, and may specifically send the state data collected in the sending period.

In another embodiment, the electronic device may collect the status data according to the set second frequency, and send the status data to the server when the electronic device is determined to be in the specified scene according to the status data.

In this embodiment, at least one specified scene may be set in advance according to specific requirements, where each scene is configured with a corresponding preset rule. And under the condition that the state data collected by the electronic equipment accords with any one preset rule, determining that the electronic equipment is in a corresponding designated scene.

When the electronic equipment is an electronic equipment installed on a vehicle, or the electronic equipment is the vehicle, the preset rule of the temperature regulation service corresponding to the temperature regulation scene is that the temperature in the vehicle exceeds the preset comfortable temperature; the preset rule of the charging prompt service corresponding to the charging prompt scene is that the electric quantity is lower than a preset threshold value, or the vehicle cannot travel to a destination based on the current electric quantity; the preset rule of the seat position adjusting service corresponding to the seat position adjusting scene is that the duration of detecting that the vehicle is in the P gear and the user sits in the driving position reaches the preset duration; the preset rule of closing the window service corresponding to the window scene is that the vehicle reaches a preset destination. The preset duration is preset according to an application scene or specific requirements, for example, the preset duration may be 5 seconds.

The electronic device may send the latest collected state data to the server when detecting that the electronic device is in any one of the specified scenarios according to the state data.

Step S2200, determining a plurality of recommended services which meet the set recommended conditions according to the state data and the pre-trained recommended model.

In this embodiment, the electronic device may embed a point for an interactive operation performed by the user, and upload, to the server, the interactive operation performed by the user and state data of the electronic device when the user performs the interactive operation, in a case where the user performs the interactive operation with the electronic device each time. The server may train according to a service corresponding to the interactive operation performed by the user and state data of the electronic device when the user performs the interactive operation, to obtain a recommendation model.

On the basis, the server can obtain the recommended service which accords with the historical operation habit of the user according to the recommended model and the state data of the electronic equipment in the appointed scene.

In one embodiment of the present disclosure, the server may obtain a matching score between each service and an operation habit of a user according to the recommendation model and state data when the electronic device is in a specified scene, and select N services with highest matching scores as recommendation services. Wherein N is a positive integer preset according to application scenes or specific requirements.

In one embodiment of the present disclosure, the electronic device may further send scene information indicating a specified scene to the server in a case where the electronic device is detected to be in any one of the specified scenes according to the status data. Then, before performing step S2200, the method may further include: receiving scene information sent by electronic equipment; and determining the target service corresponding to the scene information.

On the basis, determining a plurality of recommended services meeting the set recommended conditions according to the state data and the pre-trained recommended model may include:

and screening a plurality of recommended services which meet the set recommended conditions from the target services according to the state data and the pre-trained recommended model.

Specifically, the memory of the server may store a correspondence between the scene and the service in advance. The server may search the corresponding relationship through the scene indicated by the received scene information, and determine the service corresponding to the designated scene where the electronic device is currently located, as the target service.

Further, the server may obtain a matching score between each target service and an operation habit of the user according to the recommendation model and state data of the electronic device in the specified scene, and select N target services with highest matching scores as recommendation services. Wherein N is a positive integer preset according to application scenes or specific requirements.

Step S2300, constructing a behavior tree according to the recommended service.

The behavior tree comprises first action nodes which are in one-to-one correspondence with the recommended services. The first action node is configured to execute a corresponding recommended service when executed.

In one embodiment of the present disclosure, the behavior tree further includes a root node and at least one first order node, the first order node being a child node of the root node, and the first action node being a child node of the corresponding first order node.

In this embodiment, the first sequence node, when executing, traverses its children in sequence until a child node is found that fails to return. If a child node which returns failure is found, the first sequence node returns failure; if all child nodes return success, the first order node returns success.

The first action node may be to perform a corresponding recommended service, such as opening a music, adjusting a seat, etc. The first action node may be to return success if the corresponding recommended service execution is successful, return failure if the corresponding recommended service execution is failed, and return in progress during the corresponding recommended service execution.

In one embodiment of the present disclosure, the method may further comprise: and acquiring the equipment state corresponding to the recommended service, and constructing a behavior tree according to the equipment state.

The behavior tree further comprises first condition nodes, wherein the first sequence nodes correspond to the equipment states one by one, the first condition nodes are first child nodes of the corresponding first sequence nodes, and the first condition nodes are used for judging whether the electronic equipment accords with the equipment states corresponding to the recommended service or not when executed.

In this embodiment, for the child nodes of the same first sequence node, the first condition node is executed before the first action node, that is, the first condition node is executed first, and if the state returned by the first condition node according to the evaluation result of the first condition is successful, the first action node may be executed sequentially or in parallel.

Specifically, when the first condition node is executed, if the electronic equipment accords with the equipment state corresponding to the recommended service, the returned state is successful; if the electronic device does not recommend the device state corresponding to the service, the returned state is failure.

In this embodiment, the first action nodes corresponding to the recommended services with the same corresponding device states may be used as child nodes of the same first sequence node, and the first action nodes corresponding to the recommended services with different corresponding device states may be used as child nodes of different first sequence nodes.

On the basis, the first action node and the first condition node corresponding to the same equipment state are used as child nodes of the same first sequence node, and the first action node and the first condition node corresponding to different equipment states are used as child nodes of different first sequence nodes.

According to the embodiment, before the recommended service is executed, whether the electronic equipment meets corresponding execution conditions or not can be judged, namely whether the electronic equipment accords with the equipment state corresponding to the recommended service or not, so that the safety of the electronic equipment executing the recommended service is ensured.

In the case that the device states corresponding to the plurality of recommended services are different, the behavior tree may include a root node, a first sequence node, a first action node, a first condition node, a fourth sequence node, and forced success nodes corresponding to each device state one by one, where the fourth sequence node is a child node of the root node, each first sequence node is a child node of the corresponding forced success node, the first action node and the first condition node corresponding to the same device state are child nodes of the same first sequence node, and the first action node and the first condition node corresponding to different device states are child nodes of different first sequence nodes.

Specifically, when the forced successful node executes, if the child node returns to the in-progress state, the returned state is in-progress; otherwise, the returned state is always successful.

In this way, in the case where the electronic device does not conform to a part of the device states, the recommended service conforming to the corresponding device states can be executed.

In one example, the recommended service may include "adjust seat to comfortable position", "turn on last listened music", "start navigation", and the recommended service corresponds to a device state that the vehicle is in P-gear, time traveling in the morning, and start the vehicle for the first time, then the behavior tree may be constructed as shown in fig. 3.

Further, when the electronic device executes the behavior tree, it may execute a first leaf node first, determine whether the current user is engaged in p-gear, travel in the morning and start the vehicle for the first time, and execute a second leaf node "voice broadcast" after the condition is satisfied: inquiring whether the user needs to adjust the seat, turn on the last played music and turn on navigation ", if the user is positive feedback, the third to fifth leaf nodes start executing: the seat is adjusted to a comfortable position, the last listened music is opened, and navigation is started.

In another example, the recommended service may include "nearby charging station recommended" and "open air conditioner", where the device state corresponding to the recommended service "nearby charging station recommended" is that the electric quantity of the vehicle is less than or equal to the electric quantity threshold value in the running process, and the device state corresponding to the recommended service "open air conditioner" is that the temperature in the vehicle is greater than or equal to the temperature threshold value, and then the behavior tree may be constructed as shown in fig. 4.

The power threshold and the temperature threshold may be set in advance according to an application scenario or specific requirements, for example, the power threshold may be 15%, and the temperature threshold may be 25 degrees.

Further, when executing the behavior tree, the electronic device may execute a first leaf node, determine whether the electric quantity of the vehicle in the running process is less than or equal to 15%, and execute a second leaf node "voice prompt" after the condition is satisfied: the current power is low, whether charging is needed, and if the user answers "confirm", the third leaf node "nearby charging station recommendation" is performed. The second step executes a fourth leaf node to determine whether the temperature in the vehicle is greater than 25 degrees, and if so, executes a fifth leaf node voice prompt: whether the current in-vehicle temperature is high, air conditioner is turned on, and if the user answers "confirm", the sixth leaf node is executed to "turn on air conditioner".

In another embodiment, the behavior tree may further include a root node, a parallel node, and a first action node, where the parallel node is a child node of the root node and the first action node is a child node of the parallel node.

In executing the behavior tree, child nodes of the parallel nodes, the first action node, may be executed in parallel.

In one embodiment of the disclosure, the behavior tree further includes a second sequence node, a third sequence node, a second condition node, and a second action node, the first sequence node and the second sequence node are all child nodes of the third sequence node, and the third sequence node is a child node of the root node; the second condition node and the second action node are all child nodes of the second sequence node, the second condition node is used for judging whether a user adds the action tree into the appointed mode or not when executing, and the second action node is used for storing the action tree corresponding to the appointed mode when executing.

In this embodiment, when the electronic device executes the second sequence node of the behavior tree and the child nodes thereof, the user may be reminded to add the behavior tree of the recommended service in the specified scene as the specified mode, and under the condition of confirmation of the user, the behavior tree and the specified mode are automatically stored correspondingly, so that the subsequent user can execute the recommended service corresponding to the behavior tree according to the actual requirement, without recommending through the server, and the delay of executing the recommended service may be reduced.

In one example, the recommended service may include "adjust seat to comfortable position", "turn on last listened music", "start navigation", and the recommended service corresponds to a device state in which the vehicle is in P-gear, time traveling in the morning, and start the vehicle for the first time. Then the behavior tree constructed may be as shown in fig. 5.

Further, when the electronic device executes the behavior tree, it may execute a first leaf node first, determine whether the current user is engaged in p-gear, travel in the morning and start the vehicle for the first time, and execute a second leaf node "voice broadcast" after the condition is satisfied: inquiring whether the user needs to adjust the seat, turn on the last played music and turn on navigation ", if the user is positive feedback, the third to fifth leaf nodes start executing: the seat is adjusted to a comfortable position, the last listened music is opened, and navigation is started. And executing a sixth leaf node, judging whether the user adds a duty mode, if so, executing a seventh leaf node, and storing the behavior tree and the duty mode correspondingly.

Step S2400, converting the behavior tree into a behavior tree file.

The behavior tree file is a file representing the structure of the behavior tree. For example, the behavior tree file may be an xml file or a json file.

Step S2500, the behavior tree file is sent to the electronic equipment to conduct service recommendation.

In this embodiment, when the electronic device receives the behavior tree file, the electronic device may parse the behavior tree file to obtain a behavior tree, and execute the behavior tree to perform service recommendation.

According to the embodiment, a plurality of recommended services conforming to the operation habits of the user can be determined according to the state data of the electronic equipment, and the recommended services are sent to the electronic equipment in a behavior tree file mode to be analyzed and executed so as to recommend services, and a plurality of personalized services can be recommended to the user based on the operation habits of the user. In addition, by combining a plurality of recommended services with the behavior tree, flexible configuration of the plurality of recommended services can be realized, and different execution modes of the plurality of recommended services, such as concurrent execution, precondition sequential execution and the like, are satisfied.

In one embodiment of the present disclosure, the method may further comprise: receiving feedback information of a user on a recommendation service, wherein the feedback information is sent by electronic equipment; and updating the recommendation model according to the feedback information.

According to the embodiment, the recommendation model is updated according to the feedback information of the user on the recommendation service, so that the recommendation accuracy of the recommendation model can be improved.

The present disclosure also provides a service recommendation method, which may be implemented by an electronic device. Specifically, the electronic device may be the electronic device 1200 shown in fig. 1.

Fig. 6 is a flowchart of a service recommendation method provided according to an embodiment of the present disclosure, as shown in fig. 6, the method may include steps S6100 to S6500 as follows:

in step S6100, status data of the electronic device is obtained.

In step S6200, it is determined whether the electronic device is in the specified scene according to the status data.

Step S6300, when the electronic device is in the specified scene, sending state data to the server, and receiving the behavior tree file sent by the server.

The behavior tree file is a file representing a structure of a behavior tree, the behavior tree comprises first action nodes corresponding to a plurality of recommended services one by one, the recommended services are services which are determined according to state data and meet set recommended conditions, and the first action nodes are used for executing corresponding recommended services when executing.

In the case where it is detected that the electronic device is in any one of the specified scenes based on the state data, the state data when the electronic device is in the specified scene may be transmitted to the server.

Specifically, when the server receives the state data, a plurality of services meeting the set recommendation conditions can be screened out from the services to be recommended according to the state data and a pre-trained recommendation model, and the services can be used as recommendation services; and constructing a behavior tree according to the plurality of recommended services, converting the behavior tree into a behavior tree file, and sending the behavior tree file to the electronic equipment for analysis and execution to recommend the services.

Further, the server may obtain a matching score between each service and an operation habit of the user according to the recommendation model and state data of the electronic device in the specified scene, and select N services with highest matching scores as recommendation services. Wherein N is a positive integer preset according to application scenes or specific requirements.

In one embodiment of the present disclosure, the method may further comprise: and sending the scene information for indicating the specified scene to the server so that the server can determine the recommended service according to the scene information.

Specifically, when the server receives the state data and the scene information, the server may determine, according to the scene information, a target service corresponding to a specific scene where the electronic device is currently located, and then screen, according to the state data and a pre-trained recommendation model, a plurality of target services corresponding to the set recommendation condition from the target services corresponding to the specific scene, where the target services are all used as recommendation services.

Further, the memory of the server may store a correspondence between the scene and the service in advance. The server may determine, as the target service, a service corresponding to the specified scene in which the electronic device is currently located by searching the correspondence.

Still further, the electronic device may be configured to embed a point for an interactive operation performed by the user, and upload, to the server, the interactive operation performed by the user and state data of the electronic device when the user performs the interactive operation, in a case where the user performs the interactive operation with the electronic device each time. The server trains according to the service corresponding to the interactive operation executed by the user and the state data of the electronic equipment when the user executes the interactive operation, and a recommendation model is obtained.

The server may construct a behavior tree when obtaining a plurality of recommended services, and specifically, the plurality of recommended services may be leaf nodes of the behavior tree, and the corresponding type may be action nodes.

Step S6400, analyzing the action tree file to obtain an action tree.

The behavior tree file in this embodiment may be an xml file or json file that represents a behavior tree structure, and by analyzing the behavior tree file, a corresponding behavior tree may be obtained.

Step S6500, executing the action tree to make service recommendation.

In one embodiment of the present disclosure, a behavior tree includes a root node, at least one first order node, and first action nodes corresponding to a plurality of recommended services one to one, the first order node being a child node of the root node, the first action node being a child node of the corresponding first order node.

On this basis, the execution of the behavior tree to make service recommendations includes: traversing the first sequence node; traversing child nodes of a first sequence node currently traversed; and recommending or executing the recommendation service corresponding to the currently traversed first action node under the condition that the currently traversed child node is the first action node.

When the first sequence node executes, the child nodes of the first sequence node are traversed in sequence until a child node with failure return is found. If a child node which returns failure is found, the first sequence node returns failure; if all child nodes return success, the first order node returns success.

It may be understood that, when the currently traversed child node is the first action node, if recommending or executing the recommended service corresponding to the currently traversed first action node is successful, the first action node returns success, and continues to traverse the child nodes of the currently traversed first sequence node, and if recommending or executing the recommended service corresponding to the currently traversed first action node fails, the first action node returns failure, and does not continue to traverse the child nodes of the currently traversed first sequence node, but continues to traverse the first sequence node.

Executing the first action node may be executing a corresponding recommended service, such as opening a music, adjusting a seat, etc. The first action node may be to return success if the corresponding recommended service execution is successful, return failure if the corresponding recommended service execution is failed, and return in progress during the corresponding recommended service execution.

In one embodiment, the action tree may further include a third action node corresponding to the recommended service, where the third action node is a child node corresponding to the first order node, and the third action node may be executed before the first action node corresponding to the first order node and then executed after the first condition node corresponding to the first order node. When the third action node is executed, the user may be reminded to confirm whether to execute the corresponding recommended service. Specifically, the reminding mode can include voice cards or voice broadcasting, and also can include text reminding on a display screen.

In one embodiment of the present disclosure, the first sequence node corresponds to the device state corresponding to the recommended service one by one, the behavior tree further includes a first condition node corresponding to the device state corresponding to the recommended service one by one, the first sequence node is a child node of the root node, and the first condition node is a first child node of the corresponding first sequence node, where the first condition node is used to determine whether the electronic device conforms to the device state corresponding to the recommended service when executing;

performing the behavioral tree to make service recommendations further includes:

In one example, when executing the behavior tree as shown in fig. 3, the electronic device may execute a first sequence node first, in the process of executing the first sequence node, execute a first leaf node first, determine whether the current user hangs up p-gear, time in the morning travel time and start the vehicle for the first time, and if the execution result of the first leaf node is successful, that is, the vehicle meets the above condition, execute a second leaf node "voice broadcast: inquiring whether the user needs to adjust the seat, turn on the last played music and turn on navigation ", if the user is positive feedback, returning success to the first sequence node and executing the third to fifth leaf nodes: the method comprises the steps of adjusting a seat to a comfortable position, opening music listened to last time, starting navigation, and returning an execution result of the third to fifth leaf nodes to a first sequence node; if the user is negative feedback, failure is returned to the first sequence node, so that the first sequence node ends execution, and further the execution of the action tree is ended. If the execution result of the first leaf node is failure, that is, the vehicle does not meet the condition, failure is returned to the first sequence node, so that the first sequence node finishes executing, and further the behavior tree is finished executing.

In one embodiment of the present disclosure, the behavior tree may include a root node, a first sequence node, a first action node, a first condition node, a fourth sequence node, and a forced success node corresponding to each device state one-to-one, where the fourth sequence node is a child node of the root node, each first sequence node is a child node of the corresponding forced success node, the first action node and the first condition node corresponding to the same device state are child nodes of the same first sequence node, and the first action node and the first condition node corresponding to different device states are child nodes of different first sequence nodes.

In this embodiment, when executing the behavior tree, the electronic device may first traverse the child node of the fourth sequence node, that is, the forced success node, and in the process of executing the forced success node, may traverse the child node of the forced success node, that is, the first sequence node. The execution process of the first sequence node may refer to the foregoing embodiments, and will not be described herein. At the end of the execution of the first order node, the forced successful node will return success, whether successful or unsuccessful, to continue traversing the execution of the next forced successful node.

In this way, in the case where the electronic device does not conform to a part of the device states, the recommended service conforming to the corresponding device state can be executed.

In one example, when executing the behavior tree as shown in fig. 4, the electronic device may execute a first leaf node first in the process of executing the first sequence node, determine whether the electric quantity of the vehicle in the running process is less than or equal to 15%, and when the condition is not satisfied, return failure to the upper first sequence node, so that the first sequence node ends execution, and return failure to the upper forced successful node; when the condition is satisfied, success is returned to the upper first order node, and a second leaf node voice prompt is executed: the current electric quantity is low, whether charging is needed or not, if the user answers 'confirmation', success is returned to the upper first sequence node, and the third leaf node 'nearby charging station recommendation' is executed, and success is returned to the upper first sequence node under the condition that the execution is successful; if the user answers 'denial', failure is returned to the upper first order node, the first order node returns an execution result to the forced successful node according to the execution result of the child node, and the forced successful node returns success to the fourth order node so as to continue to execute the next forced successful node. In the process of executing the next first sequence node, executing a fourth leaf node firstly, judging whether the temperature in the vehicle is greater than 25 degrees, if not, returning failure to the upper first sequence node so that the first sequence node finishes executing, and returning failure to the upper forced success node; if so, a fifth leaf node "voice prompt" is executed: if the user answers "confirm", success is returned to the upper first order node, and the sixth leaf node is executed to "turn on the air conditioner". If the user answers 'denial', the failure is returned to the upper first sequence node, the first sequence node returns an execution result to the forced success node according to the execution result of the child node, and the forced success node returns success to the fourth sequence node, so that the execution of the behavior tree is completed.

In one embodiment of the present disclosure, the method may further comprise: responding to an instruction added as a specified mode, and storing the behavior tree file corresponding to the specified mode; the behavior tree is executed in response to an instruction to initiate a specified mode.

In this embodiment, the instruction received by the electronic device to add to the specified mode may be triggered by voice or may be triggered by a key on the display screen.

The specific name of the specified mode can be set by a user according to the actual demand of the user, or can be automatically generated according to the specified scene of the electronic equipment.

For example, the user gives a specified mode corresponding to the action tree in the commuting scene of the morning, and the specified mode is named as a commuting mode. When the following user takes the bus, the 'commute mode for working' can be directly opened through voice dialogue, and the action tree can be executed, so that the automatic execution of the recommended service of the commute scene for working in the morning is realized.

After the behavior tree is stored corresponding to the specified mode, the electronic device may execute the behavior tree in response to an instruction for starting the specified mode, so as to implement automatic execution of the recommended service in the specified scene.

In one embodiment of the present disclosure, the behavior tree may further include a second sequence node and a third sequence node, the first sequence node and the second sequence node being child nodes of the third sequence node, the third sequence node being a child node of the root node; the second condition node and the second action node are all child nodes of the second sequence node, the second condition node is used for judging whether the action tree is added into the appointed mode by a user when being executed, and the second action node is used for storing the action tree corresponding to the appointed mode when being executed.

In this embodiment, when the electronic device executes the second action node in the action tree, the user may be reminded to add the action tree of the recommended service in the specified scene as the specified mode, and under the condition of confirmation of the user, the action tree and the specified mode are automatically stored in a corresponding manner, so that the subsequent user can execute the recommended service corresponding to the action tree according to the actual requirement, without recommending through the server, and the delay of executing the recommended service may be reduced.

In one example, when executing the behavior tree as shown in fig. 5, the electronic device may execute a first sequence node first, in the process of executing the first sequence node, execute a first leaf node first, determine whether the current user hangs up p-gear, time in the morning, start the vehicle for the first time, if the execution result of the first leaf node is successful, that is, the vehicle meets the above condition, return success to the first sequence node, and execute a second leaf node "voice broadcast: inquiring whether the user needs to adjust the seat, turn on the last played music and turn on navigation ", if the user is positive feedback, the third to fifth leaf nodes start executing: the method comprises the steps of adjusting a seat to a comfortable position, opening music listened to last time, and starting navigation; if the user is negative feedback, failure is returned to the first sequence node, execution of the first sequence node is finished, and the first sequence node is caused to return failure to the third sequence node. If the execution result of the first leaf node is failure, that is, the vehicle does not meet the condition, the failure is returned to the first sequence node, so that the first sequence node returns the failure to the third sequence node. Executing the second sequence node, namely executing a sixth leaf node in the process of executing the second sequence node, judging whether a user adds a duty mode, and if not, returning failure to the second sequence node so that the second sequence node returns failure to a third sequence node; if so, returning success to the second sequence result, executing a seventh leaf node, storing the behavior tree and the duty mode correspondingly, and returning success to the second sequence node, so that the second sequence node returns success to the third sequence node.

In one embodiment of the present disclosure, the method may further comprise: acquiring feedback information of a user on recommended service; and sending the feedback information to a server to update a recommendation model, wherein the recommendation model is used for determining recommended services according to the state data.

The feedback information may be information indicating whether the user accepts execution of the corresponding recommended service. The feedback information can be input through voice or through keys on a display screen.

Further, the server may receive feedback information of the user on the recommendation service sent by the electronic device, and update the recommendation model according to the feedback information, so as to improve the recommendation accuracy of the recommendation model.

The present disclosure also provides an electronic device, as shown in fig. 7, the electronic device 7000 may include a processor 7100 and a memory 7200, the memory 7200 for storing a computer program for controlling the processor 7100 to perform the method performed by the server as described in any embodiment of the present disclosure, or for controlling the processor 7100 to perform the method performed by the electronic device as described in any embodiment of the present disclosure.

The present disclosure also provides a computer program product comprising a computer program/instructions which, when executed by a processor of the computer program/instructions, implements a service recommendation method according to any of the embodiments of the present disclosure.

The present disclosure may be a system, method, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement aspects of the present disclosure.

The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.

The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.

Computer program instructions for performing the operations of the present disclosure can be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, c++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present disclosure are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information of computer readable program instructions, which can execute the computer readable program instructions.

Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are all equivalent.

The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the technical improvement of the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the present disclosure is defined by the appended claims.

Claims

1. A service recommendation method, applied to a server, comprising:

the behavior tree file is sent to the electronic equipment to conduct service recommendation;

the behavior tree further comprises a root node and at least one first sequence node, wherein the first sequence node is a child node of the root node, and the first action node is a child node of the corresponding first sequence node;

the method further comprises the steps of: acquiring a device state corresponding to the recommended service, and constructing the behavior tree according to the device state;

2. The method according to claim 1, wherein the method further comprises:

receiving scene information sent by electronic equipment;

determining a target service corresponding to the scene information;

3. The method according to claim 1 or 2, wherein the behavior tree further comprises a second sequence node, a third sequence node, a second condition node and a second action node, the first sequence node and the second sequence node being both child nodes of the third sequence node, the third sequence node being a child node of the root node; the second condition node and the second action node are child nodes of the second sequence node, the second condition node is used for judging whether the user adds the action tree into a specified mode or not when executing, and the second action node is used for storing the action tree and the specified mode correspondingly when executing.

4. A service recommendation method, applied to an electronic device, comprising:

acquiring state data of the electronic equipment;

transmitting the state data to a server and receiving a behavior tree file transmitted by the server under the condition that the electronic equipment is in the appointed scene, wherein the behavior tree file is a file representing the structure of a behavior tree; the behavior tree comprises first action nodes which are in one-to-one correspondence with a plurality of recommended services, wherein the recommended services are services which are determined according to the state data and meet set recommended conditions, and the first action nodes are used for executing the corresponding recommended services when executing; the behavior tree further comprises a root node and at least one first sequence node, wherein the first sequence node is a child node of the root node, and the first action node is a child node of the corresponding first sequence node; the first order nodes are in one-to-one correspondence with the equipment states corresponding to the recommended service, the behavior tree further comprises first condition nodes, the first condition nodes are first child nodes of the corresponding first order nodes, and the first condition nodes are used for judging whether the electronic equipment accords with the equipment states corresponding to the recommended service or not when executed;

Analyzing the behavior tree file to obtain the behavior tree;

and executing the action tree to conduct service recommendation.

5. The method according to claim 4, wherein the method further comprises:

6. The method according to claim 4 or 5, wherein,

the performing the behavior tree to make service recommendation includes:

traversing the first sequence node;

traversing child nodes of a first sequence node currently traversed;

7. The method of claim 6, wherein the step of providing the first layer comprises,

8. An electronic device comprising a processor and a memory, the memory being for storing a computer program for controlling the processor to perform the method of any one of claims 1 to 3 or for controlling the processor to perform the method of any one of claims 4 to 7.

9. A computer readable storage medium comprising a computer program/instruction which when executed by the computer program/instruction processor implements the method of any of claims 1 to 7.