CN117998325A

CN117998325A - Processing method and device for artificial intelligence AI service

Info

Publication number: CN117998325A
Application number: CN202211387610.2A
Authority: CN
Inventors: 周通; 袁雁南
Original assignee: Vivo Mobile Communication Co Ltd
Current assignee: Vivo Mobile Communication Co Ltd
Priority date: 2022-11-07
Filing date: 2022-11-07
Publication date: 2024-05-07
Also published as: WO2024099111A1

Abstract

The application discloses a processing method and equipment of an artificial intelligence AI service, belonging to the technical field of communication, wherein the processing method of the AI service in the embodiment of the application comprises the following steps: the method comprises the steps that network side equipment receives first information from target equipment, wherein the first information comprises an AI service identifier of a first service and indication information for indicating AI service quality requirements; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements; safety requirements are used to characterize the anti-collision capabilities of the target device; the comfort requirement is used to characterize the ride comfort of the target device; the efficiency requirement is used for representing the efficiency of the target equipment to finish the task; the time delay requirement is used for representing the time difference between the initiation of the AI service request by the target equipment and the acquisition of the service result; the network side equipment feeds back a service result of the first service to the target equipment based on the AI service identification and the AI service quality requirement.

Description

Processing method and device for artificial intelligence AI service

Technical Field

The application belongs to the technical field of communication, and particularly relates to a processing method and equipment of an artificial intelligence AI service.

Background

In mobile communication systems, there are now more and more cases in which Artificial Intelligence (AI) is incorporated. For example, at the physical layer there is AI-based CSI (CHANNEL STATE information) feedback compression, AI-based beam management, AI-based positioning. The 3gpp RAN3 discusses AI-based power saving, AI-based load balancing, and the like. In the future, more use cases in combination with AI will appear in the mobile communication system.

Future mobile communication systems may not only provide AI services to the communication system inwards. AI services may also be provided to external applications. For example, AI services are provided for communication network external applications such as unmanned, robotic, etc. The wireless network of the mobile communication system is only used as a communication pipeline, namely, is only used for transmitting information, and cannot provide AI service for external applications, so that how to better support the AI service in the mobile communication system is a problem to be solved.

Disclosure of Invention

The embodiment of the application provides a processing method and equipment for an artificial intelligence AI service, which can solve the problem of how to better support the AI service in a mobile communication system.

In a first aspect, a method for processing an artificial intelligence AI service is provided, including:

The method comprises the steps that network side equipment receives first information from target equipment, wherein the first information comprises an AI service identifier of a first service and indication information for indicating AI service quality requirements; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements; the security requirement is used to characterize the anti-collision capability of the target device; the comfort requirement is used to characterize the ride comfort of the target device; the high efficiency requirement is used for representing the efficiency of the target equipment to complete tasks; the time delay requirement is used for representing the time difference between the target equipment initiating the AI service request and acquiring the service result;

And the network side equipment feeds back a service result of the first service to the target equipment based on the AI service identifier and the AI service quality requirement.

In a second aspect, a method for processing an artificial intelligence AI service is provided, including:

the method comprises the steps that target equipment sends first information to network side equipment, wherein the first information comprises an AI service identifier of a first service and indication information for indicating AI service quality requirements; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements; the security requirement is used to characterize the anti-collision capability of the target device; the comfort requirement is used to characterize the ride comfort of the target device; the high efficiency requirement is used for representing the efficiency of the target equipment to complete tasks; the time delay requirement is used for representing the time difference between the target equipment initiating the AI service request and acquiring the service result;

And the target equipment receives a service result of the first service sent by the network side equipment.

In a third aspect, there is provided a processing apparatus of an AI service, including:

A receiving module, configured to receive first information from a target device, where the first information includes an AI service identifier of a first service and indication information for indicating an AI quality of service requirement; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements; the security requirement is used to characterize the anti-collision capability of the target device; the comfort requirement is used to characterize the ride comfort of the target device; the high efficiency requirement is used for representing the efficiency of the target equipment to complete tasks; the time delay requirement is used for representing the time difference between the target equipment initiating the AI service request and acquiring the service result;

And the processing module is used for feeding back a service result of the first service to the target equipment based on the AI service identification and the AI service quality requirement.

In a fourth aspect, there is provided a processing apparatus of an AI service, including:

A sending module, configured to send first information to a network side device, where the first information includes an AI service identifier of a first service and indication information for indicating an AI service quality requirement; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements; the security requirement is used to characterize the anti-collision capability of the target device; the comfort requirement is used to characterize the ride comfort of the target device; the high efficiency requirement is used for representing the efficiency of the target equipment to complete tasks; the time delay requirement is used for representing the time difference between the target equipment initiating the AI service request and acquiring the service result;

and the receiving module is used for receiving the service result sent by the network side equipment.

In a fifth aspect, a network side device is provided, comprising a processor and a memory storing a program or instructions executable on the processor, which program or instructions when executed by the processor implement the steps of the method as described in the first aspect.

In a sixth aspect, a network side device is provided, including a processor and a communication interface, where the communication interface is configured to receive first information from a target device, where the first information includes an AI service identifier of a first service and indication information for indicating an AI quality of service requirement; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements; the security requirement is used to characterize the anti-collision capability of the target device; the comfort requirement is used to characterize the ride comfort of the target device; the high efficiency requirement is used for representing the efficiency of the target equipment to complete tasks; the time delay requirement is used for representing the time difference between the target equipment initiating the AI service request and acquiring the service result; the processor is used for feeding back a service result of the first service to the target device based on the AI service identification and the AI service quality requirement.

In a seventh aspect, there is provided a target device comprising a processor and a memory storing a program or instructions executable on the processor, which when executed by the processor, implement the steps of the method as described in the second aspect.

An eighth aspect provides a target device, including a processor and a communication interface, where the communication interface is configured to send first information to a network side device, where the first information includes an AI service identifier of a first service and indication information for indicating an AI service quality requirement; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements; the security requirement is used to characterize the anti-collision capability of the target device; the comfort requirement is used to characterize the ride comfort of the target device; the high efficiency requirement is used for representing the efficiency of the target equipment to complete tasks; the time delay requirement is used for representing the time difference between the target equipment initiating the AI service request and acquiring the service result; the communication interface is further configured to receive a service result of the first service sent by the network side device.

In a ninth aspect, there is provided a communication system comprising: a target device and a network side device, the target device being operable to perform the steps of the method for processing an AI service as described in the second aspect, the network side device being operable to perform the steps of the method for processing an AI service as described in the first aspect.

In a tenth aspect, there is provided a readable storage medium having stored thereon a program or instructions which when executed by a processor, performs the steps of the method according to the first aspect or performs the steps of the method according to the second aspect.

In an eleventh aspect, there is provided a chip comprising a processor and a communication interface coupled to the processor, the processor being for running a program or instructions to implement the method according to the first aspect or to implement the method according to the second aspect.

In a twelfth aspect, there is provided a computer program/program product stored in a storage medium, the computer program/program product being executed by at least one processor to implement the steps of the processing method of AI services as set forth in the first or second aspects.

In the embodiment of the application, a network side device receives first information from a target device, wherein the first information comprises an AI service identifier of a first service and indication information for indicating AI service quality requirements; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements; safety requirements are used to characterize the anti-collision capabilities of the target device; comfort requirements are used to characterize the ride comfort of the target device; the efficiency requirement is used for representing the efficiency of the target equipment to finish the task; the time delay requirement is used for representing the time difference between the initiation of the AI service request by the target equipment and the acquisition of the service result; further, the network side device obtains the service result of the first service based on the AI service identifier and the AI service quality requirement, and feeds back the service result to the target device, that is, the network side device can provide service for the target device based on the AI service quality requirement, so that the AI service quality can be improved, and the AI service can be better supported in the mobile communication system.

Drawings

Fig. 1 is a block diagram of a wireless communication system to which embodiments of the present application are applicable;

FIG. 2 is a flowchart of a processing method of an AI service according to an embodiment of the present application;

FIG. 3 is a schematic diagram of an interaction flow of a processing method of an AI service according to an embodiment of the application;

FIG. 4 is a second flowchart of a processing method of AI service according to an embodiment of the application;

Fig. 5 is a schematic structural diagram of a processing device for AI services according to an embodiment of the present application;

FIG. 6 is a second schematic diagram of a processing device for AI services according to an embodiment of the application;

Fig. 7 is a schematic structural diagram of a communication device according to an embodiment of the present application;

Fig. 8 is a schematic structural diagram of a terminal according to an embodiment of the present application;

Fig. 9 is a schematic structural diagram of a network side device according to an embodiment of the present application.

Detailed Description

The technical solutions of the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which are derived by a person skilled in the art based on the embodiments of the application, fall within the scope of protection of the application.

The terms first, second and the like in the description and in the claims, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the application are capable of operation in sequences other than those illustrated or otherwise described herein, and that the "first" and "second" distinguishing between objects generally are not limited in number to the extent that the first object may, for example, be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/" generally means a relationship in which the associated object is an "or" before and after.

It should be noted that the techniques described in the embodiments of the present application are not limited to long term evolution (Long Term Evolution, LTE)/LTE evolution (LTE-Advanced, LTE-a) systems, but may also be used in other wireless communication systems, such as code division multiple access (Code Division Multiple Access, CDMA), time division multiple access (Time Division Multiple Access, TDMA), frequency division multiple access (Frequency Division Multiple Access, FDMA), orthogonal frequency division multiple access (Orthogonal Frequency Division Multiple Access, OFDMA), single carrier frequency division multiple access (Single-carrier Frequency Division Multiple Access, SC-FDMA), and other systems. The terms "system" and "network" in embodiments of the application are often used interchangeably, and the techniques described may be used for both the above-mentioned systems and radio technologies, as well as other systems and radio technologies. The following description describes a New Radio (NR) system for exemplary purposes and NR terminology is used in much of the following description, but these techniques may also be applied to applications other than NR system applications, such as 6 th Generation (6G) communication systems.

Fig. 1 shows a block diagram of a wireless communication system to which an embodiment of the present application is applicable. The wireless communication system includes a terminal 11 and a network device 12. The terminal 11 may be a Mobile phone, a tablet Computer (Tablet Personal Computer), a Laptop (Laptop Computer) or a terminal-side device called a notebook, a Personal digital assistant (Personal DIGITAL ASSISTANT, PDA), a palm Computer, a netbook, an ultra-Mobile Personal Computer (ultra-Mobile Personal Computer, UMPC), a Mobile internet appliance (Mobile INTERNET DEVICE, MID), an augmented reality (augmented reality, AR)/Virtual Reality (VR) device, a robot, a wearable device (Wearable Device), a vehicle-mounted device (VUE), a pedestrian terminal (PUE), a smart home (home device with a wireless communication function, such as a refrigerator, a television, a washing machine, a furniture, etc.), a game machine, a Personal Computer (Personal Computer, a PC), a teller machine, or a self-service machine, etc., and the wearable device includes: intelligent wrist-watch, intelligent bracelet, intelligent earphone, intelligent glasses, intelligent ornament (intelligent bracelet, intelligent ring, intelligent necklace, intelligent anklet, intelligent foot chain etc.), intelligent wrist strap, intelligent clothing etc.. It should be noted that the specific type of the terminal 11 is not limited in the embodiment of the present application. The network-side device 12 may include an access network device or a core network device, where the access network device 12 may also be referred to as a radio access network device, a radio access network (Radio Access Network, RAN), a radio access network function, or a radio access network element. Access network device 12 may include a base station, a WLAN access Point, a WiFi node, or the like, which may be referred to as a node B, an evolved node B (eNB), an access Point, a base transceiver station (Base Transceiver Station, BTS), a radio base station, a radio transceiver, a Basic service set (Basic SERVICE SET, BSS), an Extended service set (Extended SERVICE SET, ESS), a home node B, a home evolved node B, a transmission and reception Point (TRANSMITTING RECEIVING Point, TRP), or some other suitable terminology in the art, and the base station is not limited to a particular technical vocabulary so long as the same technical effect is achieved, and it should be noted that in the embodiment of the present application, only a base station in an NR system is described as an example, and the specific type of the base station is not limited. The core network device may include, but is not limited to, at least one of: core network nodes, core network functions, mobility management entities (Mobility MANAGEMENT ENTITY, MME), access Mobility management functions (ACCESS AND Mobility Management Function, AMF), session management functions (Session Management Function, SMF), user plane functions (User Plane Function, UPF), policy control functions (Policy Control Function, PCF), policy and Charging Rules Function (PCRF), edge application service discovery functions (Edge Application Server Discovery Function, EASDF), unified data management (Unified DATA MANAGEMENT, UDM), unified data warehousing (Unified Data Repository, UDR), home subscriber server (Home Subscriber Server, HSS), centralized network configuration (Centralized network configuration, CNC), network storage functions (Network Repository Function, NRF), network opening functions (Network Exposure Function, NEF), local NEF (Local NEF, or L-NEF), binding support functions (Binding Support Function, BSF), application functions (Application Function, AF), and the like. It should be noted that, in the embodiment of the present application, only the core network device in the NR system is described as an example, and the specific type of the core network device is not limited.

Future mobile communication systems may not only provide AI services to the communication system inwards. AI services may also be provided to external applications. For example, AI services are provided for communication network external applications such as unmanned, robotic, etc. These thousands of industry-wide external applications have different quality of service levels. If it is also based on the quality of service index in the existing communication system as a service index for external services. The quality of service requirements of the external application cannot be matched. Therefore, the embodiment of the application provides a processing method of an AI service, which carries the indication information for indicating the AI service quality requirement when sending the AI service request, so that the mobile communication system can receive the AI service quality requirement, and the mobile communication system can provide service with higher quality for external application based on the AI service quality requirement.

The following describes in detail the processing method of the AI service provided by the embodiment of the present application through some embodiments and application scenarios thereof with reference to the accompanying drawings.

Fig. 2 is a flowchart of a processing method of an AI service according to an embodiment of the present application. As shown in fig. 2, the method provided in this embodiment includes:

Step 101, network side equipment receives first information from target equipment, wherein the first information comprises an AI service identifier of a first service and indication information for indicating AI service quality requirements; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements; safety requirements are used to characterize the anti-collision capabilities of the target device; comfort requirements are used to characterize the ride comfort of the target device; the efficiency requirement is used for representing the efficiency of the target equipment to finish the task; the time delay requirement is used for representing the time difference between the initiation of the AI service request by the target equipment and the acquisition of the service result;

specifically, a network-side device such as a base station function or a core network function, a target device such as a terminal, a vehicle.

The target device sends first information to the network side device, for example, the first information may be an AI service request, and the network side device receives the first information, where the first information includes: an AI service identity and indication information for indicating AI quality of service requirements.

For example, the service requested by the target device is environment perception, such as perception of lane lines, static objects, dynamic objects and the like, or the service requested by the target device is path planning, such as providing a track, including a plurality of track point identifiers, wherein each track point identifier corresponds to a distance and a speed; the target device is, for example, a vehicle-mounted terminal, the safety requirement can be represented by the cost calculated through the distance between the vehicle and an obstacle, the comfort requirement can be represented by the cost calculated through parameters such as the deviation of the direction of the path traveled by the vehicle, the acceleration and the like, the efficiency requirement is used for representing the efficiency of the target device to complete the task, for example, the cost calculated through parameters such as the path traveling time length, the deviation from the ideal barrier-free path, whether the road boundary is exceeded or not, the time delay requirement is used for representing the time difference between the initiation of the AI service request by the target device and the acquisition of the service result fed back by the network side device, for example, the time delay requirement is less than 100ms.

Step 102, the network side device feeds back a service result of the first service to the target device based on the AI service identifier and the AI service quality requirement.

Specifically, the network side device provides corresponding services according to the AI service identifier and the AI service quality requirement, that is, obtains a service result of the first service corresponding to the AI service identifier, for example, obtains the service result based on the AI model, for example, iterates output of the AI model according to the AI service quality requirement, obtains a service result with better service quality, and feeds back the service result to the target device.

In the method of the embodiment, a network side device receives first information from a target device, wherein the first information comprises an AI service identifier of a first service and indication information for indicating an AI service quality requirement; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements; safety requirements are used to characterize the anti-collision capabilities of the target device; comfort requirements are used to characterize the ride comfort of the target device; the efficiency requirement is used for representing the efficiency of the target equipment to finish the task; the time delay requirement is used for representing the time difference between the initiation of the AI service request by the target equipment and the acquisition of the service result; further, the network side device obtains the service result of the first service based on the AI service identifier and the AI service quality requirement, and feeds back the service result to the target device, that is, the network side device can provide service for the target device based on the AI service quality requirement, so that the AI service quality can be improved, and the AI service can be better supported in the mobile communication system.

Optionally, the network side device acquires information for determining a quality evaluation mode; the information for determining the quality assessment mode includes: executable files and running information corresponding to the quality evaluation mode; the quality evaluation mode is used for evaluating the quality of the service result.

Optionally, the operation information includes at least one of:

The running environment configuration information, file names, input formats, output formats, information indicating a preprocessing mode, and information indicating a post-processing mode.

Optionally, the network side device acquires information for determining a quality evaluation mode, including at least one of the following:

The network side equipment receives information from the target equipment, wherein the information is used for determining a quality evaluation mode;

The network side equipment receives a third party link from the target equipment and acquires information for determining a quality evaluation mode based on the third party link;

The network side device receives an application programming interface (Application Programming Interface, API) from the target device and obtains information for determining a quality assessment mode based on the API.

Specifically, the target device may directly send the information for determining the quality assessment mode to the network side device, or send the information for determining the quality assessment mode to the network side device through a third party link, or send the information for determining the quality assessment mode to the network side device through an API, where the network side device directly obtains the information for determining the quality assessment mode from the received information, or obtains the information for determining the quality assessment mode based on the third party link or the API.

Optionally, the network side device may evaluate the service result based on the information for determining the quality evaluation manner, and obtain an evaluation result.

For example, the provided services may also be optimized based on the evaluation results and the quality of service requirements, such as optimizing AI models.

Optionally, in the case that the AI quality of service requirement includes a security requirement, the first information includes a security requirement indicator threshold and first parameter information for evaluating the security quality; wherein the first parameter information includes at least one of:

The first indication information, the second information and the first weighting information;

wherein the first indication information is used for indicating at least one first target parameter item included in the security quality assessment; the first weighting information comprises a weighting value of each first target parameter item; the second information is the function mapping information of the first target parameter items and the safety cost or the corresponding relation between the first distance and the safety level;

the first target parameter item includes at least one of:

A first distance, a first guard interval threshold, and a second guard interval threshold;

Wherein the first distance is a distance of the target device from the obstacle; the first guard interval threshold is used to represent the guard interval lower limit of the highest security level, and the second guard interval threshold is used to represent the guard interval lower limit of the lowest security level.

In particular, the function mapping information is for example used to indicate an identification of the security cost function corresponding to the first target parameter item, or the content of the security cost function.

When the first distance is greater than the guard interval first threshold, the security level belongs to the highest level. When the first distance is smaller than the second threshold of the guard interval, a safety accident occurs, and the service quality requirement is not met.

For example, evaluating the security quality, i.e. calculating the security cost, may be achieved by a first distance, a first guard interval threshold, a second guard interval threshold, a correspondence of the first distance to the security level, etc.

Optionally, the greater the first distance, the higher the security level when the first distance is between the first guard interval threshold and the second guard interval threshold.

For example, a larger value of the security level indicates higher security; or, the smaller the value of the security level, the higher the security.

In the case where the smaller the value of the security level is, the higher the security is, the security level is a monotonically decreasing function of the first distance when the first distance is between the first threshold and the second threshold.

Optionally, the network side device determines the first distance according to at least one of the following information;

The at least one item of information comprises: the size of the target device, the heading angle, the location of the target device, and the obstacle boundary.

Specifically, the target device is, for example, a vehicle, and the heading angle is that of the vehicle.

Illustratively, the first distance is a distance between a boundary of the drone and a boundary of the obstacle, taking the drone as an example. For example, the unmanned vehicle boundary is represented by a three-dimensional cuboid covering the unmanned vehicle. Similarly, the boundary of the obstacle is also represented by a three-dimensional cuboid covering the obstacle.

The first protection interval threshold is 10 meters, which means that the safety cost is 0 when the first distance is greater than or equal to 10 meters;

The second guard interval threshold is 0.1 meters, indicating that the planned trajectory is not valid when the first distance is less than 0.1 meters. The safety cost is minus infinity.

The function of the security cost is identified as 4, and when the first distance is greater than or equal to 0.1 meter and less than 10 meters, the function exp (-d/10), d is selected as the first distance to calculate the security cost, as shown in Table 1 below:

TABLE 1

Function identification	Function of safety cost corresponding to first distance
		1	exp(-d/2)
2	exp(-d/4)
		3	exp(-d/8)
4	exp(-d/10)

Optionally, in the case that the AI quality of service requirement includes a comfort requirement, the first information includes a comfort requirement indicator threshold and second parameter information for evaluating comfort quality; wherein the second parameter information includes at least one of:

second indication information, third information and second weighting information;

The second indication information is used for indicating at least one second target parameter item included in comfort quality assessment, and the third information is information of comfort cost functions corresponding to the second target parameter items; the second weighting information comprises the weighting value of each second target parameter item; the second target parameter item includes at least one of:

The direction deviation of the path, the course angle of the path, the curvature derivative of the path, the curvature change rate of the path, the acceleration and the jerk.

Specifically, the second indication information is used to indicate included target parameter items for comfort quality assessment, for example, the following parameters are considered in comfort quality assessment: the deviation of the orientation, heading angle, curvature of the path.

Illustratively, the first information includes information of a direction deviation cost function (e.g., direction deviation cost function identification), information of a curvature cost function of the path (function identification), and information of a curvature change rate cost function (function identification). The cost functions of the three are agreed in advance. The weighting values of the three are also agreed in advance. If the weighted values of the three are different from the preset value, the weighted values can also be carried in the first information, namely, indicated by the first information.

For example, comfort assessment considers parameters: deviation of the orientation of the path, curvature of the path, rate of change of curvature;

assuming a total planned duration of 15 seconds and a time interval of 1 second, this path includes 15 trajectory points planned.

The direction deviation of the path is the first derivative of the path, and the direction deviation cost is calculated by squaring the first derivative of the path in each time interval; the values of 15 time intervals are then accumulated. The calculation method may be predefined or may be included in the direction deviation cost function information of the second information.

The curvature of the path is the second derivative of the path, and the curvature cost of the path is calculated by squaring the second derivative of the path in each time interval; the values of 15 time intervals are then accumulated.

The curvature change rate is the third derivative of the path, and the curvature change rate cost is calculated by squaring the third derivative of the path in each time interval; the values of 15 time intervals are then accumulated.

The weighted values of the direction deviation cost, the curvature cost of the path and the curvature change rate cost are w1, w2 and w3 respectively.

The overall cost of comfort is:

w1×direction deviation cost+w2×curvature cost+w3×curvature change rate cost of the path.

Optionally, in the case that the AI quality of service requirement includes the high efficiency requirement, the first information includes the high efficiency requirement index threshold and third parameter information for evaluating high efficiency quality; wherein the third parameter information includes at least one of:

the third indication information, the fourth information and the third weighted value;

The third indication information is used for indicating at least one third target parameter item included in the efficient quality evaluation, and the fourth information is information of an efficient cost function corresponding to each third target parameter item; the third weighting information comprises weighting values of the third target parameter items; the third target parameter item includes at least one of:

deviation from the lane center line, deviation from an ideal barrier-free path, penalty values exceeding the road boundary, path travel duration, path travel distance.

Specifically, the third indication information is used to indicate included target parameter items for efficient quality assessment, for example, the following parameters are considered in efficient quality assessment: deviation from the lane center line, path travel time length, path travel distance, penalty value exceeding the road boundary. Illustratively, the first information includes the following items:

Deviation cost function information with the lane center line; (penalty function representing deviation from ideal barrier-free path is contracted in advance.)

A penalty value of 100 exceeding the road boundary; (meaning that the value is different from or not agreed in advance)

Path travel duration cost function information; (indicating that the calculation method has been contracted in advance)

The deviation cost with the lane center line, the penalty value exceeding the road boundary and the weighted value of the path driving time length cost are respectively w1, w2 and w3.

Assuming that the total planned duration is 15 seconds and the time interval is 1 second, this path includes 15 trajectory points planned.

The calculation method of the deviation cost between the planned path and the ideal barrier-free path comprises the steps of squaring the difference between the planned path and the ideal barrier-free path in each time interval; the values of 15 time intervals are then accumulated. The calculation method may be predefined or may be included in the direction deviation cost function information of the third information.

The calculation method of the path driving duration cost is 1/(1+second distance), wherein the second distance is the total driving distance of the planned path. The calculation method may be predefined or may be included in the direction deviation cost function information of the third information.

The total cost of the efficiency requirement is:

w1×from ideal barrier-free path offset cost +w2×100+w3×1/(1+second distance).

Optionally, the AI quality of service requirements further include:

Indication information for indicating the type of qos requirements, and a combination of qos requirements for each type, the combination comprising at least one of:

Weighting function information combined by parameter items included in each type of service quality requirement;

the quality of service requirements of each type include a weighted value of the parameter term.

Specifically, the weighting function information includes, for example: the identity of the weighting function or the content of the weighting function, such as the weighting function corresponding to the safety requirement, the comfort requirement, the high efficiency requirement and the time delay requirement respectively, and the weighting value corresponding to a plurality of parameters in each type can acquire the service quality requirement of each type.

Optionally, the integrated quality of service requirement is determined by the first information, including at least one of:

Directly obtaining based on the first information;

and obtaining the AI service quality requirement based on the first information and obtaining the AI service quality requirement based on the AI service quality requirement.

Specifically, the integrated quality of service requirement may be directly obtained from the first information, for example, the first information includes the content of the integrated quality of service requirement directly, or includes the content of calculating the integrated quality of service requirement; or, the AI quality of service requirement is obtained from the first information, and then the AI quality of service requirement is obtained based on the AI quality of service requirement, for example, the first information includes a plurality of quality of service requirements, and the comprehensive quality of service requirement is obtained from the plurality of quality of service requirements.

Optionally, in the case where the integrated quality of service requirement is determined by the first information, the first information further comprises at least one of:

the service quality level is synthesized;

a comprehensive service quality threshold;

Weight of each service quality;

weighting method for each service quality.

Optionally, the correspondence between the qos classes and the qos classes is integrated, for example, as shown in table 2:

TABLE 2

Comprehensive quality of service class	Comfort level	Safety of	High efficiency	Time delay
					1	1	1	1	1
2	1	1	2	1
					3	2	1	2	1
4	3	1	2	1

Optionally, the correspondence between the qos class and each qos value (qos value is represented by a cost or a delay), for example, as shown in table 3:

TABLE 3 Table 3

The integrated quality of service value may be mapped from various quality of service values, for example. For example, quality requirement indicators involved include safety, efficiency, comfort, and time delay.

Optionally, the comprehensive quality value is calculated as follows:

Integrated quality of service value = a1×security quality of service value + a2×high efficiency quality of service value + a3×comfort quality of service value data + a4×latency. Wherein a1, a2, a3 and a4 are four weighted values, respectively.

Optionally, the correspondence between the qos level and the comfort cost is integrated, for example, as shown in table 4:

TABLE 4 Table 4

Comprehensive quality of service class	Cost of comfort
		1	Less than or equal to 20
2	Greater than 20 and less than or equal to 50
		3	Greater than 50 and less than or equal to 100

Optionally, the correspondence between the qos class and the security cost is integrated, for example, as shown in table 5: TABLE 5

Comprehensive quality of service class	Cost of collision prevention
		1	Less than or equal to 5
2	More than 5 and less than or equal to 10
		3	More than 10 and less than or equal to 20

Optionally, the correspondence between the qos class and the efficiency cost is integrated, for example, as shown in table 6:

TABLE 6

Comprehensive quality of service class	Cost of high efficiency
		1	Less than or equal to 10
2	More than 10 and less than or equal to 50
		3	Greater than 50 and less than or equal to 100

Optionally, the correspondence between the qos class and the delay is integrated, for example, as shown in table 7:

TABLE 7

Comprehensive quality of service class	Time delay
		1	Less than or equal to 100ms
2	Greater than 100ms and less than or equal to 150
		3	Greater than 150ms and less than or equal to 200

Optionally, the AI quality of service requirement is represented by at least one of:

Quality class, quality requirement index threshold; the quality requirement indicator threshold comprises at least one of the following: safety requirement index threshold, comfort requirement index threshold, high efficiency requirement index threshold and time delay requirement index threshold.

Optionally, the AI quality of service requirements further include at least one of the following types of requirements:

the speed maintenance cost;

Path monotonicity;

An upper target device speed limit;

Total duration of path planning;

Time intervals of path planning;

Wherein the speed maintenance cost is obtained based on a difference between a running speed included in the service result and a target running speed, the target running speed being determined by the second information; the second information includes at least one of: curvature of the path, traffic rules;

Path monotonicity refers to that the distance between a target device and a path starting point in a path planned at one time is monotonically increasing, or the distance between the target device and a path ending point is monotonically decreasing;

The target device speed upper limit is derived based on traffic rules and/or target device dynamics.

Specifically, the speed maintenance cost may be obtained by calculating a running speed by the network side device, and a difference between the running speed and the target running speed may be obtained, and deviation from the target running speed may be punished. The target travel speed is determined by the curvature of the path, traffic rules, etc., e.g., based on road speed limits, curvature, and other traffic rules, etc. The speed maintenance cost, the path monotonicity, the upper limit of the speed of the target device and the like can be used for the network side device to provide service for the target device, and the information is used as input data of an AI model of the network side device, so that the service quality can be improved.

Optionally, the first information further includes: information for calculating a speed maintenance cost, the information for calculating a speed maintenance cost including at least one of:

deviation speed penalty function indication information;

Penalty times for the speed of deviation.

Optionally, the deviation velocity penalty function indication information is, for example, a specific content of the deviation velocity penalty function, or a function identification. The penalty multiple may maintain a weight of the cost for computing speed. For example, the deviation speed penalty function is f, which is a function of the difference between the travel speed included in the service result and the target travel speed, and the speed maintenance cost is f (deviation speed), or the penalty multiple is a _p, and the speed maintenance cost is a _p ×deviation speed.

Optionally, the first information further includes at least one of the following:

The size of the target device;

the location of the target device;

Sensing results of surrounding objects by the target equipment; the perceived result includes a perceived result of at least one of: type, distance, velocity, acceleration, boundary;

The target device perceives the original data of surrounding objects.

Specifically, the target device is, for example, a vehicle, and the network side device can be assisted to perform reasoning or calculation of the AI model through the size of the target device, the position of the target device, the original perception data, the perception result and the like included in the first information, so that the service quality provided by the network side device is improved.

Optionally, the method further comprises:

The network side equipment determines sixth information based on the first information and the information of the quality evaluation mode, wherein the sixth information comprises at least one of the following items: quality requirement index, quality requirement index calculation method, quality requirement index input data and format, and quality requirement index threshold.

Specifically, the quality requirement index includes, for example, at least one of: the service result can be obtained based on the sixth information to provide service for the target device. Or based on the sixth information, the evaluation result may also be acquired.

Optionally, the method further comprises:

The network side equipment determines a first evaluation result of the service result based on the sixth information and the service result;

And the network side equipment sends a first evaluation result of the service result to the target equipment.

Specifically, after the network side device obtains the service result, the service result may be sent to the target device, optionally, a first evaluation result of the service result may also be sent to the target device, for example, the target device may screen the service result based on the first evaluation result, select a service result meeting the requirement, and execute a corresponding task based on the service result.

Optionally, the target device may further send a second evaluation result of the service result to the network side device, where the network side device receives the second evaluation result sent by the target device, and the second evaluation result is an evaluation result of the service result by the target device.

The second evaluation result may be used for a service provided by the network side device optimization, for example, the network side device may optimize the AI model based on the second evaluation result fed back by the target device.

Optionally, the first evaluation result or the second evaluation result includes at least one of:

AI service identification;

Service grades corresponding to the AI service identifiers;

The AI service identifier corresponds to the service quality value;

Synthesizing the quality of service value;

and integrating the service quality grades.

Specifically, for example, the AI service identifier indicates that the current service is perceived by the environment, and the current evaluation result is that the service level of the service result perceived by the environment is 5 levels, for example, the service level in the service quality requirement is 4 levels, the smaller the value is, the higher the level is, which indicates that the provided service result does not meet the service quality requirement, and the optimization needs to be performed again. Other parameters are similar.

Alternatively, step 102 may be implemented as follows:

The network side equipment determines algorithm information for providing the service based on the AI service identification and the seventh information; the seventh information includes at least one of: AI quality of service requirements, comprehensive quality of service requirements;

The network side equipment feeds back a service result to the target equipment based on the AI service identification and the algorithm information.

Specifically, the network side device determines algorithm information for providing the service based on the AI service identification and the seventh information, performs a service algorithm (e.g., AI model reasoning) based on the algorithm information, acquires a service result, and feeds back the service result to the target device.

Optionally, in the case that the AI service provided is a training service, the algorithm information includes a trained reward function;

in the case where the provided AI service is an inference service, the algorithm information includes an inference model.

Optionally, the method further comprises:

The network side equipment determines a first evaluation result of the service result corresponding to the reasoning service based on the AI service identification, the service result corresponding to the reasoning service and the comprehensive service quality requirement.

The service results corresponding to the inference service include, for example: the speed, the path and the like in the preset time range of the target equipment, the comprehensive service quality requirement comprises the requirement of the comprehensive service quality grade, the speed and the target running speed are utilized to calculate the speed maintenance cost, and the comprehensive service quality grade of the service result can be determined based on the speed maintenance cost, for example, the smaller the speed maintenance cost is, the higher the comprehensive service quality grade is, the comprehensive service quality grade corresponding to the speed maintenance cost is assumed to be 3, but the requirement of the comprehensive service quality grade is 5, and the larger the numerical value of the assumed security grade is, the higher the grade is, so that the comprehensive service quality requirement is not met.

Illustratively, the target device is a vehicle, the network-side device is a base station, and the current service is a track planning service.

The quality of service requirements have been predefined without additional indication. Can be obtained directly from the service identity.

As shown in fig. 3, the method comprises the steps of:

Step 1: the vehicle sends a service identification to the base station, the service identification being used to indicate the path planning service.

Step 2: and the base station acquires sixth information according to the service identifier. The sixth information includes at least one of: quality requirement index, quality requirement index calculation method, quality requirement index input data and format, quality requirement index threshold.

For example, determining quality requirement metrics includes safety, comfort, efficiency, and latency.

The quality requirement index calculating method has the advantages that the quality requirement index input data and the format are predefined.

The quality requirement indicator threshold is an integrated quality of service threshold, e.g., a threshold of 10. When the threshold is less than 10, the quality of service requirement is met.

Step 3: based on the service identification, a service algorithm is determined. And executing a service algorithm (such as AI model reasoning), acquiring a service result, and verifying whether the service result meets the service requirement based on a quality requirement index calculation method. Or selecting a service result with the highest service quality.

Step 4: and feeding back a service result and an evaluation result. The evaluation result may be an integrated quality of service value, or a grade.

Optionally, the network side device determines the comprehensive service quality requirement according to the first information, and further determines a service algorithm.

In this case, the quality requirement index calculation method, and the quality requirement index input data and format are both predefined.

For example, the quality requirement indicators include: comfort, efficiency, safety and latency

The quality requirement index calculating method is characterized in that the quality requirement index input data and the format are predefined. As shown in table 8:

TABLE 8

In the above embodiment, by providing the AI quality of service requirements, the network side device may obtain more complete and richer information, thereby improving the quality of service, and the target device may provide more flexible services for the target device by enjoying the services provided by the network side device, reducing the complexity of the device itself, and further, the network side device may identify different AI quality of service requirements.

Fig. 4 is a second flowchart of a processing method of AI services according to an embodiment of the present application. As shown in fig. 3 and 4, the method provided in this embodiment includes:

Step 201, the target device sends first information to the network side device, wherein the first information comprises an AI service identifier of the first service and indication information for indicating AI service quality requirements; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements;

Wherein the security requirement is used to characterize the anti-collision capability of the target device; the comfort requirement is used to characterize the ride comfort of the target device; the high efficiency requirement is used for representing the efficiency of the target equipment to complete tasks; the time delay requirement is used for representing the time difference between the target equipment initiating the AI service request and acquiring the service result;

step 202, the target device receives a service result of the first service sent by the network side device.

Optionally, the indication information indicates the AI quality of service requirement by at least one of:

quality class, quality requirement index threshold; wherein the quality requirement indicator threshold comprises at least one of: safety requirement index threshold, comfort requirement index threshold, high efficiency requirement index threshold and time delay requirement index threshold.

Optionally, the method further comprises:

The target equipment sends information for determining a quality evaluation mode to the network equipment; the quality evaluation mode is used for evaluating the quality of the service result; the information for determining the quality assessment mode comprises: executable files and running information corresponding to the quality evaluation mode.

Optionally, the operation information includes at least one of:

Optionally, the target device sends information of a quality evaluation mode to the network side device, including at least one of the following:

The target equipment sends a third party link to the network side equipment, wherein the third party link is used for acquiring the information for determining the quality evaluation mode;

and the target equipment sends an Application Programming Interface (API) to the network side equipment, wherein the API is used for acquiring the information for determining the quality evaluation mode.

Optionally, in the case that the AI quality of service requirement includes the security requirement, the first information includes the security requirement indicator threshold and first parameter information for evaluating security quality; wherein the first parameter information includes at least one of:

wherein the first indication information is used for indicating at least one first target parameter item included in the comfort quality assessment; the first weighting information comprises a weighting value of each first target parameter item;

the first target parameter item includes at least one of:

Wherein the first distance is a distance of the target device from an obstacle; the first guard interval threshold is used for representing the guard interval lower limit of the highest security level, and the second guard interval threshold is used for representing the guard interval lower limit of the lowest security level;

The second information is the function mapping information of the first target parameter item and the security cost or the corresponding relation between the first distance and the security level.

Optionally, when the first distance is between the first guard interval threshold and the second guard interval threshold, the higher the security level, the greater the first distance.

Optionally, the first distance is determined based on at least one of the following information;

The at least one item of information includes: the size of the target device, the heading angle, the location of the target device, and the obstacle boundary.

Optionally, in the case that the AI quality of service requirement includes the comfort requirement, the first information includes the comfort requirement indicator threshold and second parameter information for evaluating comfort quality; wherein the second parameter information includes at least one of:

The second indication information is used for indicating at least one second target parameter item included in comfort quality assessment, and the third information is information of comfort cost functions corresponding to the second target parameter items; the second weighting information comprises weighting values of the second target parameter items; the second target parameter item includes at least one of:

Optionally, in the case that the AI quality of service requirement includes the high efficiency requirement, the first information includes the high efficiency requirement indicator threshold and third parameter information for evaluating high efficiency quality; wherein the third parameter information includes at least one of:

third indication information, fourth information and third weighting information;

the speed maintenance cost;

Path monotonicity;

An upper target device speed limit;

Total duration of path planning;

Time intervals of path planning;

Wherein the speed maintenance cost is obtained based on a difference between a running speed included in the service result and a target running speed determined by the fifth information; the fifth information includes at least one of: curvature of the path, traffic rules;

Path monotonicity means that the distance between the target device and the path start point or the distance between the target device and the path end point in a path planned at one time is monotonically increasing;

deviation speed penalty function information;

Penalty times for the speed of deviation.

Optionally, the AI quality of service requirement further includes indication information for indicating a type of quality of service requirement, and a merging manner of the quality of service requirements of each type, where the merging manner includes at least one of the following:

The size of the target device;

the location of the target device;

The target device perceives the original data of surrounding objects.

Optionally, the method further comprises:

The target equipment receives a first evaluation result of the service result sent by the network side equipment; a first evaluation result of the service result is determined based on the sixth information and the service result; the sixth information includes at least one of: quality requirement index, quality requirement index calculation method, quality requirement index input data and format, and quality requirement index threshold.

Optionally, the method further comprises:

the target equipment sends a second evaluation result to the network side equipment, wherein the second evaluation result is an evaluation result of the service result evaluated by the target equipment.

AI service identification;

Service grades corresponding to the AI service identifiers;

The AI service identifier corresponds to the service quality value;

Synthesizing the quality of service value;

and integrating the service quality grades.

directly obtaining based on the first information;

And obtaining the AI service quality requirement based on the first information, and obtaining the AI service quality requirement based on the AI service quality requirement.

Optionally, in the case that the integrated quality of service requirement is determined by the first information, the first information further comprises at least one of:

the service quality level is synthesized;

a comprehensive service quality threshold;

Weight of each service quality;

weighting method for each service quality.

The specific implementation process and technical effects of the method of the present embodiment are similar to those of the network side method embodiment, and specific reference may be made to the detailed description of the terminal side method embodiment, which is not repeated herein.

According to the AI service processing method provided by the embodiment of the application, the execution main body can be the AI service processing device. In the embodiment of the present application, a processing method for executing an AI service by an AI service processing device is taken as an example, and the AI service processing device provided in the embodiment of the present application is described.

Fig. 5 is a schematic structural diagram of a processing device for AI services according to the present application. As shown in fig. 5, the processing apparatus for AI services provided in this embodiment includes:

A receiving module 210, configured to receive first information from a target device, where the first information includes an AI service identifier of a first service and indication information for indicating an AI quality of service requirement; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements; the security requirement is used to characterize the anti-collision capability of the target device; the comfort requirement is used to characterize the ride comfort of the target device; the high efficiency requirement is used for representing the efficiency of the target equipment to complete tasks; the time delay requirement is used for representing the time difference between the target equipment initiating the AI service request and acquiring the service result;

And the processing module 220 is configured to feed back a service result of the first service to the target device based on the AI service identifier and AI service quality requirement.

Optionally, the receiving module 210 is further configured to:

Acquiring information for determining a quality evaluation mode; the quality evaluation mode is used for evaluating the quality of the service result; the information for determining the quality assessment mode comprises: executable files and running information corresponding to the quality evaluation mode.

Optionally, the operation information includes at least one of:

Optionally, the receiving module 210 is specifically configured to perform at least one of the following:

receiving the information for determining the quality assessment mode from the target equipment;

receiving a third-party link from the target equipment, and acquiring the information for determining the quality evaluation mode based on the third-party link;

And receiving an Application Programming Interface (API) from the target equipment, and acquiring the information for determining the quality evaluation mode based on the API.

the first target parameter item includes at least one of:

Optionally, the processing module 220 is further configured to:

Determining the first distance according to at least one of the following information;

Optionally, in the case that the AI quality of service requirement includes the high efficiency requirement, the first information includes the high efficiency requirement indicator threshold and third parameter information for high efficiency quality assessment; wherein the third parameter information includes at least one of:

the speed maintenance cost;

Path monotonicity;

An upper target device speed limit;

Total duration of path planning;

Time intervals of path planning;

deviation speed penalty function information;

Penalty times for the speed of deviation.

Optionally, the AI quality of service requirement further includes: indication information for indicating the type of qos requirements, and a combination of qos requirements for each type, the combination comprising at least one of:

The size of the target device;

the location of the target device;

The target device perceives the original data of surrounding objects.

Optionally, the processing module 220 is further configured to:

Determining third information based on the first information and information of the quality assessment mode, or based on the first information, wherein the third information comprises at least one of the following: quality requirement index, quality requirement index calculation method, quality requirement index input data and format, and quality requirement index threshold.

Optionally, the processing module 220 is further configured to:

Determining a first evaluation result of the service result based on the third information and the service result;

Optionally, the receiving module 210 is further configured to:

And receiving a second evaluation result sent by the target equipment, wherein the second evaluation result is an evaluation result of the service result evaluated by the target equipment.

AI service identification;

Service grades corresponding to the AI service identifiers;

The AI service identifier corresponds to the service quality value;

Synthesizing the quality of service value;

and integrating the service quality grades.

Optionally, the processing module 220 is specifically configured to:

Determining algorithm information for providing services based on the AI service identification and fourth information; the fourth information includes at least one of: AI quality of service requirements, comprehensive quality of service requirements;

And feeding back the service result to target equipment based on the AI service identification and the algorithm information.

Optionally, in the case that the provided AI service is a training service, the algorithm information includes a trained reward function;

Optionally, the processing module 220 is further configured to:

and determining a first evaluation result of the service result corresponding to the reasoning service based on the AI service identification, the service result corresponding to the reasoning service and the comprehensive service quality requirement.

directly obtaining based on the first information;

the service quality level is synthesized;

a comprehensive service quality threshold;

Weight of each service quality;

weighting method for each service quality.

The apparatus of the present embodiment may be used to execute the method of any one of the foregoing network side method embodiments, and specific implementation processes and technical effects of the apparatus are similar to those of the network side method embodiment, and specific details of the network side method embodiment may be referred to in the detailed description of the network side method embodiment and are not repeated herein.

Fig. 6 is a second schematic structural diagram of the AI service processing device provided by the present application. As shown in fig. 6, the processing apparatus for AI services provided in this embodiment includes:

A sending module 310, configured to send first information to a network side device, where the first information includes an AI service identifier of a first service and indication information for indicating an AI service quality requirement; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements; the security requirement is used to characterize the anti-collision capability of the target device; the comfort requirement is used to characterize the ride comfort of the target device; the high efficiency requirement is used for representing the efficiency of the target equipment to complete tasks; the time delay requirement is used for representing the time difference between the target equipment initiating the AI service request and acquiring the service result;

and the receiving module 320 is configured to receive a service result of the first service sent by the network side device.

Optionally, the sending module 310 is further configured to:

Transmitting information for determining a quality evaluation mode to the network side equipment; the quality evaluation mode is used for evaluating the quality of the service result; the information for determining the quality assessment mode comprises: executable files and running information corresponding to the quality evaluation mode.

Optionally, the operation information includes at least one of:

Optionally, the sending module 310 is specifically configured to perform at least one of the following:

a third party link is sent to the network side equipment, and the third party link is used for acquiring the information for determining the quality evaluation mode;

And sending an Application Programming Interface (API) to the network side equipment, wherein the API is used for acquiring the information for determining the quality evaluation mode.

the first target parameter item includes at least one of:

the speed maintenance cost;

Path monotonicity;

An upper target device speed limit;

Total duration of path planning;

Time intervals of path planning;

deviation speed penalty function information;

Penalty times for the speed of deviation.

The size of the target device;

the location of the target device;

The target device perceives the original data of surrounding objects.

Optionally, the receiving module 320 is further configured to:

Receiving a first evaluation result of the service result sent by the network side equipment; a first evaluation result of the service result is determined based on the sixth information and the service result; the sixth information includes at least one of: quality requirement index, quality requirement index calculation method, quality requirement index input data and format, and quality requirement index threshold.

Optionally, the sending module 310 is further configured to:

And sending a second evaluation result to the network side equipment, wherein the second evaluation result is an evaluation result of the target equipment for evaluating the service result.

AI service identification;

Service grades corresponding to the AI service identifiers;

The AI service identifier corresponds to the service quality value;

Synthesizing the quality of service value;

and integrating the service quality grades.

directly obtaining based on the first information;

the service quality level is synthesized;

a comprehensive service quality threshold;

Weight of each service quality;

weighting method for each service quality.

The apparatus of this embodiment may be used to execute the method of any one of the foregoing target device side method embodiments, and the specific implementation process and technical effects of the apparatus of this embodiment are similar to those of the target device side method embodiment, and specific reference may be made to the detailed description of the target device side method embodiment, which is not repeated herein.

The processing device of the AI service in the embodiment of the application may be an electronic device, for example, an electronic device with an operating system, or may be a component in the electronic device, for example, an integrated circuit or a chip. The electronic device may be a terminal, or may be other devices than a terminal. By way of example, the terminals may include, but are not limited to, the types of terminals 11 listed above, other devices may be servers, network attached storage (Network Attached Storage, NAS), etc., and embodiments of the present application are not limited in detail.

The processing device for AI service provided by the embodiment of the present application can implement each process implemented by the embodiments of the methods of fig. 2 to fig. 4, and achieve the same technical effects, and for avoiding repetition, a detailed description is omitted here.

Optionally, as shown in fig. 7, the embodiment of the present application further provides a communication device 700, including a processor 701 and a memory 702, where the memory 702 stores a program or an instruction that can be executed on the processor 701, for example, when the communication device 700 is a target device, the program or the instruction implements the steps of the processing method embodiment of the AI service when executed by the processor 701, and the same technical effects can be achieved. When the communication device 700 is a network side device, the program or the instruction implements the steps of the processing method embodiment of the AI service when executed by the processor 701, and the same technical effects can be achieved, so that repetition is avoided, and no further description is given here.

The embodiment of the application also provides target equipment, which comprises a processor and a communication interface, wherein the communication interface is used for sending first information to the network side equipment, and the first information comprises an AI service identifier of a first service and indication information for indicating AI service quality requirements; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements; the security requirement is used to characterize the anti-collision capability of the target device; the comfort requirement is used to characterize the ride comfort of the target device; the high efficiency requirement is used for representing the efficiency of the target equipment to complete tasks; the time delay requirement is used for representing the time difference between the target equipment initiating the AI service request and acquiring the service result; the communication interface is further configured to receive a service result of the first service sent by the network side device. The target device embodiment corresponds to the target device side method embodiment, and each implementation process and implementation manner of the method embodiment can be applied to the terminal embodiment, and the same technical effects can be achieved. Specifically, fig. 8 is a schematic hardware structure of a terminal for implementing an embodiment of the present application.

The terminal 1000 includes, but is not limited to: at least some of the components of the radio frequency unit 1001, the network module 1002, the audio output unit 1003, the input unit 1004, the sensor 1005, the display unit 1006, the user input unit 1007, the interface unit 1008, the memory 1009, and the processor 1010, etc.

Those skilled in the art will appreciate that terminal 1000 can also include a power source (e.g., a battery) for powering the various components, which can be logically connected to processor 1010 by a power management system so as to perform functions such as managing charge, discharge, and power consumption by the power management system. The terminal structure shown in fig. 8 does not constitute a limitation of the terminal, and the terminal may include more or less components than shown, or may combine certain components, or may be arranged in different components, which will not be described in detail herein.

It should be appreciated that in embodiments of the present application, the input unit 1004 may include a graphics processing unit (Graphics Processing Unit, GPU) 10041 and a microphone 10042, where the graphics processor 10041 processes image data of still pictures or video obtained by an image capturing device (e.g., a camera) in a video capturing mode or an image capturing mode. The display unit 1006 may include a display panel 10061, and the display panel 10061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 1007 includes at least one of a touch panel 10071 and other input devices 10072. The touch panel 10071 is also referred to as a touch screen. The touch panel 10071 can include two portions, a touch detection device and a touch controller. Other input devices 10072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and so forth, which are not described in detail herein.

In the embodiment of the present application, after receiving downlink data from the network side device, the radio frequency unit 1001 may transmit the downlink data to the processor 1010 for processing; in addition, the radio frequency unit 1001 may send uplink data to the network side device. In general, the radio frequency unit 1001 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like.

The memory 1009 may be used to store software programs or instructions and various data. The memory 1009 may mainly include a first storage area storing programs or instructions, which may store an operating system, application programs or instructions (such as a sound playing function, an image playing function, etc.) required for at least one function, and a second storage area storing data. Further, the memory 1009 may include volatile memory or nonvolatile memory, or the memory 1009 may include both volatile and nonvolatile memory. Including high-speed random access Memory, and may also include non-volatile Memory, where the non-volatile Memory may be Read-Only Memory (ROM), programmable ROM (PROM), erasable Programmable ROM (EPROM), electrically Erasable Programmable EPROM (EEPROM), or flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM), static random access memory (STATIC RAM, SRAM), dynamic random access memory (DYNAMIC RAM, DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate Synchronous dynamic random access memory (Double DATA RATE SDRAM, DDRSDRAM), enhanced Synchronous dynamic random access memory (ENHANCED SDRAM, ESDRAM), synchronous link dynamic random access memory (SYNCH LINK DRAM, SLDRAM), and Direct random access memory (DRRAM). The memory 1009 in embodiments of the application includes, but is not limited to, these and any other suitable types of memory such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device.

The processor 1010 may include one or more processing units; alternatively, the processor 1010 may integrate an application processor that primarily processes operations involving an operating system, a user interface, and applications or instructions, and a modem processor that primarily processes wireless communication signals, such as a baseband processor. It will be appreciated that the modem processor described above may not be integrated into the processor 1010.

The radio frequency unit 1001 is configured to send first information to a network side device, where the first information includes an AI service identifier of a first service and indication information for indicating an AI service quality requirement; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements; the security requirement is used to characterize the anti-collision capability of the target device; the comfort requirement is used to characterize the ride comfort of the target device; the high efficiency requirement is used for representing the efficiency of the target equipment to complete tasks; the time delay requirement is used for representing the time difference between the target equipment initiating the AI service request and acquiring the service result;

the radio frequency unit 1001 is further configured to receive a service result of the first service sent by the network side device.

Optionally, the radio frequency unit 1001 is further configured to:

Optionally, the operation information includes at least one of:

Optionally, the radio frequency unit 1001 is specifically configured to perform at least one of the following:

the first target parameter item includes at least one of:

the speed maintenance cost;

Path monotonicity;

An upper target device speed limit;

Total duration of path planning;

Time intervals of path planning;

deviation speed penalty function information;

Penalty times for the speed of deviation.

The size of the target device;

the location of the target device;

The target device perceives the original data of surrounding objects.

Optionally, the radio frequency unit 1001 is further configured to:

AI service identification;

Service grades corresponding to the AI service identifiers;

The AI service identifier corresponds to the service quality value;

Synthesizing the quality of service value;

and integrating the service quality grades.

directly obtaining based on the first information;

the service quality level is synthesized;

a comprehensive service quality threshold;

Weight of each service quality;

weighting method for each service quality.

The embodiment of the application also provides network side equipment, which comprises a processor and a communication interface, wherein the communication interface is used for receiving first information from target equipment, and the first information comprises an AI service identifier of first service and indication information for indicating AI service quality requirements; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements; the security requirement is used to characterize the anti-collision capability of the target device; the comfort requirement is used to characterize the ride comfort of the target device; the high efficiency requirement is used for representing the efficiency of the target equipment to complete tasks; the time delay requirement is used for representing the time difference between the target equipment initiating the AI service request and acquiring the service result; the processor is used for feeding back a service result to the target equipment based on the AI service identification and the AI service quality requirement. The network side device embodiment corresponds to the network side device method embodiment, and each implementation process and implementation manner of the method embodiment can be applied to the network side device embodiment, and the same technical effects can be achieved.

Specifically, the embodiment of the application also provides network side equipment. As shown in fig. 9, the network side device 800 includes: an antenna 81, a radio frequency device 82, a baseband device 83, a processor 85 and a memory 85.

The antenna 81 is connected to a radio frequency device 82.

In the uplink direction, the radio frequency device 82 receives information via the antenna 81, and transmits the received information to the baseband device 83 for processing.

In the downlink direction, the baseband device 83 processes information to be transmitted, and transmits the processed information to the radio frequency device 82, and the radio frequency device 82 processes the received information and transmits the processed information through the antenna 81.

The above-mentioned band processing means may be located in the baseband means 83, and the method performed by the access network device in the above embodiment may be implemented in the baseband means 83, which baseband means 83 comprises a baseband processor 85 and a memory 85.

The baseband device 83 may, for example, include at least one baseband board, where a plurality of chips are disposed, as shown in fig. 9, where one chip, for example, a baseband processor 85, is connected to the memory 85 through a bus interface, so as to call a program in the memory 85, and perform the operation of the access network device shown in the foregoing method embodiment.

The access network device 800 may further comprise a network interface 86 for interacting with the radio frequency means 82, such as a common public radio interface (common public radio interface, CPRI for short).

Specifically, the access network device 800 implemented by the present application further includes: instructions or programs stored in the memory 85 and executable on the processor 85, the processor 85 invokes the instructions or programs in the memory 85 to perform the method performed by the module shown in fig. 5, and achieve the same technical effects, so that repetition is avoided and will not be described here.

The embodiment of the application also provides a readable storage medium, on which a program or an instruction is stored, which when executed by a processor, implements each process of the above-mentioned AI service processing method embodiment, and can achieve the same technical effects, so that repetition is avoided, and no further description is given here.

Wherein the processor is a processor in the terminal described in the above embodiment. The readable storage medium includes computer readable storage medium such as computer readable memory ROM, random access memory RAM, magnetic or optical disk, etc.

The embodiment of the application further provides a chip, which comprises a processor and a communication interface, wherein the communication interface is coupled with the processor, and the processor is used for running programs or instructions to realize the processes of the processing method embodiment of the AI service, and the same technical effects can be achieved, so that repetition is avoided, and the description is omitted here.

It should be understood that the chips referred to in the embodiments of the present application may also be referred to as system-on-chip chips, or the like.

The embodiments of the present application further provide a computer program/program product stored in a storage medium, where the computer program/program product is executed by at least one processor to implement each process of the above-mentioned AI service processing method embodiment, and achieve the same technical effects, so that repetition is avoided and details are not repeated herein.

The embodiment of the application also provides a communication system, which comprises: the method comprises a target device and a network side device, wherein the target device can be used for executing the steps of the processing method of the AI service, and the network side device can be used for executing the steps of the processing method of the AI service.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a computer software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.

The embodiments of the present application have been described above with reference to the accompanying drawings, but the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present application and the scope of the claims, which are to be protected by the present application.

Claims

1. A method for processing an artificial intelligence AI service, comprising:

2. The method of claim 1, wherein the step of determining the position of the substrate comprises,

The indication information indicates the AI quality of service requirement by at least one of:

3. The method according to claim 1 or 2, characterized in that the method further comprises at least one of the following:

The network side equipment receives an Application Programming Interface (API) from the target equipment and acquires information for determining a quality evaluation mode based on the API;

The quality evaluation mode is used for evaluating the quality of the service result; the information for determining the quality assessment mode comprises: executable files and running information corresponding to the quality evaluation mode;

The operation information includes at least one of:

4. A method according to claim 1 or 2, characterized in that,

In the case that the AI quality of service requirement includes the security requirement, the first information includes the security requirement indicator threshold and first parameter information for evaluating security quality; wherein the first parameter information includes at least one of:

wherein the first indication information is used for indicating at least one first target parameter item included in the security quality assessment; the first weighting information comprises a weighting value of each first target parameter item;

the first target parameter item includes at least one of:

The second information is the function mapping information of the first target parameter items and the safety cost or the corresponding relation between the first distance and the safety level;

The first distance is determined by at least one of the following information; the at least one item of information includes: the size of the target device, the heading angle, the location of the target device, and the obstacle boundary.

5. A method according to claim 1 or 2, characterized in that,

In the case that the AI quality of service requirement includes the comfort requirement, the first information includes the comfort requirement indicator threshold and second parameter information for evaluating comfort quality; wherein the second parameter information includes at least one of:

6. A method according to claim 1 or 2, characterized in that,

In the case that the AI quality of service requirement includes the high efficiency requirement, the first information includes the high efficiency requirement indicator threshold and third parameter information for evaluating high efficiency quality; wherein the third parameter information includes at least one of:

7. A method according to claim 1 or 2, characterized in that,

The AI quality of service requirements further include at least one of the following types of requirements:

the speed maintenance cost;

Path monotonicity;

An upper target device speed limit;

Total duration of path planning;

Time intervals of path planning;

the upper speed limit of the target equipment is obtained based on traffic rules and/or dynamics of the target equipment;

The first information further includes: information for calculating a speed maintenance cost, the information for calculating a speed maintenance cost including at least one of:

deviation speed penalty function information;

Penalty times for the speed of deviation.

8. The method according to any one of claim 4 to 6, wherein,

The AI quality of service requirements further include: indication information for indicating the type of qos requirements, and a combination of qos requirements for each type, the combination comprising at least one of:

9. A method according to claim 1 or 2, characterized in that,

The first information further includes at least one of the following:

The size of the target device;

the location of the target device;

The target device perceives the original data of surrounding objects.

10. A method according to any one of claims 1-3, wherein the method further comprises:

The network side equipment determines sixth information based on the first information and the information of the quality evaluation mode or based on the first information, wherein the sixth information comprises at least one of the following: quality requirement index, quality requirement index calculation method, quality requirement index input data and format, and quality requirement index threshold.

11. The method according to claim 10, wherein the method further comprises:

the network side equipment sends a first evaluation result of the service result to the target equipment;

the first evaluation result includes at least one of:

AI service identification;

Service grades corresponding to the AI service identifiers;

The AI service identifier corresponds to the service quality value;

Synthesizing the quality of service value;

and integrating the service quality grades.

12. The method according to claim 1 or 2, characterized in that the method further comprises:

The network side equipment receives a second evaluation result sent by the target equipment, wherein the second evaluation result is an evaluation result of the service result evaluated by the target equipment; the second evaluation result includes at least one of:

AI service identification;

Service grades corresponding to the AI service identifiers;

The AI service identifier corresponds to the service quality value;

Synthesizing the quality of service value;

and integrating the service quality grades.

13. A method according to any one of claims 1-3, wherein the network side device feeding back a service result to a target device based on the AI service identification and AI quality of service requirements, comprising:

the network side equipment determines algorithm information for providing service based on the AI service identification and seventh information; the seventh information includes at least one of: AI quality of service requirements, comprehensive quality of service requirements;

and the network side equipment feeds back the service result to the target equipment based on the AI service identification and the algorithm information.

14. The method of claim 13, wherein the integrated quality of service requirement is determined from the first information, comprising at least one of:

directly obtaining based on the first information;

Acquiring an AI service quality requirement based on the first information, and acquiring the AI service quality requirement based on the AI service quality requirement; the first information further includes at least one of:

the service quality level is synthesized;

a comprehensive service quality threshold;

Weight of each service quality;

weighting method for each service quality.

15. A method for processing an artificial intelligence AI service, comprising:

and the target equipment receives the service result of the first service sent by the network side equipment.

16. The method of claim 15, wherein the step of determining the position of the probe is performed,

17. The method according to claim 15 or 16, further comprising at least one of:

The target equipment sends information for determining a quality evaluation mode to the network equipment;

the target equipment sends a third party link to the network side equipment, wherein the third party link is used for acquiring information for determining a quality evaluation mode;

The target device sends an Application Programming Interface (API) to the network side device, wherein the API is used for acquiring information for determining a quality evaluation mode;

The operation information includes at least one of:

18. The method according to claim 15 or 16, wherein,

the first target parameter item includes at least one of:

the first distance is determined based on at least one of the following information; the at least one item of information includes: the size of the target device, the heading angle, the location of the target device, and the obstacle boundary.

19. The method according to claim 15 or 16, wherein,

20. The method according to claim 15 or 16, wherein,

21. The method according to claim 15 or 16, wherein,

the speed maintenance cost;

Path monotonicity;

An upper target device speed limit;

Total duration of path planning;

Time intervals of path planning;

deviation speed penalty function information;

Penalty times for the speed of deviation.

22. The method according to any one of claims 18 to 20, wherein,

The AI quality of service requirements further include indication information for indicating the type of quality of service requirements, and a merging manner of the quality of service requirements of each type, the merging manner including at least one of:

23. The method according to claim 15 or 16, characterized in that the method further comprises:

The target equipment receives a first evaluation result of the service result sent by the network side equipment; the first evaluation result of the service result is determined based on sixth information and the service result; the sixth information includes at least one of: quality requirement index, quality requirement index calculation method, quality requirement index input data and format, and quality requirement index threshold; the first evaluation result includes at least one of:

AI service identification;

Service grades corresponding to the AI service identifiers;

The AI service identifier corresponds to the service quality value;

Synthesizing the quality of service value;

and integrating the service quality grades.

24. The method according to claim 15 or 16, characterized in that the method further comprises:

the target equipment sends a second evaluation result to the network side equipment, wherein the second evaluation result is an evaluation result of the service result evaluated by the target equipment;

the second evaluation result includes at least one of:

AI service identification;

Service grades corresponding to the AI service identifiers;

The AI service identifier corresponds to the service quality value;

Synthesizing the quality of service value;

and integrating the service quality grades.

25. The method according to claim 15 or 16, wherein the integrated quality of service requirement is determined from the first information, comprising at least one of:

directly obtaining based on the first information;

the service quality level is synthesized;

a comprehensive service quality threshold;

Weight of each service quality;

weighting method for each service quality.

26. An AI service processing apparatus, comprising:

A receiving module, configured to receive first information from a target device, where the first information includes an AI service identifier of a first service and indication information for indicating an AI quality of service requirement; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements; the safety requirement is used for representing and evaluating the anti-collision capability of the target equipment; the comfort requirement is used to characterize the ride comfort of the target device; the high efficiency requirement is used for representing the efficiency of the target equipment to complete tasks; the time delay requirement is used for representing the time difference between the target equipment initiating the AI service request and acquiring the service result;

27. An AI service processing apparatus, comprising:

A sending module, configured to send first information to a network side device, where the first information includes an AI service identifier of a first service and indication information for indicating an AI service quality requirement; the AI quality of service requirements include at least one of the following types of requirements: safety requirements, comfort requirements, high efficiency requirements and latency requirements; the safety requirement is used for representing the anti-collision capability of the target equipment; the comfort requirement is used to characterize the ride comfort of the target device; the high efficiency requirement is used for representing the efficiency of the target equipment to finish the task; the time delay requirement is used for representing the time difference between the target equipment initiating the AI service request and acquiring the service result;

and the receiving module is used for receiving the service result of the first service sent by the network side equipment.

28. A network side device comprising a processor and a memory storing a program or instructions executable on the processor, which when executed by the processor, implement the steps of the AI service processing method of any of claims 1-14.

29. A target device comprising a processor and a memory storing a program or instructions executable on the processor, which when executed by the processor, implement the steps of the AI service processing method of any of claims 15 to 25.

30. A readable storage medium, wherein a program or an instruction is stored on the readable storage medium, which when executed by a processor, implements the AI service processing method of any of claims 1 to 14, or implements the AI service processing method steps of any of claims 15 to 25.