CN114579691A - Information processing method and related device - Google Patents

Abstract

The embodiment of the application discloses an information processing method, which comprises the following steps: after the terminal equipment acquires the target information, the associated information is inquired according to the target information to determine the associated information corresponding to the target information, and the associated information is output. The terminal device can output the relevant information besides the feedback information corresponding to the target information.

Description

An information processing method and related device

technical field

The embodiments of the present application relate to the field of artificial intelligence, an information processing method and related devices.

Background technique

With the development and popularization of terminal devices, more and more people own multiple terminal devices (such as mobile phones, watches, speakers, large screens, etc.). Different terminal devices provide users with a variety of skills/services. For example, watches provide services such as message notification, heart rate monitoring, exercise/activity monitoring, sleep recording, mobile payment, and bus cards; smart large screens provide video calls, AI fitness, children's exclusive, high-definition video services.

After the terminal device obtains the target information, the terminal device can perform the corresponding reply operation. Taking the terminal device as a mobile phone and the target information as the language "How many steps are I?" for example, after the terminal device obtains the target information, it can send the Feedback the current number of steps.

There may be correlations between different target information. For example, when the target information is the language "How many steps are I?", the corresponding correlation information can be heart rate data, healthy diet, exercise time, etc. How can the terminal device reasonably determine And output the related information as the problem to be solved.

SUMMARY OF THE INVENTION

A first aspect of the embodiments of the present application provides an information processing method, including:

After the terminal device obtains the target information, it queries the associated information according to the target information. Taking the terminal device as a mobile phone and the target information as the voice "How many steps are I?" as an example, after the terminal device obtains the target information, it determines its implicit intention as Exercise health, the implicit intent is the user's behavior category, the terminal device queries the associated information corresponding to the implicit intent, such as heart rate data, healthy diet, exercise time, etc., and the terminal device outputs the associated information.

In this embodiment of the present application, in addition to outputting feedback information corresponding to the target information, the terminal device may also output associated information.

Based on the first aspect of the embodiments of the present application, in the first implementation manner of the first aspect of the embodiments of the present application, the terminal device may acquire target information from an associated terminal, or the terminal device may collect target information through a sensor.

In the embodiments of the present application, a variety of ways to obtain target information are provided, which improves the flexibility of the solution.

Based on the first aspect of the embodiments of the present application or the first implementation manner of the first aspect, in the second implementation manner of the first aspect of the embodiments of the present application, the terminal device outputs associated information in the target scene, where the target scene and the acquisition target are The moment of information can be unrelated. Taking the target information as the language "how many steps are I" as an example, after the terminal device obtains the target information, it determines the corresponding associated information, such as healthy diet, and the terminal device outputs the healthy diet during the meal time.

In this embodiment of the present application, the terminal device may record target information or implicit intention, and determine different associated information in different scenarios, thereby improving the reliability of the solution.

Based on the second implementation manner of the first aspect to the first aspect of the embodiments of the present application, in the third implementation manner of the first aspect of the embodiments of the present application, the target information includes voice information, text information, and\or image information.

In the embodiments of the present application, various forms of target information are provided, which improves the achievability of the solution.

A second aspect of the embodiments of the present application provides a terminal device, where the terminal device executes the foregoing first aspect and the method of any implementation manner of the first aspect.

A third aspect of the embodiments of the present application provides a computer storage medium, where instructions are stored in the computer storage medium, and when executed on a computer, the instructions cause the computer to execute the first aspect and the method of any embodiment of the first aspect.

A fourth aspect of the embodiments of the present application provides a computer software product, which, when executed on a computer, enables the computer to execute the first aspect and the method of any embodiment of the first aspect.

Description of drawings

1 is a schematic flowchart of an information processing method in an embodiment of the application;

FIG. 2 is a schematic diagram of a multi-terminal device system in an embodiment of the present application;

3 is a schematic diagram of a user operation record in an embodiment of the application;

Fig. 4 is the training schematic diagram of the intention flow model in the embodiment of the application;

Fig. 5 is a flow frame diagram of the information processing method in the embodiment of the application;

FIG. 6 is a schematic structural diagram of a terminal device in an embodiment of the present application;

FIG. 7 is another schematic structural diagram of a terminal device in an embodiment of the present application.

Detailed ways

The embodiments of the present application provide an information processing method.

The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application. In this application, "at least one" means one or more, and "plurality" means two or more. "And/or", which describes the association relationship of the associated objects, indicates that there can be three kinds of relationships, for example, A and/or B, which can indicate: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A, B can be singular or plural. The character "/" generally indicates that the associated objects are an "or" relationship. "At least one item(s) below" or similar expressions thereof refer to any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (a) of a, b or c, can represent: a, b, c, a and b, a and c, b and c or a and b and c, where a, b and c can be It can be single or multiple. It is worth noting that "at least one item(s)" can also be interpreted as "one item(s) or more(s)".

It should be noted that, in this application, words such as "exemplary" or "for example" are used to represent examples, illustrations or illustrations. Any embodiment or design described in this application as "exemplary" or "such as" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present the related concepts in a specific manner.

The descriptions of the first, second, etc. appearing in the embodiments of the present application are only used for illustration and distinguishing the description objects, and have no order. any limitations of the examples.

The technical solutions provided in the embodiments of the present application can be applied to various communication systems, for example, a long term evolution (LTE) system, a fifth generation (5G) mobile communication system, and a sixth generation (6G) mobile communication system. Communication systems, wireless-fidelity (WiFi) systems, short-range communication systems, satellite communication systems, Internet of Vehicles communication systems, non-terrestrial communication systems, future communication systems, or systems that integrate multiple communication systems, etc. The application examples are not limited. Among them, 5G can also be called new radio (NR).

The technical solutions provided in the embodiments of the present application can be applied to various communication scenarios, for example, can be applied to one or more of the following communication scenarios: enhanced mobile broadband (eMBB), ultra-reliable and low-latency communication (ultra-reliable and low-latency communication) -reliable low-latency communication (URLLC), machine type communication (MTC), massive machine type communication (mMTC), device-to-device (D2D), vehicle outreach ( Vehicle toeverything (V2X), vehicle to vehicle (V2V), and Internet of things (IoT), Virtual Reality (VR), Augmented Reality (AR), customer premises equipment ( Customer Premise Equipment, CPE), sensors, etc.

The embodiments of the present invention are applicable to both homogeneous network and heterogeneous network scenarios, and also have no limitation on transmission points, which may be multi-point coordinated transmission between macro base station and macro base station, micro base station and micro base station, and macro base station and micro base station , applicable to frequency division multiplexing system, time division multiplexing system, duplex system, access backhaul system, relay system, etc. The embodiments of the present invention are applicable to low-frequency scenarios (sub 6G) and high-frequency scenarios (above 6G), terahertz, optical communication, and the like.

Terminal equipment, also known as user equipment (UE), mobile station (MS), mobile terminal (MT), etc., is a device that provides voice and/or data connectivity to users. For example, handheld devices, in-vehicle devices, etc. with wireless connectivity. A terminal device may also be simply referred to as a terminal. At present, some examples of terminals are: mobile phone (mobile phone), tablet computer, notebook computer, palmtop computer, mobile internet device (mobile internet device, MID), wearable device, virtual reality (virtual reality, VR) device, augmented reality (augmented reality, AR) equipment, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, and smart grids wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, sensor, cellular phone, cordless phone, Session Initiation Protocol (SIP) , session initiation protocol) telephones, wireless local loop (WLL, wireless local loop) stations, personal digital assistants (PDAs, personal digital assistants), handheld devices with wireless communication capabilities, computing devices, or other processing devices connected to a wireless modem , in-vehicle equipment, wearable equipment, terminal equipment in 5G network or terminal equipment in the future evolved public land mobile communication network (PLMN, publicland mobile network), etc.

Among them, wearable devices can also be called wearable smart devices, which is a general term for the intelligent design of daily wear and the development of wearable devices using wearable technology, such as glasses, gloves, watches, clothing and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothing or accessories.

Wearable device is not only a hardware device, but also realizes powerful functions through software support, data interaction, and cloud interaction. In a broad sense, wearable smart devices include full functions, large sizes, and can achieve complete or partial functions without relying on smart phones, such as smart watches or smart glasses, and only focus on a certain type of application function, which needs to cooperate with other devices such as smart phones. Use, such as all kinds of smart bracelets, smart jewelry, etc. for physical sign monitoring.

In addition, the terminal device may also be a terminal device in an Internet of Things (IoT, internet of things) system. IoT is an important part of the development of information technology in the future. Its main technical feature is to connect items to the network through communication technology, so as to realize the intelligent network of human-machine interconnection and interconnection of things. IoT technology can achieve massive connections, deep coverage, and terminal power saving through, for example, narrowband (NB, narrowband) technology.

In addition, terminal equipment can also include sensors such as smart printers, train detectors, and gas stations. The main functions include collecting data, receiving control information and downlink data from network equipment, and sending electromagnetic waves to transmit uplink data to network equipment.

Referring to FIG. 1, the information processing method in the embodiment of the present application includes:

101. The terminal device obtains target information;

The terminal device can obtain target information in various ways, such as through the sensor collection of the terminal device, or from other terminal devices.

Taking the connection of multiple terminal devices to form a terminal device system as an example, after the terminal device obtains the target information, it can broadcast the target information to the associated terminal devices. See Figure 2. The audio sensor of the mobile phone terminal collects the target information: " Xiaoyi Xiaoyi, what is my heart rate", broadcast the target information to other terminal devices such as smart watch terminals, large-screen terminals, etc. At this time, the mobile phone terminal collects target information through the audio sensor, and other terminal devices such as smart watch terminals and large-screen terminals obtain target information from the associated terminal devices (mobile phone terminals).

It can be understood that the target information can be in various forms, such as voice information, text information, image information, and the like.

Optionally, referring to FIG. 3 , the target information may also be the user's operation records (dot data), such as browsing records, search records, software usage records, and the like. During the user's daily use of the terminal device, an intent sequence will be generated to check data. For example, the user uses the terminal device to perform operations such as listening to music, chatting, ordering takeout, and swiping Douyin for a period of time, resulting in a sequence of intents. The intent sequence includes operation records such as listening to music, chatting, ordering takeout, and swiping Douyin. At the same time, the user's feedback on the operation of the device, such as viewing, clicking, ignoring, and closing the mobile phone software (application, APP), can also be used as an operation record, that is, the management data with the user's feedback.

102. The terminal device determines an implicit intent according to the target information;

The terminal device can obtain the implicit intent of the target information. The implicit intent is the user's intent classification. See Figure 2. The intent classification includes sports health, travel, etc., for example, the target information is "Xiaoyi Xiaoyi, what is my heart rate" , the implicit intention at this time is exercise health, and the explicit intentions corresponding to exercise health include checking heart rate, light meal, exercise, etc. The terminal device can broadcast the implicit intention to the associated terminal device. At this time, the associated terminal device The acquired target information is an implicit intent.

It can be understood that one target information may correspond to multiple implicit intentions. For example, when the target information is listening to music, the corresponding implicit intention may be entertainment and leisure, and may also be sports and health.

103. The terminal device queries the associated information based on the implicit intent;

The terminal device can query the corresponding associated information according to the implicit intent. Taking the target information as "Xiaoyi Xiaoyi, what is my heart rate" as an example, the implicit intent of the target information is sports health, and the associated information can be obtained. Such as exercise (exercise duration, exercise intensity), light food, calorie query, etc.

It can be understood that the setting of the associated information can be pre-defined by the user and pre-configured by the system, etc., and can also be obtained by the terminal device through historical records. It is saved in the record that the user will search for TV dramas after choosing to order takeout. At this time, it can be considered that ordering takeout and watching TV series are related.

104. The terminal device outputs the associated information.

The terminal device outputs the associated information obtained in step 102. In this embodiment of the present application, the output timing of the associated information may be determined according to the scene, for example, light food may be output during the meal time period. The terminal device can record target information or implicit intentions, and determine different associated information in different scenarios to improve the reliability of the solution.

It can be understood that there may be various kinds of related information of the target information, and the specific recommended priority can be judged by the intelligent module. The specific judgment method is not limited in the embodiment of this application. For example, only the association existing in the historical record is output. Information can also be used in other ways. Here is a way to judge through the intent flow model:

The training of the intent flow model consists of two parts, as shown in Figure 4:

The intent embedding module is trained based on the dotted data of unsupervised intent sequences. The input is the first intent in the sequence, and the output is other intents in the intent sequence, that is, predicting other intents that have a co-occurrence relationship with the first intent. Intent embedding can be obtained in this way.

In the state embedding module, the user state includes perception items and implicit intentions. When pushing, input the perception item data and implicit intentions, go through the feature extraction module to get the same state embedding dimension as the intention embedding, and then do the intention embedding and state embedding. The inner product is used as the predicted value of the user feedback score, and the loss is calculated with the real user feedback score, and the gradient descent method is used for training.

The terminal device can use the sensors included in a variety of associated terminal devices to obtain perceptual target information such as user action, location, time, and emotion, and determine the association information corresponding to the cached implicit intent based on the association between the target information and the implicit intent. The target information and implicit intent are input into the state embedding module as the user state, the state embedding is extracted, and the inner product of the embedding of the associated information is used to obtain the score of the candidate intent, and the highest score is selected as the flow intent. That is, intents (related information) with high scores are output first.

For the user's operation record (dotting data), as shown in Figure 3, the intent sequence includes operation records such as listening to music, chatting, ordering takeout, and swiping Douyin. Intent embeddings can be trained with action records of intent sequences. At the same time, based on perception items (such as user action, location, time, etc.) and implicit intent, the intent flow model makes decisions to recommend skills/services for users. Users may have feedback such as viewing, clicking, ignoring, closing, etc., using user feedback Data training intent flow model.

For example: The implicit intentions of the current memory are fat loss and entertainment. The perception items include but are not limited to data such as user pressure perceived by the watch, user heart rate, and user location perceived by the mobile phone. These perception items and implicit intentions are expressed as a vector s. , each candidate intent is represented as a vector t (such as using one-hot encoding), and the feature extraction function is f, the intent embedding function is g, then s′=f(s) is the user state embedding, then t′=g( t) is the intent embedding, then the inner product of s' and t' is the score of the candidate intent (related information) t, and the score for each candidate intent is calculated and sorted to obtain the final output candidate intent. In the embodiment of the present invention, the functions f and g are matrix multiplication, that is, f(s)=As, g(t)=Bs, where A and B are the feature extraction matrix and the intent embedding matrix, respectively.

It can be understood that the determination of the candidate intent may also be other machine learning models, and this embodiment is only one of the implementation manners.

5 is a flow frame diagram of the information processing method in the embodiment of the present application. The system architecture diagram includes modules such as perception module, explicit intention recognition, implicit intention management, data collection module, intention flow model, and intention push display. The sensing module senses user status, environmental status (such as weather status, geographic location information, etc.), and device status (whether the user carries a terminal device, running, standby, etc. status of the terminal device, etc.) through sensors. The explicit intent recognition module identifies explicit intents corresponding to user actions or speech through rules or natural language understanding techniques. The implicit intent management module is responsible for saving the implicit intent corresponding to the explicit intent exposed by the user for a period of time, and synchronizing it to all terminal devices of the user. The data collection module is responsible for collecting information with user feedback and user intent sequences for updating the intent flow model. The intent flow model is responsible for model training updates and predictions. Input the user's current goal information and implicit intent, and return the score of the candidate intent. Contains a variety of pre-set display methods, including but not limited to notifications, pop-up cards, etc.

The information processing method in the embodiment of the present application is described above, and the apparatus in the embodiment of the present application is described below. Please refer to FIG. 6 . An embodiment of the terminal device in the embodiment of the present application includes:

an obtaining unit 601, configured to obtain target information;

a determining unit 602, configured to determine an implicit intent according to the target information;

a query unit 603, configured to query associated information based on the implicit intent;

The output unit 604 is used for outputting the associated information.

Each unit can perform the operations performed by the terminal device in the foregoing embodiment shown in FIG. 1 , and details are not repeated here.

Referring to FIG. 7 , an embodiment of the present application provides a terminal device 700. The terminal device may serve as a first communication device. The terminal device 700 may include one or more processors 701 and a memory 705, where a program is stored in the memory 705. Code, and further, data may also be stored in the memory 705 .

Among them, the memory 705 may be volatile memory or non-volatile memory or persistent memory. The program code stored in the memory 705 may include one or more modules, and each module may include a series of instructions to operate on the terminal device. Furthermore, the processor 701 may be configured to communicate with the memory 705 to execute a series of instruction operations in the memory 705 on the terminal device 700 .

The terminal device 700 may also include one or more power supplies 702 , one or more wired or wireless network interfaces 703 , and one or more input and output interfaces 704 .

The processor 701 can perform the operations performed by the terminal device in the foregoing embodiment shown in FIG. 1 , and details are not repeated here.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above may refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.

The integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application can be embodied in the form of software products in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, and the computer software products are stored in a storage medium , including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, removable hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), magnetic disk or optical disk and other media that can store program codes.

Claims (10)

1. an information processing method, is characterized in that, comprises: The terminal device obtains target information; The terminal device determines an implicit intent according to the target information, where the implicit intent is a behavioral intent corresponding to the target information; The terminal device queries the associated information according to the implicit intent; The terminal device outputs the association information. 2 . The information processing method according to claim 1 , wherein, acquiring the target information by the terminal device comprises: 2 . The terminal device acquires the target information from an associated terminal; or, The terminal device collects the target information through a sensor. 3. The information processing method according to claim 1 or 2, wherein the output of the associated information by the terminal device comprises: The terminal device outputs the associated information in the target scene, and the target scene is not associated with the time when the target information is acquired. 4. The information processing method according to any one of claims 1 to 3, wherein the target information includes voice information, text information, and/or image information. 5. A terminal device, comprising: an acquisition unit for acquiring target information; a determining unit, configured to determine an implicit intention according to the target information, where the implicit intention is a behavioral intention corresponding to the target information; a query unit, configured to query the associated information based on the implicit intent; An output unit, configured to output the associated information. 6 . The device according to claim 5 , wherein the obtaining unit is specifically configured to obtain the target information from an associated terminal, or collect the target information through a sensor. 7 . 7. The device according to claim 5 or 6, wherein the output unit is specifically configured to output the associated information in a target scene, and the target scene is not associated with the moment when the target information is acquired . 8. The device according to any one of claims 5 to 7, wherein the target information includes voice information, text information, and/or image information. 9. A computer storage medium, characterized in that the computer storage medium stores instructions that, when executed on a computer, cause the computer to execute the method according to any one of claims 1 to 4 . 10. A computer program product, characterized in that, when executed on a computer, the computer program product causes the computer to execute the method according to any one of claims 1 to 4.

Images