WO2021031862A1 - 一种数据处理方法及其装置 - Google Patents
一种数据处理方法及其装置 Download PDFInfo
- Publication number
- WO2021031862A1 WO2021031862A1 PCT/CN2020/107291 CN2020107291W WO2021031862A1 WO 2021031862 A1 WO2021031862 A1 WO 2021031862A1 CN 2020107291 W CN2020107291 W CN 2020107291W WO 2021031862 A1 WO2021031862 A1 WO 2021031862A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- queried
- objects
- text
- query
- word segmentation
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
Definitions
- This application relates to the field of communication technology, and in particular to a data processing method and device.
- the terminal device receives the query request, it can send the query request to all service providers supported by the terminal device, and after receiving the query result returned by each service provider, feed back the query result to the user.
- the embodiment of the present application provides a data processing method and device, which can determine the query field corresponding to the text to be queried, thereby helping to reduce the redundancy of query results.
- an embodiment of the present application provides a data processing method, which can be applied to the field of intelligent search based on artificial intelligence.
- the method includes: obtaining a text to be queried; and determining the text to be queried corresponding to the text to be queried from a preset database.
- Query object collection the number of the object collection to be queried is one or more, each object collection to be queried includes one or more objects to be queried; each object collection to be queried is determined from the preset relationship information between the two objects
- the relationship information of the object to be queried in each set of objects to be queried is used to determine the query field corresponding to the text to be queried.
- the relationship information of the objects to be queried in each collection of objects to be queried it can be determined that the user actually wants to access resources in the multiple fields supported by the service device when entering the text to be queried, and then The field that the user actually wants to access is the query field corresponding to the text to be queried.
- This helps to reduce the number of query fields, that is, to narrow the scope of the query, so that not only the query results matching the user's intention can be obtained, but also the query efficiency is improved and the query result redundancy is reduced.
- each set of objects to be queried may include one object to be queried, and the relationship information of the objects to be queried in each set of objects to be queried may include one or more relationship types; according to the object to be queried in each set of objects to be queried
- the specific implementation manner for determining the query field corresponding to the text to be queried may be: for each set of objects to be queried, if there is a relationship belonging to the first preset field among the relationship types of the objects to be queried in the set of objects to be queried Type, it is determined that the first preset field belongs to the query field corresponding to the text to be queried.
- the query field corresponding to the text to be queried is determined by the relationship type of the query object, which can improve the determination of the query field corresponding to the text to be queried. s efficiency.
- each set of objects to be queried may include multiple objects to be queried, and the relationship information of each object to be queried in each set of objects to be queried may include the object to be queried and the set of objects to be queried except for the object to be queried.
- the type of relationship between the objects to be queried other than the query object; according to the relationship information of the objects to be queried in each collection of objects to be queried, the specific implementation manner for determining the query field corresponding to the text to be queried can be: for each collection of objects to be queried If each object to be queried in the set of objects to be queried is connected by a relationship whose type belongs to the first preset field, then it is determined that the first preset field belongs to the query field corresponding to the text to be queried above.
- each collection of objects to be queried includes multiple objects to be queried
- the relationship type of the objects to be queried in each collection of objects to be queried it can be determined that the user actually wants to access the service device when entering the text to be queried.
- Which of the multiple domains supported is the resource, and then the domain that the user actually wants to access is used as the query domain corresponding to the text to be queried.
- determining the query field corresponding to the text to be queried by the relationship type of the query object can improve the efficiency of determining the query field corresponding to the text to be queried.
- a specific implementation manner of determining the set of query objects corresponding to the text to be queried from the preset database may be: determining the target text, the target text being the natural language understanding NLU processing of the text to be queried The obtained text; perform word segmentation processing on the target text to obtain each word segmentation of the target text; according to each word segmentation of the target text, determine the object to be queried in the set of objects to be queried from the preset database.
- each word segmentation of the target text has a corresponding object in the preset database; according to each word segmentation of the target text, the specific object to be queried in each set of objects to be queried is determined from the preset database.
- the implementation may be as follows: for each word segmentation of the target text, different objects corresponding to the word segmentation in the preset database are used as objects to be queried in different sets of objects to be queried.
- the word segmentation of the target text may include at least a first word segmentation and a second word segmentation.
- the first word segmentation corresponds to the first object in the preset database, and the second word segmentation does not exist in the preset database.
- Corresponding object; according to each word segmentation of the target text, the specific implementation manner of determining the object to be queried in each object set to be queried from the preset database may be: determining the object from the preset relationship information between the two objects The relationship information of the first object; determine the first relationship information that has a matching relationship with the second participle from the relationship information of the first object; if the first object passes the first relationship information and the second relationship information in the preset database If the objects are connected, the target object is determined according to the second object; and the target object is taken as the object to be queried in each set of objects to be queried.
- the word segmentation of the target text includes a first word segmentation and multiple second word segmentation
- multi-level inference can be performed according to the first word segmentation corresponding to the first object and the multiple second word segmentation in the preset database ,
- To obtain the target entity and use the target entity as the object to be queried in each collection of objects to be queried. In this way, it is helpful to determine the objects that users actually need to query.
- the method may further include: sending text information corresponding to any set of objects to be queried to a service device corresponding to the query domain; receiving a query result from the service device corresponding to the query domain; and outputting the search result.
- the user can not only obtain the required query result, but also avoid corresponding to all the fields supported by the service device.
- it can also avoid the search results that users do not need, which helps reduce the redundancy of the query results.
- an embodiment of the present application provides a data processing device, which may be a service device or a device (such as a chip) used for the service device.
- the device has the function of realizing the data processing method provided in the first aspect, and the function can be realized by hardware, or by hardware executing corresponding software.
- the hardware or software includes one or more modules corresponding to the above-mentioned functions.
- an embodiment of the present application provides a computer-readable storage medium for storing computer program instructions used by the data processing device described in the second aspect, including instructions for executing the program involved in the first aspect.
- an embodiment of the present application provides yet another data processing device, which may be a service device or a device (for example, a chip) used for the service device.
- the device includes a memory and a processor, the processor is connected to the memory through a bus, the memory stores program instructions, and the processor calls the program instructions stored in the memory to implement the data processing method provided in the first aspect.
- an embodiment of the present application provides a computer program product, which includes a program, which when executed by a data processing device, causes the data processing device to implement the method described in the first aspect.
- Figure 1a is a schematic diagram of the architecture of a communication system disclosed in an embodiment of the present application.
- Figure 1b is a schematic structural diagram of a service device disclosed in an embodiment of the present application.
- Fig. 1c is a schematic diagram of a software system of a service device disclosed in an embodiment of the present application.
- FIG. 2 is a schematic flowchart of a data processing method disclosed in an embodiment of the present application.
- FIG. 3 is a schematic flowchart of another data processing method disclosed in an embodiment of the present application.
- Figure 5 is a schematic structural diagram of a data processing device disclosed in an embodiment of the present application.
- Fig. 6 is a schematic structural diagram of another data processing device disclosed in an embodiment of the present application.
- Knowledge graph is a graph-based data structure composed of nodes and edges.
- the knowledge graph is used to describe various entities and concepts that exist in the real world, as well as the relationships between them (that is, between concepts and concepts, between concepts and entities, and between entities and entities).
- a piece of knowledge in the knowledge graph can be represented by triples, which can be represented as (entity 1, entity relationship, entity 2).
- entity 1 and entity 2 represent nodes in the knowledge graph
- entity relationships represent edges in the knowledge graph
- the triples indicate that entity 1 and entity 2 are related in the knowledge graph through the entity relationship.
- a concept is a collection of entities with the same characteristics, such as countries, nations, books, computers, etc.
- Concepts mainly refer to collections, categories, object types, and types of things, such as people, geography, etc.
- Entity represents the basic element belonging to a concept, that is, the specific entity referred to by a concept.
- An entity is something that is distinguishable and exists independently. Such as a certain person, a certain city, a certain kind of plant, a certain kind of commodity, etc.
- Entities are the most basic elements in the knowledge graph, and different entities have different relationships.
- AI Artificial intelligence
- the core of AI is the use of machine learning technology to allow machines to simulate certain core aspects of human behavior.
- AI allows machines to behave as autonomous systems that can perceive, learn, make decisions, and take actions with little or no human intervention.
- NLU is an application field of artificial intelligence. NLU is a technology that uses natural language to communicate with computers. Through NLU, computers can "understand" natural language, and then perform certain language functions expected by humans. In other words, NLU is a human and machine A bridge of communication.
- Language understanding can include but is not limited to the following: 1 able to understand the correct order rules and concepts of sentences, and also understand sentences without rules; 2 know the exact meaning, form, part of speech and word formation of words; 3 understand the semantic classification of words, The ambiguity of words, the ambiguity of words; 4designated and indefinite characteristics and all characteristics; 5the structural knowledge and practical concepts of the problem domain; 6the tone information and prosodic expression of the language; 7the text knowledge about the language expression; 8theory Background knowledge of the domain.
- FIG. 1a is a schematic structural diagram of a communication system disclosed in an embodiment of the present application.
- the communication system includes a terminal device 101 and a service device 102.
- the user can input the text to be queried (for example, "Guo Degang's Water Margin") in the text box displayed by the terminal device 101 through the input device of the terminal device 101, and then click the query button, so that when the terminal device 101 detects that the query button is clicked, it will The text to be queried is sent to the service device 102;
- the text to be queried for example, "Guo Degang's Water Margin”
- the service device 102 can determine the set of objects to be queried corresponding to the text to be queried from the preset database.
- the number of the set of objects to be queried can be one or more, and then select from the preset two or two objects.
- the relationship information the relationship information of the objects to be queried in each set of objects to be queried is determined, and then the query field corresponding to the text to be queried is determined according to the relationship information of the objects to be queried in each set of objects to be queried.
- each set of objects to be queried may include one or more objects to be queried.
- the object to be queried may be an entity in the preset database.
- the text to be queried is "Guo Degang's Water Margin”
- the objects to be queried in the collection of objects to be queried may include the character “Guo Degang” and the cross talk “Water Margin”.
- the character "Guo Degang” and the cross talk “Water Margin” are respectively an entity in the preset database.
- the relationship information of the object to be queried is the relationship information of the entity corresponding to the object to be queried in the preset database, that is, the relationship information of the object to be queried may include the entity corresponding to the object to be queried in the preset database and the difference in the preset database. Relation information between entities other than the entity corresponding to the object to be queried. For example, when the object to be queried is the character "Guo Degang", the relationship information of the object to be queried may include, but is not limited to: the relationship information between the character "Guo Degang” and the cross talk "Water Margin", and the character "Guo Degang” and Degang founded by Guo Degang. Information about the relationship between cloud agencies.
- the communication system shown in FIG. 1a may also include a data server (not shown in FIG. 1a).
- the service device 102 determines the query field, it can send text information corresponding to any set of objects to be queried to the query.
- the data server corresponding to the domain receives the query result from the data server and outputs the query result for the user to choose according to his needs.
- the steps performed by the service device 102 in FIG. 1a can be performed by the terminal device 101 instead, that is, the terminal device 101 can determine the set of objects to be queried corresponding to the text to be queried from a preset database, and read from Determine the relationship information of the objects to be queried in each set of objects to be queried in the preset relationship information between the two objects, and then determine the query field corresponding to the text to be queried according to the relationship information of the objects to be queried in each set of objects to be queried .
- the steps performed by the terminal device 101 in FIG. 1a can be performed by the service device 102 instead, that is, the text to be queried received by the service device 102 in FIG. 1a may be the service device 102 according to the user The input operation is obtained.
- the terminal device 101 in the embodiment of the present application is an entity on the user side for receiving or transmitting signals, such as a mobile phone.
- the terminal device may also be called a terminal (terminal), user equipment (UE), mobile station (mobile station, MS), mobile terminal (mobile terminal, MT), and so on.
- the terminal device can be a mobile phone (mobile phone), smart TV, wearable device, tablet computer (Pad), computer with wireless transceiver function, virtual reality (VR) terminal device, augmented reality (AR) terminal Equipment, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grid, transportation Wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, and so on.
- the embodiment of the present application does not limit the specific technology and specific device form adopted by the terminal device.
- the service device 102 in the embodiment of the present application may be composed of a processor, a memory, and a network interface, and the service device 102 may be a terminal device or a server.
- the technical solutions of the embodiments of the present application can be applied to query systems such as artificial intelligence-based intelligent search systems and intelligent question and answer systems.
- the data server can be a resource server such as a search engine server and a multimedia server.
- the data server can be a search engine server or other resource server.
- FIG. 1b shows a schematic structural diagram of a service device 1300.
- the service device 1300 may include a processor 1310, an external memory interface 1320, an internal memory 1321, a universal serial bus (USB) interface 1330, a charging management module 1340, a power management module 1341, a battery 1342, an antenna 1, and an antenna 2.
- Mobile communication module 1350 wireless communication module 1360, audio module 1370, speaker 1370A, receiver 1370B, microphone 1370C, earphone jack 1370D, sensor module 1380, buttons 1390, motor 1391, indicator 1392, camera 1393, display 1394, and Subscriber identification module (subscriber identification module, SIM) card interface 1395, etc.
- SIM Subscriber identification module
- the sensor module 1380 may include pressure sensor 1380A, gyroscope sensor 1380B, air pressure sensor 1380C, magnetic sensor 1380D, acceleration sensor 1380E, distance sensor 1380F, proximity light sensor 1380G, fingerprint sensor 1380H, temperature sensor 1380J, touch sensor 1380K, environment Light sensor 1380L, bone conduction sensor 1380M, etc.
- the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the service device 1300.
- the service device 1300 may include more or fewer components than shown, or combine certain components, or split certain components, or arrange different components.
- the illustrated components can be implemented in hardware, software, or a combination of software and hardware.
- the processor 1310 may include one or more processing units.
- the processor 1310 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), and an image signal processor. (image signal processor, ISP), controller, video codec, digital signal processor (digital signal processor, DSP), baseband processor, and/or neural-network processing unit (NPU), etc.
- AP application processor
- modem processor modem processor
- GPU graphics processing unit
- image signal processor image signal processor
- ISP image signal processor
- controller video codec
- digital signal processor digital signal processor
- DSP digital signal processor
- NPU neural-network processing unit
- the different processing units may be independent devices or integrated in one or more processors.
- the controller can generate operation control signals according to the instruction operation code and timing signals to complete the control of fetching and executing instructions.
- a memory may also be provided in the processor 1310 to store instructions and data.
- the memory in the processor 1310 is a cache memory.
- the memory can store instructions or data that have just been used or recycled by the processor 1310. If the processor 1310 needs to use the instruction or data again, it can be directly called from the memory. Repeated accesses are avoided, the waiting time of the processor 1310 is reduced, and the efficiency of the system is improved.
- the processor 1310 may include one or more interfaces.
- the interface may include an integrated circuit (inter-integrated circuit, I2C) interface, an integrated circuit built-in audio (inter-integrated circuit sound, I2S) interface, a pulse code modulation (pulse code modulation, PCM) interface, and a universal asynchronous transmitter (universal asynchronous transmitter) interface.
- I2C integrated circuit
- I2S integrated circuit built-in audio
- PCM pulse code modulation
- PCM pulse code modulation
- UART universal asynchronous transmitter
- MIPI mobile industry processor interface
- GPIO general-purpose input/output
- SIM subscriber identity module
- USB Universal Serial Bus
- the I2C interface is a two-way synchronous serial bus, including a serial data line (SDA) and a serial clock line (SCL).
- the processor 1310 may include multiple sets of I2C buses.
- the processor 1310 can couple the touch sensor 1380K, charger, flash, camera 1393, etc., through different I2C bus interfaces.
- the processor 1310 may couple the touch sensor 1380K through an I2C interface, so that the processor 1310 and the touch sensor 1380K communicate through an I2C bus interface to realize the touch function of the service device 1300.
- the I2S interface can be used for audio communication.
- the processor 1310 may include multiple sets of I2S buses.
- the processor 1310 may be coupled with the audio module 1370 through an I2S bus to realize communication between the processor 1310 and the audio module 1370.
- the audio module 1370 can transmit audio signals to the wireless communication module 1360 through the I2S interface, so as to realize the function of answering calls through the Bluetooth headset.
- the PCM interface can also be used for audio communication to sample, quantize and encode analog signals.
- the audio module 1370 and the wireless communication module 1360 may be coupled through a PCM bus interface.
- the audio module 1370 may also transmit audio signals to the wireless communication module 1360 through the PCM interface, so as to realize the function of answering calls through the Bluetooth headset. Both the I2S interface and the PCM interface can be used for audio communication.
- the UART interface is a universal serial data bus used for asynchronous communication.
- the bus can be a two-way communication bus. It converts the data to be transmitted between serial communication and parallel communication.
- the UART interface is generally used to connect the processor 1310 and the wireless communication module 1360.
- the processor 1310 communicates with the Bluetooth module in the wireless communication module 1360 through the UART interface to realize the Bluetooth function.
- the audio module 1370 may transmit audio signals to the wireless communication module 1360 through the UART interface, so as to realize the function of playing music through the Bluetooth headset.
- the MIPI interface can be used to connect the processor 1310 with the display 1394, camera 1393 and other peripheral devices.
- the MIPI interface includes camera serial interface (camera serial interface, CSI), display serial interface (display serial interface, DSI), etc.
- the processor 1310 and the camera 1393 communicate through a CSI interface to implement the shooting function of the service device 1300.
- the processor 1310 and the display screen 1394 communicate through the DSI interface to realize the display function of the service device 1300.
- the GPIO interface can be configured through software.
- the GPIO interface can be configured as a control signal or as a data signal.
- the GPIO interface can be used to connect the processor 1310 with the camera 1393, the display screen 1394, the wireless communication module 1360, the audio module 1370, the sensor module 1380, and so on.
- GPIO interface can also be configured as I2C interface, I2S interface, UART interface, MIPI interface, etc.
- the USB interface 1330 is an interface that complies with the USB standard and specifications, and specifically can be a Mini USB interface, a Micro USB interface, a USB Type C interface, and so on.
- the USB interface 1330 can be used to connect a charger to charge the service device 1300, and can also be used to transfer data between the service device 1300 and peripheral devices. It can also be used to connect headphones and play audio through the headphones. This interface can also be used to connect to other service devices, such as AR devices.
- the interface connection relationship between the modules illustrated in the embodiment of the present invention is merely illustrative and does not constitute a structural limitation of the service device 1300.
- the service device 1300 may also adopt different interface connection modes or a combination of multiple interface connection modes in the foregoing embodiments.
- the charging management module 1340 is used to receive charging input from the charger.
- the charger can be a wireless charger or a wired charger.
- the charging management module 1340 may receive the charging input of the wired charger through the USB interface 1330.
- the charging management module 1340 may receive the wireless charging input through the wireless charging coil of the service device 1300. While the charging management module 1340 charges the battery 1342, it can also supply power to the service device through the power management module 1341.
- the power management module 1341 is used to connect the battery 1342, the charging management module 1340 and the processor 1310.
- the power management module 1341 receives input from the battery 1342 and/or the charging management module 1340, and supplies power to the processor 1310, internal memory 1321, display screen 1394, camera 1393, and wireless communication module 1360.
- the power management module 1341 can also be used to monitor battery capacity, battery cycle times, battery health status (leakage, impedance) and other parameters.
- the power management module 1341 may also be provided in the processor 1310.
- the power management module 1341 and the charging management module 1340 may also be provided in the same device.
- the wireless communication function of the service device 1300 can be implemented by antenna 1, antenna 2, mobile communication module 1350, wireless communication module 1360, modem processor, baseband processor, and so on.
- the antenna 1 and the antenna 2 are used to transmit and receive electromagnetic wave signals.
- Each antenna in the service device 1300 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization.
- antenna 1 can be multiplexed as a diversity antenna of a wireless local area network.
- the antenna can be used in combination with a tuning switch.
- the mobile communication module 1350 can provide a wireless communication solution including 2G/3G/4G/5G and the like applied to the service device 1300.
- the mobile communication module 1350 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), and so on.
- the mobile communication module 1350 can receive electromagnetic waves by the antenna 1, and perform processing such as filtering, amplifying and transmitting the received electromagnetic waves to the modem processor for demodulation.
- the mobile communication module 1350 can also amplify the signal modulated by the modem processor, and convert it to electromagnetic wave radiation via the antenna 1.
- at least part of the functional modules of the mobile communication module 1350 may be provided in the processor 1310.
- at least part of the functional modules of the mobile communication module 1350 and at least part of the modules of the processor 1310 may be provided in the same device.
- the modem processor may include a modulator and a demodulator.
- the modulator is used to modulate the low frequency baseband signal to be sent into a medium and high frequency signal.
- the demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. Then the demodulator transmits the demodulated low-frequency baseband signal to the baseband processor for processing.
- the low-frequency baseband signal is processed by the baseband processor and then passed to the application processor.
- the application processor outputs a sound signal through an audio device (not limited to a speaker 1370A, a receiver 1370B, etc.), or displays an image or video through a display screen 1394.
- the modem processor may be an independent device.
- the modem processor may be independent of the processor 1310 and be provided in the same device as the mobile communication module 1350 or other functional modules.
- the wireless communication module 1360 can provide applications on the service device 1300 including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), bluetooth (BT), and global navigation satellites.
- WLAN wireless local area networks
- BT wireless fidelity
- GNSS global navigation satellite system
- FM frequency modulation
- NFC near field communication technology
- infrared technology infrared, IR
- the wireless communication module 1360 may be one or more devices integrating at least one communication processing module.
- the wireless communication module 1360 receives electromagnetic waves via the antenna 2, frequency modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 1310.
- the wireless communication module 1360 may also receive the signal to be sent from the processor 1310, perform frequency modulation, amplify, and convert it into electromagnetic waves to radiate through the antenna 2.
- the antenna 1 of the service device 1300 is coupled with the mobile communication module 1350, and the antenna 2 is coupled with the wireless communication module 1360, so that the service device 1300 can communicate with the network and other devices through wireless communication technology.
- the wireless communication technologies may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), broadband Code division multiple access (wideband code division multiple access, WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC , FM, and/or IR technology, etc.
- the GNSS may include global positioning system (GPS), global navigation satellite system (GLONASS), Beidou navigation satellite system (BDS), quasi-zenith satellite system (quasi -zenith satellite system, QZSS) and/or satellite-based augmentation systems (SBAS).
- GPS global positioning system
- GLONASS global navigation satellite system
- BDS Beidou navigation satellite system
- QZSS quasi-zenith satellite system
- SBAS satellite-based augmentation systems
- the service device 1300 implements a display function through a GPU, a display screen 1394, and an application processor.
- GPU is a microprocessor for image processing, connected to the display 1394 and application processor.
- the GPU is used to perform mathematical and geometric calculations for graphics rendering.
- the processor 1310 may include one or more GPUs, which execute program instructions to generate or change display information.
- the display 1394 is used to display images, videos, etc.
- the display screen 1394 includes a display panel.
- the display panel can adopt liquid crystal display (LCD), organic light-emitting diode (OLED), active matrix organic light-emitting diode or active-matrix organic light-emitting diode (active-matrix organic light-emitting diode).
- LCD liquid crystal display
- OLED organic light-emitting diode
- active-matrix organic light-emitting diode active-matrix organic light-emitting diode
- AMOLED flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, quantum dot light-emitting diode (QLED), etc.
- the service device 1300 may include 1 or N display screens 1394, and N is a positive integer greater than 1.
- the service device 1300 may implement a shooting function through an ISP, a camera 1393, a video codec, a GPU, a display 1394, and an application processor.
- the ISP is used to process the data fed back by the camera 1393. For example, when taking a picture, the shutter is opened, the light is transmitted to the photosensitive element of the camera through the lens, the light signal is converted into an electrical signal, and the photosensitive element of the camera transfers the electrical signal to the ISP for processing and is converted into an image visible to the naked eye.
- ISP can also optimize the image noise, brightness, and skin color. ISP can also optimize the exposure, color temperature and other parameters of the shooting scene.
- the ISP may be provided in the camera 1393.
- the camera 1393 is used to capture still images or videos.
- the object generates an optical image through the lens and projects it to the photosensitive element.
- the photosensitive element may be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor.
- CMOS complementary metal-oxide-semiconductor
- the photosensitive element converts the optical signal into an electrical signal, and then transmits the electrical signal to the ISP to convert it into a digital image signal.
- ISP outputs digital image signals to DSP for processing.
- DSP converts digital image signals into standard RGB, YUV and other formats.
- the service device 1300 may include 1 or N cameras 1393, and N is a positive integer greater than 1.
- Digital signal processors are used to process digital signals. In addition to digital image signals, they can also process other digital signals. For example, when the service device 1300 selects a frequency point, the digital signal processor is used to perform Fourier transform on the energy of the frequency point.
- Video codecs are used to compress or decompress digital video.
- the service device 1300 may support one or more video codecs. In this way, the service device 1300 can play or record videos in multiple encoding formats, such as: moving picture experts group (MPEG) 1, MPEG2, MPEG3, MPEG4, and so on.
- MPEG moving picture experts group
- NPU is a neural-network (NN) computing processor.
- NN neural-network
- applications such as intelligent cognition of the service device 1300 can be realized, such as image recognition, face recognition, voice recognition, text understanding, etc.
- the external memory interface 1320 may be used to connect an external memory card, such as a Micro SD card, so as to expand the storage capacity of the service device 1300.
- the external memory card communicates with the processor 1310 through the external memory interface 1320 to realize the data storage function. For example, save music, video and other files in an external memory card.
- the internal memory 1321 may be used to store computer executable program code, where the executable program code includes instructions.
- the internal memory 1321 may include a program storage area and a data storage area.
- the storage program area can store an operating system, at least one application program (such as a sound playback function, an image playback function, etc.) required by at least one function.
- the storage data area can store data (such as audio data, phone book, etc.) created during the use of the service device 1300.
- the internal memory 1321 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, a universal flash storage (UFS), etc.
- the processor 1310 executes various functional applications and data processing of the service device 1300 by running instructions stored in the internal memory 1321 and/or instructions stored in a memory provided in the processor.
- the service device 1300 can implement audio functions through an audio module 1370, a speaker 1370A, a receiver 1370B, a microphone 1370C, a headset interface 1370D, and an application processor. For example, music playback, recording, etc.
- the audio module 1370 is used for converting digital audio information into an analog audio signal for output, and also for converting an analog audio input into a digital audio signal.
- the audio module 1370 can also be used to encode and decode audio signals.
- the audio module 1370 may be provided in the processor 1310, or part of the functional modules of the audio module 1370 may be provided in the processor 1310.
- the speaker 1370A also called a “speaker” is used to convert audio electrical signals into sound signals.
- the service device 1300 can listen to music through the speaker 1370A, or listen to a hands-free call.
- the receiver 1370B also called “earpiece” is used to convert audio electrical signals into sound signals.
- the service device 1300 answers a call or voice message, it can receive the voice by bringing the receiver 1370B close to the human ear.
- Microphone 1370C also called “microphone” or “microphone” is used to convert sound signals into electrical signals. When making a call or sending a voice message, the user can approach the microphone 1370C through the mouth to make a sound, and input the sound signal into the microphone 1370C.
- the service device 1300 may be provided with at least one microphone 1370C. In other embodiments, the service device 1300 may be provided with two microphones 1370C, which can implement noise reduction functions in addition to collecting sound signals. In other embodiments, the service device 1300 may also be provided with three, four or more microphones 1370C to collect sound signals, reduce noise, identify sound sources, and realize directional recording functions.
- the earphone interface 1370D is used to connect wired earphones.
- the earphone interface 1370D can be a USB interface 1330, or a 3.5mm open mobile terminal platform (OMTP) standard interface, or a cellular telecommunications industry association (cellular telecommunications industry association of the USA, CTIA) standard interface.
- OMTP open mobile terminal platform
- CTIA cellular telecommunications industry association
- the pressure sensor 1380A is used to sense pressure signals and can convert the pressure signals into electrical signals.
- the pressure sensor 1380A may be disposed on the display screen 1394.
- the capacitive pressure sensor may include at least two parallel plates with conductive material. When a force is applied to the pressure sensor 1380A, the capacitance between the electrodes changes.
- the service device 1300 determines the intensity of the pressure according to the change in capacitance. When a touch operation acts on the display screen 1394, the service device 1300 detects the intensity of the touch operation according to the pressure sensor 1380A.
- the service device 1300 may also calculate the touched position according to the detection signal of the pressure sensor 1380A.
- touch operations that act on the same touch location but have different touch operation strengths may correspond to different operation instructions. For example: when a touch operation whose intensity of the touch operation is less than the first pressure threshold is applied to the short message application icon, an instruction to view the short message is executed. When a touch operation with a touch operation intensity greater than or equal to the first pressure threshold acts on the short message application icon, an instruction to create a new short message is executed.
- the gyro sensor 1380B may be used to determine the motion posture of the service device 1300.
- the angular velocity of the service device 1300 around three axes ie, x, y, and z axes
- the gyro sensor 1380B can be used for image stabilization.
- the gyroscope sensor 1380B detects the jitter angle of the service device 1300, calculates the distance that the lens module needs to compensate according to the angle, and allows the lens to counteract the jitter of the service device 1300 through a reverse movement to achieve anti-shake.
- the gyro sensor 1380B can also be used for navigation and somatosensory game scenes.
- the air pressure sensor 1380C is used to measure air pressure.
- the service device 1300 calculates the altitude based on the air pressure value measured by the air pressure sensor 1380C, to assist positioning and navigation.
- the magnetic sensor 1380D includes a Hall sensor.
- the service device 1300 may use the magnetic sensor 1380D to detect the opening and closing of the flip holster.
- the service device 1300 may detect the opening and closing of the flip according to the magnetic sensor 1380D.
- features such as automatic unlocking of the flip cover are set.
- the acceleration sensor 1380E can detect the magnitude of the acceleration of the service device 1300 in various directions (generally three axes). When the service device 1300 is stationary, the magnitude and direction of gravity can be detected. It can also be used to identify the posture of the service device, applied to applications such as horizontal and vertical screen switching, and pedometer.
- the service device 1300 can measure the distance by infrared or laser. In some embodiments, when shooting a scene, the service device 1300 may use the distance sensor 1380F to measure the distance to achieve fast focusing.
- the proximity light sensor 1380G may include, for example, a light emitting diode (LED) and a light detector, such as a photodiode.
- the light emitting diode may be an infrared light emitting diode.
- the service device 1300 emits infrared light to the outside through the light emitting diode.
- the service device 1300 uses a photodiode to detect infrared reflected light from nearby objects. When sufficient reflected light is detected, it can be determined that there is an object near the service device 1300. When insufficient reflected light is detected, the service device 1300 may determine that there is no object near the service device 1300.
- the service device 1300 can use the proximity light sensor 1380G to detect that the user holds the service device 1300 close to the ear to talk, so as to automatically turn off the screen to save power.
- the proximity light sensor 1380G can also be used in leather case mode, and the pocket mode will automatically unlock and lock the screen.
- the ambient light sensor 1380L is used to sense the brightness of the ambient light.
- the service device 1300 may adaptively adjust the brightness of the display screen 1394 according to the perceived brightness of the ambient light.
- the ambient light sensor 1380L can also be used to automatically adjust the white balance when taking pictures.
- the ambient light sensor 1380L can also cooperate with the proximity light sensor 1380G to detect whether the service device 1300 is in the pocket to prevent accidental touch.
- the fingerprint sensor 1380H is used to collect fingerprints.
- the service device 1300 may use the collected fingerprint characteristics to implement fingerprint unlocking, access application locks, fingerprint photographs, fingerprint answering calls, etc.
- the temperature sensor 1380J is used to detect temperature.
- the service device 1300 uses the temperature detected by the temperature sensor 1380J to execute a temperature processing strategy. For example, when the temperature reported by the temperature sensor 1380J exceeds the threshold, the service device 1300 performs a reduction in the performance of the processor located near the temperature sensor 1380J, so as to reduce power consumption and implement thermal protection.
- the service device 1300 when the temperature is lower than another threshold, the service device 1300 heats the battery 1342 to avoid abnormal shutdown of the service device 1300 due to low temperature.
- the service device 1300 boosts the output voltage of the battery 1342 to avoid abnormal shutdown caused by low temperature.
- Touch sensor 1380K also called “touch device”.
- the touch sensor 1380K can be arranged on the display screen 1394, and the touch screen is composed of the touch sensor 1380K and the display screen 1394, which is also called a "touch screen”.
- the touch sensor 1380K is used to detect touch operations acting on or near it.
- the touch sensor can pass the detected touch operation to the application processor to determine the type of touch event.
- the visual output related to the touch operation can be provided through the display 1394.
- the touch sensor 1380K may also be disposed on the surface of the service device 1300, which is different from the position of the display screen 1394.
- the bone conduction sensor 1380M can acquire vibration signals.
- the bone conduction sensor 1380M can obtain the vibration signal of the vibrating bone mass of the human voice.
- the bone conduction sensor 1380M can also contact the human pulse and receive the blood pressure pulse signal.
- the bone conduction sensor 1380M may also be provided in the earphone, combined with the bone conduction earphone.
- the audio module 1370 can parse out the voice signal based on the vibration signal of the vibrating bone block of the voice obtained by the bone conduction sensor 1380M to realize the voice function.
- the application processor can analyze the heart rate information based on the blood pressure beating signal obtained by the bone conduction sensor 1380M, and realize the heart rate detection function.
- the button 1390 includes a power-on button, a volume button and so on.
- the button 1390 may be a mechanical button. It can also be a touch button.
- the service device 1300 may receive key input, and generate key signal input related to user settings and function control of the service device 1300.
- the motor 1391 can generate vibration prompts.
- the motor 1391 can be used for incoming call vibration notification, and can also be used for touch vibration feedback.
- touch operations applied to different applications can correspond to different vibration feedback effects.
- Acting on touch operations in different areas of the display screen 1394, the motor 1391 can also correspond to different vibration feedback effects.
- Different application scenarios for example: time reminding, receiving information, alarm clock, games, etc.
- the touch vibration feedback effect can also support customization.
- the indicator 1392 can be an indicator light, which can be used to indicate the charging status, power change, and can also be used to indicate messages, missed calls, notifications, and so on.
- the SIM card interface 1395 is used to connect to the SIM card.
- the SIM card can be inserted into the SIM card interface 1395 or pulled out from the SIM card interface 1395 to achieve contact and separation with the service device 1300.
- the service device 1300 may support 1 or N SIM card interfaces, and N is a positive integer greater than 1.
- the SIM card interface 1395 can support Nano SIM cards, Micro SIM cards, SIM cards, etc.
- the same SIM card interface 1395 can insert multiple cards at the same time. The types of the multiple cards can be the same or different.
- the SIM card interface 1395 can also be compatible with different types of SIM cards.
- the SIM card interface 1395 can also be compatible with external memory cards.
- the service device 1300 interacts with the network through the SIM card to implement functions such as call and data communication.
- the service device 1300 adopts an eSIM, that is, an embedded SIM card.
- the eSIM card can be embedded in the service device 1300 and cannot be separated from the service device 1300.
- the software system of the service device 1300 may adopt a layered architecture, an event-driven architecture, a microkernel architecture, a microservice architecture, or a cloud architecture.
- the embodiment of the present invention takes a layered Android system as an example to illustrate the software structure of the service device 1300.
- FIG. 1c is a software structure block diagram of a service device 1300 according to an embodiment of the present invention.
- the layered architecture divides the software into several layers, and each layer has a clear role and division of labor. Communication between layers through software interface.
- the Android system is divided into four layers, from top to bottom, the application layer, the application framework layer, the Android runtime and system library, and the kernel layer.
- the application layer can include a series of application packages.
- the application package may include applications such as camera, gallery, calendar, call, map, navigation, WLAN, Bluetooth, music, video, short message, etc.
- the application framework layer provides application programming interfaces (application programming interface, API) and programming frameworks for applications in the application layer.
- the application framework layer includes some predefined functions. As shown in Figure 1c, the application framework layer can include a window manager, a content provider, a view system, a phone manager, a resource manager, and a notification manager.
- the window manager is used to manage window programs.
- the window manager can obtain the size of the display, determine whether there is a status bar, lock the screen, take a screenshot, etc.
- the content provider is used to store and retrieve data and make these data accessible to applications.
- the data may include video, image, audio, phone calls made and received, browsing history and bookmarks, phone book, etc.
- the view system includes visual controls, such as controls that display text and controls that display pictures.
- the view system can be used to build applications.
- the display interface can be composed of one or more views.
- a display interface that includes a short message notification icon may include a view that displays text and a view that displays pictures.
- the phone manager is used to provide the communication function of the service device 1300. For example, the management of the call status (including connecting, hanging up, etc.).
- the resource manager provides various resources for the application, such as localized strings, icons, pictures, layout files, video files, etc.
- the notification manager enables the application to display notification information in the status bar, which can be used to convey notification-type messages, and can disappear automatically after a short stay without user interaction.
- the notification manager is used to notify the download completion, message reminder, etc.
- the notification manager can also be a notification that appears in the status bar at the top of the system in the form of a chart or scroll bar text, such as a notification of an application running in the background, or a notification that appears on the screen in the form of a dialog window.
- the status bar prompts text messages, sounds prompts, service equipment vibrates, and indicator lights flash.
- Android Runtime includes core libraries and virtual machines. Android runtime is responsible for the scheduling and management of the Android system.
- the core library consists of two parts: one part is the function functions that the java language needs to call, and the other part is the core library of Android.
- the application layer and the application framework layer run in a virtual machine.
- the virtual machine executes the java files of the application layer and the application framework layer as binary files.
- the virtual machine is used to perform functions such as object life cycle management, stack management, thread management, security and exception management, and garbage collection.
- the system library can include multiple functional modules. For example: surface manager (surface manager), media library (Media Libraries), three-dimensional graphics processing library (for example: OpenGL ES), 2D graphics engine (for example: SGL), etc.
- the surface manager is used to manage the display subsystem and provides a combination of 2D and 3D layers for multiple applications.
- the media library supports playback and recording of a variety of commonly used audio and video formats, as well as still image files.
- the media library can support multiple audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.
- the 3D graphics processing library is used to realize 3D graphics drawing, image rendering, synthesis, and layer processing.
- the 2D graphics engine is a drawing engine for 2D drawing.
- the kernel layer is the layer between hardware and software.
- the kernel layer contains at least display driver, camera driver, audio driver, and sensor driver.
- the corresponding hardware interrupt is sent to the kernel layer.
- the kernel layer processes touch operations into original input events (including touch coordinates, time stamps of touch operations, etc.).
- the original input events are stored in the kernel layer.
- the application framework layer obtains the original input event from the kernel layer, and identifies the control corresponding to the input event. Taking the touch operation as a touch click operation, and the control corresponding to the click operation is the control of the camera application icon as an example, the camera application calls the interface of the application framework layer to start the camera application, and then starts the camera driver by calling the kernel layer.
- the camera 1393 captures still images or video.
- FIG. 2 is a schematic flowchart of a data processing method provided by an embodiment of the present application.
- the execution subject of steps S201 to S204 is the service device, or the chip in the service device.
- the following takes the service device as the execution subject of the data processing method as an example for description.
- the method may include but is not limited to the following steps:
- Step S201 The service device obtains the text to be queried.
- the text to be queried can be a word or a sentence composed of multiple words.
- the text to be queried may be the query entered by the user during the query search, and the query may be entered in the form of text , It can also be input by voice.
- the query is input by voice, the query in voice format needs to be converted into text format.
- the text to be queried can be a question entered by the user when asking, and the question can be entered in text or It is input by voice.
- the question is input by voice, the question in the voice format needs to be converted into a text format.
- the text to be queried may be input by the user in the terminal device and sent by the terminal device to the service device, or the text to be queried may also be input by the user in the service device.
- the service device may be the service device 102 in FIG. 1a.
- the service device when the service device obtains the text to be queried, it indicates that the query field corresponding to the text to be queried needs to be determined. Specifically, before the service device determines the query field corresponding to the text to be queried, it needs to determine the set of objects to be queried corresponding to the text to be queried, and determine the text to be queried based on the relationship information of the objects to be queried in the set of objects to be queried The corresponding query field.
- Step S202 The service device determines from the preset database a set of objects to be queried corresponding to the text to be queried, the number of object sets to be queried is one or more, and each set of objects to be queried includes one or more objects to be queried.
- the service device can determine the set of objects to be queried corresponding to the text to be queried from a preset database.
- the number of object sets to be queried may be one or more, and each object set to be queried may include one or more objects to be queried, and the number of objects to be queried in each object set to be queried is the same.
- the object to be queried may be an entity in the preset database.
- the text to be queried is "Guo Degang's Water Margin”
- the objects to be queried in the collection of objects to be queried may include the character “Guo Degang” and the cross talk “Water Margin”.
- the character "Guo Degang” and the cross talk “Water Margin” are respectively an entity in the preset database.
- the objects to be queried in different sets of objects to be queried can be completely different or partly different.
- the text to be queried is "Guo Degang's Water Margin”
- the objects to be queried in the first set of objects to be queried may include the character “Guo Degang” and the cross talk "Water Margin” "Biography”
- the objects to be queried in the second set of objects to be queried can include the character “Guo Degang” and the TV series “Water Margin”.
- cross talk "Water Margin” and TV series “Water Margin” are two different entities corresponding to the word "Water Margin” in the preset database.
- the same word can correspond to one or more entities in the preset database, and the number of object sets to be queried can be determined according to the number of entities that the word corresponding to the text to be queried exists in the preset database. Specifically, the number of object sets to be queried may be the product of the number of entities existing in the preset database for each word corresponding to the text to be queried.
- the objects to be searched in the first set of objects to be searched include: character "Guo Degang” and cross talk "Water Margin”; the objects to be searched in the second set of objects to be searched include: character "Guo Degang” and TV series “Water Margin”;
- the objects to be queried in the third object set to be queried include: the book “Guo Degang” and the cross talk "Water Margin”; the objects to be queried in the fourth object set to be queried include: the book "Guo Degang” and the TV series “Water Margin".
- the number of object sets to be queried may be smaller than the product of the number of entities existing in the preset database for each word corresponding to the text to be queried. For example, when the text to be queried is "Guo Degang's Water Margin" and the two words corresponding to the text to be queried are "Guo Degang” and “Water Margin”, if the word "Guo Degang” corresponds to 2 entities in the default database ( For example, the character “Guo Degang” and the book “Guo Degang”), the word “Water Margin” corresponds to 2 entities in the preset database (such as cross talk “Water Margin” and TV series “Water Margin”).
- the service device can perform entity disambiguation processing on the words "Guo Degang” and “Water Margin” respectively, and then determine that the entity corresponding to the word "Guo Degang” is the character "Guo Degang”, and the entity corresponding to the word “Water Margin” is the cross talk "Water Margin” "Biography” and the TV series “Water Margin”.
- the entity disambiguation processing it can be determined that the number of object collections to be queried is 1*2.
- the objects to be queried in the first set of objects to be queried include the character "Guo Degang” and the cross talk "Water Margin”
- the objects to be queried in the second set of objects to be queried include the character "Guo Degang” and the TV series “Water Margin”.
- the words corresponding to the objects to be queried in each set of objects to be queried are the same.
- the words corresponding to the objects to be queried in the first set of objects to be queried and the second set of objects to be queried are both "Guo Degang” and "Water Margin".
- the ambiguity of an entity means that the same word can correspond to multiple different concepts.
- the word "Guo Degang” can refer to a character, or it can refer to the book “Guo Degang” with the same name as the character "Guo Degang”.
- Entity disambiguation can determine which concept the word actually corresponds to. For example, when the text to be queried is "Guo Degang's Water Margin", it can be determined that the real entity corresponding to the word "Guo Degang" in the text to be queried is a character, that is, the corresponding real entity is the character "Guo Degang".
- directly searching for the text to be queried entered by the user may not be able to search for the query results actually needed by the user, or it may cause redundant query results.
- the search results may be obtained. It is a resource related to Deng Chao’s work.
- the query result that the user actually needs cannot be searched.
- the search results are resources related to Deng Chao’s works and resources related to Sun Li’s works.
- the resources related to Deng Chao’s works in the query results are information that the user does not need, which will cause redundant query results. .
- the text information corresponding to the set of objects to be queried may be information that the user actually wants to query.
- the set of objects to be queried may include an object to be queried, and the object to be queried is the character "Sun Li".
- the text information corresponding to the object set to be queried where the character "Sun Li" is located is "Sun Li's work”
- the text information is the information that the user actually wants to query.
- the query field corresponding to the text to be queried is determined by the relationship information of the object to be queried in the set of objects to be queried. By determining the set of objects to be queried, the information that the user actually wants to query can be determined. It is helpful to improve the accuracy of the query field corresponding to the text to be queried, so that the query can obtain query results that match the user's intention.
- the object to be queried may be an entity corresponding to a word in the text to be queried in a preset database.
- the object set to be queried may include two objects to be queried (such as the character “Guo Degang” and the cross talk "Water Margin"), where the character "Guo Degang” is the text to be queried
- the corresponding entity of the word "Guo Degang” in the preset database, cross talk "Water Margin” is the entity corresponding to the word “Water Margin” in the text to be queried in the preset database.
- the object to be queried may be a second entity inferred from the first entity, where the first entity is an entity corresponding to a word in the text to be queried in a preset database.
- the text to be queried is "Works of Deng Chao's Wife”
- the first entity corresponding to the word "Deng Chao” in the text to be queried in the preset database is the character “Deng Chao”
- the character “Deng Chao” is in the preset database Connect with the character “Sun Li” through husband and wife relationship. Based on this, it can be inferred that the second entity is the character "Sun Li”.
- the preset database may be a local database in the service device, or a cloud database, which is not limited in the embodiment of the present application.
- a knowledge graph may be stored in the preset database.
- the service device may determine the set of objects to be queried corresponding to the text to be queried from the knowledge graph in the preset database.
- the place of the preset database may specifically refer to the knowledge graph in the preset database. It should be noted that the embodiment of this application takes the determination of the set of objects to be queried corresponding to the text to be queried from the knowledge graph as an example, but does not constitute a limitation to the embodiment of this application.
- the service device The set of objects to be queried corresponding to the text to be queried can also be determined from the knowledge organization structure of the non-knowledge graph.
- the knowledge organization structure is used to store multiple objects and the relationship between each object.
- the knowledge organization structure is stored in a preset database .
- Step S203 The service device determines the relationship information of the object to be queried in each set of objects to be queried from the preset relationship information between the pair of objects.
- the service device can determine the relationship information of the objects to be queried in each set of objects to be queried from the preset relationship information between the two objects , And further determine the query field corresponding to the text to be queried according to the relationship information of the objects to be queried in each collection of objects to be queried.
- the preset relationship information between the two objects can be stored in the aforementioned preset database.
- the relationship between the entities corresponding to the two nodes Information can be stored in a preset database.
- the relationship information between two objects can be the relationship between the corresponding nodes of the two objects in the knowledge graph. For example, when the two objects are the characters "Guo Degang” and the crosstalk "Water Margin", the characters "Guo Degang” and The relationship information between the cross talk "Water Margin” can be a creation relationship or a performance relationship (assuming that the cross talk "Water Margin” was created or performed by Guo Degang).
- nodes, entities, and objects are equivalent to the same concept in a preset database (such as a knowledge graph in a preset database).
- the relationship information of the object to be queried in each set of objects to be queried refers to the relationship information between the object to be queried and all objects in the knowledge graph except the object to be queried, where the other objects are in the knowledge graph.
- the corresponding node and the corresponding node of the object to be queried in the knowledge graph are connected by an edge, that is, the other objects have an association relationship with the object to be queried in the knowledge graph.
- the relationship information of the object to be queried may include the relationship information between the object to be queried and one or more objects.
- the relationship information of the object to be queried may include relationship information between the object to be queried and all objects, or relationship information between the object to be queried and some of all objects.
- the all objects are all objects that have an association relationship in the knowledge graph of the object to be queried. For example, if the node corresponding to the object 1 to be queried is connected to 10 nodes in the knowledge graph by different edges, that is, the object 1 to be queried has an association relationship with the 10 objects. At this time, all the aforementioned objects include these 10 objects, and the aforementioned partial objects are some of these 10 objects.
- the service device can obtain the relationship information between all objects associated with the object to be queried and the object to be queried. If the set of objects to be queried includes multiple objects to be queried, for each object to be queried, the service device can obtain the relationship information between all objects associated with the object to be queried in the set of objects to be queried and the object to be queried.
- the set of objects to be queried includes 4 objects to be queried (such as object to be queried 1, object to be queried 2, object to be queried 3, object to be queried 4), and the relationship of the four objects to be queried in the knowledge graph is as follows :
- the object to be queried 1 is associated with the object to be queried 2, the object to be queried 3, and the object 5 (object 5 is an entity in the knowledge graph), and the object to be queried 3 is associated with the object 4 to be queried.
- the relationship information acquired by the service device may include: the relationship information between the object to be queried 1 and the object to be queried 2, the relationship information between the object to be queried 1 and the object to be queried 3, and the object to be queried 3 and the object to be queried Information about the relationship between objects 4. It can be seen that when the service device obtains the relationship information of the object to be queried 1, it can obtain all the objects (ie, the object to be queried 2 and the object to be queried 3) associated with the object to be queried 1 and the object to be queried 1 There is no need to obtain the relationship information between the object 1 to be queried and other objects (ie, object 5) outside the set of objects to be queried.
- the preset relationship information between the two objects can be automatically captured from the network and can be refreshed in real time.
- the generation and maintenance of the preset relationship information between the two objects can be generated and maintained without manual participation. . This can make it more efficient to determine the relationship information of the object to be queried in each set of objects to be queried from the preset relationship information between the pair of objects, and can ensure the timeliness of the determined relationship information of the object to be queried.
- Step S204 The service device determines the query field corresponding to the aforementioned text to be queried according to the relationship information of the objects to be queried in each set of objects to be queried.
- the service device can determine the query field corresponding to the text to be queried according to the relationship information of the objects to be queried in each set of objects to be queried.
- the service device may preset a supported field, and the service device may support one or more fields.
- the embodiment of the present application takes the service device supporting multiple fields as an example for description.
- the service device supports multiple domains: the service device can obtain resources in each of the supported domains.
- the resources of the field supported by the service device may be stored locally in the service device, or may be stored in the cloud server corresponding to each field, which is not limited in the embodiment of the present application.
- the number of query fields corresponding to the text to be queried may be one or more.
- the service device can determine which resources in the multiple domains that the user actually wants to access when entering the text to be queried, and then determine which domain the user actually wants to access
- the query is performed only on the service device corresponding to the query field, thereby helping to reduce the redundancy of query results.
- the service device corresponding to the query field may be a data server.
- the service device may also send text information corresponding to any set of objects to be queried to the Query the service equipment corresponding to the field.
- the service device corresponding to the query field can obtain the query result according to the text information, and send the query result to the service device.
- the service device receives the query result from the service device corresponding to the query domain, it can output the query result.
- the text information corresponding to each set of objects to be queried may include words corresponding to the objects to be queried in the set of objects to be queried.
- the objects to be queried in the first set of objects to be queried include the character "Guo Degang” and the cross talk "Water Margin”
- the objects to be queried in the second set of objects to be queried include the character "Guo Degang” and the TV series "Water Margin”
- the text information corresponding to the first set of objects to be queried and the text information corresponding to the second set of objects to be queried can both be "Guo Degang” and "Water Margin".
- the service device sends the text information corresponding to any set of objects to be queried to the service device corresponding to the query field to obtain the query results required by the user. .
- the user can not only get the required query result, but also avoid sending the query to the service device corresponding to all the fields supported by the service device The additional overhead caused by the text information corresponding to the set of objects. At the same time, it can also avoid the search results that users do not need, which helps reduce the redundancy of the query results.
- the service device corresponding to the query domain may be the same device as the service device in the determined query domain, or may be different devices.
- the service device corresponding to the query field and the service device that determines the query field are different devices, after the service device determines the query field corresponding to the text to be queried, it sends the text information corresponding to the set of objects to be queried to the service device corresponding to the query field. It is used for illustration and does not constitute a limitation to the embodiments of the present application.
- the service device corresponding to the query domain is the same device as the service device in the determined query domain, the service device can obtain the query result according to the text information corresponding to any set of objects to be queried in the database corresponding to the query domain.
- the resources corresponding to different fields supported by the service device can be stored in different local databases in the service device. In this way, it is possible to avoid querying in the database corresponding to all fields supported by the service equipment, and only need to query in the database corresponding to the query field. This can ensure that the query results required by the user are obtained, and the query efficiency is improved. Can reduce the redundancy of query results.
- the number of query results obtained by the service device may be one or more.
- the service device can also sort the query result and output the sorted query result.
- the query results that are more in line with the user's search requirements can be preferentially output, that is, the query results that are more in line with the user's search requirements will be displayed to the user first, which can effectively improve the effect of intelligent search.
- the application example can reduce the number of query fields, that is, the query scope can be narrowed, so that not only query results that match the user's intention can be obtained, but also It is also beneficial to improve query efficiency and reduce query result redundancy.
- Figure 3 is a schematic flow diagram of another data processing method provided by an embodiment of the present application. This method describes in detail how to determine the set of objects to be queried corresponding to the text to be queried from a preset database, and when each When the query object set includes an object to be queried, how to determine the query field corresponding to the text to be queried according to the relationship information of the object to be queried in the object set to be queried.
- the execution subject of steps S301 to S306 is the service device, or the chip in the service device, and the following description will be made by taking the service device as the execution subject of the data processing method as an example.
- the method may include but is not limited to the following steps:
- Step S301 The service device obtains the text to be queried.
- step S301 refers to the specific description of step S201 in FIG. 2, which will not be repeated here.
- Step S302 The service device determines the target text, and the target text is the text obtained after natural language understanding NLU processing is performed on the text to be queried.
- the service device may perform NLU processing on the text to be queried to obtain the target text.
- the target text can be a phrase.
- the number of target texts obtained by processing the query text can be one or more. For example, when the text to be queried is "Guo Degang's Water Margin", after NLU processing the text to be queried, a phrase is obtained, which is "Guo Degang's Water Margin”. For another example, when the text to be queried is "Water Margin of Guo Qilin's father", two phrases are obtained after NLU processing on the text to be queried, which are "Guo Qilin's father” and “Water Margin”. For another example, when the text to be queried is "the work of Deng Chao's wife", after NLU processing the text to be queried, a phrase is obtained, which is "Deng Chao's wife".
- Step S303 The service device performs word segmentation processing on the target text to obtain each word segmentation of the target text.
- the service device may perform word segmentation processing on each target text respectively to obtain each word segmentation of each target text.
- the service device may call the word segmentation algorithm to perform word segmentation processing on the target text, and obtain each word segmentation of the target text.
- the word segmentation algorithm may include, but is not limited to, a word segmentation algorithm based on string matching (such as forward maximum matching method, reverse maximum matching method, least segmentation, two-way maximum matching method, etc.), word segmentation algorithm based on understanding And the word segmentation algorithm based on statistics, this embodiment of the application does not limit this.
- the two target texts are "Guo Qilin's father” and “Water Margin"
- the participles obtained after word segmentation of "Guo Qilin's father” include “Guo Qilin” and "Father”.
- the word segmentation obtained after word segmentation processing includes "Water Margin”.
- Step S304 The service device determines the object to be queried in each set of objects to be queried from the preset database according to each word segmentation of the target text.
- the number of object sets to be queried is one or more, and each set of objects to be queried includes one or Multiple objects to be queried.
- the service device can determine the object to be queried in each set of objects to be queried from a preset database according to each word segmentation of the target text.
- a word segmentation may correspond to one or more objects (ie entities) in the preset database, or there may be no corresponding objects (ie entities).
- the number of objects corresponding to different word segmentation in the same target text in the preset database are independent of each other.
- the target text is "Guo Qilin's father”
- the target text includes two participles (ie, "Guo Qilin” and "father”).
- the participle "Guo Qilin” can correspond to an entity in the preset database (such as The character "Guo Qilin")
- the participle "father” may not have a corresponding entity in the preset database.
- At least one object to be queried can be determined in the preset database.
- the object to be queried can be an entity corresponding to one of the word segmentation of the target text in the preset database, or an entity corresponding to one of the word segmentation of the target text in the preset database, and the word segmentation in the target text Entity obtained by reasoning other than word segmentation.
- each word segmentation of the target text has a corresponding object in the preset database
- the service device determines from the preset database the value of the object to be queried in the set of objects to be queried according to each word segmentation of the target text.
- the specific implementation may be as follows: for each word segmentation of the target text, different objects corresponding to the word segmentation in the preset database are used as objects to be queried in different sets of objects to be queried. For example, when the target text is "Water Margin", the target text only includes one word segmentation (ie "Water Margin"). If the word segmentation corresponds to two different objects in the preset database, the two objects are crosstalk "Water Margin".
- the service equipment can take the cross talk "Water Margin” as the object to be queried in the first set of objects to be queried, and the TV series “Water Margin” as the object to be queried in the second set of objects to be queried Object.
- the first set of objects to be queried and the second set of objects to be queried are different sets of objects to be queried.
- the service device can store the word segmentation in the preset database The corresponding object in is used as the object to be queried in the set of N objects to be queried.
- the number of objects to be queried in each object set to be queried is the same, and the number of objects to be queried in the object set to be queried may be the number of target texts obtained after NLU processing of the text to be queried. For example, when the text to be queried is "Water Margin of Guo Qilin's father", after NLU processing the text to be queried, two target texts (ie "Guo Qilin's father" and “Water Margin”) can be obtained.
- the objects to be queried in the set of objects to be queried corresponding to the text can include the character "Guo Degang” and the cross talk “Water Margin” (or the character “Guo Degang” and the TV series “Water Margin”), that is, the objects in the set of objects to be queried corresponding to the text to be queried
- the number of objects to be queried is also two.
- the word segmentation of the target text may include at least a first word segmentation and a second word segmentation.
- the first word segmentation corresponds to the first object in the preset database, and the second word segmentation does not correspond to the preset database.
- the object; the service device determines the object to be queried in the set of objects to be queried from a preset database according to each word segmentation of the target text.
- the specific implementation can be: Determine from the preset relationship information between the two objects The relationship information of the first object; the first relationship information that has a matching relationship with the second participle is determined from the relationship information of the first object; if the first object passes the first relationship information and the first relationship information in the preset database If the two objects are connected, the target object is determined according to the second object; and the target object is taken as the object to be queried in each collection of objects to be queried.
- the relationship information of the first object may include the relationship between the first object and each of the multiple objects, or the relationship type between the first object and each of the multiple objects, and the multiple Each object in the object is an object that has an association relationship with the first object in a preset database.
- the first object is the character "Guo Qilin”
- the character "Guo Qilin” has an association relationship with two objects (such as the character “Guo Degang” and the comedy show "Happy Comedian") in the preset database.
- the relationship between the character "Guo Qilin” and the character “Guo Degang” can be father and son, and the type of relationship can be relatives; the relationship between the character “Guo Qilin” and the comedy show "Happy Comedian” can be a guest of the show ,
- the relationship type can be program.
- the matching relationship between the first relationship information and the second participle in the relationship information of the first object may indicate that the first relationship information and the second participle are synonyms.
- the target participle is "Guo Qilin's father”
- the first participle in the target participle is "Guo Qilin”
- the second participle is "father”
- the first object corresponding to the first participle in the preset database is a person In "Guo Qilin”
- the character "Guo Qilin” has an association relationship with two objects (such as the character "Guo Degang” and the comedy show "Happy Comedian) in the preset database
- the character "Guo Qilin” and the character “Guo Degang” The relationship between "” is the father and son, and the relationship between the character “Guo Qilin” and the comedy show "Happy Comedian” is the guest of the show.
- the "father-son” relationship can be regarded as the first relationship information. Since the character "Guo Qilin” and the character “Guo Degang” are connected in the preset database through the first relationship information (that is, the "father-son” relationship), the character “Guo Degang” can be determined as the second object.
- the service device may use the second object as the target object, that is, the second object as the object to be queried in each set of objects to be queried.
- the service device may determine the target object according to the second object, and use the target object as the object to be queried in each collection of objects to be queried Object. Specifically, the service device may determine the target object according to the second object and other second participles of the plurality of second participles except for determining the second object. For example, if the target text is "Guo Qilin’s brother’s elder brother’s father", then the target text includes a first participle (ie "Guo Qilin”), three second participles (respectively "brother", " ⁇ ") ",” father”).
- the second object is the character "Guo Fenyi”.
- the third object is the character "Guo Qilin”.
- the fourth object is the character "Guo Degang”.
- Step S305 The service device determines the relationship information of the object to be queried in each set of objects to be queried from the preset relationship information between the pair of objects.
- step S305 refers to the specific description of step S203 in FIG. 2, which will not be repeated here.
- Step S306 For each set of objects to be queried, if there is a relationship type belonging to the first preset field among the relationship types of the objects to be queried in the set of objects to be queried, the service device determines that the first preset field belongs to the aforementioned text to be queried Corresponding query field; each set of objects to be queried includes one object to be queried, and the relationship information of the objects to be queried in each set of objects to be queried includes one or more relationship types.
- each set of objects to be queried includes one object to be queried
- the service The device may determine that the first preset field belongs to the query field corresponding to the aforementioned text to be queried.
- the number of the first preset domain may be one or more, and the first preset domain may be one or more domains among a plurality of domains supported by the service device. That is, the service device can first determine the field to which the relationship type of the object to be queried in the set of objects to be queried belongs according to the corresponding relationship between the preset relationship type and the preset field. If the field is any of the fields supported by the service device Or multiple fields, the service device can determine that the one or more fields belong to the query field corresponding to the aforementioned text to be queried.
- relationship types of the objects to be queried in different sets of objects to be queried there may be relationship types belonging to different first preset domains.
- the service device supports 3 fields (such as film and television, music, and sound)
- the number of query object sets corresponding to the text to be queried is 2, and the two query object sets include one object to be queried
- the first The relationship types of the objects to be queried in a set of objects to be queried can have relationship types that belong to the two fields of film and television
- the relationship types of the objects to be queried in the second set of objects to be queried can have a voice domain.
- the type of relationship is a set of objects to be queried.
- the first preset field corresponding to the first set of objects to be queried includes film and television, music
- the first preset field corresponding to the second set of objects to be queried includes audio
- the first set of objects to be queried and the second set of objects to be queried The first preset field corresponding to the object set is different.
- the query field corresponding to the text to be queried includes the first preset field corresponding to each set of objects to be queried, that is, the query field corresponding to the text to be queried includes three fields of film, television, music, and sound.
- an entity ie, an object
- the query field corresponding to the text to be queried can also be determined through the relationship type of the entity. Compared with the query field corresponding to the text to be queried by the entity relationship, the query field corresponding to the text to be queried can be determined by the relationship type of the entity. Improve the efficiency of determining the query field corresponding to the text to be queried.
- the relationship information of the object to be queried in each object set to be queried may include multiple relationship types.
- the object set to be queried includes an object to be queried (such as "Guo Degang")
- the object to be queried is in The knowledge graph
- object 1 such as Crosstalk "Water Margin”
- object 2 such as the movie Falling Leaves Returning to the Roots
- the type of creation relationship belongs to In the field of film and television or audio
- the type of performance relationship belongs to the field of film and television.
- the relationship information of the object to be queried may include the type of creation relationship and the type of performance relationship.
- the query field corresponding to the text to be queried may also be determined by the relationship between the objects to be queried in the set of objects to be queried. Specifically, the service device may determine the field to which the relationship of the object to be queried in the set of objects to be queried belongs. If the field is any one or more of the fields supported by the service device, the service device may determine the one or more fields It belongs to the query field corresponding to the aforementioned text to be queried.
- the embodiment of this application can not only determine the query field corresponding to the text to be queried through the knowledge graph, but also obtain the relationship information between the objects to be queried from the knowledge graph, and the relationship information belongs to the text to be queried.
- Query field the embodiments of the present application can provide an interpretable field verification function, which can not only determine the query field corresponding to the text to be queried, but also determine the relationship through which the objects to be queried in the query field are related.
- the query field corresponding to the query text is determined to be film and television, and it can also be determined that the character “Guo Degang” and the cross talk “Water Margin” belong to the field of film and television.
- the creation relationship is associated.
- the application example can reduce the number of query fields, that is, the query scope can be narrowed, so that not only query results that match the user's intention can be obtained, but also It is also beneficial to improve query efficiency and reduce query result redundancy.
- determining the query field corresponding to the text to be queried by the relationship type of the query object can improve the efficiency of determining the query field corresponding to the text to be queried.
- Figure 4 is a schematic flow diagram of another data processing method provided by an embodiment of the present application. This method describes in detail how to query the object set according to each set of objects to be queried includes multiple objects to be queried Determine the query field corresponding to the text to be queried in the relationship information of the object to be queried.
- the execution subject of steps S401 to S406 is the service device, or the chip in the service device, and the following description will be made by taking the service device as the execution subject of the data processing method as an example.
- the method may include but is not limited to the following steps:
- Step S401 The service device obtains the text to be queried.
- step S401 refers to the specific description of step S201 in FIG. 2, which will not be repeated here.
- Step S402 The service device determines a target text, which is a text obtained after natural language understanding NLU processing is performed on the text to be queried.
- Step S403 The service device performs word segmentation processing on the target text to obtain each word segmentation of the target text.
- Step S404 The service device determines the object to be queried in each set of objects to be queried from the preset database according to each word segmentation of the target text.
- the number of object sets to be queried is one or more, and each set of objects to be queried includes one or Multiple objects to be queried.
- Step S405 The service device determines the relationship information of the object to be queried in each set of objects to be queried from the preset relationship information between the pair of objects.
- steps S402 to S405 please refer to the specific descriptions of steps S302 to S304 in FIG. 3 and step S203 in FIG. 2 respectively, which will not be repeated here.
- Step S406 For each set of objects to be queried, if each object to be queried in the set of objects to be queried is connected by a relationship whose type belongs to the first preset field, the service device determines that the first preset field belongs to the aforementioned text to be queried Corresponding query field; where each collection of objects to be queried includes a plurality of objects to be queried, and the relationship information of each object to be queried in each collection of objects to be queried includes the object to be queried and the object to be queried except for the object to be queried The type of relationship between objects to be queried other than.
- the relationship information of each object to be queried in the set of objects to be queried may include the object to be queried and other objects to be queried in the set of objects to be queried except the object to be queried The type of relationship between objects.
- the objects to be queried in the query object set corresponding to the text to be queried include the character “Guo Degang” and the cross talk “Water Margin”, and the character “Guo Degang” is in the knowledge graph
- the relationship information of the character "Guo Degang” obtained by the service device can include the relationship between the character "Guo Degang” and the cross talk "Water Margin” That is, the service device may not acquire the type of relationship between the character “Guo Degang” and the character “Guo Qilin” (the character “Guo Qilin” is an object outside the set of objects to be queried). Therefore, only the type of relationship between the character “Guo Degang” and the cross talk "Water Margin” can be used to determine the query field corresponding to the text to be queried.
- the service device determines the query field corresponding to the text to be queried according to the relationship information of the objects to be queried in each set of objects to be queried.
- the specific implementation manner may be: for each object to be queried Set, determine whether each object to be queried in the set of objects to be queried is connected in the preset database. If they are connected, then further according to the correspondence between the preset relationship type and the preset field, confirm the Whether each object to be queried is connected by a relationship of type belonging to the same field, if so, and the same field is one or more of the multiple fields supported by the service device, it is determined that the one or more fields belong to the aforementioned text to be queried The corresponding query field.
- each object to be queried in the set of objects to be queried is not connected in the preset database, it means that the query field corresponding to the text to be queried cannot be determined through the set of objects to be queried.
- the service device can use other query
- the object set determines the query field corresponding to the aforementioned text to be queried. For example, if the text to be queried is "Guo Degang's Water Margin", and the text to be queried corresponds to two sets of objects to be queried, the first set of objects to be queried includes the character “Guo Degang” and the TV series “Water Margin” , The second set of query objects includes the characters "Guo Degang” and the cross talk "Water Margin".
- the service device can determine the query field corresponding to the text to be queried through the second set of objects to be queried.
- the character "Guo Degang” in the second set of objects to be queried and the crosstalk "Water Margin” are connected through a creative relationship in the preset database.
- the type of creative relationship belongs to the audio field. If the service equipment supports the field including film and television, audio and Music, at this time, the service device can use the voiced domain as the query domain corresponding to the text to be queried.
- each object to be queried in the object set to be queried is not connected by a relationship of type belonging to the same field, it indicates that the query field corresponding to the text to be queried cannot be determined through the object set to be queried. At this time, the service device can pass other objects to be queried.
- the query object set determines the query field corresponding to the aforementioned text to be queried.
- the number of the first preset domain may be one or more, and the first preset domain may be one or more domains among a plurality of domains supported by the service device.
- each set of objects to be queried includes multiple objects to be queried
- the relationship type of the objects to be queried in each set of objects to be queried it can be determined that the user actually wants to access the service device when entering the text to be queried Which of the multiple domains supported resources, and then the domain that the user actually wants to access is used as the query domain corresponding to the text to be queried, and the query is performed only on the service device corresponding to the query domain.
- the application example can reduce the number of query fields, that is, the query scope can be narrowed, so that not only query results that match the user's intention can be obtained, but also It is also beneficial to improve query efficiency and reduce query result redundancy.
- determining the query field corresponding to the text to be queried by the relationship type of the query object can improve the efficiency of determining the query field corresponding to the text to be queried.
- FIG. 5 is a schematic structural diagram of a data processing device provided by an embodiment of the present application.
- the data processing device may be a service device or a device (such as a chip) used for the service device.
- the data processing device 50 is used to execute For the steps performed by the service equipment in the method embodiments corresponding to FIGS. 2 to 4, the data processing apparatus 50 may include:
- the obtaining module 501 is used to obtain the text to be queried
- the processing module 502 is configured to determine from a preset database a set of objects to be queried corresponding to the text to be queried, the number of the object sets to be queried is one or more, and each set of objects to be queried includes one or more objects to be queried;
- the processing module 502 is further configured to determine the relationship information of the object to be queried in each set of objects to be queried from the preset relationship information between the pair of objects;
- the processing module 502 is further configured to determine the query field corresponding to the text to be queried according to the relationship information of the objects to be queried in each collection of objects to be queried.
- each set of objects to be queried may include one object to be queried, and the relationship information of the objects to be queried in each set of objects to be queried may include one or more relationship types;
- the processing module 502 is configured to When determining the query field corresponding to the text to be queried in the collection, the relationship information can be specifically used: For each collection of objects to be queried, if the relationship type of the object to be queried in the collection of objects to be queried belongs to the first The relationship type of the preset field determines that the first preset field belongs to the query field corresponding to the text to be queried.
- each set of objects to be queried may include multiple objects to be queried, and the relationship information of each object to be queried in each set of objects to be queried may include the object to be queried and the set of objects to be queried except for the object to be queried.
- the type of relationship between the objects to be queried other than the query object; the processing module 502 is used to determine the query field corresponding to the text to be queried according to the relationship information of the object to be queried in each set of objects to be queried, which can be specifically used for: Each set of objects to be queried, if each object to be queried in the set of objects to be queried is connected by a relationship whose type belongs to the first preset field, then it is determined that the first preset field belongs to the query field corresponding to the text to be queried above .
- the processing module 502 when used to determine the set of objects to be queried corresponding to the text to be queried from the preset database, it can be specifically used to: determine the target text, which is a natural analysis of the text to be queried.
- the text obtained after language understanding NLU processing; word segmentation processing is performed on the target text to obtain each word segmentation of the target text; according to each word segmentation of the target text, the preset database is used to determine the set of objects to be queried Query object.
- each word segmentation of the target text has a corresponding object in the preset database; the processing module 502 is configured to determine the set of objects to be queried from the preset database according to each word segmentation of the target text When the object to be queried, it can be specifically used to: for each word segmentation of the target text, different objects corresponding to the word segmentation in the preset database are used as the object to be queried in different sets of objects to be queried.
- the word segmentation of the target text may include at least a first word segmentation and a second word segmentation.
- the first word segmentation corresponds to the first object in the preset database, and the second word segmentation does not exist in the preset database.
- the processing module 502 is used to determine the object to be queried in the set of objects to be queried from the preset database according to each word segmentation of the target text.
- it can be used to: Determine the relationship information of the first object in the relationship information; determine the first relationship information that has a matching relationship with the second participle from the relationship information of the first object; if the first object passes the first relationship information in the preset database When the relationship information is connected with the second object, the target object is determined according to the second object; and the target object is taken as the object to be queried in each collection of objects to be queried.
- the data processing device 50 may further include a communication module 503 and an output module 504; the communication module 503 may be used to send text information corresponding to any set of objects to be queried to the service equipment corresponding to the aforementioned query field The communication module 503 can also be used to receive the query result from the service device corresponding to the query field; the output module 504 can be used to output the query result.
- FIG. 6 is a schematic structural diagram of another data processing device provided by an embodiment of the present application.
- the data processing device may be a service device or a device (such as a chip) for a service device.
- the data processing device 60 may include a communication interface 601, a processor 602, and a memory 603.
- the communication interface 601, the processor 602, and the memory 603 may be connected to each other through one or more communication buses, or may be connected in other ways.
- the related functions implemented by the acquisition module 501, the processing module 502, the communication module 503, and the output module 504 shown in FIG. 5 may be implemented by the same processor 602, or may be implemented by multiple different processors 602.
- the communication interface 601 may be used to send data and/or signaling, and receive data and/or signaling.
- the communication interface 601 can be used to send text information corresponding to any set of objects to be queried to the service device corresponding to the aforementioned query field.
- the communication interface 601 may be a transceiver.
- the processor 602 is configured to perform corresponding functions of the service device in the methods described in FIGS. 2 to 4.
- the processor 602 may include one or more processors.
- the processor 602 may be one or more central processing units (CPU), network processors (NP), hardware chips, or any of them. combination.
- the processor 602 is a CPU, the CPU may be a single-core CPU or a multi-core CPU.
- the memory 603 is used to store program codes and the like.
- the memory 603 may include a volatile memory (volatile memory), such as random access memory (random access memory, RAM); the memory 603 may also include a non-volatile memory (non-volatile memory), such as read-only memory (read-only memory). Only memory (ROM), flash memory (flash memory), hard disk drive (HDD) or solid-state drive (SSD); memory 603 may also include a combination of the foregoing types of memories.
- the processor 602 may call the program code stored in the memory 603 to perform the following operations:
- the query field corresponding to the text to be queried is determined.
- each set of objects to be queried may include one object to be queried, and the relationship information of the objects to be queried in each set of objects to be queried may include one or more relationship types; the processor 602 executes according to each set of objects to be queried
- the following operations can be specifically performed: For each set of objects to be queried, if the relationship type of the object to be queried in the set of objects to be queried belongs to the first The relationship type of the preset field determines that the first preset field belongs to the query field corresponding to the text to be queried.
- each set of objects to be queried may include multiple objects to be queried, and the relationship information of each object to be queried in each set of objects to be queried may include the object to be queried and the set of objects to be queried except for the object to be queried.
- the type of relationship between the objects to be queried other than the query object when the processor 602 determines the query field corresponding to the text to be queried according to the relationship information of the object to be queried in each set of objects to be queried, the following operations can be specifically performed: Each set of objects to be queried, if each object to be queried in the set of objects to be queried is connected by a relationship whose type belongs to the first preset field, then it is determined that the first preset field belongs to the query field corresponding to the text to be queried above .
- the processor 602 when the processor 602 executes to determine the set of objects to be queried corresponding to the text to be queried from the preset database, it can specifically perform the following operations: determine the target text, which is a natural analysis of the text to be queried. The text obtained after language understanding NLU processing; word segmentation processing is performed on the target text to obtain each word segmentation of the target text; according to each word segmentation of the target text, the preset database is used to determine the set of objects to be queried Query object.
- each word segmentation of the target text has a corresponding object in a preset database; the processor 602 executes each word segmentation of the target text to determine from the preset database a set of objects to be queried.
- the following operations can be specifically performed: for each word segmentation of the target text, different objects corresponding to the word segmentation in the preset database are used as the objects to be queried in different sets of objects to be queried.
- the word segmentation of the target text may include at least a first word segmentation and a second word segmentation.
- the first word segmentation corresponds to the first object in the preset database, and the second word segmentation does not exist in the preset database.
- the processor 602 may also perform the following operations: send text information corresponding to any set of objects to be queried to the service device corresponding to the aforementioned query field; receive query results from the service device corresponding to the query field; And output the query result.
- processor 602 may also perform operations corresponding to the service device in the embodiment shown in FIG. 2 to FIG. 4. For details, please refer to the description in the method embodiment, which will not be repeated here.
- the embodiment of the present application also provides a computer-readable storage medium, which can be used to store computer software instructions used by the data processing device in the embodiment shown in FIG. 5, which includes a program for executing the program designed for the service device in the above embodiment .
- the aforementioned computer-readable storage medium includes, but is not limited to, flash memory, hard disk, and solid state hard disk.
- the embodiments of the present application also provide a computer program product.
- the computer product When the computer product is run by a computing device, it can execute the method designed for the service device in the above-mentioned embodiments of FIGS. 2 to 4.
- An embodiment of the present application also provides a chip, including a processor and a memory, the memory includes a processor and a memory, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory.
- the computer program is used to implement the method in the above method embodiment.
- the computer program product includes one or more computer instructions.
- the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
- the computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium.
- the computer instructions can be sent from one website site, computer, server, or data center to another website site via wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) , Computer, server or data center for transmission.
- the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center integrated with one or more available media.
- the usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, and a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)).
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
一种数据处理方法及其装置,该方法可以应用于基于人工智能的智能搜索领域,该方法包括:获取待查询文本(S201);从预设数据库中确定该待查询文本对应的待查询对象集合,该待查询对象集合的数量为一个或多个,各个待查询对象集合包括一个或多个待查询对象(S202);从预设的两两对象之间的关系信息中确定各个待查询对象集合中待查询对象的关系信息(S203);根据各个待查询对象集合中待查询对象的关系信息,确定上述待查询文本对应的查询领域(S204)。可以确定待查询文本对应的查询领域,从而有利于降低查询结果冗余。
Description
本申请要求于2019年8月21日提交中国专利局、申请号为201910776210.2、申请名称为“一种数据处理方法及其装置”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请涉及通信技术领域,尤其涉及一种数据处理方法及其装置。
随着通信技术的不断发展,终端设备支持的应用越来越丰富。当终端设备接收到查询请求后,可以向该终端设备支持的所有服务提供商发送查询请求,并在接收到每个服务提供商返回的查询结果之后,向用户反馈查询结果。
当前互联网中信息量巨大,且每个服务提供商对应的领域中的数据存在重名问题。如“水浒传”在影视领域存在多个版本的电视剧《水浒传》,在有声领域存在相声《水浒传》和评书《水浒传》。因此,针对同一查询请求每个服务提供商对应的领域中均存在对应的查询结果,但是实际上用户需要的查询结果属于一个或少数的服务提供商对应的领域。所以,采用现有查询方法进行查询,会导致查询结果冗余。
发明内容
本申请实施例提供一种数据处理方法及其装置,可以确定待查询文本对应的查询领域,从而有利于降低查询结果冗余。
第一方面,本申请实施例提供一种数据处理方法,该方法可以应用于基于人工智能的智能搜索领域,该方法包括:获取待查询文本;从预设数据库中确定该待查询文本对应的待查询对象集合,该待查询对象集合的数量为一个或多个,各个待查询对象集合包括一个或多个待查询对象;从预设的两两对象之间的关系信息中确定各个待查询对象集合中待查询对象的关系信息;根据各个待查询对象集合中待查询对象的关系信息,确定上述待查询文本对应的查询领域。
在该技术方案中,根据各个待查询对象集合中待查询对象的关系信息,可以确定用户输入待查询文本时实际想访问的是服务设备所支持的多个领域中的哪个领域的资源,进而将用户实际想访问的领域作为该待查询文本对应的查询领域。这样有利于降低查询的领域数量,即可以缩小查询范围,这样不仅可以查询得到与用户意图相匹配的查询结果,还有利于提高查询效率、降低查询结果冗余。
在一种实现方式中,各个待查询对象集合可以包括一个待查询对象,各个待查询对象集合中待查询对象的关系信息可以包括一个或多个关系类型;根据各个待查询对象集合中待查询对象的关系信息,确定上述待查询文本对应的查询领域的具体实施方式可以为:针对各个待查询对象集合,若该待查询对象集合中待查询对象的关系类型中存在属于第一预设领域的关系类型,则确定该第一预设领域属于上述待查询文本对应的查询领域。
在该技术方案中,相较于通过待查询对象的关系确定待查询文本对应的查询领域,通 过待查询对象的关系类型确定待查询文本对应的查询领域,可以提高确定待查询文本对应的查询领域的效率。
在一种实现方式中,各个待查询对象集合可以包括多个待查询对象,各个待查询对象集合中的各个待查询对象的关系信息可以包括该待查询对象与该待查询对象集合中除该待查询对象以外的其他待查询对象之间的关系类型;根据各个待查询对象集合中待查询对象的关系信息,确定上述待查询文本对应的查询领域的具体实施方式可以为:针对各个待查询对象集合,若该待查询对象集合中的各个待查询对象通过类型属于第一预设领域的关系相连接,则确定该第一预设领域属于上所述待查询文本对应的查询领域。
在该技术方案中,当各个待查询对象集合包括多个待查询对象时,根据各个待查询对象集合中待查询对象的关系类型,可以确定用户输入待查询文本时实际想访问的是服务设备所支持的多个领域中的哪个领域的资源,进而将用户实际想访问的领域作为该待查询文本对应的查询领域。这样不仅可以查询得到与用户意图相匹配的查询结果,还有利于降低查询的领域数量、提高查询效率、降低查询结果冗余。另外,相较于通过待查询对象的关系确定待查询文本对应的查询领域,通过待查询对象的关系类型确定待查询文本对应的查询领域,可以提高确定待查询文本对应的查询领域的效率。
在一种实现方式中,从预设数据库中确定上述待查询文本对应的待查询对象集合的具体实施方式可以为:确定目标文本,该目标文本为对上述待查询文本进行自然语言理解NLU处理后得到的文本;对该目标文本进行分词处理,得到该目标文本的各个分词;根据该述目标文本的各个分词,从所述预设数据库中确定各个待查询对象集合中的待查询对象。
在一种实现方式中,上述目标文本的各个分词在预设数据库中均存在对应的对象;根据上述目标文本的各个分词,从预设数据库中确定各个待查询对象集合中的待查询对象的具体实施方式可以为:针对该目标文本的各个分词,将该分词在预设数据库中对应的不同对象作为不同待查询对象集合中的待查询对象。
在一种实现方式中,上述目标文本的分词至少可以包括第一分词和第二分词,该第一分词在预设数据库中对应第一对象,该第二分词在所述预设数据库中不存在对应的对象;根据该目标文本的各个分词,从预设数据库中确定各个待查询对象集合中的待查询对象的具体实施方式可以为:从预设的两两对象之间的关系信息中确定该第一对象的关系信息;从该第一对象的关系信息中确定与该第二分词具有匹配关系的第一关系信息;若该第一对象在预设数据库中通过该第一关系信息与第二对象相连接,则根据该第二对象确定目标对象;并将该目标对象作为各个待查询对象集合中的待查询对象。
在该技术方案中,当目标文本的分词包括一个第一分词和多个第二分词时,可以根据该第一分词在预设数据库中对应第一对象和该多个第二分词进行多级推理,以得到目标实体,并将目标实体作为各个待查询对象集合中的待查询对象。通过这种方式,有利于确定出用户实际需要查询的对象。
在一种实现方式中,该方法还可以包括:将任意一个待查询对象集合对应的文本信息发送给上述查询领域对应的服务设备;接收来自该查询领域对应的服务设备的查询结果;并输出该查询结果。
在该技术方案中,通过仅将待查询对象集合对应的文本信息发送给上述查询领域对应 的服务设备,既可以使得用户可以得到需要的查询结果,也可以避免向服务设备所支持的所有领域对应的服务设备发送待查询对象集合对应的文本信息所导致的额外开销。同时,还能避免搜索得到一些用户并不需要的查询结果,这样有利于降低查询结果冗余。
第二方面,本申请实施例提供一种数据处理装置,该装置可以是服务设备,也可以是用于服务设备的装置(例如芯片)。该装置具有实现第一方面所提供的数据处理方法的功能,该功能可以通过硬件实现,也可以通过硬件执行相应的软件实现。该硬件或软件包括一个或多个与上述功能相对应的模块。
第三方面,本申请实施例提供一种计算机可读存储介质,用于储存为第二方面所述的数据处理装置所用的计算机程序指令,其包含用于执行上述第一方面所涉及的程序。
第四方面,本申请实施例提供又一种数据处理装置,该装置可以为服务设备或用于服务设备的装置(例如芯片)。该装置包括存储器和处理器,所述处理器通过总线与所述存储器连接,存储器中存储有程序指令,处理器调用存储器中存储的程序指令以实现第一方面所提供的数据处理方法。
第五方面,本申请实施例提供一种计算机程序产品,该程序产品包括程序,所述程序被数据处理装置执行时,使得所述数据处理装置实现上述第一方面所述的方法。
图1a是本申请实施例公开的一种通信系统的架构示意图;
图1b是本申请实施例公开的一种服务设备的结构示意图;
图1c是本申请实施例公开的一种服务设备的软件系统的示意图;
图2是本申请实施例公开的一种数据处理方法的流程示意图;
图3是本申请实施例公开的另一种数据处理方法的流程示意图;
图4是本申请实施例公开的又一种数据处理方法的流程示意图;
图5是本申请实施例公开的一种数据处理装置的结构示意图;
图6是本申请实施例公开的另一种数据处理装置的结构示意图。
为了便于理解,首先介绍本申请涉及的术语。
1、知识图谱(knowledge graph,KG)
知识图谱是一种基于图的数据结构,由节点和边组成。知识图谱用于描述真实世界中存在的各种实体和概念,以及他们之间(即概念与概念之间、概念与实体之间、实体与实体之间)的关系。知识图谱中的一条知识可以用三元组(triple)来表示,三元组可以表示为(实体1,实体关系,实体2)。其中,实体1和实体2表示知识图谱中的节点,实体关系表示知识图谱中的边,该三元组表示实体1和实体2在知识图谱中通过该实体关系相关联。
概念是具有同种特性的实体构成的集合,如国家、民族、书籍、电脑等。概念主要指集合、类别、对象类型、事物的种类,例如人物、地理等。实体代表属于某概念的基本元素,即某概念所指的具体实体。实体是具有可区别性且独立存在的某种事物。如某一个人、 某一个城市、某一种植物、某一种商品等。实体是知识图谱中的最基本元素,不同的实体间存在不同的关系。
2、自然语言理解(natural language understanding,NLU)
人工智能(artificial intelligence,AI)是研究、开发用于模拟、延伸和扩展人的智能的理论、方法、技术及应用系统的一门新的技术科学。AI的核心是使用机器学习技术,以允许机器模拟人类行为的某些核心方面。换言之,AI允许机器表现为能够在很少或没有人为干预的情况下感知、学习、做出决策、以及采取行动的自主系统。
NLU是人工智能的一个应用领域,NLU是使用自然语言同计算机进行通讯的技术,通过NLU可以让计算机“理解”自然语言,进而执行人类所期望的某些语言功能,换言之,NLU是人与机器交流的桥梁。
语言理解可以包括但不限于以下内容:①能够理解句子的正确次序规则和概念,也能理解不含规则的句子;②知道词的确切含义、形式、词类及构词法;③了解词的语义分类、词的多义性、词的歧义性;④指定和不定特性及所有特性;⑤问题领域的结构知识和实践概念;⑥语言的语气信息和韵律表现;⑦有关语言表达形式的文字知识;⑧论域的背景知识。
为了更好的理解本申请实施例公开的一种数据处理方法,下面首先对本申请实施例适用的通信系统进行描述。
请参见图1a,图1a是本申请实施例公开的一种通信系统的架构示意图。如图1a所示,该通信系统包括终端设备101和服务设备102。
用户可以通过终端设备101的输入设备在终端设备101显示的文本框中输入待查询文本(例如“郭德纲的水浒传”),然后点击查询按钮,以便终端设备101检测到查询按钮被点击时,将该待查询文本发送给服务设备102;
服务设备102接收到该待查询文本之后,可以从预设数据库中确定该待查询文本对应的待查询对象集合,待查询对象集合的数量可以为一个或多个,然后从预设的两两对象之间的关系信息中确定各个待查询对象集合中待查询对象的关系信息,然后根据各个待查询对象集合中待查询对象的关系信息,确定该待查询文本对应的查询领域。其中,各个待查询对象集合可以包括一个或多个待查询对象。
待查询对象可以为预设数据库中的一个实体。例如,待查询文本为“郭德纲的水浒传”时,若该待查询文本对应一个待查询对象集合,则该待查询对象集合中的待查询对象可以包括人物“郭德纲”和相声《水浒传》。其中,人物“郭德纲”、相声《水浒传》分别为预设数据库中的一个实体。
待查询对象的关系信息为该待查询对象在预设数据库中对应的实体的关系信息,即待查询对象的关系信息可以包括该待查询对象在预设数据库中对应的实体与预设数据库中除该待查询对象对应的实体以外的其他实体之间的关系信息。例如,待查询对象为人物“郭德纲”时,该待查询对象的关系信息可以包括但不限于:人物“郭德纲”与相声《水浒传》之间的关系信息、人物“郭德纲”与郭德纲创办的德云社之间的关系信息。
在一种实现方式中,图1a所示的通信系统还可以包括数据服务器(图1a未示),服 务设备102确定查询领域之后,可以将任意一个待查询对象集合对应的文本信息发送给该查询领域对应的数据服务器,接收来自该数据服务器的查询结果,并输出该查询结果,以供用户根据自身需要进行选择。
在一种实现方式中,图1a中由服务设备102执行的步骤,可以由终端设备101替代执行,即终端设备101可以从预设数据库中确定该待查询文本对应的待查询对象集合,并从预设的两两对象之间的关系信息中确定各个待查询对象集合中待查询对象的关系信息,然后根据各个待查询对象集合中待查询对象的关系信息,确定该待查询文本对应的查询领域。同理,在一种实现方式中,图1a中由终端设备101执行的步骤,可以由服务设备102替代执行,即图1a中服务设备102接收到的待查询文本,可以是服务设备102根据用户的输入操作得到的。
其中,本申请实施例中的终端设备101是用户侧的一种用于接收或发射信号的实体,如手机。终端设备也可以称为终端(terminal)、用户设备(user equipment,UE)、移动台(mobile station,MS)、移动终端(mobile terminal,MT)等。终端设备可以是手机(mobile phone)、智能电视、穿戴式设备、平板电脑(Pad)、带无线收发功能的电脑、虚拟现实(virtual reality,VR)终端设备、增强现实(augmented reality,AR)终端设备、工业控制(industrial control)中的无线终端、无人驾驶(self-driving)中的无线终端、远程手术(remote medical surgery)中的无线终端、智能电网(smart grid)中的无线终端、运输安全(transportation safety)中的无线终端、智慧城市(smart city)中的无线终端、智慧家庭(smart home)中的无线终端等等。本申请的实施例对终端设备所采用的具体技术和具体设备形态不做限定。
本申请实施例中的服务设备102可以由处理器、存储器和网络接口组成,服务设备102可以是终端设备或者服务器。
需要说明的是,本申请实施例的技术方案可以应用于基于人工智能的智能搜索系统、智能问答系统等查询系统。当应用于智能搜索系统时,数据服务器可以为搜索引擎服务器、多媒体服务器等资源服务器。当应用于智能问答系统时,数据服务器可以为搜索引擎服务器或其他资源服务器。
可以理解的是,本申请实施例描述的通信系统是为了更加清楚的说明本申请实施例的技术方案,并不构成对于本申请实施例提供的技术方案的限定,本领域普通技术人员可知,随着系统架构的演变和新业务场景的出现,本申请实施例提供的技术方案对于类似的技术问题,同样适用。
为了能够更好地理解本申请实施例,下面对本申请实施例的服务设备的结构进行介绍:
图1b示出了服务设备1300的结构示意图。服务设备1300可以包括处理器1310,外部存储器接口1320,内部存储器1321,通用串行总线(universal serial bus,USB)接口1330,充电管理模块1340,电源管理模块1341,电池1342,天线1,天线2,移动通信模块1350,无线通信模块1360,音频模块1370,扬声器1370A,受话器1370B,麦克风1370C,耳机接口1370D,传感器模块1380,按键1390,马达1391,指示器1392,摄像头1393,显示屏1394,以及用户标识模块(subscriber identification module,SIM)卡接口1395等。其中,传感器模块1380可以包括压力传感器1380A,陀螺仪传感器1380B,气压传感器1380C,磁传感器1380D,加速度传感器1380E,距离传感器1380F,接近光传感器1380G,指纹传 感器1380H,温度传感器1380J,触摸传感器1380K,环境光传感器1380L,骨传导传感器1380M等。
可以理解的是,本发明实施例示意的结构并不构成对服务设备1300的具体限定。在本申请另一些实施例中,服务设备1300可以包括比图示更多或更少的部件,或者组合某些部件,或者拆分某些部件,或者不同的部件布置。图示的部件可以以硬件,软件或软件和硬件的组合实现。
处理器1310可以包括一个或多个处理单元,例如:处理器1310可以包括应用处理器(application processor,AP),调制解调处理器,图形处理器(graphics processing unit,GPU),图像信号处理器(image signal processor,ISP),控制器,视频编解码器,数字信号处理器(digital signal processor,DSP),基带处理器,和/或神经网络处理器(neural-network processing unit,NPU)等。其中,不同的处理单元可以是独立的器件,也可以集成在一个或多个处理器中。
控制器可以根据指令操作码和时序信号,产生操作控制信号,完成取指令和执行指令的控制。
处理器1310中还可以设置存储器,用于存储指令和数据。在一些实施例中,处理器1310中的存储器为高速缓冲存储器。该存储器可以保存处理器1310刚用过或循环使用的指令或数据。如果处理器1310需要再次使用该指令或数据,可从所述存储器中直接调用。避免了重复存取,减少了处理器1310的等待时间,因而提高了系统的效率。
在一些实施例中,处理器1310可以包括一个或多个接口。接口可以包括集成电路(inter-integrated circuit,I2C)接口,集成电路内置音频(inter-integrated circuit sound,I2S)接口,脉冲编码调制(pulse code modulation,PCM)接口,通用异步收发传输器(universal asynchronous receiver/transmitter,UART)接口,移动产业处理器接口(mobile industry processor interface,MIPI),通用输入输出(general-purpose input/output,GPIO)接口,用户标识模块(subscriber identity module,SIM)接口,和/或通用串行总线(universal serial bus,USB)接口等。
I2C接口是一种双向同步串行总线,包括一根串行数据线(serial data line,SDA)和一根串行时钟线(derail clock line,SCL)。在一些实施例中,处理器1310可以包含多组I2C总线。处理器1310可以通过不同的I2C总线接口分别耦合触摸传感器1380K,充电器,闪光灯,摄像头1393等。例如:处理器1310可以通过I2C接口耦合触摸传感器1380K,使处理器1310与触摸传感器1380K通过I2C总线接口通信,实现服务设备1300的触摸功能。
I2S接口可以用于音频通信。在一些实施例中,处理器1310可以包含多组I2S总线。处理器1310可以通过I2S总线与音频模块1370耦合,实现处理器1310与音频模块1370之间的通信。在一些实施例中,音频模块1370可以通过I2S接口向无线通信模块1360传递音频信号,实现通过蓝牙耳机接听电话的功能。
PCM接口也可以用于音频通信,将模拟信号抽样,量化和编码。在一些实施例中,音频模块1370与无线通信模块1360可以通过PCM总线接口耦合。在一些实施例中,音频模块1370也可以通过PCM接口向无线通信模块1360传递音频信号,实现通过蓝牙耳机接听电话的功能。所述I2S接口和所述PCM接口都可以用于音频通信。
UART接口是一种通用串行数据总线,用于异步通信。该总线可以为双向通信总线。 它将要传输的数据在串行通信与并行通信之间转换。在一些实施例中,UART接口通常被用于连接处理器1310与无线通信模块1360。例如:处理器1310通过UART接口与无线通信模块1360中的蓝牙模块通信,实现蓝牙功能。在一些实施例中,音频模块1370可以通过UART接口向无线通信模块1360传递音频信号,实现通过蓝牙耳机播放音乐的功能。
MIPI接口可以被用于连接处理器1310与显示屏1394,摄像头1393等外围器件。MIPI接口包括摄像头串行接口(camera serial interface,CSI),显示屏串行接口(display serial interface,DSI)等。在一些实施例中,处理器1310和摄像头1393通过CSI接口通信,实现服务设备1300的拍摄功能。处理器1310和显示屏1394通过DSI接口通信,实现服务设备1300的显示功能。
GPIO接口可以通过软件配置。GPIO接口可以被配置为控制信号,也可被配置为数据信号。在一些实施例中,GPIO接口可以用于连接处理器1310与摄像头1393,显示屏1394,无线通信模块1360,音频模块1370,传感器模块1380等。GPIO接口还可以被配置为I2C接口,I2S接口,UART接口,MIPI接口等。
USB接口1330是符合USB标准规范的接口,具体可以是Mini USB接口,Micro USB接口,USB Type C接口等。USB接口1330可以用于连接充电器为服务设备1300充电,也可以用于服务设备1300与外围设备之间传输数据。也可以用于连接耳机,通过耳机播放音频。该接口还可以用于连接其他服务设备,例如AR设备等。
可以理解的是,本发明实施例示意的各模块间的接口连接关系,只是示意性说明,并不构成对服务设备1300的结构限定。在本申请另一些实施例中,服务设备1300也可以采用上述实施例中不同的接口连接方式,或多种接口连接方式的组合。
充电管理模块1340用于从充电器接收充电输入。其中,充电器可以是无线充电器,也可以是有线充电器。在一些有线充电的实施例中,充电管理模块1340可以通过USB接口1330接收有线充电器的充电输入。在一些无线充电的实施例中,充电管理模块1340可以通过服务设备1300的无线充电线圈接收无线充电输入。充电管理模块1340为电池1342充电的同时,还可以通过电源管理模块1341为服务设备供电。
电源管理模块1341用于连接电池1342,充电管理模块1340与处理器1310。电源管理模块1341接收电池1342和/或充电管理模块1340的输入,为处理器1310,内部存储器1321,显示屏1394,摄像头1393,和无线通信模块1360等供电。电源管理模块1341还可以用于监测电池容量,电池循环次数,电池健康状态(漏电,阻抗)等参数。在其他一些实施例中,电源管理模块1341也可以设置于处理器1310中。在另一些实施例中,电源管理模块1341和充电管理模块1340也可以设置于同一个器件中。
服务设备1300的无线通信功能可以通过天线1,天线2,移动通信模块1350,无线通信模块1360,调制解调处理器以及基带处理器等实现。
天线1和天线2用于发射和接收电磁波信号。服务设备1300中的每个天线可用于覆盖单个或多个通信频带。不同的天线还可以复用,以提高天线的利用率。例如:可以将天线1复用为无线局域网的分集天线。在另外一些实施例中,天线可以和调谐开关结合使用。
移动通信模块1350可以提供应用在服务设备1300上的包括2G/3G/4G/5G等无线通信的解决方案。移动通信模块1350可以包括至少一个滤波器,开关,功率放大器,低噪声放 大器(low noise amplifier,LNA)等。移动通信模块1350可以由天线1接收电磁波,并对接收的电磁波进行滤波,放大等处理,传送至调制解调处理器进行解调。移动通信模块1350还可以对经调制解调处理器调制后的信号放大,经天线1转为电磁波辐射出去。在一些实施例中,移动通信模块1350的至少部分功能模块可以被设置于处理器1310中。在一些实施例中,移动通信模块1350的至少部分功能模块可以与处理器1310的至少部分模块被设置在同一个器件中。
调制解调处理器可以包括调制器和解调器。其中,调制器用于将待发送的低频基带信号调制成中高频信号。解调器用于将接收的电磁波信号解调为低频基带信号。随后解调器将解调得到的低频基带信号传送至基带处理器处理。低频基带信号经基带处理器处理后,被传递给应用处理器。应用处理器通过音频设备(不限于扬声器1370A,受话器1370B等)输出声音信号,或通过显示屏1394显示图像或视频。在一些实施例中,调制解调处理器可以是独立的器件。在另一些实施例中,调制解调处理器可以独立于处理器1310,与移动通信模块1350或其他功能模块设置在同一个器件中。
无线通信模块1360可以提供应用在服务设备1300上的包括无线局域网(wireless local area networks,WLAN)(如无线保真(wireless fidelity,Wi-Fi)网络),蓝牙(bluetooth,BT),全球导航卫星系统(global navigation satellite system,GNSS),调频(frequency modulation,FM),近距离无线通信技术(near field communication,NFC),红外技术(infrared,IR)等无线通信的解决方案。无线通信模块1360可以是集成至少一个通信处理模块的一个或多个器件。无线通信模块1360经由天线2接收电磁波,将电磁波信号调频以及滤波处理,将处理后的信号发送到处理器1310。无线通信模块1360还可以从处理器1310接收待发送的信号,对其进行调频,放大,经天线2转为电磁波辐射出去。
在一些实施例中,服务设备1300的天线1和移动通信模块1350耦合,天线2和无线通信模块1360耦合,使得服务设备1300可以通过无线通信技术与网络以及其他设备通信。所述无线通信技术可以包括全球移动通讯系统(global system for mobile communications,GSM),通用分组无线服务(general packet radio service,GPRS),码分多址接入(code division multiple access,CDMA),宽带码分多址(wideband code division multiple access,WCDMA),时分码分多址(time-division code division multiple access,TD-SCDMA),长期演进(long term evolution,LTE),BT,GNSS,WLAN,NFC,FM,和/或IR技术等。所述GNSS可以包括全球卫星定位系统(global positioning system,GPS),全球导航卫星系统(global navigation satellite system,GLONASS),北斗卫星导航系统(beidou navigation satellite system,BDS),准天顶卫星系统(quasi-zenith satellite system,QZSS)和/或星基增强系统(satellite based augmentation systems,SBAS)。
服务设备1300通过GPU,显示屏1394,以及应用处理器等实现显示功能。GPU为图像处理的微处理器,连接显示屏1394和应用处理器。GPU用于执行数学和几何计算,用于图形渲染。处理器1310可包括一个或多个GPU,其执行程序指令以生成或改变显示信息。
显示屏1394用于显示图像,视频等。显示屏1394包括显示面板。显示面板可以采用液晶显示屏(liquid crystal display,LCD),有机发光二极管(organic light-emitting diode,OLED), 有源矩阵有机发光二极体或主动矩阵有机发光二极体(active-matrix organic light emitting diode的,AMOLED),柔性发光二极管(flex light-emitting diode,FLED),Miniled,MicroLed,Micro-oLed,量子点发光二极管(quantum dot light emitting diodes,QLED)等。在一些实施例中,服务设备1300可以包括1个或N个显示屏1394,N为大于1的正整数。
服务设备1300可以通过ISP,摄像头1393,视频编解码器,GPU,显示屏1394以及应用处理器等实现拍摄功能。
ISP用于处理摄像头1393反馈的数据。例如,拍照时,打开快门,光线通过镜头被传递到摄像头感光元件上,光信号转换为电信号,摄像头感光元件将所述电信号传递给ISP处理,转化为肉眼可见的图像。ISP还可以对图像的噪点,亮度,肤色进行算法优化。ISP还可以对拍摄场景的曝光,色温等参数优化。在一些实施例中,ISP可以设置在摄像头1393中。
摄像头1393用于捕获静态图像或视频。物体通过镜头生成光学图像投射到感光元件。感光元件可以是电荷耦合器件(charge coupled device,CCD)或互补金属氧化物半导体(complementary metal-oxide-semiconductor,CMOS)光电晶体管。感光元件把光信号转换成电信号,之后将电信号传递给ISP转换成数字图像信号。ISP将数字图像信号输出到DSP加工处理。DSP将数字图像信号转换成标准的RGB,YUV等格式的图像信号。在一些实施例中,服务设备1300可以包括1个或N个摄像头1393,N为大于1的正整数。
数字信号处理器用于处理数字信号,除了可以处理数字图像信号,还可以处理其他数字信号。例如,当服务设备1300在频点选择时,数字信号处理器用于对频点能量进行傅里叶变换等。
视频编解码器用于对数字视频压缩或解压缩。服务设备1300可以支持一种或多种视频编解码器。这样,服务设备1300可以播放或录制多种编码格式的视频,例如:动态图像专家组(moving picture experts group,MPEG)1,MPEG2,MPEG3,MPEG4等。
NPU为神经网络(neural-network,NN)计算处理器,通过借鉴生物神经网络结构,例如借鉴人脑神经元之间传递模式,对输入信息快速处理,还可以不断的自学习。通过NPU可以实现服务设备1300的智能认知等应用,例如:图像识别,人脸识别,语音识别,文本理解等。
外部存储器接口1320可以用于连接外部存储卡,例如Micro SD卡,实现扩展服务设备1300的存储能力。外部存储卡通过外部存储器接口1320与处理器1310通信,实现数据存储功能。例如将音乐,视频等文件保存在外部存储卡中。
内部存储器1321可以用于存储计算机可执行程序代码,所述可执行程序代码包括指令。内部存储器1321可以包括存储程序区和存储数据区。其中,存储程序区可存储操作系统,至少一个功能所需的应用程序(比如声音播放功能,图像播放功能等)等。存储数据区可存储服务设备1300使用过程中所创建的数据(比如音频数据,电话本等)等。此外,内部存储器1321可以包括高速随机存取存储器,还可以包括非易失性存储器,例如至少一个磁盘存储器件,闪存器件,通用闪存存储器(universal flash storage,UFS)等。处理器1310通过运行存储在内部存储器1321的指令,和/或存储在设置于处理器中的存储器的指令,执行服务设备1300的各种功能应用以及数据处理。
服务设备1300可以通过音频模块1370,扬声器1370A,受话器1370B,麦克风1370C,耳机接口1370D,以及应用处理器等实现音频功能。例如音乐播放,录音等。
音频模块1370用于将数字音频信息转换成模拟音频信号输出,也用于将模拟音频输入转换为数字音频信号。音频模块1370还可以用于对音频信号编码和解码。在一些实施例中,音频模块1370可以设置于处理器1310中,或将音频模块1370的部分功能模块设置于处理器1310中。
扬声器1370A,也称“喇叭”,用于将音频电信号转换为声音信号。服务设备1300可以通过扬声器1370A收听音乐,或收听免提通话。
受话器1370B,也称“听筒”,用于将音频电信号转换成声音信号。当服务设备1300接听电话或语音信息时,可以通过将受话器1370B靠近人耳接听语音。
麦克风1370C,也称“话筒”,“传声器”,用于将声音信号转换为电信号。当拨打电话或发送语音信息时,用户可以通过人嘴靠近麦克风1370C发声,将声音信号输入到麦克风1370C。服务设备1300可以设置至少一个麦克风1370C。在另一些实施例中,服务设备1300可以设置两个麦克风1370C,除了采集声音信号,还可以实现降噪功能。在另一些实施例中,服务设备1300还可以设置三个,四个或更多麦克风1370C,实现采集声音信号,降噪,还可以识别声音来源,实现定向录音功能等。
耳机接口1370D用于连接有线耳机。耳机接口1370D可以是USB接口1330,也可以是3.5mm的开放移动服务设备平台(open mobile terminal platform,OMTP)标准接口,美国蜂窝电信工业协会(cellular telecommunications industry association of the USA,CTIA)标准接口。
压力传感器1380A用于感受压力信号,可以将压力信号转换成电信号。在一些实施例中,压力传感器1380A可以设置于显示屏1394。压力传感器1380A的种类很多,如电阻式压力传感器,电感式压力传感器,电容式压力传感器等。电容式压力传感器可以是包括至少两个具有导电材料的平行板。当有力作用于压力传感器1380A,电极之间的电容改变。服务设备1300根据电容的变化确定压力的强度。当有触摸操作作用于显示屏1394,服务设备1300根据压力传感器1380A检测所述触摸操作强度。服务设备1300也可以根据压力传感器1380A的检测信号计算触摸的位置。在一些实施例中,作用于相同触摸位置,但不同触摸操作强度的触摸操作,可以对应不同的操作指令。例如:当有触摸操作强度小于第一压力阈值的触摸操作作用于短消息应用图标时,执行查看短消息的指令。当有触摸操作强度大于或等于第一压力阈值的触摸操作作用于短消息应用图标时,执行新建短消息的指令。
陀螺仪传感器1380B可以用于确定服务设备1300的运动姿态。在一些实施例中,可以通过陀螺仪传感器1380B确定服务设备1300围绕三个轴(即,x,y和z轴)的角速度。陀螺仪传感器1380B可以用于拍摄防抖。示例性的,当按下快门,陀螺仪传感器1380B检测服务设备1300抖动的角度,根据角度计算出镜头模组需要补偿的距离,让镜头通过反向运动抵消服务设备1300的抖动,实现防抖。陀螺仪传感器1380B还可以用于导航,体感游戏场景。
气压传感器1380C用于测量气压。在一些实施例中,服务设备1300通过气压传感器 1380C测得的气压值计算海拔高度,辅助定位和导航。
磁传感器1380D包括霍尔传感器。服务设备1300可以利用磁传感器1380D检测翻盖皮套的开合。在一些实施例中,当服务设备1300是翻盖机时,服务设备1300可以根据磁传感器1380D检测翻盖的开合。进而根据检测到的皮套的开合状态或翻盖的开合状态,设置翻盖自动解锁等特性。
加速度传感器1380E可检测服务设备1300在各个方向上(一般为三轴)加速度的大小。当服务设备1300静止时可检测出重力的大小及方向。还可以用于识别服务设备姿态,应用于横竖屏切换,计步器等应用。
距离传感器1380F,用于测量距离。服务设备1300可以通过红外或激光测量距离。在一些实施例中,拍摄场景,服务设备1300可以利用距离传感器1380F测距以实现快速对焦。
接近光传感器1380G可以包括例如发光二极管(LED)和光检测器,例如光电二极管。发光二极管可以是红外发光二极管。服务设备1300通过发光二极管向外发射红外光。服务设备1300使用光电二极管检测来自附近物体的红外反射光。当检测到充分的反射光时,可以确定服务设备1300附近有物体。当检测到不充分的反射光时,服务设备1300可以确定服务设备1300附近没有物体。服务设备1300可以利用接近光传感器1380G检测用户手持服务设备1300贴近耳朵通话,以便自动熄灭屏幕达到省电的目的。接近光传感器1380G也可用于皮套模式,口袋模式自动解锁与锁屏。
环境光传感器1380L用于感知环境光亮度。服务设备1300可以根据感知的环境光亮度自适应调节显示屏1394亮度。环境光传感器1380L也可用于拍照时自动调节白平衡。环境光传感器1380L还可以与接近光传感器1380G配合,检测服务设备1300是否在口袋里,以防误触。
指纹传感器1380H用于采集指纹。服务设备1300可以利用采集的指纹特性实现指纹解锁,访问应用锁,指纹拍照,指纹接听来电等。
温度传感器1380J用于检测温度。在一些实施例中,服务设备1300利用温度传感器1380J检测的温度,执行温度处理策略。例如,当温度传感器1380J上报的温度超过阈值,服务设备1300执行降低位于温度传感器1380J附近的处理器的性能,以便降低功耗实施热保护。在另一些实施例中,当温度低于另一阈值时,服务设备1300对电池1342加热,以避免低温导致服务设备1300异常关机。在其他一些实施例中,当温度低于又一阈值时,服务设备1300对电池1342的输出电压执行升压,以避免低温导致的异常关机。
触摸传感器1380K,也称“触控器件”。触摸传感器1380K可以设置于显示屏1394,由触摸传感器1380K与显示屏1394组成触摸屏,也称“触控屏”。触摸传感器1380K用于检测作用于其上或附近的触摸操作。触摸传感器可以将检测到的触摸操作传递给应用处理器,以确定触摸事件类型。可以通过显示屏1394提供与触摸操作相关的视觉输出。在另一些实施例中,触摸传感器1380K也可以设置于服务设备1300的表面,与显示屏1394所处的位置不同。
骨传导传感器1380M可以获取振动信号。在一些实施例中,骨传导传感器1380M可以获取人体声部振动骨块的振动信号。骨传导传感器1380M也可以接触人体脉搏,接收血压跳动信号。在一些实施例中,骨传导传感器1380M也可以设置于耳机中,结合成骨传导 耳机。音频模块1370可以基于所述骨传导传感器1380M获取的声部振动骨块的振动信号,解析出语音信号,实现语音功能。应用处理器可以基于所述骨传导传感器1380M获取的血压跳动信号解析心率信息,实现心率检测功能。
按键1390包括开机键,音量键等。按键1390可以是机械按键。也可以是触摸式按键。服务设备1300可以接收按键输入,产生与服务设备1300的用户设置以及功能控制有关的键信号输入。
马达1391可以产生振动提示。马达1391可以用于来电振动提示,也可以用于触摸振动反馈。例如,作用于不同应用(例如拍照,音频播放等)的触摸操作,可以对应不同的振动反馈效果。作用于显示屏1394不同区域的触摸操作,马达1391也可对应不同的振动反馈效果。不同的应用场景(例如:时间提醒,接收信息,闹钟,游戏等)也可以对应不同的振动反馈效果。触摸振动反馈效果还可以支持自定义。
指示器1392可以是指示灯,可以用于指示充电状态,电量变化,也可以用于指示消息,未接来电,通知等。
SIM卡接口1395用于连接SIM卡。SIM卡可以通过插入SIM卡接口1395,或从SIM卡接口1395拔出,实现和服务设备1300的接触和分离。服务设备1300可以支持1个或N个SIM卡接口,N为大于1的正整数。SIM卡接口1395可以支持Nano SIM卡,Micro SIM卡,SIM卡等。同一个SIM卡接口1395可以同时插入多张卡。所述多张卡的类型可以相同,也可以不同。SIM卡接口1395也可以兼容不同类型的SIM卡。SIM卡接口1395也可以兼容外部存储卡。服务设备1300通过SIM卡和网络交互,实现通话以及数据通信等功能。在一些实施例中,服务设备1300采用eSIM,即:嵌入式SIM卡。eSIM卡可以嵌在服务设备1300中,不能和服务设备1300分离。
以下对服务设备1300的软件系统进行详细介绍:
服务设备1300的软件系统可以采用分层架构,事件驱动架构,微核架构,微服务架构,或云架构。本发明实施例以分层架构的Android系统为例,示例性说明服务设备1300的软件结构。
如图1c所示,图1c是本发明实施例的服务设备1300的软件结构框图。分层架构将软件分成若干个层,每一层都有清晰的角色和分工。层与层之间通过软件接口通信。在一些实施例中,将Android系统分为四层,从上至下分别为应用程序层,应用程序框架层,安卓运行时(Android runtime)和系统库,以及内核层。
应用程序层可以包括一系列应用程序包。如图1c所示,应用程序包可以包括相机,图库,日历,通话,地图,导航,WLAN,蓝牙,音乐,视频,短信息等应用程序。
应用程序框架层为应用程序层的应用程序提供应用编程接口(application programming interface,API)和编程框架。应用程序框架层包括一些预先定义的函数。如图1c所示,应用程序框架层可以包括窗口管理器,内容提供器,视图系统,电话管理器,资源管理器,通知管理器等。
窗口管理器用于管理窗口程序。窗口管理器可以获取显示屏大小,判断是否有状态栏,锁定屏幕,截取屏幕等。
内容提供器用来存放和获取数据,并使这些数据可以被应用程序访问。所述数据可以 包括视频,图像,音频,拨打和接听的电话,浏览历史和书签,电话簿等。
视图系统包括可视控件,例如显示文字的控件,显示图片的控件等。视图系统可用于构建应用程序。显示界面可以由一个或多个视图组成的。例如,包括短信通知图标的显示界面,可以包括显示文字的视图以及显示图片的视图。
电话管理器用于提供服务设备1300的通信功能。例如通话状态的管理(包括接通,挂断等)。
资源管理器为应用程序提供各种资源,比如本地化字符串,图标,图片,布局文件,视频文件等等。
通知管理器使应用程序可以在状态栏中显示通知信息,可以用于传达告知类型的消息,可以短暂停留后自动消失,无需用户交互。比如通知管理器被用于告知下载完成,消息提醒等。通知管理器还可以是以图表或者滚动条文本形式出现在系统顶部状态栏的通知,例如后台运行的应用程序的通知,还可以是以对话窗口形式出现在屏幕上的通知。例如在状态栏提示文本信息,发出提示音,服务设备振动,指示灯闪烁等。
Android Runtime包括核心库和虚拟机。Android runtime负责安卓系统的调度和管理。
核心库包含两部分:一部分是java语言需要调用的功能函数,另一部分是安卓的核心库。
应用程序层和应用程序框架层运行在虚拟机中。虚拟机将应用程序层和应用程序框架层的java文件执行为二进制文件。虚拟机用于执行对象生命周期的管理,堆栈管理,线程管理,安全和异常的管理,以及垃圾回收等功能。
系统库可以包括多个功能模块。例如:表面管理器(surface manager),媒体库(Media Libraries),三维图形处理库(例如:OpenGL ES),2D图形引擎(例如:SGL)等。
表面管理器用于对显示子系统进行管理,并且为多个应用程序提供了2D和3D图层的融合。
媒体库支持多种常用的音频,视频格式回放和录制,以及静态图像文件等。媒体库可以支持多种音视频编码格式,例如:MPEG4,H.264,MP3,AAC,AMR,JPG,PNG等。
三维图形处理库用于实现三维图形绘图,图像渲染,合成,和图层处理等。
2D图形引擎是2D绘图的绘图引擎。
内核层是硬件和软件之间的层。内核层至少包含显示驱动,摄像头驱动,音频驱动,传感器驱动。
下面结合捕获拍照场景,示例性说明服务设备1300软件以及硬件的工作流程。
当触摸传感器1380K接收到触摸操作,相应的硬件中断被发给内核层。内核层将触摸操作加工成原始输入事件(包括触摸坐标,触摸操作的时间戳等信息)。原始输入事件被存储在内核层。应用程序框架层从内核层获取原始输入事件,识别该输入事件所对应的控件。以该触摸操作是触摸单击操作,该单击操作所对应的控件为相机应用图标的控件为例,相机应用调用应用框架层的接口,启动相机应用,进而通过调用内核层启动摄像头驱动,通过摄像头1393捕获静态图像或视频。
下面结合附图对本申请所提供的数据处理方法及其装置进行详细地介绍。
请参见图2,图2是本申请实施例提供的一种数据处理方法的流程示意图。其中,步骤S201~S204的执行主体为服务设备,或者为服务设备中的芯片,以下以服务设备为数据处理方法的执行主体为例进行说明。如图2所示,该方法可以包括但不限于如下步骤:
步骤S201:服务设备获取待查询文本。
其中,待查询文本可以是一个词,也可以是由多个词组成的句子。在一种实现方式中,当图2所示方法应用于基于人工智能的智能搜索系统时,该待查询文本可以是用户在查询搜索时输入的查询语,该查询语可以是以文本方式输入的,也可以是以语音方式输入的,当查询语以语音方式输入时,需要将语音格式的查询语转换为文本格式。
在一种实现方式中,当图2所示方法应用于基于人工智能的智能问答系统时,该待查询文本可以是用户在询问时输入的问题,该问题可以是以文本方式输入的,也可以是以语音方式输入的,当问题以语音方式输入时,需要将语音格式的问题转换为文本格式。
在一种实现方式中,待查询文本可以是用户在终端设备中输入,并由该终端设备发送给服务设备的,或者,该待查询文本也可以是用户在服务设备中输入的,本申请实施例对此不作限定。其中,服务设备可以是图1a中的服务设备102。
在本申请实施例中,服务设备获取到待查询文本时,表示需要确定该待查询文本对应的查询领域。具体的,服务设备确定该待查询文本对应的查询领域之前,需要确定该待查询文本对应的待查询对象集合,并通过该待查询对象集合中的待查询对象的关系信息,确定该待查询文本对应的查询领域。
步骤S202:服务设备从预设数据库中确定该待查询文本对应的待查询对象集合,待查询对象集合的数量为一个或多个,各个待查询对象集合包括一个或多个待查询对象。
具体的,服务设备获取待查询文本之后,可以从预设数据库中确定该待查询文本对应的待查询对象集合。待查询对象集合的数量可以为一个或多个,各个待查询对象集合可以包括一个或多个待查询对象,各个待查询对象集合中的待查询对象的数量相同。
待查询对象可以为预设数据库中的一个实体。例如,待查询文本为“郭德纲的水浒传”时,若该待查询文本对应一个待查询对象集合,则该待查询对象集合中的待查询对象可以包括人物“郭德纲”和相声《水浒传》。其中,人物“郭德纲”、相声《水浒传》分别为预设数据库中的一个实体。
不同待查询对象集合中的待查询对象可以完全不同,也可以部分不同。例如,待查询文本为“郭德纲的水浒传”时,若该待查询文本对应两个待查询对象集合,则第一个待查询对象集合中的待查询对象可以包括人物“郭德纲”和相声《水浒传》,第二个待查询对象集合中的待查询对象可以包括人物“郭德纲”和电视剧《水浒传》。其中,相声《水浒传》和电视剧《水浒传》是词语“水浒传”在预设数据库中对应的两个不同的实体。
同一字词在预设数据库中可以对应一个或多个实体,待查询对象集合的数量可以根据待查询文本对应的字词在预设数据库中存在的实体数量确定。具体的,待查询对象集合的数量可以为待查询文本对应的各个字词在预设数据库中存在的实体数量之间的乘积。例如,待查询文本为“郭德纲的水浒传”,且该待查询文本对应的两个词语分别为“郭德纲”和“水浒传”时,若词语“郭德纲”在预设数据库中对应2个实体(如人物“郭德纲”和书籍《郭德纲》),词语“水浒传”在预设数据库中也对应2个实体(如相声《水浒传》和 电视剧《水浒传》),则待查询对象集合的数量可以为2*2个。第一个待查询对象集合中的待查询对象包括:人物“郭德纲”和相声《水浒传》;第二个待查询对象集合中的待查询对象包括:人物“郭德纲”和电视剧《水浒传》;第三个待查询对象集合中的待查询对象包括:书籍《郭德纲》和相声《水浒传》;第四个待查询对象集合中的待查询对象包括:书籍《郭德纲》和电视剧《水浒传》。
在一种实现方式中,待查询对象集合的数量可以小于待查询文本对应的各个字词在预设数据库中存在的实体数量之间的乘积。例如,待查询文本为“郭德纲的水浒传”,且该待查询文本对应的两个词语分别为“郭德纲”和“水浒传”时,若词语“郭德纲”在预设数据库中对应2个实体(如人物“郭德纲”和书籍《郭德纲》),词语“水浒传”在预设数据库中对应2个实体(如相声《水浒传》和电视剧《水浒传》)。此时,服务设备可以对词语“郭德纲”和“水浒传”分别进行实体排歧处理,进而确定词语“郭德纲”对应的实体为人物“郭德纲”,词语“水浒传”对应的实体为相声《水浒传》和电视剧《水浒传》。经过实体排歧处理之后,可以确定待查询对象集合的数量为1*2个。其中,第一个待查询对象集合中的待查询对象包括人物“郭德纲”和相声《水浒传》,第二个待查询对象集合中的待查询对象包括人物“郭德纲”和电视剧《水浒传》。需要说明的是,每个待查询对象集合中的待查询对象对应的字词相同,例如,上例中第一个待查询对象集合和第二个待查询对象集合中的待查询对象对应的字词均为“郭德纲”和“水浒传”。
实体的歧义是指同一字词可以对应多个不同的概念,例如,词语“郭德纲”可以指一个人物,也可以指与人物“郭德纲”同名的书籍《郭德纲》。实体排歧可以确定字词真正对应的概念。例如,待查询文本为“郭德纲的水浒传”时,可以确定该待查询文本中的词语“郭德纲”对应的真正实体是一个人物,即对应的真正实体为人物“郭德纲”。
在实际应用中,直接搜索用户输入的待查询文本,可能不能搜索到用户实际需要的查询结果,或者会导致查询结果冗余。例如,用户输入的待查询文本为“邓超的妻子的作品”时,实际上用户希望查询的是“孙俪的作品”(邓超的妻子为孙俪),但是在实际搜索过程中,可能搜索得到的结果是与邓超的作品相关的资源,此时,不能搜索到用户实际需要的查询结果。或者,搜索得到的结果是与邓超的作品相关的资源以及与孙俪的作品相关的资源,此时,查询结果中与邓超的作品相关的资源是用户不需要的信息,这样会导致查询结果冗余。
在本申请实施例中,待查询对象集合对应的文本信息可以是用户实际希望查询的信息。例如,待查询文本为“邓超的妻子的作品”时,待查询对象集合可以包括一个待查询对象,该待查询对象是人物“孙俪”。此时,人物“孙俪”所在的待查询对象集合对应的文本信息为“孙俪的作品”,该文本信息是用户实际希望查询的信息。在本申请实施例中,待查询文本对应的查询领域是通过该待查询对象集合中的待查询对象的关系信息来确定的,通过确定待查询对象集合,可以确定用户实际希望查询的信息,这样有利于提高待查询文本对应的查询领域的准确度,从而有利于查询得到与用户意图相匹配的查询结果。
在一种实现方式中,待查询对象可以是待查询文本中的字词在预设数据库中对应的实体。例如,待查询文本为“郭德纲的水浒传”时,待查询对象集合可以包括两个待查询对象(如人物“郭德纲”和相声《水浒传》),其中,人物“郭德纲”是该待查询文本中的 词语“郭德纲”在预设数据库中对应的实体,相声《水浒传》是该待查询文本中的词语“水浒传”在预设数据库中对应的实体。在一种实现方式中,待查询对象可以是根据第一实体推理得到的第二实体,其中,第一实体是待查询文本中的字词在预设数据库中对应的实体。例如,待查询文本为“邓超的妻子的作品”,该待查询文本中的词语“邓超”在预设数据库中对应的第一实体为人物“邓超”,且人物“邓超”在预设数据库中通过夫妻关系与人物“孙俪”相连接。据此,可以推理得到第二实体为人物“孙俪”。
其中,预设数据库可以是服务设备中的本地数据库,也可以云端的数据库,本申请实施例对此不做限定。在本申请实施例中,预设数据库中可以存储有知识图谱,具体的,服务设备可以从预设数据库中的知识图谱中确定该待查询文本对应的待查询对象集合,本申请实施例中提及预设数据库之处,具体可以指该预设数据库中的知识图谱。需要说明的是,本申请实施例以从知识图谱中确定待查询文本对应的待查询对象集合为例进行介绍,但并不构成对本申请实施例的限定,在其他可行的实现方式中,服务设备也可以从非知识图谱的知识组织结构中确定待查询文本对应的待查询对象集合,该知识组织结构用于存储多个对象以及各个对象之间的关系,该知识组织结构存储于预设数据库中。
步骤S203:服务设备从预设的两两对象之间的关系信息中确定各个待查询对象集合中待查询对象的关系信息。
具体的,服务设备从预设数据库中确定该待查询文本对应的待查询对象集合之后,可以从预设的两两对象之间的关系信息中确定各个待查询对象集合中待查询对象的关系信息,进而根据各个待查询对象集合中待查询对象的关系信息,确定前述待查询文本对应的查询领域。
在本申请实施例中,预设的两两对象之间的关系信息可以存储于前述预设数据库,知识图谱中的两个节点通过一条边相连时,这两个节点对应的实体之间的关系信息可以存储于预设数据库中。两个对象之间的关系信息可以为该两个对象在知识图谱中对应的节点之间的关系,例如,两个对象分别为人物“郭德纲”和相声《水浒传》时,人物“郭德纲”和相声《水浒传》之间的关系信息可以为创作关系或者表演关系(假设相声《水浒传》是由郭德纲创作或者表演的)。
需要说明的是,在本申请实施例中,节点、实体和对象在预设数据库(如预设数据库中的知识图谱)中相当于同一概念。各个待查询对象集合中待查询对象的关系信息是指该待查询对象与知识图谱中的所有对象中除该待查询对象以外的其他对象之间的关系信息,其中,该其他对象在知识图谱中对应的节点与该待查询对象在知识图谱中对应的节点通过一条边相连接,即该其他对象与该待查询对象在知识图谱中具有关联关系。
待查询对象的关系信息可以包括该待查询对象与一个或多个对象之间的关系信息。在一种实现方式中,待查询对象的关系信息可以包括该待查询对象与所有对象之间的关系信息,或者该待查询对象与所有对象中的部分对象之间的关系信息。其中,该所有对象为该待查询对象在知识图谱中具有关联关系的所有对象。例如,若待查询对象1对应的节点在知识图谱中与10个节点分别通过不同的边相连,即待查询对象1与10个对象具有关联关系。此时,前述所有对象即包括这10个对象,前述部分对象即为这10个对象中的部分对象。
具体的,若待查询对象集合包括一个待查询对象,则服务设备可以获取该待查询对象关联的所有对象与该待查询对象之间的关系信息。若待查询对象集合包括多个待查询对象,针对各个待查询对象,服务设备可以获取该待查询对象在该待查询对象集合中关联的所有对象与该待查询对象之间的关系信息。例如,若待查询对象集合包括4个待查询对象(如待查询对象1、待查询对象2、待查询对象3、待查询对象4),且该4个待查询对象在知识图谱中的关系如下:待查询对象1与待查询对象2、待查询对象3、对象5(对象5是知识图谱中的一个实体)均关联,待查询对象3与待查询对象4关联。此时,服务设备获取的关系信息可以包括:待查询对象1与待查询对象2之间的关系信息,待查询对象1与待查询对象3之间的关系信息,以及待查询对象3与待查询对象4之间的关系信息。由此可见,服务设备在获取待查询对象1的关系信息时,可以获取待查询对象1在待查询对象集合中关联的所有对象(即待查询对象2和待查询对象3)与待查询对象1之间的关系信息,而不用获取待查询对象1与待查询对象集合以外的其他对象(即对象5)之间的关系信息。
在本申请实施例中,预设的两两对象之间的关系信息可以从网络中自动抓取,且可以实时刷新,预设的两两对象之间的关系信息的生成和维护可以不用人工参与。这样可以使得从预设的两两对象之间的关系信息中确定各个待查询对象集合中待查询对象的关系信息的效率更高,且可以确保确定出的待查询对象的关系信息的时效性。
步骤S204:服务设备根据各个待查询对象集合中待查询对象的关系信息,确定前述待查询文本对应的查询领域。
具体的,服务设备确定各个待查询对象集合中待查询对象的关系信息之后,可以根据各个待查询对象集合中待查询对象的关系信息,确定前述待查询文本对应的查询领域。
在本申请实施例中,服务设备可以预先设置支持的领域,服务设备可以支持一个或多个领域,本申请实施例以服务设备支持多个领域为例进行说明。需要说明的是,服务设备支持多个领域表示:服务设备可以获取所支持的每个领域中的资源。具体的,服务设备所支持的领域的资源可以存储于服务设备本地,也可以存储于各个领域对应的云端服务器中,本申请实施例对此不做限定。在本申请实施例中,待查询文本对应的查询领域的数量可以为一个或多个。
服务设备根据各个待查询对象集合中待查询对象的关系信息,可以确定用户输入待查询文本时实际想访问的是所支持的多个领域中的哪个领域的资源,进而将用户实际想访问的领域作为该待查询文本对应的查询领域,并仅在查询领域对应的服务设备进行查询,从而有利于降低查询结果冗余。其中,查询领域对应的服务设备可以为数据服务器。
在一种实现方式中,服务设备根据各个待查询对象集合中待查询对象的关系信息,确定前述待查询文本对应的查询领域之后,还可以将任意一个待查询对象集合对应的文本信息发送给该查询领域对应的服务设备。查询领域对应的服务设备接收到待查询对象集合对应的文本信息之后,可以根据该文本信息得到查询结果,并将查询结果发送给服务设备。服务设备接收到来自查询领域对应的服务设备的查询结果之后,可以输出该查询结果。
其中,各个待查询对象集合对应的文本信息可以包括该待查询对象集合中的待查询对象对应的字词。例如,第一个待查询对象集合中的待查询对象包括人物“郭德纲”和相声《水浒传》,且第二个待查询对象集合中的待查询对象包括人物“郭德纲”和电视剧《水 浒传》时,第一个待查询对象集合对应的文本信息和第二个待查询对象集合对应的文本信息均可以为“郭德纲”和“水浒传”。需要说明的是,各个待查询对象集合对应的文本信息均相同,因此,服务设备将任意一个待查询对象集合对应的文本信息发送给该查询领域对应的服务设备,即可得到用户需要的查询结果。
通过仅将待查询对象集合对应的文本信息发送给上述查询领域对应的服务设备,既可以使得用户可以得到需要的查询结果,也可以避免向服务设备所支持的所有领域对应的服务设备发送待查询对象集合对应的文本信息所导致的额外开销。同时,还能避免搜索得到一些用户并不需要的查询结果,这样有利于降低查询结果冗余。
需要说明的是,查询领域对应的服务设备可以与确定查询领域的服务设备为同一设备,也可以为不同设备。当查询领域对应的服务设备与确定查询领域的服务设备为不同设备时,服务设备确定待查询文本对应的查询领域之后,将待查询对象集合对应的文本信息发送给该查询领域对应的服务设备仅用于举例说明,并不构成对本申请实施例的限定。当查询领域对应的服务设备与确定查询领域的服务设备为同一设备时,服务设备可以在查询领域对应的数据库中,根据任意一个待查询对象集合对应的文本信息得到查询结果。其中,服务设备支持的不同领域对应的资源可以存储于该服务设备中不同的本地数据库中。通过这种方式,可以避免在服务设备支持的所有领域对应的数据库中进行查询,而仅需在查询领域对应的数据库中查询,这样可以确保得到用户需要的查询结果的同时,提高查询效率,还可以降低查询结果冗余。
在一种实现方式中,服务设备获取的查询结果的数量可以为一个或多个。当查询结果的数量为多个时,服务设备得到查询结果之后,还可以对该查询结果进行排序处理,并输出排序后的查询结果。通过对查询结果进行排序处理,可以优先输出更符合用户搜索需求的查询结果,即将更符合用户搜索需求的查询结果排在前面展示给用户,这样可以有效提高智能搜索效果。
通过实施本申请实施例,根据各个待查询对象集合中待查询对象的关系信息,可以确定用户输入待查询文本时实际想访问的是服务设备所支持的多个领域中的哪个领域的资源,进而将用户实际想访问的领域作为该待查询文本对应的查询领域,并仅在查询领域对应的服务设备进行查询。相较于在服务设备支持的所有领域对应的服务设备中进行查询,采用本申请实例,可以降低查询的领域数量,即可以缩小查询范围,这样不仅可以查询得到与用户意图相匹配的查询结果,还有利于提高查询效率、降低查询结果冗余。
请参见图3,图3是本申请实施例提供的另一种数据处理方法的流程示意图,该方法详细描述了如何从预设数据库中确定待查询文本对应的待查询对象集合,以及当各个待查询对象集合包括一个待查询对象时,如何根据各个待查询对象集合中待查询对象的关系信息,确定待查询文本对应的查询领域。其中,步骤S301~S306的执行主体为服务设备,或者为服务设备中的芯片,以下以服务设备为数据处理方法的执行主体为例进行说明。如图3所示,该方法可以包括但不限于如下步骤:
步骤S301:服务设备获取待查询文本。
需要说明的是,步骤S301的执行过程可参见图2中步骤S201的具体描述,此处不再 赘述。
步骤S302:服务设备确定目标文本,该目标文本为对该待查询文本进行自然语言理解NLU处理后得到的文本。
具体的,服务设备获取待查询文本之后,可以对该待查询文本进行NLU处理,得到目标文本。其中,目标文本可以是一个短语。对待查询文本进行处理得到的目标文本的数量可以为一个或多个。例如,待查询文本为“郭德纲的水浒传”时,对该待查询文本进行NLU处理后得到一个短语,该短语为“郭德纲的水浒传”。又如,待查询文本为“郭麒麟的父亲的水浒传”时,对该待查询文本进行NLU处理后得到两个短语,两个短语分别为“郭麒麟的父亲”、“水浒传”。又如,待查询文本为“邓超的妻子的作品”时,对该待查询文本进行NLU处理后得到一个短语,该短语为“邓超的妻子”。
步骤S303:服务设备对该目标文本进行分词处理,得到该目标文本的各个分词。
具体的,服务设备确定目标文本之后,可以分别对各个目标文本进行分词处理,得到各个目标文本的各个分词。
在一种实现方式中,服务设备可以调用分词算法对目标文本进行分词处理,得到该目标文本的各个分词。在一种实现方式中,分词算法可以包括但不限于基于字符串匹配的分词算法(如正向最大匹配法、逆向最大匹配法、最少切分、双向最大匹配法等)、基于理解的分词算法和基于统计的分词算法,本申请实施例对此不作限定。
例如,当两个目标文本分别为“郭麒麟的父亲”和“水浒传”时,对“郭麒麟的父亲”进行分词处理后得到的分词包括“郭麒麟”和“父亲”,对“水浒传”进行分词处理后得到的分词包括“水浒传”。
步骤S304:服务设备根据该目标文本的各个分词,从预设数据库中确定各个待查询对象集合中的待查询对象,待查询对象集合的数量为一个或多个,各个待查询对象集合包括一个或多个待查询对象。
具体的,服务设备得到目标文本的各个分词之后,可以根据该目标文本的各个分词,从预设数据库中确定各个待查询对象集合中的待查询对象。
在本申请实施例中,一个分词在预设数据库中可以对应一个或多个对象(即实体),也可以不存在对应的对象(即实体)。需要说明的是,同一目标文本中的不同分词在预设数据库中对应的对象数量相互独立。例如,目标文本为“郭麒麟的父亲”时,该目标文本包括两个分词(即“郭麒麟”和“父亲”),其中,分词“郭麒麟”在预设数据库中可以对应一个实体(如人物“郭麒麟”),分词“父亲”在预设数据库中可以不存在对应的实体。
需要说明的是,根据每个目标文本的分词,在预设数据库中至少可以确定一个待查询对象。该待查询对象可以是该目标文本的其中一个分词在预设数据库中对应的实体,也可以是根据该目标文本的其中一个分词在预设数据库中对应的实体,以及该目标文本中除该分词以外的其他分词推理得到的实体。
在一种实现方式中,目标文本的各个分词在预设数据库中均存在对应的对象,服务设备根据该目标文本的各个分词,从预设数据库中确定各个待查询对象集合中的待查询对象的具体实施方式可以为:针对目标文本的各个分词,将该分词在预设数据库中对应的不同 对象作为不同待查询对象集合中的待查询对象。例如,目标文本为“水浒传”时,该目标文本仅包括一个分词(即“水浒传”),若该分词在预设数据库中对应2个不同的对象,该2个对象分别为相声《水浒传》和电视剧《水浒传》时,服务设备可以将相声《水浒传》作为第一待查询对象集合中的待查询对象,并将电视剧《水浒传》作为第二待查询对象集合中的待查询对象。其中,第一待查询对象集合和第二待查询对象集合为不同的待查询对象集合。
在一种实现方式中,若目标文本仅包括一个分词,且该分词在预设数据库中仅对应一个对象,且待查询对象集合的数量为N个,则服务设备可以将该分词在预设数据库中对应的对象作为该N个待查询对象集合中的待查询对象。
在一种实现方式中,各个待查询对象集合中的待查询对象的数量相同,待查询对象集合中的待查询对象的数量可以为对待查询文本进行NLU处理之后得到的目标文本的数量。例如,待查询文本为“郭麒麟的父亲的水浒传”时,对该待查询文本进行NLU处理后可以得到2个目标文本(即“郭麒麟的父亲”和“水浒传”),该待查询文本对应的待查询对象集合中的待查询对象可以包括人物“郭德纲”和相声《水浒传》(或者人物“郭德纲”和电视剧《水浒传),即该待查询文本对应的待查询对象集合中的待查询对象的数量也为2个。
在一种实现方式中,目标文本的分词至少可以包括一个第一分词和一个第二分词,该第一分词在预设数据库中对应第一对象,该第二分词在预设数据库中不存在对应的对象;服务设备根据该目标文本的各个分词,从预设数据库中确定各个待查询对象集合中的待查询对象的具体实施方式可以为:从预设的两两对象之间的关系信息中确定该第一对象的关系信息;从该第一对象的关系信息中确定与该第二分词具有匹配关系的第一关系信息;若该第一对象在预设数据库中通过该第一关系信息与第二对象相连接,则根据该第二对象确定目标对象;并将该目标对象作为各个待查询对象集合中的待查询对象。
其中,第一对象的关系信息可以包括该第一对象与多个对象中的各个对象之间的关系,或者包括该第一对象与多个对象中的各个对象之间的关系类型,该多个对象中的各个对象为与该第一对象在预设数据库中存在关联关系的对象。例如,第一对象为人物“郭麒麟”,且人物“郭麒麟”在预设数据库中与2个对象(如人物“郭德纲”和喜剧节目《欢乐喜剧人》)具有关联关系时。此时,人物“郭麒麟”与人物“郭德纲”之间的关系可以为父子,该关系的类型可以为亲属;人物“郭麒麟”与喜剧节目《欢乐喜剧人》之间的关系可以为节目嘉宾,该关系的类型可以为节目。
第一对象的关系信息中的第一关系信息与第二分词具有匹配关系可以表示:该第一关系信息与该第二分词为同义词。例如,目标分词为“郭麒麟的父亲”,该目标分词中的第一分词为“郭麒麟”,第二分词为“父亲”,且第一分词在预设数据库中对应的第一对象为人物“郭麒麟”时,若人物“郭麒麟”在预设数据库中与2个对象(如人物“郭德纲”和喜剧节目《欢乐喜剧人》)具有关联关系,且人物“郭麒麟”与人物“郭德纲”之间的关系为父子,人物“郭麒麟”与喜剧节目《欢乐喜剧人》之间的关系为节目嘉宾。由于“父亲”(即第二分词)与人物“郭麒麟”的关系信息中的父子关系为同义词,因此,可以将“父子”关系作为第一关系信息。由于人物“郭麒麟”与人物“郭德纲”在预设数据库中 通过该第一关系信息(即“父子”关系)相连接,因此,可以将人物“郭德纲”确定为第二对象。
在一种实现方式中,若目标文本包括一个第一分词和一个第二分词,则服务设备可以将第二对象作为目标对象,即将第二对象作为各个待查询对象集合中的待查询对象。
在一种实现方式中,若目标文本包括一个第一分词和多个第二分词,则服务设备可以根据该第二对象确定目标对象,并将该目标对象作为各个待查询对象集合中的待查询对象。具体的,服务设备可以根据该第二对象和该多个第二分词中除了用于确定该第二对象以外的其他第二分词,确定目标对象。例如,若目标文本为“郭麒麟的弟弟的哥哥的父亲”,此时,该目标文本包括一个第一分词(即“郭麒麟”),三个第二分词(分别为“弟弟”、“哥哥”、“父亲”)。根据该第一分词和第一个第二分词(即“弟弟”)确定出的第二对象为人物“郭汾瑒”。根据人物“郭汾瑒”和第二个第二分词(即“哥哥”)确定出的第三对象为人物“郭麒麟”。根据人物“郭麒麟”和第三个第二分词(即“父亲”)确定出的第四对象为人物“郭德纲”。直至目标文本的所有第二分词均用于确定出一个对象之后,可以将最后得到的对象(即第四对象)作为目标对象。通过这种方式,可以实现多级推理(如上例中实现了三级推理),从而有利于确定出用户实际需要查询的对象(即目标对象)。
步骤S305:服务设备从预设的两两对象之间的关系信息中确定各个待查询对象集合中待查询对象的关系信息。
需要说明的是,步骤S305的执行过程可参见图2中步骤S203的具体描述,此处不再赘述。
步骤S306:针对各个待查询对象集合,若该待查询对象集合中待查询对象的关系类型中存在属于第一预设领域的关系类型,则服务设备确定该第一预设领域属于前述待查询文本对应的查询领域;各个待查询对象集合包括一个待查询对象,各个待查询对象集合中待查询对象的关系信息包括一个或多个关系类型。
具体的,当各个待查询对象集合包括一个待查询对象时,针对各个待查询对象集合,若该待查询对象集合中待查询对象的关系类型中存在属于第一预设领域的关系类型,则服务设备可以确定该第一预设领域属于前述待查询文本对应的查询领域。
其中,第一预设领域的数量可以为一个或多个,该第一预设领域可以是服务设备支持的多个领域中的一个或多个领域。即服务设备首先可以根据预设的关系类型和预设领域之间的对应关系,确定待查询对象集合中待查询对象的关系类型所属的领域,若该领域为服务设备支持的领域中的任意一个或多个领域,则服务设备可以确定该一个或多个领域属于前述待查询文本对应的查询领域。
需要说明的是,不同待查询对象集合中待查询对象的关系类型中可以存在属于不同的第一预设领域的关系类型。例如,当服务设备支持3个领域(如影视、音乐、有声),且待查询文本对应的待查询对象集合的数量为2个,且该2个待查询对象集合包括一个待查询对象时,第一个待查询对象集合中的待查询对象的关系类型中可以存在属于影视、音乐这两个领域的关系类型,第二个待查询对象集合中的待查询对象的关系类型中可以存在属有声领域的关系类型。即第一个待查询对象集合对应的第一预设领域包括影视、音乐,第 二个待查询对象集合对应的第一预设领域包括有声,第一个待查询对象集合和第二个待查询对象集合对应的第一预设领域不同。前述待查询文本对应的查询领域包括各个待查询对象集合对应的第一预设领域,即前述待查询文本对应的查询领域包括影视、音乐、有声这3个领域。
实际情况下,一个实体(即对象)在知识图谱中可以存在大量的关系,通过将关系进行分类,可以将大量的关系分成较少的关系类型。并且通过实体的关系类型也同样可以确定出待查询文本对应的查询领域,相较于通过实体的关系确定待查询文本对应的查询领域,通过实体的关系类型确定待查询文本对应的查询领域,可以提高确定待查询文本对应的查询领域的效率。
在本申请实施例中,各个待查询对象集合中待查询对象的关系信息可以包括多个关系类型,例如,当待查询对象集合包括一个待查询对象(如“郭德纲”),该待查询对象在知识图谱中可以通过创作关系和/或表演关系与对象1(如相声《水浒传》)相连接,还可以通过表演关系与对象2(如电影《落叶归根》)相连接,且创作关系的类型属于影视领域或有声领域,表演关系的类型属于影视领域。此时,该待查询对象的关系信息可以包括创作关系的类型和表演关系的类型。
需要说明的是,本申请实施例也可以通过待查询对象集合中待查询对象的关系确定待查询文本对应的查询领域。具体的,服务设备可以确定待查询对象集合中待查询对象的关系所属的领域,若该领域为服务设备支持的领域中的任意一个或多个领域,则服务设备可以确定该一个或多个领域属于前述待查询文本对应的查询领域。
还需要说明的是,本申请实施例通过知识图谱不仅可以确定待查询文本对应的查询领域,还可以从该知识图谱中获取待查询对象之间的关系信息,该关系信息属于待查询文本对应的查询领域。换言之,本申请实施例可以提供可解释的领域校验功能,不仅可以确定待查询文本对应的查询领域,还可以确定在该查询领域中待查询对象之间是通过何种关系相关联的。例如,待查询文本为“郭德纲的水浒传”时,确定出的该查询文本对应的查询领域为影视,并且还可以确定待查询对象人物“郭德纲”和相声《水浒传》是通过属于影视领域的创作关系相关联。
通过实施本申请实施例,根据各个待查询对象集合中待查询对象的关系类型,可以确定用户输入待查询文本时实际想访问的是服务设备所支持的多个领域中的哪个领域的资源,进而将用户实际想访问的领域作为该待查询文本对应的查询领域,并仅在查询领域对应的服务设备进行查询。相较于在服务设备支持的所有领域对应的服务设备中进行查询,采用本申请实例,可以降低查询的领域数量,即可以缩小查询范围,这样不仅可以查询得到与用户意图相匹配的查询结果,还有利于提高查询效率、降低查询结果冗余。另外,相较于通过待查询对象的关系确定待查询文本对应的查询领域,通过待查询对象的关系类型确定待查询文本对应的查询领域,可以提高确定待查询文本对应的查询领域的效率。
请参见图4,图4是本申请实施例提供的又一种数据处理方法的流程示意图,该方法详细描述了当各个待查询对象集合包括多个待查询对象时,如何根据各个待查询对象集合中待查询对象的关系信息,确定待查询文本对应的查询领域。其中,步骤S401~S406的执 行主体为服务设备,或者为服务设备中的芯片,以下以服务设备为数据处理方法的执行主体为例进行说明。如图4所示,该方法可以包括但不限于如下步骤:
步骤S401:服务设备获取待查询文本。
需要说明的是,步骤S401的执行过程可参见图2中步骤S201的具体描述,此处不再赘述。
步骤S402:服务设备确定目标文本,该目标文本为对该待查询文本进行自然语言理解NLU处理后得到的文本。
步骤S403:服务设备对该目标文本进行分词处理,得到该目标文本的各个分词。
步骤S404:服务设备根据该目标文本的各个分词,从预设数据库中确定各个待查询对象集合中的待查询对象,待查询对象集合的数量为一个或多个,各个待查询对象集合包括一个或多个待查询对象。
步骤S405:服务设备从预设的两两对象之间的关系信息中确定各个待查询对象集合中待查询对象的关系信息。
需要说明的是,步骤S402~S405的执行过程可分别参见图3中步骤S302~S304、图2中步骤S203的具体描述,此处不再赘述。
步骤S406:针对各个待查询对象集合,若该待查询对象集合中的各个待查询对象通过类型属于第一预设领域的关系相连接,则服务设备确定该第一预设领域属于前述待查询文本对应的查询领域;其中,各个待查询对象集合包括多个待查询对象,各个待查询对象集合中的各个待查询对象的关系信息包括该待查询对象与该待查询对象集合中除该待查询对象以外的其他待查询对象之间的关系类型。
当各个待查询对象集合包括多个待查询对象时,待查询对象集合中的各个待查询对象的关系信息可以包括该待查询对象与该待查询对象集合中除该待查询对象以外的其他待查询对象之间的关系类型。例如,当待查询文本为“郭德纲的水浒传”,该待查询文本对应的待查询对象集合中的待查询对象包括人物“郭德纲”和相声《水浒传》,且人物“郭德纲”在知识图谱中与2个对象(如相声《水浒传》和人物“郭麒麟”)具有关联关系时,服务设备获取的人物“郭德纲”的关系信息可以包括人物“郭德纲”和相声《水浒传》之间的关系的类型,即服务设备可以不获取人物“郭德纲”和人物“郭麒麟”(人物“郭麒麟”是待查询对象集合以外的对象)之间的关系的类型。因此,只有人物“郭德纲”和相声《水浒传》之间的关系的类型可以用于确定上述待查询文本对应的查询领域。
当各个待查询对象集合包括多个待查询对象时,服务设备根据各个待查询对象集合中待查询对象的关系信息,确定待查询文本对应的查询领域的具体实施方式可以为:针对各个待查询对象集合,判断该待查询对象集合中的各个待查询对象在预设数据库中是否连通,若连通,则进一步根据预设的关系类型和预设领域之间的对应关系,确认待查询对象集合中的各个待查询对象是否通过类型属于同一领域的关系相连接,若是,且该同一领域为服务设备支持的多个领域中的一个或多个领域,则确定该一个或多个领域属于前述待查询文本对应的查询领域。
若该待查询对象集合中的各个待查询对象在预设数据库中不连通,则表明通过该待查询对象集合无法确定前述待查询文本对应的查询领域,此时,服务设备可以通过其他的待 查询对象集合确定前述待查询文本对应的查询领域。例如,若待查询文本为“郭德纲的水浒传”,且该待查询文本对应两个待查询对象集合,第一个待查询对象集合包括的待查询对象为人物“郭德纲”和电视剧《水浒传》,第二个待查询对象集合包括的待查询对象为人物“郭德纲”和相声《水浒传》。若人物“郭德纲”和电视剧《水浒传》在预设数据库中不具有关联关系,即人物“郭德纲”在预设数据库的知识图谱中对应的节点和电视剧《水浒传》在预设数据库的知识图谱中对应的节点之间没有边相连接,此时,服务设备可以通过第二个待查询对象集合确定该待查询文本对应的查询领域。第二个待查询对象集合中的人物“郭德纲”和相声《水浒传》在预设数据库中通过创作关系相连接,该创作关系的类型属于有声领域,若服务设备支持的领域包括影视、有声和音乐,此时,服务设备可以将有声领域作为上述待查询文本对应的查询领域。
若待查询对象集合中的各个待查询对象不通过类型属于同一领域的关系相连接,表明通过该待查询对象集合无法确定前述待查询文本对应的查询领域,此时,服务设备可以通过其他的待查询对象集合确定前述待查询文本对应的查询领域。
其中,第一预设领域的数量可以为一个或多个,该第一预设领域可以是服务设备支持的多个领域中的一个或多个领域。
通过实施本申请实施例,当各个待查询对象集合包括多个待查询对象时,根据各个待查询对象集合中待查询对象的关系类型,可以确定用户输入待查询文本时实际想访问的是服务设备所支持的多个领域中的哪个领域的资源,进而将用户实际想访问的领域作为该待查询文本对应的查询领域,并仅在查询领域对应的服务设备进行查询。相较于在服务设备支持的所有领域对应的服务设备中进行查询,采用本申请实例,可以降低查询的领域数量,即可以缩小查询范围,这样不仅可以查询得到与用户意图相匹配的查询结果,还有利于提高查询效率、降低查询结果冗余。另外,相较于通过待查询对象的关系确定待查询文本对应的查询领域,通过待查询对象的关系类型确定待查询文本对应的查询领域,可以提高确定待查询文本对应的查询领域的效率。
上述详细阐述了本申请实施例的方法,下面提供本申请实施例的装置。
请参见图5,图5是本申请实施例提供的一种数据处理装置的结构示意图,该数据处理装置可以为服务设备或用于服务设备的装置(例如芯片),数据处理装置50用于执行图2-图4对应的方法实施例中服务设备所执行的步骤,数据处理装置50可以包括:
获取模块501,用于获取待查询文本;
处理模块502,用于从预设数据库中确定该待查询文本对应的待查询对象集合,该待查询对象集合的数量为一个或多个,各个待查询对象集合包括一个或多个待查询对象;
该处理模块502,还用于从预设的两两对象之间的关系信息中确定各个待查询对象集合中待查询对象的关系信息;
该处理模块502,还用于根据各个待查询对象集合中待查询对象的关系信息,确定上述待查询文本对应的查询领域。
在一种实现方式中,各个待查询对象集合可以包括一个待查询对象,各个待查询对象集合中待查询对象的关系信息可以包括一个或多个关系类型;处理模块502用于根据各个 待查询对象集合中待查询对象的关系信息,确定上述待查询文本对应的查询领域时,具体可以用于:针对各个待查询对象集合,若该待查询对象集合中待查询对象的关系类型中存在属于第一预设领域的关系类型,则确定该第一预设领域属于上述待查询文本对应的查询领域。
在一种实现方式中,各个待查询对象集合可以包括多个待查询对象,各个待查询对象集合中的各个待查询对象的关系信息可以包括该待查询对象与该待查询对象集合中除该待查询对象以外的其他待查询对象之间的关系类型;处理模块502用于根据各个待查询对象集合中待查询对象的关系信息,确定上述待查询文本对应的查询领域时,具体可以用于:针对各个待查询对象集合,若该待查询对象集合中的各个待查询对象通过类型属于第一预设领域的关系相连接,则确定该第一预设领域属于上所述待查询文本对应的查询领域。
在一种实现方式中,处理模块502用于从预设数据库中确定上述待查询文本对应的待查询对象集合时,具体可以用于:确定目标文本,该目标文本为对上述待查询文本进行自然语言理解NLU处理后得到的文本;对该目标文本进行分词处理,得到该目标文本的各个分词;根据该述目标文本的各个分词,从所述预设数据库中确定各个待查询对象集合中的待查询对象。
在一种实现方式中,上述目标文本的各个分词在预设数据库中均存在对应的对象;处理模块502用于根据上述目标文本的各个分词,从预设数据库中确定各个待查询对象集合中的待查询对象时,具体可以用于:针对该目标文本的各个分词,将该分词在预设数据库中对应的不同对象作为不同待查询对象集合中的待查询对象。
在一种实现方式中,上述目标文本的分词至少可以包括第一分词和第二分词,该第一分词在预设数据库中对应第一对象,该第二分词在所述预设数据库中不存在对应的对象;处理模块502用于根据该目标文本的各个分词,从预设数据库中确定各个待查询对象集合中的待查询对象时,具体可以用于:从预设的两两对象之间的关系信息中确定该第一对象的关系信息;从该第一对象的关系信息中确定与该第二分词具有匹配关系的第一关系信息;若该第一对象在预设数据库中通过该第一关系信息与第二对象相连接,则根据该第二对象确定目标对象;并将该目标对象作为各个待查询对象集合中的待查询对象。
在一种实现方式中,数据处理装置50还可以包括通信模块503和输出模块504;该通信模块503,可以用于将任意一个待查询对象集合对应的文本信息发送给上述查询领域对应的服务设备;该通信模块503,还可以用于接收来自该查询领域对应的服务设备的查询结果;输出模块504,可以用于输出该查询结果。
需要说明的是,图5对应的实施例中未提及的内容以及各个模块执行步骤的具体实现方式可参见图2-图4所示实施例以及前述内容,这里不再赘述。
在一种实现方式中,图5中的各个模块所实现的相关功能可以结合处理器与通信接口来实现。参见图6,图6是本申请实施例提供的另一种数据处理装置的结构示意图,该数据处理装置可以为服务设备或用于服务设备的装置(例如芯片)。该数据处理装置60可以包括通信接口601、处理器602和存储器603,通信接口601、处理器602和存储器603可以通过一条或多条通信总线相互连接,也可以通过其它方式相连接。图5所示的获取模块501、处理模块502、通信模块503和输出模块504所实现的相关功能可以通过同一个处理 器602来实现,也可以通过多个不同的处理器602来实现。
通信接口601可以用于发送数据和/或信令,以及接收数据和/或信令。应用在本申请实施例中,通信接口601可以用于将任意一个待查询对象集合对应的文本信息发送给上述查询领域对应的服务设备。通信接口601可以为收发器。
处理器602被配置为执行图2-图4所述方法中服务设备相应的功能。该处理器602可以包括一个或多个处理器,例如该处理器602可以是一个或多个中央处理器(central processing unit,CPU),网络处理器(network processor,NP),硬件芯片或者其任意组合。在处理器602是一个CPU的情况下,该CPU可以是单核CPU,也可以是多核CPU。
存储器603用于存储程序代码等。存储器603可以包括易失性存储器(volatile memory),例如随机存取存储器(random access memory,RAM);存储器603也可以包括非易失性存储器(non-volatile memory),例如只读存储器(read-only memory,ROM),快闪存储器(flash memory),硬盘(hard disk drive,HDD)或固态硬盘(solid-state drive,SSD);存储器603还可以包括上述种类的存储器的组合。
处理器602可以调用存储器603中存储的程序代码以执行以下操作:
获取待查询文本;
从预设数据库中确定该待查询文本对应的待查询对象集合,该待查询对象集合的数量为一个或多个,各个待查询对象集合包括一个或多个待查询对象;
从预设的两两对象之间的关系信息中确定各个待查询对象集合中待查询对象的关系信息;
根据各个待查询对象集合中待查询对象的关系信息,确定上述待查询文本对应的查询领域。
在一种实现方式中,各个待查询对象集合可以包括一个待查询对象,各个待查询对象集合中待查询对象的关系信息可以包括一个或多个关系类型;处理器602执行根据各个待查询对象集合中待查询对象的关系信息,确定上述待查询文本对应的查询领域时,具体可以执行以下操作:针对各个待查询对象集合,若该待查询对象集合中待查询对象的关系类型中存在属于第一预设领域的关系类型,则确定该第一预设领域属于上述待查询文本对应的查询领域。
在一种实现方式中,各个待查询对象集合可以包括多个待查询对象,各个待查询对象集合中的各个待查询对象的关系信息可以包括该待查询对象与该待查询对象集合中除该待查询对象以外的其他待查询对象之间的关系类型;处理器602执行根据各个待查询对象集合中待查询对象的关系信息,确定上述待查询文本对应的查询领域时,具体可以执行以下操作:针对各个待查询对象集合,若该待查询对象集合中的各个待查询对象通过类型属于第一预设领域的关系相连接,则确定该第一预设领域属于上所述待查询文本对应的查询领域。
在一种实现方式中,处理器602执行从预设数据库中确定上述待查询文本对应的待查询对象集合时,具体可以执行以下操作:确定目标文本,该目标文本为对上述待查询文本进行自然语言理解NLU处理后得到的文本;对该目标文本进行分词处理,得到该目标文本的各个分词;根据该述目标文本的各个分词,从所述预设数据库中确定各个待查询对象集 合中的待查询对象。
在一种实现方式中,上述目标文本的各个分词在预设数据库中均存在对应的对象;处理器602执行根据上述目标文本的各个分词,从预设数据库中确定各个待查询对象集合中的待查询对象时,具体可以执行以下操作:针对该目标文本的各个分词,将该分词在预设数据库中对应的不同对象作为不同待查询对象集合中的待查询对象。
在一种实现方式中,上述目标文本的分词至少可以包括第一分词和第二分词,该第一分词在预设数据库中对应第一对象,该第二分词在所述预设数据库中不存在对应的对象;处理器602执行根据该目标文本的各个分词,从预设数据库中确定各个待查询对象集合中的待查询对象时,具体可以执行以下操作:从预设的两两对象之间的关系信息中确定该第一对象的关系信息;从该第一对象的关系信息中确定与该第二分词具有匹配关系的第一关系信息;若该第一对象在预设数据库中通过该第一关系信息与第二对象相连接,则根据该第二对象确定目标对象;并将该目标对象作为各个待查询对象集合中的待查询对象。
在一种实现方式中,处理器602还可以执行以下操作:将任意一个待查询对象集合对应的文本信息发送给上述查询领域对应的服务设备;接收来自该查询领域对应的服务设备的查询结果;并输出该查询结果。
进一步地,处理器602还可以执行图2-图4所示实施例中服务设备对应的操作,具体可参见方法实施例中的描述,在此不再赘述。
本申请实施例还提供一种计算机可读存储介质,可以用于存储图5所示实施例中数据处理装置所用的计算机软件指令,其包含用于执行上述实施例中为服务设备所设计的程序。
上述计算机可读存储介质包括但不限于快闪存储器、硬盘、固态硬盘。
本申请实施例还提供一种计算机程序产品,该计算机产品被计算设备运行时,可以执行上述图2-图4实施例中为服务设备所设计的方法。
在本申请实施例中还提供一种芯片,包括处理器和存储器,该存储器用包括处理器和存储器,该存储器用于存储计算机程序,该处理器用于从存储器中调用并运行该计算机程序,该计算机程序用于实现上述方法实施例中的方法。
本领域普通技术人员可以意识到,结合本申请中所公开的实施例描述的各示例的单元及算法步骤,能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行,取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能,但是这种实现不应认为超出本申请的范围。
在上述实施例中,可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时,可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机程序指令时,全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中,或者通过所述计算机可读存储介质进行传输。所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(DSL))或无 线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质,(例如,软盘、硬盘、磁带)、光介质(例如,DVD)、或者半导体介质(例如固态硬盘(solid state disk,SSD))等。
以上所述,仅为本申请的具体实施方式,但本申请的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本申请揭露的技术范围内,可轻易想到变化或替换,都应涵盖在本申请的保护范围之内。因此,本申请的保护范围应以所述权利要求的保护范围为准。
Claims (15)
- 一种数据处理方法,其特征在于,所述方法包括:获取待查询文本;从预设数据库中确定所述待查询文本对应的待查询对象集合,所述待查询对象集合的数量为一个或多个,各个所述待查询对象集合包括一个或多个待查询对象;从预设的两两对象之间的关系信息中确定各个所述待查询对象集合中待查询对象的关系信息;根据各个所述待查询对象集合中待查询对象的关系信息,确定所述待查询文本对应的查询领域。
- 根据权利要求1所述的方法,其特征在于,各个所述待查询对象集合包括一个待查询对象,各个所述待查询对象集合中待查询对象的关系信息包括一个或多个关系类型;所述根据各个所述待查询对象集合中待查询对象的关系信息,确定所述待查询文本对应的查询领域,包括:针对各个所述待查询对象集合,若所述待查询对象集合中待查询对象的关系类型中存在属于第一预设领域的关系类型,则确定所述第一预设领域属于所述待查询文本对应的查询领域。
- 根据权利要求1所述的方法,其特征在于,各个所述待查询对象集合包括多个待查询对象,各个所述待查询对象集合中的各个待查询对象的关系信息包括所述待查询对象与所述待查询对象集合中除所述待查询对象以外的其他待查询对象之间的关系类型;所述根据各个所述待查询对象集合中待查询对象的关系信息,确定所述待查询文本对应的查询领域,包括:针对各个所述待查询对象集合,若所述待查询对象集合中的各个待查询对象通过类型属于第一预设领域的关系相连接,则确定所述第一预设领域属于所述待查询文本对应的查询领域。
- 根据权利要求1所述的方法,其特征在于,所述从预设数据库中确定所述待查询文本对应的待查询对象集合,包括:确定目标文本,所述目标文本为对所述待查询文本进行自然语言理解NLU处理后得到的文本;对所述目标文本进行分词处理,得到所述目标文本的各个分词;根据所述目标文本的各个分词,从所述预设数据库中确定各个所述待查询对象集合中的待查询对象。
- 根据权利要求4所述的方法,其特征在于,所述目标文本的各个分词在所述预设数据库中均存在对应的对象;所述根据所述目标文本的各个分词,从所述预设数据库中确定各个所述待查询对象集合中的待查询对象,包括:针对目标文本的各个分词,将所述分词在所述预设数据库中对应的不同对象作为不同待查询对象集合中的待查询对象。
- 根据权利要求4所述的方法,其特征在于,所述目标文本的分词至少包括第一分词和第二分词,所述第一分词在所述预设数据库中对应第一对象,所述第二分词在所述预设数据库中不存在对应的对象;所述根据所述目标文本的各个分词,从所述预设数据库中确定各个所述待查询对象集合中的待查询对象,包括:从所述预设的两两对象之间的关系信息中确定所述第一对象的关系信息;从所述第一对象的关系信息中确定与所述第二分词具有匹配关系的第一关系信息;若所述第一对象在所述预设数据库中通过所述第一关系信息与第二对象相连接,则根据所述第二对象确定目标对象;将所述目标对象作为各个所述待查询对象集合中的待查询对象。
- 根据权利要求1~6任一项所述的方法,其特征在于,所述根据各个所述待查询对象集合中待查询对象的关系信息,确定所述待查询文本对应的查询领域之后,所述方法还包括:将任意一个所述待查询对象集合对应的文本信息发送给所述查询领域对应的服务设备;接收来自所述服务设备的查询结果;输出所述查询结果。
- 一种数据处理装置,其特征在于,所述装置包括:获取模块,用于获取待查询文本;处理模块,用于从预设数据库中确定所述待查询文本对应的待查询对象集合,所述待查询对象集合的数量为一个或多个,各个所述待查询对象集合包括一个或多个待查询对象;所述处理模块,还用于从预设的两两对象之间的关系信息中确定各个所述待查询对象集合中待查询对象的关系信息;所述处理模块,还用于根据各个所述待查询对象集合中待查询对象的关系信息,确定所述待查询文本对应的查询领域。
- 根据权利要求8所述的装置,其特征在于,各个所述待查询对象集合包括一个待查询对象,各个所述待查询对象集合中待查询对象的关系信息包括一个或多个关系类型;所述处理模块用于根据各个所述待查询对象集合中待查询对象的关系信息,确定所述待查询文本对应的查询领域时,具体用于:针对各个所述待查询对象集合,若所述待查询对象集合中待查询对象的关系类型中存在属于第一预设领域的关系类型,则确定所述第一预设领域属于所述待查询文本对应的查询领域。
- 根据权利要求8所述的装置,其特征在于,各个所述待查询对象集合包括多个待查询对象,各个所述待查询对象集合中的各个待查询对象的关系信息包括所述待查询对象与所述待查询对象集合中除所述待查询对象以外的其他待查询对象之间的关系类型;所述处理模块用于根据各个所述待查询对象集合中待查询对象的关系信息,确定所述待查询文本对应的查询领域时,具体用于:针对各个所述待查询对象集合,若所述待查询对象集合中的各个待查询对象通过类型属于第一预设领域的关系相连接,则确定所述第一预设领域属于所述待查询文本对应的查询领域。
- 根据权利要求8所述的装置,其特征在于,所述处理模块用于从预设数据库中确定所述待查询文本对应的待查询对象集合时,具体用于:确定目标文本,所述目标文本为对所述待查询文本进行自然语言理解NLU处理后得到的文本;对所述目标文本进行分词处理,得到所述目标文本的各个分词;根据所述目标文本的各个分词,从所述预设数据库中确定各个所述待查询对象集合中的待查询对象。
- 根据权利要求11所述的装置,其特征在于,所述目标文本的各个分词在所述预设数据库中均存在对应的对象;所述处理模块用于根据所述目标文本的各个分词,从所述预设数据库中确定各个所述待查询对象集合中的待查询对象时,具体用于:针对目标文本的各个分词,将所述分词在所述预设数据库中对应的不同对象作为不同待查询对象集合中的待查询对象。
- 根据权利要求11所述的装置,其特征在于,所述目标文本的分词至少包括第一分词和第二分词,所述第一分词在所述预设数据库中对应第一对象,所述第二分词在所述预设数据库中不存在对应的对象;所述处理模块用于根据所述目标文本的各个分词,从所述预设数据库中确定各个所述待查询对象集合中的待查询对象时,具体用于:从所述预设的两两对象之间的关系信息中确定所述第一对象的关系信息;从所述第一对象的关系信息中确定与所述第二分词具有匹配关系的第一关系信息;若所述第一对象在所述预设数据库中通过所述第一关系信息与第二对象相连接,则根据所述第二对象确定目标对象;将所述目标对象作为各个所述待查询对象集合中的待查询对象。
- 根据权利要求8~13任一项所述的装置,其特征在于,所述装置还包括通信模块和输出模块;所述通信模块,用于将任意一个所述待查询对象集合对应的文本信息发送给所述查询领域对应的服务设备;所述通信模块,还用于接收来自所述服务设备的查询结果;所述输出模块,用于输出所述查询结果。
- 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质存储有计算机程序,所述计算机程序包括程序指令,所述程序指令当被处理器执行时使所述处理器执行如权利要求1~7任一项所述的方法。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP20854658.0A EP4020251A4 (en) | 2019-08-21 | 2020-08-06 | DATA PROCESSING METHOD AND ASSOCIATED APPARATUS |
US17/637,362 US12050633B2 (en) | 2019-08-21 | 2020-08-06 | Data processing method and apparatus |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910776210.2 | 2019-08-21 | ||
CN201910776210.2A CN112416984B (zh) | 2019-08-21 | 2019-08-21 | 一种数据处理方法及其装置 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021031862A1 true WO2021031862A1 (zh) | 2021-02-25 |
Family
ID=74660406
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/107291 WO2021031862A1 (zh) | 2019-08-21 | 2020-08-06 | 一种数据处理方法及其装置 |
Country Status (3)
Country | Link |
---|---|
EP (1) | EP4020251A4 (zh) |
CN (1) | CN112416984B (zh) |
WO (1) | WO2021031862A1 (zh) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113902315A (zh) * | 2021-10-13 | 2022-01-07 | 四川才能科技有限公司 | 一种智能生活服务系统及方法 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070088743A1 (en) * | 2003-09-19 | 2007-04-19 | Toshiba Solutions Corporation | Information processing device and information processing method |
CN102339294A (zh) * | 2010-07-27 | 2012-02-01 | 卓望数码技术(深圳)有限公司 | 一种对关键词进行预处理的搜索方法和系统 |
CN107451208A (zh) * | 2017-07-12 | 2017-12-08 | 北京潘达互娱科技有限公司 | 一种数据搜索方法与装置 |
CN108228657A (zh) * | 2016-12-22 | 2018-06-29 | 沈阳美行科技有限公司 | 一种关键字检索的实现方法及装置 |
CN108268500A (zh) * | 2016-12-30 | 2018-07-10 | 阿里巴巴集团控股有限公司 | 传输信息和显示信息的方法、设备及系统 |
CN108427686A (zh) * | 2017-02-15 | 2018-08-21 | 北京国双科技有限公司 | 文本数据查询方法及装置 |
CN108628941A (zh) * | 2018-03-23 | 2018-10-09 | 华为技术有限公司 | 关联对象获取方法和装置 |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7747601B2 (en) * | 2006-08-14 | 2010-06-29 | Inquira, Inc. | Method and apparatus for identifying and classifying query intent |
US10657572B2 (en) * | 2017-03-16 | 2020-05-19 | Wipro Limited | Method and system for automatically generating a response to a user query |
CN107402954B (zh) * | 2017-05-26 | 2020-07-10 | 百度在线网络技术(北京)有限公司 | 建立排序模型的方法、基于该模型的应用方法和装置 |
CN110019911A (zh) * | 2017-12-29 | 2019-07-16 | 苏州工业职业技术学院 | 支持知识演化的知识图谱的查询方法和装置 |
CN108205593A (zh) * | 2017-12-29 | 2018-06-26 | 华为技术有限公司 | 一种查询的方法及装置 |
CN108228820A (zh) * | 2017-12-30 | 2018-06-29 | 厦门太迪智能科技有限公司 | 用户查询意图理解方法、系统及计算机终端 |
CN108170859B (zh) * | 2018-01-22 | 2020-07-28 | 北京百度网讯科技有限公司 | 语音查询的方法、装置、存储介质及终端设备 |
CN110008413B (zh) * | 2019-03-14 | 2023-11-10 | 海信集团有限公司 | 一种交通出行问题查询方法和装置 |
-
2019
- 2019-08-21 CN CN201910776210.2A patent/CN112416984B/zh active Active
-
2020
- 2020-08-06 WO PCT/CN2020/107291 patent/WO2021031862A1/zh unknown
- 2020-08-06 EP EP20854658.0A patent/EP4020251A4/en not_active Ceased
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070088743A1 (en) * | 2003-09-19 | 2007-04-19 | Toshiba Solutions Corporation | Information processing device and information processing method |
CN102339294A (zh) * | 2010-07-27 | 2012-02-01 | 卓望数码技术(深圳)有限公司 | 一种对关键词进行预处理的搜索方法和系统 |
CN108228657A (zh) * | 2016-12-22 | 2018-06-29 | 沈阳美行科技有限公司 | 一种关键字检索的实现方法及装置 |
CN108268500A (zh) * | 2016-12-30 | 2018-07-10 | 阿里巴巴集团控股有限公司 | 传输信息和显示信息的方法、设备及系统 |
CN108427686A (zh) * | 2017-02-15 | 2018-08-21 | 北京国双科技有限公司 | 文本数据查询方法及装置 |
CN107451208A (zh) * | 2017-07-12 | 2017-12-08 | 北京潘达互娱科技有限公司 | 一种数据搜索方法与装置 |
CN108628941A (zh) * | 2018-03-23 | 2018-10-09 | 华为技术有限公司 | 关联对象获取方法和装置 |
Non-Patent Citations (1)
Title |
---|
See also references of EP4020251A4 |
Also Published As
Publication number | Publication date |
---|---|
US20220292122A1 (en) | 2022-09-15 |
CN112416984A (zh) | 2021-02-26 |
EP4020251A4 (en) | 2022-08-24 |
CN112416984B (zh) | 2024-06-04 |
EP4020251A1 (en) | 2022-06-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110910872B (zh) | 语音交互方法及装置 | |
CN113704014B (zh) | 日志获取系统、方法、电子设备及存储介质 | |
CN115473957B (zh) | 一种图像处理方法和电子设备 | |
WO2020093988A1 (zh) | 一种图像处理方法及电子设备 | |
WO2021254411A1 (zh) | 意图识别方法和电子设备 | |
CN111970401B (zh) | 一种通话内容处理方法、电子设备和存储介质 | |
WO2021104122A1 (zh) | 呼叫需求响应方法、装置及电子设备 | |
US20230418630A1 (en) | Operation sequence adding method, electronic device, and system | |
CN115033313A (zh) | 终端应用控制方法、终端设备及芯片系统 | |
WO2023273543A1 (zh) | 一种文件夹管理方法及装置 | |
WO2022179495A1 (zh) | 一种隐私风险反馈方法、装置及第一终端设备 | |
WO2022143258A1 (zh) | 一种语音交互处理方法及相关装置 | |
CN115333941A (zh) | 获取应用运行情况的方法及相关设备 | |
CN116828100A (zh) | 蓝牙音频播放方法、电子设备及存储介质 | |
WO2021238371A1 (zh) | 生成虚拟角色的方法及装置 | |
WO2021031862A1 (zh) | 一种数据处理方法及其装置 | |
CN115022982B (zh) | 多屏协同无感接入方法、电子设备及存储介质 | |
CN113380240B (zh) | 语音交互方法和电子设备 | |
WO2022089276A1 (zh) | 一种收藏处理的方法及相关装置 | |
US12050633B2 (en) | Data processing method and apparatus | |
WO2023179682A1 (zh) | 一种设备协同方法 | |
CN116709609B (zh) | 消息传递方法、电子设备及存储介质 | |
WO2022166550A1 (zh) | 数据传输方法及电子设备 | |
CN116795476B (zh) | 一种删除壁纸的方法及电子设备 | |
WO2024114785A1 (zh) | 一种图像处理方法、电子设备及系统 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20854658 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2020854658 Country of ref document: EP Effective date: 20220321 |