Display device and semantic understanding method

Abstract

This disclosure relates to a display device, a semantic understanding method, a semantic understanding apparatus, and a storage medium. The display device includes: a controller configured to: acquire word segmentation information corresponding to voice-generated food ingredient data, the word segmentation information including: at least one food ingredient word and an attribute identifier corresponding to the food ingredient word; determine a target word among the at least one food ingredient word based on the attribute identifier; and determine semantically understood content corresponding to the at least one food ingredient word based on the order relationship between the target word and other words among the at least one food ingredient word; and a display configured to: display the semantically understood content corresponding to the at least one food ingredient word. Embodiments of this disclosure are used to improve the semantic understanding capability of the display device, thereby enhancing the user experience.

Description

Technical Field

[0001] This disclosure relates to the field of display technology, and in particular to a display device, a semantic understanding method, a semantic understanding apparatus, and a storage medium. Background Technology

[0002] Voice interaction falls under the category of human-computer interaction. It can be understood as the process of giving instructions to a machine using natural human language to achieve one's goals. The application scope of voice interaction technology has gradually expanded from single products to all categories of terminal products, and refrigerator terminals are also gradually integrating intelligent voice services.

[0003] In related technologies, when food is placed in the refrigerator, the display device shows the attributes of each food item based on the user's voice. However, using this method, the refrigerator cannot accurately understand the user's speech. Therefore, improving the semantic understanding ability of refrigerators is a pressing issue that needs to be addressed. Summary of the Invention

[0004] To address the aforementioned technical problems, or at least partially address them, this disclosure provides a display device and a semantic understanding method. When a user describes the storage of multiple ingredients, the method can determine the semantic understanding content corresponding to the segmented words of each ingredient, effectively improving the semantic understanding capability of the display device and further enhancing the user experience.

[0005] When users watch multimedia content, the system provides them with target bullet comments that correspond to the multimedia content, enabling them to send the bullet comments they want, thereby improving their viewing experience and satisfaction.

[0006] In a first aspect, this disclosure provides a display device, comprising:

[0007] The controller is configured to: acquire word segmentation information corresponding to voice ingredient data, wherein the word segmentation information includes: at least one ingredient word segment and the attribute identifier corresponding to the ingredient word segment;

[0008] Based on the attribute identifier, at least one target word in the word segmentation of the food ingredient is determined;

[0009] Based on the order relationship between the target word segment and other words in at least one of the food ingredient word segments, determine the semantic understanding content corresponding to at least one of the food ingredient word segments;

[0010] The display is configured to display at least one semantically understood content corresponding to the segmentation of the food ingredient.

[0011] As an optional implementation of this invention, the target word segmentation is at least one of the first subject words in the order of the food ingredient word segments;

[0012] The controller is specifically configured as follows:

[0013] Based on the attribute identifier of at least one of the first traversed words in the food ingredient word segmentation, and the order relationship between the first traversed word segmentation and the target word segmentation, the word group information is determined;

[0014] Based on the phrase information, determine the semantic understanding content corresponding to at least one of the food ingredient segmentation words.

[0015] As an optional implementation of this invention, the controller is specifically configured as follows:

[0016] Based on the attribute identifier of the first traversed word in at least one of the food ingredient word segments, it is determined that the first traversed word is not the second subject word, and it is determined that there is no word with the same attribute identifier as the first traversed word.

[0017] Based on the sequential relationship between the first traversal word segmentation and the target word segmentation, the word group information is determined.

[0018] As an optional implementation of this invention, the controller is specifically configured as follows:

[0019] It is determined that the order relationship between the first traversed word segment and the target word segment belongs to a preset relationship, and it is determined that there is an object word between the first traversed word segment and the target word segment;

[0020] The objective word and its corresponding word segment are combined to form a first word group. Based on the other words between the first traversed word segment and the target word segment, as well as the first word group, the word group information is determined.

[0021] As an optional implementation of this invention, the controller is specifically configured as follows:

[0022] Based on the attribute identifier of the second traversal word in at least one of the food ingredient word segments, the second traversal word segment is determined to be the second subject word segment. Based on the other words between the target word segment and the first traversal word segment and the first word group, a second word group is formed.

[0023] The second traversal word segment is determined to be the last untraversed second subject word segment, and the second traversal word segment is combined with at least one untraversed remaining word segment in the ingredients to form a third word group;

[0024] The word group information is determined based on the order relationship between the second word group and the third word group.

[0025] As an optional implementation of this invention, the controller is specifically configured as follows:

[0026] Candidate information is determined based on the sequential relationship between the second and third word groups;

[0027] Add verb segmentation to the candidate information to obtain phrase information.

[0028] As an optional implementation of this invention, the display is specifically configured as follows:

[0029] In response to a preset operation of the display device, at least one semantic understanding content corresponding to the food ingredient segmentation is displayed, or, when displaying at least one semantic understanding content corresponding to the food ingredient segmentation, the verb segmentation included in the semantic understanding content is hidden.

[0030] Secondly, a semantic understanding method is provided, the method comprising:

[0031] Obtain word segmentation information corresponding to the voice ingredient data, wherein the word segmentation information includes: at least one ingredient word segment and the attribute identifier corresponding to the ingredient word segment;

[0032] Based on the attribute identifier, at least one target word in the word segmentation of the food ingredient is determined;

[0033] Based on the order relationship between the target word segment and other words in at least one of the food ingredient word segments, determine the semantic understanding content corresponding to at least one of the food ingredient word segments;

[0034] Display the semantic understanding content corresponding to at least one of the food ingredient segmentation words.

[0035] As an optional implementation of this invention, the target word segment is the first subject word segment that appears first in the order of at least one of the food ingredient word segments; the step of determining the semantic understanding content corresponding to at least one food ingredient word based on the order relationship between the target word segment and other word segments in at least one of the food ingredient word segments includes:

[0036] Based on the attribute identifier of at least one of the first traversed words in the food ingredient word segmentation, and the order relationship between the first traversed word segmentation and the target word segmentation, the word group information is determined;

[0037] Based on the phrase information, determine the semantic understanding content corresponding to at least one of the food ingredient segmentation words.

[0038] As an optional implementation of this invention, determining the word group information based on the attribute identifier of at least one of the first traversed words in the food ingredient word segmentation, and the order relationship between the first traversed words and the target word, includes:

[0039] Based on the attribute identifier of the first traversed word in at least one of the food ingredient word segments, it is determined that the first traversed word is not the second subject word, and it is determined that there is no word with the same attribute identifier as the first traversed word.

[0040] Based on the sequential relationship between the first traversal word segmentation and the target word segmentation, the word group information is determined.

[0041] As an optional implementation of this invention, determining the word group information based on the sequential relationship between the first traversal word segmentation and the target word segmentation includes:

[0042] It is determined that the order relationship between the first traversed word segment and the target word segment belongs to a preset relationship, and it is determined that there is an object word between the first traversed word segment and the target word segment;

[0043] The objective word and its corresponding word segment are combined to form a first word group. Based on the other words between the first traversed word segment and the target word segment, as well as the first word group, the word group information is determined.

[0044] As an optional implementation of this invention, determining the word group information based on other word segments between the first traversed word segment and the target word segment, as well as the first word group, includes:

[0045] Based on the attribute identifier of the second traversal word in at least one of the food ingredient word segments, the second traversal word segment is determined to be the second subject word segment. Based on the other words between the target word segment and the first traversal word segment and the first word group, a second word group is formed.

[0046] The second traversal word segment is determined to be the last untraversed second subject word segment, and the second traversal word segment is combined with at least one untraversed remaining word segment in the ingredients to form a third word group;

[0047] The word group information is determined based on the order relationship between the second word group and the third word group.

[0048] As an optional implementation of this invention, determining the phrase information based on the sequential relationship between the second phrase and the third phrase includes:

[0049] Candidate information is determined based on the sequential relationship between the second and third word groups;

[0050] Add verb segmentation to the candidate information to obtain phrase information.

[0051] As an optional implementation of this invention, displaying at least one semantic understanding content corresponding to the segmentation of the food ingredient includes:

[0052] In response to a preset operation of the display device, at least one semantic understanding content corresponding to the food ingredient segmentation is displayed, or, when displaying at least one semantic understanding content corresponding to the food ingredient segmentation, the verb segmentation included in the semantic understanding content is hidden.

[0053] Thirdly, a semantic understanding apparatus is provided, the apparatus comprising:

[0054] The ingredient segmentation acquisition module is used to acquire the segmentation information corresponding to the voice ingredient data. The segmentation information includes: at least one ingredient segmentation and the attribute identifier corresponding to the ingredient segmentation.

[0055] The target word segmentation determination module is used to determine at least one target word in the word segmentation of the food ingredient based on the attribute identifier;

[0056] The semantic content determination module is used to determine the semantic understanding content corresponding to at least one ingredient segment based on the order relationship between the target segment and other segments in at least one ingredient segment;

[0057] The semantic content display module is used to display the semantic understanding content corresponding to at least one of the food ingredient word segments.

[0058] As an optional implementation of this invention, the semantic content determination module includes:

[0059] The phrase information determination unit is used to determine phrase information based on the attribute identifier of at least one of the first traversed words in the ingredient word segmentation and the order relationship between the first traversed words and the target word;

[0060] The semantic content determination unit is used to determine the semantic understanding content corresponding to at least one of the food ingredient segmentation words based on the word group information.

[0061] As an optional implementation of this invention, the phrase information determination unit is specifically used for:

[0062] Based on the attribute identifier of the first traversed word in at least one of the food ingredient word segments, it is determined that the first traversed word is not the second subject word, and it is determined that there is no word with the same attribute identifier as the first traversed word.

[0063] Based on the sequential relationship between the first traversal word segmentation and the target word segmentation, the word group information is determined.

[0064] As an optional implementation of this invention, determining the word group information based on the sequential relationship between the first traversal word segmentation and the target word segmentation includes:

[0065] It is determined that the order relationship between the first traversed word segment and the target word segment belongs to a preset relationship, and it is determined that there is an object word between the first traversed word segment and the target word segment;

[0066] The objective word and its corresponding word segment are combined to form a first word group. Based on the other words between the first traversed word segment and the target word segment, as well as the first word group, the word group information is determined.

[0067] As an optional implementation of this invention, determining the word group information based on other word segments between the first traversed word segment and the target word segment, as well as the first word group, includes:

[0068] Based on the attribute identifier of the second traversal word in at least one of the food ingredient word segments, the second traversal word segment is determined to be the second subject word segment. Based on the other words between the target word segment and the first traversal word segment and the first word group, a second word group is formed.

[0069] The second traversal word segment is determined to be the last untraversed second subject word segment, and the second traversal word segment is combined with at least one untraversed remaining word segment in the ingredients to form a third word group;

[0070] The word group information is determined based on the order relationship between the second word group and the third word group.

[0071] As an optional implementation of this invention, determining the phrase information based on the sequential relationship between the second phrase and the third phrase includes:

[0072] Candidate information is determined based on the sequential relationship between the second and third word groups;

[0073] Add verb segmentation to the candidate information to obtain phrase information.

[0074] As an optional implementation of this invention, displaying at least one semantic understanding content corresponding to the segmentation of the food ingredient includes:

[0075] In response to a preset operation of the display device, at least one semantic understanding content corresponding to the food ingredient segmentation is displayed, or, when displaying at least one semantic understanding content corresponding to the food ingredient segmentation, the verb segmentation included in the semantic understanding content is hidden.

[0076] Fourthly, a computer-readable storage medium is provided, comprising: storing a computer program on the computer-readable storage medium, wherein the computer program, when executed by a processor, implements the semantic understanding method as described in the second aspect.

[0077] Fifthly, a computer program product is provided, comprising: when the computer program product is run on a computer, causing the computer to implement the semantic understanding method as shown in the second aspect.

[0078] The technical solution provided in this disclosure has the following advantages compared with the prior art: The display device first acquires the word segmentation information corresponding to the voice ingredient data, wherein the word segmentation information includes at least one ingredient word and the attribute identifier corresponding to the ingredient word. Then, based on the attribute identifier, the target word in the at least one ingredient word is determined. Next, based on the order relationship between the target word and other words in the at least one ingredient word, the semantic understanding content corresponding to the at least one ingredient word is determined. Finally, the semantic understanding content corresponding to the at least one ingredient word is displayed. By acquiring at least one ingredient word corresponding to the voice ingredient data and the attribute identifier corresponding to the ingredient word, it is possible to understand multiple ingredients and their attributes and their matching relationships, thereby improving the display device's ability to understand inverted and disordered speech in ingredient management, further enabling accurate display and improving the user experience. Attached Figure Description

[0079] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0080] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0081] Figure 1A This is a schematic diagram illustrating an operational scenario between a display device and a control device according to one or more embodiments of the present disclosure;

[0082] Figure 1B This is a hardware configuration block diagram of a control device 100 according to one or more embodiments of the present disclosure;

[0083] Figure 2 This is a hardware configuration block diagram of a display device 200 according to one or more embodiments of the present disclosure;

[0084] Figure 3 This is a schematic diagram of the software configuration in a display device 200 according to one or more embodiments of the present disclosure;

[0085] Figure 4 This is a schematic diagram showing the icon control page of an application in a display device 200 according to one or more embodiments of the present disclosure;

[0086] Figure 5AA flowchart illustrating a semantic understanding method provided in an embodiment of this disclosure;

[0087] Figure 5B A schematic diagram illustrating the preprocessing of a semantic understanding method provided in this embodiment of the present disclosure;

[0088] Figure 6A A flowchart illustrating another semantic understanding method provided in this embodiment of the disclosure;

[0089] Figure 6B A schematic diagram illustrating the principle of another semantic understanding method provided in this embodiment of the disclosure;

[0090] Figure 7A A flowchart illustrating yet another semantic understanding method provided in this disclosure embodiment;

[0091] Figure 7B A schematic diagram illustrating the principle of yet another semantic understanding method provided in this disclosure embodiment;

[0092] Figure 7C One of the interface display diagrams for a semantic understanding method provided in this embodiment of the disclosure;

[0093] Figure 7D A second interface display diagram of a semantic understanding method provided in an embodiment of this disclosure;

[0094] Figure 7E The third diagram shows the interface of a semantic understanding method provided in this embodiment of the present disclosure;

[0095] Figure 8 This is a schematic diagram of the structure of a semantic understanding device provided in an embodiment of the present disclosure;

[0096] Figure 9 This is a schematic diagram of the structure of a computer device provided in an embodiment of this disclosure. Detailed Implementation

[0097] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0098] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0099] The terms "first," "second," "third," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar or related objects or entities, and do not necessarily imply a specific order or sequence, unless otherwise specified. It should be understood that such terms are interchangeable where appropriate.

[0100] The terms “comprising” and “having”, and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device that includes a range of components is not necessarily limited to all of the components that are clearly listed, but may include other components that are not clearly listed or that are inherent to such product or device.

[0101] Smart refrigerators can semantically understand control commands for various ingredients and attributes that are frequently used in refrigerator food management. They can record the shelf life and quantity of ingredients. For food that is about to expire or has already expired, smart refrigerators can automatically issue reminders and warnings to remind users to pay attention to the food's shelf life and to make reasonable dietary choices. This expands the semantic understanding capabilities and improves the accuracy of semantic understanding.

[0102] For example, such as Figure 1A As shown, Figure 1A This is a schematic diagram illustrating an application scenario of the semantic understanding process of a display device provided in an embodiment of the present invention. Figure 1A In this system, users can operate the display device 200 through the control device 100 or the terminal device 300. The semantic understanding process can be used in voice interaction scenarios between users and smart homes. For example, the display device 200 in this scenario can be a smart refrigerator, a smart washing machine, or other smart devices with intelligent display functions. When a user wants to control a smart device in this scenario, they need to issue a voice command. When the smart device receives the voice command, it performs semantic understanding on the voice command to determine the semantic understanding result corresponding to the voice command. This allows the smart device to subsequently display or execute corresponding control commands based on the semantic result, meeting the user's needs and improving the user experience.

[0103] In some embodiments, the control device 100 may be a remote control. Communication between the remote control and the display device includes infrared protocol communication, Bluetooth protocol communication, and other short-range communication methods, controlling the display device 200 wirelessly or via wired means. Users can input user commands through buttons on the remote control, voice input, control panel input, etc., to control the display device 200. Figure 1B An exemplary configuration block diagram of the control device 100 is shown. (Refer to...) Figure 1BAs shown, the control device 100 includes a controller 110, a communication interface 130, a user input / output interface 140, a storage device, and a power supply. The control device 100 can receive user input operation commands and convert them into commands that the display device 200 can recognize and respond to, acting as an intermediary for interaction between the user and the display device 200. The communication interface 130 is used for external communication and includes at least one of the following: a Wi-Fi chip, a Bluetooth module, NFC (Near Field Communication), or a suitable alternative module. The user input / output interface 140 includes at least one of the following: a microphone, a touchpad, a sensor, buttons, or a suitable alternative module.

[0104] In some embodiments, a terminal device 300 (e.g., a mobile terminal, tablet computer, laptop computer, etc.) can also be used to control the display device 200. For example, an application running on the terminal device 300 can be used to control the display device 200. The terminal device 300 can install software applications with the display device 200 to establish a connection and communication via network communication protocols, achieving one-to-one control operations and data communication. Semantic content displayed on the terminal device 300 can also be transmitted to the display device 200 to achieve synchronous display functionality.

[0105] In some embodiments, the display device 200 can also display content based on the user's voice commands. For example, if the user's voice command is "Could you please put two pounds of beef with a shelf life of three days and three pounds of pork into the refrigerator?", the display device 200 will perform semantic understanding and display the corresponding content.

[0106] In some embodiments, the display device 200 may receive commands without using the aforementioned terminal device 300, but instead receive user control via touch or gestures. For example, when the display device 200 is a smart refrigerator, and the user changes its upper refrigerator door from an open state to a closed state, the display device 200 displays the various food items placed before closing the refrigerator door, along with the corresponding attribute labels for each food item.

[0107] The semantic understanding method provided in this disclosure can be implemented based on a computer device, or a functional module or functional entity in a computer device.

[0108] The computer equipment can be a personal computer (PC), server, mobile phone, tablet computer, laptop computer, mainframe computer, etc., and this disclosure does not specifically limit it.

[0109] For example, Figure 2 This is a hardware configuration block diagram of a computer device according to one or more embodiments of the present disclosure. Figure 2As shown, the computer device includes at least one of the following: a tuner / demodulator 210, a communicator 220, a detector 230, an external device interface 240, a controller 250, a display 260, an audio output interface 270, a memory, a power supply, and a user interface 280. The controller 250 includes at least one of a central processing unit (CPU), a video processor, an audio processor, a graphics processing unit (GPU), RAM (Random Access Memory), ROM (Read-Only Memory), a first to nth interface for input / output, and a communication bus. The display 260 can be at least one of a liquid crystal display, an OLED display, a touch display, and a projection display, and can also be a projection device and a projection screen. The tuner / demodulator 210 receives broadcast television signals via wired or wireless means, and demodulates audio and video signals, such as EPG audio and video data signals, from multiple wireless or wired broadcast television signals. The communicator 220 is a component used to communicate with external devices or servers according to various communication protocol types. For example, the communicator may include at least one of the following: a Wi-Fi module, a Bluetooth module, a wired Ethernet module, other network communication protocol chips or near-field communication protocol chips, and an infrared receiver. Computer equipment can establish the transmission and reception of control signals and data signals with a server or local control device through the communicator 220. The detector 230 is used to collect signals from the external environment or to interact with the external environment. For example, the detector 230 includes a light receiver, a sensor for collecting ambient light intensity; or, the detector 230 includes an image acquisition device, such as a camera, which can be used to collect external environmental scenes, user attributes, or user interaction gestures; or, the detector 230 includes a sound acquisition device, such as a microphone, for receiving external sound. The external device interface 240 may include, but is not limited to, one or more of the following: a high-definition multimedia interface (HDMI), an analog or data high-definition component input interface (component), a composite video input interface (CVBS), a USB input interface (USB), an RGB port, etc. It may also be a composite input / output interface formed by multiple of the above interfaces. The controller 250 and the tuner 210 can be located in different separate devices, that is, the tuner 210 can also be located in an external device of the main device where the controller 250 is located, such as an external set-top box.

[0110] In some embodiments, the controller 250 controls the operation of the computer device and responds to user operations through various software control programs stored in memory. The controller 250 controls the overall operation of the computer device. The user can input commands through a graphical user interface (GUI) displayed on the monitor 260, and the user input interface receives the user input commands through the GUI. Alternatively, the user can input commands by entering specific sounds or gestures, and the user input interface receives the user input commands by recognizing the sounds or gestures through sensors.

[0111] In some embodiments, the display 260 includes a display screen assembly for presenting images, a driving assembly for driving image display, an assembly for receiving image signals output from a controller, and a user interface (UI) for displaying video content, image content, menu control interface, and user control interface. For example, the display may be at least one of a liquid crystal display (LCD), an OLED (Organic Light-Emitting Diode) display, a touch display, and a projection display, and may also be a projection device and a projection screen. Users can input user commands through a graphical user interface (GUI) displayed on the display 260, and the user input interface receives the user input commands through the GUI. Alternatively, users can input user commands by inputting specific sounds or gestures, and the user input interface receives the user input commands by recognizing the sounds or gestures through sensors. A "user interface" is the medium through which an application or operating system interacts and exchanges information with a user; it realizes the conversion between the internal form of information and a form acceptable to the user. A common form of user interface is the graphical user interface, which refers to a user interface related to computer operation displayed graphically. For example, it can be an interface element such as an icon, window, or control displayed on the screen of an electronic device. Controls can include visible interface elements such as icons, buttons, menus, tabs, text boxes, dialog boxes, status bars, and navigation bars. The user interface can be used to receive control signals from terminal devices 300 (such as infrared remote controls).

[0112] Figure 3 This is a schematic diagram of the software configuration of a computer device according to one or more embodiments of the present disclosure, such as... Figure 3 As shown, the system is divided into four layers, from top to bottom: the Applications layer (referred to as the "Application Layer"), the Application Framework layer (referred to as the "Framework Layer"), the Android runtime and system library layer (referred to as the "System Runtime Library Layer"), and the kernel layer.

[0113] Figure 4 This is a schematic diagram showing the icon control interface of an application included in a smart device (mainly a smart playback device, such as a smart TV, digital cinema system, or audio-visual server) according to one or more embodiments of this disclosure. Figure 4 As shown, the application layer contains at least one application whose corresponding icon control can be displayed on the screen, such as: live TV application icon control, video-on-demand (VOD) application icon control, media center application icon control, application center icon control, game application icon control, etc. Live TV applications can provide live television from different signal sources. Video-on-demand (VOD) applications can provide video from different storage sources. Unlike live TV applications, video-on-demand provides video display from certain storage sources. Media center applications can provide applications for playing various multimedia content. The application center can provide storage for various applications.

[0114] To illustrate this solution in more detail, the following will use examples to illustrate it. Figure 5A Figure 6A , Figure 7A To explain, it is understandable that, although Figure 5A , Figure 6A , Figure 7A The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 5A , Figure 6A , Figure 7A At least some steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps. The method is designed to implement the semantic understanding method provided in the embodiments of the present invention. Semantic understanding uses a series of AI (Artificial Intelligence) algorithms to parse text into structured, machine-readable intent and speech information, facilitating internet developers to better understand and meet user needs. For example, in the embodiments of this disclosure, the semantic understanding scenario involves a smart refrigerator performing semantic understanding on the user's statements regarding multiple ingredients, multiple attributes, or missing attributes, and displaying the semantically understood content on the smart refrigerator's display device.

[0115] like Figure 5A As shown, the method specifically includes the following steps:

[0116] S51. Obtain the word segmentation information corresponding to the voice ingredient data. The word segmentation information includes: at least one ingredient word segment and the attribute identifier corresponding to the ingredient word segment.

[0117] Specifically, for voice-based food data related to refrigerator food management, the steps to obtain the corresponding word segmentation information can be as follows: First, remove words such as prepositions and adverbs that do not have the professional attributes of refrigerator food management; then, obtain all recognizable food names and uniformly label them according to food type; finally, label other attributes such as quantity words in different dimensions.

[0118] For example, taking the voice-based food data "Could you please put two pounds of beef and three pounds of pork with a shelf life of three days into the refrigerator?" as an example, refer to... Figure 5B As shown, the corresponding word segmentation information obtained includes: two jin, shelf life, 3 days, beef, pork, three jin.

[0119] S52. Determine at least one target word in the food ingredient segmentation based on the attribute identifier.

[0120] The food ingredient segmentation can include terms like mango, apple, beef, pork, and mutton, while the corresponding attribute identifiers can be fruit, meat, vegetables, or weight. No specific restrictions are placed on food ingredient segmentation and attribute identifiers here.

[0121] For example, in the sentence "Can you help me put two pounds of beef with a shelf life of 3 days and three pounds of pork into the refrigerator?", the attribute identifiers are "two pounds" and "three pounds". Therefore, the food segmentation words are "beef" and "pork", and the corresponding target segmentation words are "beef" and "pork".

[0122] It should be noted that after preprocessing the user's voice data, the corresponding word segmentation information is obtained, and the presence of a subject (words related to ingredients) is determined based on the attribute identifier. If a subject is present, the next step S53 is executed; if no subject is present, the display device can output prompts such as "I don't understand this sentence" indicating that the keywords in the user's voice data cannot be recognized.

[0123] S53. Based on the order relationship between the target word and other words in at least one of the food ingredient words, determine the semantic understanding content corresponding to at least one of the food ingredient words.

[0124] For example, based on the order relationship between the target word and other words in at least one food ingredient word segment, the semantic understanding content corresponding to at least one food ingredient word segment is determined. Taking "Can you help me put two jin of beef with a shelf life of 3 days and three jin of pork in the refrigerator?" as an example, the determined semantic understanding content corresponding to at least one food ingredient word segment is: beef, two jin, shelf life of 3 days; pork, three jin.

[0125] S54. Display the semantic understanding content corresponding to at least one of the food ingredient segmentation words.

[0126] For example, the semantic understanding content corresponding to at least one food ingredient segmentation is displayed as: beef, two jin, shelf life 3 days; pork, three jin.

[0127] In this embodiment, the display device first acquires the word segmentation information corresponding to the voice-based food ingredient data. This word segmentation information includes at least one food ingredient word and its corresponding attribute identifier. Then, based on the attribute identifier, a target word is determined from the at least one food ingredient word. Next, based on the order relationship between the target word and other words in the at least one food ingredient word, the semantic understanding content corresponding to the at least one food ingredient word is determined. Finally, the semantic understanding content corresponding to the at least one food ingredient word is displayed. By acquiring at least one food ingredient word corresponding to the voice-based food ingredient data and its corresponding attribute identifier, the device can understand multiple food ingredients and their attributes and their pairing relationships. This improves the display device's ability to understand inverted and disordered speech in food ingredient management, leading to more accurate display and enhanced user experience.

[0128] Figure 6A This is a flowchart illustrating another semantic understanding method provided in this embodiment. Figure 5A This is further expanded and optimized based on the existing model. Optionally, this embodiment mainly describes the process of step S53 (determining the semantic understanding content corresponding to at least one ingredient segment based on the order relationship between the target segment and other segments in at least one ingredient segment).

[0129] S531. Based on the attribute identifier of the first traversed word in at least one of the food ingredient word segments, and the order relationship between the first traversed word segment and the target word segment, determine the word group information.

[0130] The target word segment is the first subject word segment that appears first in the order of at least one ingredient word segment. The phrase information includes at least one set of phrases. In this embodiment, the phrase information represents the combination of the phrase corresponding to the first subject word segment and the phrase corresponding to the second subject word segment.

[0131] S532. Based on the phrase information, determine at least one semantic understanding content corresponding to the word segmentation of the food ingredient.

[0132] For example, refer to Figure 6BAs shown, taking the example of "Could you help me put two jin of beef with a shelf life of 3 days and three jin of pork into the refrigerator?", the leftmost subject in the word segmentation list is obtained, that is, the first subject segmentation is "beef". Then, the word segmentation list is traversed from the left side based on the subject. Since the target word is the first subject segmentation in the order of at least one food ingredient segmentation, in this embodiment, the target word is beef. The phrase corresponding to the first subject segmentation is "two jin, shelf life of 3 days", the second subject segmentation is "pork", and the phrase corresponding to the second subject segmentation is "three jin". Based on the phrase information, the semantic understanding content corresponding to at least one food ingredient segmentation is determined to be: beef, two jin, shelf life of 3 days; pork, three jin.

[0133] Figure 7A This is a flowchart illustrating another semantic understanding method provided in this embodiment. Figure 6A This is further expanded and optimized based on the existing model. Optionally, this embodiment mainly describes the process of step S531 (determining phrase information based on the attribute identifier of at least one of the first traversed words in the ingredient segmentation and the sequential relationship between the first traversed words and the target words).

[0134] S5311. Based on the attribute identifier of the first traversed word in at least one of the food ingredient word segments, determine that the first traversed word is not the second subject word segment, and determine that there is no word segment with the same attribute identifier as the first traversed word segment.

[0135] For example, taking the sentence "Could you help me put two jin of beef with a shelf life of 3 days and three jin of pork into the refrigerator?" as an example, the corresponding word segmentation information obtained includes: "two jin", "shelf life", "3 days", "beef", "pork", and "three jin". The first traversal word segmentation is "two jin", where the second subject word segmentation can be multiple. In this embodiment of the disclosure, the second subject word segmentation is "pork".

[0136] S5312. Based on the sequential relationship between the first traversed word segmentation and the target word segmentation, determine the word group information.

[0137] For example, the first word segmentation is "two jin", the target word is "beef", and the phrase information is "shelf life 3 days".

[0138] This embodiment is a further extension and optimization based on the above embodiment. Optionally, this embodiment mainly describes the process of step S6312 (determining word group information based on the sequential relationship between the first traversed word segmentation and the target word segmentation).

[0139] A. Determine that the order relationship between the first traversed word segment and the target word segment belongs to a preset relationship, and determine that there is an object word between the first traversed word segment and the target word segment.

[0140] For example, taking the sentence "Could you help me put two jin of beef with a shelf life of 3 days and three jin of pork into the refrigerator?" as an example, the corresponding word segmentation information obtained includes: "two jin", "shelf life", "3 days", "beef", "pork", and "three jin". The first traversal word segmentation is "two jin", and the target word segmentation is "beef". The order relationship between the first traversal word segmentation and the target word segmentation is a pre-defined relationship. There is an objective word between the first traversal word segmentation and the target word segmentation, and the objective word is "shelf life".

[0141] B. Combine the accusative word with the corresponding word segment to form a first word group. Based on the other words between the first traversed word segment and the target word segment, as well as the first word group, determine the word group information.

[0142] For example, the objective word is "shelf life", the corresponding participle is "3 days", and the first phrase is composed of the objective word and the corresponding participle, that is, "shelf life 3 days".

[0143] Optionally, step B can be implemented in the following way:

[0144] B-1. Based on the attribute identifier of the second traversal segment in at least one of the ingredient segmentation words, determine that the second traversal segmentation word is the second subject segmentation word, and based on the other segments between the target segmentation word and the first traversal segmentation word and the first word group, form the second word group.

[0145] For example, taking the sentence "Could you help me put two jin of beef with a shelf life of 3 days and three jin of pork into the refrigerator?" as an example, the corresponding word segmentation information obtained includes: "two jin", "shelf life", "3 days", "beef", "pork", and "three jin". The second traversal word segmentation is "pork", and the attribute identifier of the second traversal word segmentation is "three jin". Therefore, the second traversal word segmentation is determined to be the second subject word segmentation, the target word segmentation is "beef", the first traversal word segmentation is "two jin", and other word segments include: the first phrase "shelf life of 3 days" and the first subject word segmentation "beef".

[0146] Among them, the individual words included in other word segments can be the same as the individual words split from the first word group (the first word group can be a compound word). For example, other word segments include: "shelf life 3 days", the first word group is split into "shelf life + 3 days", and the second word group is: "beef + two catties + shelf life 3 days".

[0147] Alternatively, the individual words included in other word segments may differ from the individual words split from the first word group (which can be a compound word). For example, other word segments may include: "shelf life + 3 days + quality", the first word group is split into "shelf life + 3 days", and the resulting second word group is "beef + two jin + shelf life 3 days + quality". Generally, beef is classified into eight levels based on its quality (represented by the marbling of the fat) and physiological maturity (age): premium, selected, optional, standard, commercial, usable, shredded, and canned. In this embodiment, if the other word segment is "shelf life + 3 days + premium", the first word group is split into "shelf life + 3 days", and the resulting second word group is "beef + two jin + shelf life 3 days + premium".

[0148] B-2. Determine that the second traversed word segment is the last untraversed second subject word segment, and combine the second traversed word segment with at least one untraversed remaining word segment in the ingredients to form a third word group.

[0149] For example, the second traversal segment is the last untraversed second subject segment. The second traversal segment is combined with at least one untraversed remaining segment from the ingredients to form a third word group. Taking "Can you help me put two jin of beef with a shelf life of 3 days and three jin of pork in the refrigerator?" as an example, the corresponding segmentation information includes: "two jin", "shelf life", "3 days", "beef", "pork", and "three jin". The second traversal segment is "pork", and the untraversed remaining segment is "three jin", forming the third word group "pork + three jin".

[0150] B-3. ​​Determine the phrase information based on the order relationship between the second phrase and the third phrase.

[0151] Optionally, step B-3 can be implemented in the following way:

[0152] ① Based on the order relationship between the second phrase and the third phrase, candidate information is determined.

[0153] For example, the second phrase is "beef + two jin + shelf life 3 days", and the third phrase is "pork + three jin". The determined candidate information is "beef", "two jin", "shelf life", "3 days", "pork", and "three jin".

[0154] ② Add verb segmentation to the candidate information to obtain phrase information.

[0155] For example, such as Figure 7BAs shown, a verb segment is added based on the subject segment included in each phrase. The verb segment can be "add" or "put into". For example, if the added verb is "add", the resulting phrase information is "beef", "add", "two jin", "shelf life", "3 days"; "pork", "add", "three jin".

[0156] In some embodiments, step S64 (displaying at least one semantic understanding content corresponding to the food ingredient segmentation) can be implemented in the following ways: in response to a preset operation of the display device, displaying at least one semantic understanding content corresponding to the food ingredient segmentation, or, when displaying at least one semantic understanding content corresponding to the food ingredient segmentation, hiding the verb segmentation included in the semantic understanding content.

[0157] The preset actions can include closing the refrigerator door, triggering a preset gesture / button, etc., to bring up the display interface. Furthermore, after the refrigerator detects that the door is closed, it will not repeatedly display the interface, thus avoiding multiple displays and improving the user experience.

[0158] For example, in response to a preset operation of the display device, a display method may refer to Figure 7C As shown, this displays the semantic understanding content corresponding to at least one ingredient segmentation, including verb segmentation corresponding to the subject. Another display method can be found by referring to... Figure 7D As shown, when displaying the semantic understanding content corresponding to at least one ingredient segmentation, the verb segmentation included in the semantic understanding content is hidden.

[0159] Additionally, when the food stored in the refrigerator changes, parameters such as food type and attribute labels can be modified accordingly. For example, if a user stores "two pounds of beef with a shelf life of three days and three pounds of pork" in the morning, and takes out one pound of beef and one pound of pork for lunch at noon, they can then tell the refrigerator, "Change the beef to one pound with a shelf life of three days and the pork to two pounds." Figure 7E As shown, the refrigerator's display device displays the semantically understood content corresponding to at least one food ingredient segmentation word after modification.

[0160] In this embodiment, the display device first acquires the word segmentation information corresponding to the voice-based food ingredient data. This word segmentation information includes at least one food ingredient word and its corresponding attribute identifier. Then, based on the attribute identifier, a target word is determined from the at least one food ingredient word. Next, based on the order relationship between the target word and other words in the at least one food ingredient word, the semantic understanding content corresponding to the at least one food ingredient word is determined. Finally, the semantic understanding content corresponding to the at least one food ingredient word is displayed. By acquiring at least one food ingredient word corresponding to the voice-based food ingredient data and its corresponding attribute identifier, the device can understand multiple food ingredients and their attributes and their pairing relationships. This improves the display device's ability to understand inverted and disordered speech in food ingredient management, leading to more accurate display and enhanced user experience.

[0161] Figure 8 This is a schematic diagram of a semantic understanding device provided in an embodiment of this disclosure. The device is configured in a smart device and can implement the semantic understanding method described in any embodiment of this application. The device 800 specifically includes the following:

[0162] The ingredient segmentation acquisition module 810 is used to acquire the segmentation information corresponding to the voice ingredient data. The segmentation information includes: at least one ingredient segmentation and the attribute identifier corresponding to the ingredient segmentation.

[0163] The target word segmentation determination module 820 is used to determine at least one target word in the word segmentation of the food ingredient based on the attribute identifier;

[0164] The semantic content determination module 830 is used to determine the semantic understanding content corresponding to at least one ingredient segment based on the order relationship between the target segment and other segments in at least one ingredient segment;

[0165] The semantic content display module 840 is used to display the semantic understanding content corresponding to at least one of the food ingredient word segments.

[0166] As an optional implementation of this invention, the semantic content determination module 830 includes:

[0167] The phrase information determination unit is used to determine phrase information based on the attribute identifier of at least one of the first traversed words in the ingredient word segmentation and the order relationship between the first traversed words and the target word;

[0168] The semantic content determination unit is used to determine the semantic understanding content corresponding to at least one of the food ingredient segmentation words based on the word group information.

[0169] As an optional implementation of this invention, the phrase information determination unit is specifically used for:

[0170] Based on the attribute identifier of the first traversed word in at least one of the food ingredient word segments, it is determined that the first traversed word is not the second subject word, and it is determined that there is no word with the same attribute identifier as the first traversed word.

[0171] Based on the sequential relationship between the first traversal word segmentation and the target word segmentation, the word group information is determined.

[0172] As an optional implementation of this invention, determining the word group information based on the sequential relationship between the first traversal word segmentation and the target word segmentation includes:

[0173] It is determined that the order relationship between the first traversed word segment and the target word segment belongs to a preset relationship, and it is determined that there is an object word between the first traversed word segment and the target word segment;

[0174] The objective word and its corresponding word segment are combined to form a first word group. Based on the other words between the first traversed word segment and the target word segment, as well as the first word group, the word group information is determined.

[0175] As an optional implementation of this invention, determining the word group information based on other word segments between the first traversed word segment and the target word segment, as well as the first word group, includes:

[0176] Based on the attribute identifier of the second traversal word in at least one of the food ingredient word segments, the second traversal word segment is determined to be the second subject word segment. Based on the other words between the target word segment and the first traversal word segment and the first word group, a second word group is formed.

[0177] The second traversal word segment is determined to be the last untraversed second subject word segment, and the second traversal word segment is combined with at least one untraversed remaining word segment in the ingredients to form a third word group;

[0178] The word group information is determined based on the order relationship between the second word group and the third word group.

[0179] As an optional implementation of this invention, determining the phrase information based on the sequential relationship between the second phrase and the third phrase includes:

[0180] Candidate information is determined based on the sequential relationship between the second and third word groups;

[0181] Add verb segmentation to the candidate information to obtain phrase information.

[0182] As an optional implementation of this invention, displaying at least one semantic understanding content corresponding to the segmentation of the food ingredient includes:

[0183] In response to a preset operation of the display device, at least one semantic understanding content corresponding to the food ingredient segmentation is displayed, or, when displaying at least one semantic understanding content corresponding to the food ingredient segmentation, the verb segmentation included in the semantic understanding content is hidden.

[0184] In this embodiment, the display device first acquires the word segmentation information corresponding to the voice-based food ingredient data. This word segmentation information includes at least one food ingredient word and its corresponding attribute identifier. Then, based on the attribute identifier, a target word is determined from the at least one food ingredient word. Next, based on the order relationship between the target word and other words in the at least one food ingredient word, the semantic understanding content corresponding to the at least one food ingredient word is determined. Finally, the semantic understanding content corresponding to the at least one food ingredient word is displayed. By acquiring at least one food ingredient word corresponding to the voice-based food ingredient data and its corresponding attribute identifier, the device can understand multiple food ingredients and their attributes and their pairing relationships. This improves the display device's ability to understand inverted and disordered speech in food ingredient management, leading to more accurate display and enhanced user experience.

[0185] The semantic understanding apparatus provided in this disclosure can execute the semantic understanding method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of the execution method. To avoid repetition, it will not be described again here.

[0186] This disclosure provides a computer device, including: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any of the semantic understanding methods described in this disclosure.

[0187] Figure 9 This is a schematic diagram of the structure of a computer device provided in an embodiment of this disclosure. Figure 9 As shown, the computer device includes a processor 910 and a storage device 920; the number of processors 910 in the computer device can be one or more. Figure 9 Taking a processor 910 as an example; the processor 910 and the storage device 920 in a computer device can be connected via a bus or other means. Figure 9 Taking the example of a connection between China and Israel via a bus.

[0188] Storage device 920, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the semantic understanding method in the embodiments of this disclosure. Processor 910 executes various functional applications and data processing of computer devices by running the software programs, instructions, and modules stored in storage device 920, thereby realizing the semantic understanding method provided in the embodiments of this disclosure.

[0189] Storage device 920 may primarily include a stored program area and a stored data area. The stored program area may store the operating system and at least one application program required for a given function; the stored data area may store data created based on terminal usage. Furthermore, storage device 920 may include a high-speed random access storage device, and may also include a non-volatile storage device, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, storage device 920 may further include storage devices remotely located relative to processor 910, which can be connected to computer equipment via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0190] The computer device provided in this embodiment can be used to execute the semantic understanding method provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0191] This disclosure also provides a storage medium containing computer-executable instructions. When executed by a computer processor, the computer-executable instructions implement the various processes of the methods provided in any of the above embodiments and achieve the same technical effects. To avoid repetition, further details are omitted here.

[0192] The computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0193] For ease of explanation, the above description has been provided in conjunction with specific embodiments. However, the discussion in some embodiments above is not intended to be exhaustive or to limit the embodiments to the specific forms disclosed above. Various modifications and variations can be obtained based on the above teachings. The selection and description of the above embodiments are for the purpose of better explaining the principles and practical applications, thereby enabling those skilled in the art to better utilize the embodiments and various different variations of the embodiments suitable for specific application considerations.

Claims

1. A display device, characterized in that, include: The controller is configured to: acquire word segmentation information corresponding to voice ingredient data, wherein the word segmentation information includes: at least one ingredient word segment and the attribute identifier corresponding to the ingredient word segment; Based on the attribute identifier, at least one target word in the word segmentation of the food ingredient is determined; Based on the order relationship between the target word segment and other words in at least one of the food ingredient word segments, determine the semantic understanding content corresponding to at least one of the food ingredient word segments; The display is configured to display at least one semantically understood content corresponding to the word segmentation of the food ingredient; The target word segment is at least one of the first subject word segments in the order of the ingredient word segments; The controller is specifically configured as follows: Based on the attribute identifier of at least one of the first traversed words in the food ingredient word segmentation, and the order relationship between the first traversed word segmentation and the target word segmentation, the word group information is determined; Based on the phrase information, determine at least one semantic understanding content corresponding to the word segmentation of the food ingredient; The controller is specifically configured as follows: Based on the attribute identifier of the first traversed word in at least one of the food ingredient word segments, it is determined that the first traversed word is not the second subject word, and it is determined that there is no word with the same attribute identifier as the first traversed word. Based on the sequential relationship between the first traversal word segmentation and the target word segmentation, the word group information is determined; The controller is specifically configured as follows: It is determined that the order relationship between the first traversed word segment and the target word segment belongs to a preset relationship, and it is determined that there is an object word between the first traversed word segment and the target word segment; The objective word and its corresponding word segment are combined to form a first word group. Based on the other word segments between the first traversed word segment and the target word segment, as well as the first word group, the word group information is determined. The controller is specifically configured as follows: Based on the attribute identifier of the second traversal word in at least one of the food ingredient word segments, the second traversal word segment is determined to be the second subject word segment. Based on the other words between the target word segment and the first traversal word segment and the first word group, a second word group is formed. The second traversal word segment is determined to be the last untraversed second subject word segment, and the second traversal word segment is combined with at least one untraversed remaining word segment in the ingredients to form a third word group; The word group information is determined based on the order relationship between the second word group and the third word group.

2. The display device according to claim 1, characterized in that, The controller is specifically configured as follows: Candidate information is determined based on the sequential relationship between the second and third word groups; Add verb segmentation to the candidate information to obtain phrase information.

3. The display device according to claim 2, characterized in that, The display is specifically configured as follows: In response to a preset operation of the display device, at least one semantic understanding content corresponding to the food ingredient segmentation is displayed, or, when displaying at least one semantic understanding content corresponding to the food ingredient segmentation, the verb segmentation included in the semantic understanding content is hidden.

4. A semantic understanding method, characterized in that, include: Obtain word segmentation information corresponding to the voice ingredient data, wherein the word segmentation information includes: at least one ingredient word segment and the attribute identifier corresponding to the ingredient word segment; Based on the attribute identifier, at least one target word in the word segmentation of the food ingredient is determined; Based on the order relationship between the target word segment and other words in at least one of the food ingredient word segments, determine the semantic understanding content corresponding to at least one of the food ingredient word segments; Display the semantic understanding content corresponding to at least one of the food ingredient segmentations; The target word segment is at least one of the first subject word segments in the order of the ingredient word segments; The step of determining the semantic understanding content corresponding to at least one ingredient segment based on the order relationship between the target segment and other segments in at least one ingredient segment includes: Based on the attribute identifier of at least one of the first traversed words in the food ingredient word segmentation, and the order relationship between the first traversed word segmentation and the target word segmentation, the word group information is determined; Based on the phrase information, determine at least one semantic understanding content corresponding to the word segmentation of the food ingredient; The step of determining phrase information based on the attribute identifier of at least one of the first traversed words in the ingredient word segmentation, and the order relationship between the first traversed words and the target word, includes: Based on the attribute identifier of the first traversed word in at least one of the food ingredient word segments, it is determined that the first traversed word is not the second subject word, and it is determined that there is no word with the same attribute identifier as the first traversed word. Based on the sequential relationship between the first traversal word segmentation and the target word segmentation, the word group information is determined; The step of determining word group information based on the sequential relationship between the first traversal word segmentation and the target word segmentation includes: It is determined that the order relationship between the first traversed word segment and the target word segment belongs to a preset relationship, and it is determined that there is an object word between the first traversed word segment and the target word segment; The objective word and its corresponding word segment are combined to form a first word group. Based on the other word segments between the first traversed word segment and the target word segment, as well as the first word group, the word group information is determined. The step of determining phrase information based on the attribute identifier of at least one of the first traversed words in the ingredient word segmentation, and the order relationship between the first traversed words and the target word, further includes: Based on the attribute identifier of the second traversal word in at least one of the food ingredient word segments, the second traversal word segment is determined to be the second subject word segment. Based on the other words between the target word segment and the first traversal word segment and the first word group, a second word group is formed. The second traversal word segment is determined to be the last untraversed second subject word segment, and the second traversal word segment is combined with at least one untraversed remaining word segment in the ingredients to form a third word group; The word group information is determined based on the order relationship between the second word group and the third word group.

5. A semantic understanding device, characterized in that, The device includes: The ingredient segmentation acquisition module is used to acquire the segmentation information corresponding to the voice ingredient data. The segmentation information includes: at least one ingredient segmentation and the attribute identifier corresponding to the ingredient segmentation. The target word segmentation determination module is used to determine at least one target word in the word segmentation of the food ingredient based on the attribute identifier; The semantic content determination module is used to determine the semantic understanding content corresponding to at least one ingredient segment based on the order relationship between the target segment and other segments in at least one ingredient segment; A semantic content display module is used to display the semantic understanding content corresponding to at least one of the food ingredient word segments; The semantic content determination module includes: The phrase information determination unit is used to determine phrase information based on the attribute identifier of at least one of the first traversed words in the ingredient word segmentation and the order relationship between the first traversed words and the target word; A semantic content determination unit is used to determine the semantic understanding content corresponding to at least one of the food ingredient segmentation words based on the word group information; The phrase information determination unit is specifically used for: Based on the attribute identifier of the first traversed word in at least one of the food ingredient word segments, it is determined that the first traversed word is not the second subject word, and it is determined that there is no word with the same attribute identifier as the first traversed word. Based on the sequential relationship between the first traversal word segmentation and the target word segmentation, the word group information is determined; The phrase information determination unit is specifically used for: It is determined that the order relationship between the first traversed word segment and the target word segment belongs to a preset relationship, and it is determined that there is an object word between the first traversed word segment and the target word segment; The objective word and its corresponding word segment are combined to form a first word group. Based on the other word segments between the first traversed word segment and the target word segment, as well as the first word group, the word group information is determined. The phrase information determination unit is specifically used for: Based on the attribute identifier of the second traversal word in at least one of the food ingredient word segments, the second traversal word segment is determined to be the second subject word segment. Based on the other words between the target word segment and the first traversal word segment and the first word group, a second word group is formed. The second traversal word segment is determined to be the last untraversed second subject word segment, and the second traversal word segment is combined with at least one untraversed remaining word segment in the ingredients to form a third word group; The word group information is determined based on the order relationship between the second word group and the third word group.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the semantic understanding method as described in claim 4.

Images