Image acquisition method, device, computer readable storage medium and equipment

Abstract

The application provides an image acquisition method and device, a computer readable storage medium and an electronic device, and relates to the technical field of artificial intelligence. The method can directly generate corpus information related to demand information according to user input demand information, without the user having to conceive corpus information by himself / herself. Furthermore, the method can generate an image corresponding to the demand information according to the corpus information, without going through a retrieval process, so that a personalized image can be obtained. Compared with setting a keyword in a search engine and selecting an image by relying on returned results, the application can one-keyedly generate corpus information suitable for an image generation process for a user and generate a personalized image directly related to demand information, thereby saving corpus conception time, retrieval time and image selection time and improving the efficiency of image acquisition.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and more specifically, to an image acquisition method, apparatus, computer-readable storage medium, and device. Background Technology

[0002] Images are generally more intuitive and easier to understand than text, making it easier for people to comprehend things, times, environments, etc. Typically, when faced with situations that are difficult to describe clearly with words, users will search for keywords using a search engine and select the images they need from the search results. These images serve as an auxiliary tool for verbal description, making it easier for the recipient to understand the user's intended meaning.

[0003] However, user-provided keywords may not be accurate. When using a search engine, users typically need to adjust their keywords multiple times based on the search results to obtain the final image. Furthermore, some related technologies may provide keywords, but users still need to select from the search results to determine the final image. Therefore, the efficiency of users obtaining images is relatively low.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute related technology known to those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide an image acquisition method, apparatus, computer-readable storage medium, and electronic device that can directly generate corpus information related to user input requirements without requiring the user to conceive the corpus information themselves. Furthermore, it can generate images corresponding to the requirements based on the corpus information, obtaining personalized images without a retrieval process. Compared to setting keywords in a search engine and relying on the returned results to select images, this application can generate corpus information suitable for the image generation process for users with one click, and generate personalized images directly related to the requirements information, saving time on corpus conception, retrieval, and image selection, and improving the efficiency of image acquisition.

[0006] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0007] According to one aspect of this application, an image acquisition method is provided, the method comprising:

[0008] Obtain the input requirement information;

[0009] Generate corpus information related to the requirements;

[0010] Generate an image corresponding to the required information based on the corpus information.

[0011] According to one aspect of this application, an image acquisition apparatus is provided, the apparatus comprising:

[0012] The information acquisition unit is used to acquire the input requirement information;

[0013] The corpus generation unit is used to generate corpus information related to the requirements information;

[0014] The image generation unit is used to generate images corresponding to the required information based on the corpus information.

[0015] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various alternative implementations described above.

[0016] According to one aspect of this application, a computer-readable storage medium is provided, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the method of any one of the above.

[0017] According to one aspect of this application, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any of the above methods by executing the executable instructions.

[0018] The exemplary embodiments of this application may have some or all of the following beneficial effects:

[0019] In an example embodiment of this application, the image acquisition method can directly generate corpus information related to the user's input requirements, eliminating the need for the user to conceive the corpus information themselves. Furthermore, it can generate an image corresponding to the requirements based on the corpus information, obtaining a personalized image without a retrieval process. Compared to setting keywords in a search engine and selecting images from the returned results, this application can generate corpus information suitable for the image generation process with a single click, and generate personalized images directly related to the requirements, saving time on corpus conception, retrieval, and image selection, thus improving the efficiency of image acquisition. Moreover, since this application can generate personalized images corresponding to the requirements, these personalized images can more directly and accurately represent user needs compared to images selected from search results; therefore, this application also improves image quality.

[0020] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0021] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0022] Figure 1 A flowchart illustrating an image acquisition method according to an embodiment of this application is shown schematically;

[0023] Figure 2 The diagram illustrates a dialog box of a text input interface according to one embodiment of the present application.

[0024] Figure 3 This illustration schematically shows an image acquisition process according to an embodiment of the present application;

[0025] Figure 4 A flowchart illustrating another embodiment of an image acquisition method according to this application is shown schematically;

[0026] Figure 5 The schematic diagram illustrates the structure of an image acquisition apparatus according to an embodiment of this application;

[0027] Figure 6 The schematic diagram illustrates the structure of a computer system suitable for implementing the electronic devices of the present application. Detailed Implementation

[0028] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of the embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced with one or more of the specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this application.

[0029] Please see Figure 1 , Figure 1 A flowchart illustrating an image acquisition method according to an embodiment of this application is shown schematically. Figure 1 As shown, the method includes the following steps.

[0030] Step S110: Obtain the input requirement information.

[0031] Step S120: Generate corpus information related to the demand information.

[0032] Step S130: Generate an image corresponding to the required information based on the corpus information.

[0033] Implementation Figure 1 The method described can directly generate corpus information related to user input requirements, eliminating the need for users to conceive the corpus information themselves. Furthermore, it can generate images corresponding to the requirements based on the corpus information, obtaining personalized images without a retrieval process. Compared to setting keywords in a search engine and relying on the returned results to select images, this application can generate corpus information suitable for the image generation process with a single click, and generate personalized images directly related to the requirements, saving time on corpus conception, retrieval, and image selection, thus improving image acquisition efficiency. Moreover, because this application can generate personalized images corresponding to the requirements, these personalized images can more directly and accurately represent user needs compared to images selected from search results; therefore, this application also improves image quality.

[0034] The steps described above in this example implementation will now be explained in more detail.

[0035] In step S110, the input requirement information is obtained.

[0036] In related technologies, to find the desired image, accurate / appropriate keywords need to be entered into the search engine. These keywords typically need to be conceived by the user, which takes time and requires a certain level of language proficiency. Furthermore, even after determining the accurate / appropriate keywords, the user still needs to select the desired image from the numerous images returned by the search engine. Clearly, this entire process requires a high degree of user involvement, has low automation, and is relatively inefficient.

[0037] To address this issue, this application provides a text input interface for users. In this interface, users do not need to conceive their own language; they only need to input colloquial language. Based on the user's input, this application can determine the required information and further automate the generation of language data and images, thereby reducing user involvement and perception, and efficiently and accurately providing users with the images they need. The required information may include characters, symbols, emoticons, etc., and this application does not limit the scope of the embodiments.

[0038] As an optional embodiment, obtaining input requirement information includes: in response to multiple input operations within a dialog, if the text corresponding to each of the multiple input operations belongs to the same topic, then the text corresponding to each of the multiple input operations is integrated into requirement information; if the text corresponding to each of the multiple input operations belongs to different topics, then the text is integrated according to the topics to obtain requirement information corresponding to each topic. This allows for the integration of text based on topics when multiple texts are detected, thereby obtaining requirement information and improving the efficiency of requirement information acquisition.

[0039] Specifically, the text input interface provided to the user by this application may include forms such as Figure 2 The dialog box allows users to input text. This application can respond to input operations within the dialog box and determine the typed text. If there is only one input operation within a unit of time in the dialog box, the typed text corresponding to the input operation is determined as the required information. If there are multiple input operations within a unit of time in the dialog box, it means that each input operation corresponds to one typed text.

[0040] Based on this, the specific implementation of the above embodiments is as follows: in response to the first input operation in the dialogue, the first typed text (e.g., I want an image of a small animal with wings) is determined and semantic analysis is performed on the first typed text based on a natural language processing model to obtain a first semantic result, and a first reply text (e.g., what animal?) is generated based on the first semantic result and displayed in the dialogue.

[0041] In response to a second input operation on the first reply text within the dialogue, the second input text is determined and semantic and contextual analyses are performed on the second input text (e.g., puppy) based on a natural language processing model to obtain a second semantic result. Based on the second semantic result, a second reply text (e.g., how much do you want) is generated and displayed within the dialogue.

[0042] In response to a third input operation on the second reply text within the dialogue, the third input text is determined (e.g., 100, that's it), and semantic and contextual analysis is performed on the third input text based on a natural language processing model to obtain a third semantic result. Based on the third semantic result, a third reply text (e.g., Okay) is generated and displayed in the dialogue.

[0043] If the dialogue ends, it is determined whether the first, second, and third typed texts belong to the same topic. If so, the typed texts corresponding to the multiple input operations are combined into the demand information. If not, the typed texts are combined according to the topic to obtain the demand information corresponding to each topic. For example, if the first and second typed texts belong to the first topic and the third typed text belongs to the second topic, then the first and second typed texts are combined into the first demand information; the third typed text is determined as the second demand information, or the third typed text is refined into the second demand information.

[0044] The conditions for determining the end of the dialogue are: the typed text contains a preset ending word (such as "that's enough", "that's it", "okay", etc.), or the semantic representation of the typed text ends. This application embodiment does not limit these conditions.

[0045] As an optional embodiment, the input text corresponding to multiple input operations is integrated into demand information, including: concatenating the input text corresponding to multiple input operations to obtain comprehensive text; and performing semantic analysis on the comprehensive text to extract demand information. This can improve the effectiveness of demand information, because since demand information is the result of extracting comprehensive text, the personalized image finally obtained based on demand information can more accurately represent demand information.

[0046] Specifically, if multiple text entries belonging to the same topic exist, they can be concatenated according to the order in which they were entered to obtain a composite text. Semantic analysis of the composite text can extract it into required information that meets a preset format; this preset format can be used to limit the number of characters, text display format, number of keywords, etc., but this embodiment does not impose such limitations. Furthermore, the required information can be understood as a summary of the composite text.

[0047] As an optional embodiment, acquiring input requirement information includes: in response to the activation of the speech extraction function, real-time monitoring of teaching speech; when a target teaching speech describing an entity is detected, converting the target teaching speech into text data; and refining the text data into requirement information. This can improve teaching efficiency, as the target teaching speech can be promptly refined into requirement information upon detection, enabling the subsequent efficient generation of images based on the target teaching speech to assist teachers in implementing teaching and providing a more intuitive teaching effect.

[0048] Specifically, in teaching scenarios, teachers typically need to create teaching slides, which can be used to preview the teaching effect during class. However, when explaining the slides (e.g., slides about prehistoric animals), teachers often encounter additional teaching content or questions from students (e.g., how large is the size difference between a saber-toothed tiger and a mammoth). The explanations for these questions are usually not included in the slides and require verbal explanation from the teacher. To explain these questions, teachers sometimes need to devise keywords and use search engines to find relevant information. However, due to imprecise keywords or the search engine's database not recording such information, the required images may not be found. In the classroom, time is often limited, and teachers are unlikely to spend much time using search engines. Given these circumstances, it is often difficult for teachers to answer questions outside the main teaching content in a timely manner during class.

[0049] To address the aforementioned issues, this application proposes a method to monitor teaching audio in real-time in response to the activation of the speech extraction function. This real-time monitoring can be achieved by segmenting the teaching audio into units of duration, continuously obtaining audio segments, each segment satisfying a unit duration. When target teaching audio describing entities (e.g., objects, animals, academic terms, formulas, theories, architectures, networks, etc.) is detected, the target teaching audio can be converted into text data, and the text data can be refined into requirement information to generate corpus information related to the requirement information. Based on the corpus information, one or more images corresponding to the requirement information can be generated for the user to select. The target teaching audio may include one or more teaching audio segments, which is not limited in this embodiment.

[0050] Through the above implementation method, teachers can automatically obtain corresponding images for teaching without having to come up with keywords or rely on search engines.

[0051] In step S120, corpus information related to the demand information is generated.

[0052] Specifically, there can be one or more corpus information (Prompts) related to the demand information; that is, one or more corpus information can be generated for a single demand information.

[0053] In step S130, an image corresponding to the requirement information is generated based on the corpus information.

[0054] Specifically, one or more images can be generated for a single corpus of information, but this application does not limit the scope of the embodiments.

[0055] Please see Figure 3 , Figure 3 The illustration shows a schematic diagram of an image acquisition process according to an embodiment of this application. Figure 3As shown, when demand information 310 is detected, corresponding corpus information 320, corpus information 330, ..., corpus information 340 can be generated. Based on corpus information 320, corresponding images 321, 322, ..., 323 can be generated; based on corpus information 330, corresponding images 331, 332, ..., 333 can be generated; based on corpus information 340, corresponding images 341, 342, ..., 343 can be generated.

[0056] As an optional embodiment, the method further includes: determining a target image from images corresponding to the required information in response to an image selection operation; and controlling a teaching projection device to display the target image. This can improve teaching effectiveness.

[0057] Specifically, when applied in the field of education, it can determine the target image in response to the image selection operation triggered by the teacher, and control the teaching projection equipment to display the target image, so that students can understand the relevant knowledge by combining the displayed target image with the teacher's knowledge introduction.

[0058] As an optional embodiment, if the demand information includes building parameters and the image corresponding to the demand information includes an architectural design image, the method further includes: generating and outputting an architectural engineering plan based on the image corresponding to the demand information. This allows architectural designers to quickly obtain architectural design images and, once the architectural design image is selected, promptly generate an architectural engineering plan for reference by relevant personnel. When applied to construction-related fields, this can shorten the overall construction cycle and help improve infrastructure efficiency.

[0059] Specifically, if the demand information includes building parameters, then a building design image corresponding to the demand information can be generated; wherein, the building project planning may include bidding scheme, construction requirements, building requirements, construction period, daily construction plan within the period, etc., which are not limited in this application embodiment.

[0060] As an optional embodiment, the method further includes: in response to an image selection operation, determining a target image from each image set; determining target corpus information corresponding to the target image from each corpus information; and adjusting the model parameters of the corpus generation model based on other corpus information besides the target corpus information in each corpus information. This allows for reverse optimization of the model based on the user's image selection, thereby improving the model's generation accuracy.

[0061] Specifically, model parameters may include the weights and biases of the corpus generation model.

[0062] Alternatively, the model parameters of the image generation model can be adjusted based on other images in the image set besides the target image.

[0063] Please see Figure 4 , Figure 4 A flowchart illustrating another embodiment of an image acquisition method according to this application is shown schematically. Figure 4 As shown, the image acquisition method includes steps S400 to S406.

[0064] Step S400: In response to multiple input operations within the dialog, if the text corresponding to the multiple input operations belongs to the same topic, then the text corresponding to the multiple input operations is integrated into the requirement information; if the text corresponding to the multiple input operations belongs to different topics, then the text is integrated according to the topic to obtain the requirement information corresponding to each topic.

[0065] Step S402: Generate corpus information related to the demand information.

[0066] Step S404: Generate an image corresponding to the required information based on the corpus information.

[0067] Step S406: In response to the image selection operation, determine the target image from each image set and determine the target corpus information corresponding to the target image from each corpus information. Based on the other corpus information in each corpus information besides the target corpus information, adjust the model parameters of the corpus generation model.

[0068] It should be noted that steps S400 to S406 are related to... Figure 1 For the specific implementation details of steps S400 to S406, please refer to the examples shown. Figure 1 The steps and their embodiments shown are not repeated here.

[0069] It is evident that implementation Figure 4 The method described can directly generate corpus information related to user input requirements, eliminating the need for users to conceive the corpus information themselves. Furthermore, it can generate images corresponding to the requirements based on the corpus information, obtaining personalized images without a retrieval process. Compared to setting keywords in a search engine and relying on the returned results to select images, this application can generate corpus information suitable for the image generation process with a single click, and generate personalized images directly related to the requirements, saving time on corpus conception, retrieval, and image selection, thus improving image acquisition efficiency. Moreover, because this application can generate personalized images corresponding to the requirements, these personalized images can more directly and accurately represent user needs compared to images selected from search results; therefore, this application also improves image quality.

[0070] Please see Figure 5 , Figure 5A schematic block diagram of an image acquisition apparatus according to one embodiment of this application is shown. Figure 5 As shown, the image acquisition device 500 may include the following units.

[0071] Information acquisition unit 501 is used to acquire input requirement information;

[0072] Corpus generation unit 502 is used to generate corpus information related to the demand information;

[0073] The image generation unit 503 is used to generate an image corresponding to the required information based on the corpus information.

[0074] It is evident that implementation Figure 5 The device shown can directly generate corpus information related to user input based on user-input requirements, eliminating the need for users to conceive the corpus information themselves. Furthermore, it can generate images corresponding to the user's requirements based on the corpus information, providing personalized images without a retrieval process. Compared to setting keywords in a search engine and selecting images from the results, this application can generate corpus information suitable for the image generation process with a single click, and generate personalized images directly related to the user's requirements, saving time on corpus conception, retrieval, and image selection, thus improving image acquisition efficiency. Moreover, because this application can generate personalized images corresponding to user requirements, these personalized images more directly and accurately represent user needs compared to images selected from search results, thus also improving image quality.

[0075] As an optional embodiment, the information acquisition unit 501 acquires the input requirement information, including:

[0076] In response to multiple input operations within a dialog, if the text corresponding to each of the multiple input operations belongs to the same topic, then the text corresponding to each of the multiple input operations is integrated into the request information.

[0077] If multiple input operations correspond to different topics, the input texts are integrated according to the topics to obtain the required information corresponding to each topic.

[0078] As can be seen, implementing this optional embodiment can integrate the typed text according to the topic when multiple typed texts are detected, thereby obtaining demand information and improving the efficiency of demand information acquisition.

[0079] As an optional embodiment, the information acquisition unit 501 integrates the typed text corresponding to multiple input operations into demand information, including:

[0080] The text entered from multiple input operations is concatenated to obtain a composite text.

[0081] Semantic analysis is performed on the comprehensive text to extract the required information.

[0082] It is evident that implementing this optional embodiment can improve the effectiveness of demand information. Since demand information is the result of extracting comprehensive text, the personalized image obtained based on the demand information can more accurately represent the demand information.

[0083] As an optional embodiment, the information acquisition unit 501 acquires the input requirement information, including:

[0084] In response to the activation of the voice extraction function, the teaching voice is monitored in real time.

[0085] When the target instructional speech used to describe an entity is detected, the target instructional speech is converted into text data;

[0086] Extract the text data into the required information.

[0087] As can be seen, implementing this optional embodiment can improve teaching efficiency. Upon detecting the target teaching speech, it can be promptly extracted into demand information so that images of the target teaching speech can be efficiently generated subsequently to help teachers implement teaching and provide a more intuitive teaching effect.

[0088] As an optional embodiment, it also includes:

[0089] An image determination unit is used to determine a target image from an image corresponding to the required information in response to an image selection operation;

[0090] The image display unit is used to control the display of target images on the teaching projection equipment.

[0091] It is evident that implementing this optional embodiment can improve teaching effectiveness.

[0092] As an optional embodiment, if the demand information includes building parameters and the image corresponding to the demand information includes architectural design images, it also includes:

[0093] The planning generation unit is used to generate and output the building engineering plan based on the image corresponding to the demand information.

[0094] It is evident that implementing this optional embodiment can, on the one hand, facilitate architectural designers to quickly obtain architectural design images, and on the other hand, generate architectural engineering plans in a timely manner after the architectural design images are selected for reference by relevant personnel. When applied to architectural-related fields, it can shorten the overall construction cycle and improve infrastructure efficiency.

[0095] As an optional embodiment, wherein:

[0096] The image determination unit is also configured to determine a target image from each image set in response to an image selection operation;

[0097] The corpus determination unit is used to determine the target corpus information corresponding to the target image from each corpus information;

[0098] The model optimization unit is used to adjust the model parameters of the corpus generation model based on other corpus information besides the target corpus information in each corpus.

[0099] As can be seen, implementing this optional embodiment allows for reverse optimization of the model based on the user's image selection, thereby improving the model's generation accuracy.

[0100] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0101] Since the functional modules of the image acquisition device in the example embodiments of this application correspond to the steps of the example embodiments of the image acquisition device described above, for details not disclosed in the device embodiments of this application, please refer to the embodiments of the image acquisition device described above.

[0102] Please see Figure 6 , Figure 6 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown.

[0103] It should be noted that, Figure 6 The computer system 600 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0104] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 602 or programs loaded from storage section 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for system operation. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0105] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0106] Specifically, according to embodiments of this application, the processes described below with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs the various functions defined in the methods and apparatus of this application.

[0107] In another aspect, this application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to implement the methods described in the above embodiments.

[0108] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0109] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0110] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0111] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the claims.

Claims

1. An image acquisition method, characterized in that, include: Obtaining input requirement information includes: responding to multiple input operations within a dialog; if the text corresponding to each of the multiple input operations belongs to the same topic, then integrating the text corresponding to each of the multiple input operations into requirement information; if the text corresponding to each of the multiple input operations belongs to different topics, then integrating the text according to the topics to obtain requirement information corresponding to each topic. Generate corpus information related to the aforementioned requirement information; Generate an image corresponding to the required information based on the corpus information; The method further includes: In response to an image selection operation, a target image is determined from each image set; wherein one piece of corpus information corresponds to one image set; Determine the target corpus information corresponding to the target image from each of the corpus information; Based on the corpus information other than the target corpus information in each corpus, the model parameters of the corpus generation model are adjusted.

2. The method according to claim 1, characterized in that, The text entered for each of the multiple input operations is integrated into the requirement information, including: The text entered for each of the multiple input operations is concatenated to obtain a composite text. Semantic analysis is performed on the comprehensive text to extract the required information.

3. The method according to claim 1, characterized in that, Obtain the input requirements information, including: In response to the activation of the voice extraction function, the teaching voice is monitored in real time. When the target instructional speech used to describe an entity is detected, the target instructional speech is converted into text data; The text data is then extracted into requirement information.

4. The method according to claim 3, characterized in that, Also includes: In response to an image selection operation, a target image is determined from the images corresponding to the required information; Control the teaching projection equipment to display the target image.

5. The method according to claim 1, characterized in that, If the demand information includes architectural parameters, and the image corresponding to the demand information includes architectural design images, it also includes: Based on the image corresponding to the required information, a construction project plan is generated and output.

6. An image acquisition device, characterized in that, include: An information acquisition unit is used to acquire input demand information, including: responding to multiple input operations within a dialogue; if the text corresponding to the multiple input operations belongs to the same topic, then integrating the text corresponding to the multiple input operations into demand information; if the text corresponding to the multiple input operations belongs to different topics, then integrating the text according to the topics to obtain demand information corresponding to each topic. The corpus generation unit is used to generate corpus information related to the required information. An image generation unit is used to generate an image corresponding to the requirement information based on the corpus information; The device further includes: An image determination unit is configured to determine a target image from each image set in response to an image selection operation; wherein one piece of corpus information corresponds to one image set; The corpus determination unit is used to determine the target corpus information corresponding to the target image from each corpus information; The model optimization unit is used to adjust the model parameters of the corpus generation model based on other corpus information besides the target corpus information in each corpus.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-5.

8. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the method of any one of claims 1-5 by executing the executable instructions.

Images