Model-based user push information generation method, storage medium and electronic device

Abstract

The invention discloses a model-based user push information generation method, a storage medium and an electronic device, and relates to the technical field of smart home, the model-based user push information generation method comprises the following steps: obtaining prompt word information and type information, the type information representing the type of push information, and the type information representing the type of the push information; the type information comprises at least one of texts, images, audios and videos; based on each type of information, target models in one-to-one correspondence with the type information are selected from a preset model library, and the preset model library comprises at least one of a text model, an image model, an audio model and a video model; and for each target model, generating push information of a corresponding type based on the cue word information and the target model. According to the method, the generation models of various types are integrated into the preset model library, and the corresponding target model is called to generate the push information of the corresponding type based on the generation type information. According to the invention, diversified push information can be generated in a one-stop manner.

Description

Technical Field

[0001] The present application relates to the field of smart home technology, and more specifically, to a model-based user push information generation method, storage medium, and electronic device. Background Art

[0002] With the development of artificial intelligence technology, natural language processing, image generation, video synthesis and other technologies have made significant progress. The application of deep learning algorithms in these fields enables machines to learn and understand large amounts of data, thereby generating more realistic text, image and video content. At the same time, the popularity of cloud computing technology provides powerful computing support for large-scale data processing and model training.

[0003] In the existing technology, although artificial intelligence technology can be used to assist in the creation of push content to a certain extent, there are still many limitations. For example, it can only generate a single type of push content, the quality and flexibility of the generated content are poor, and it is impossible to achieve real-time feedback and optimization.

[0004] Accordingly, the art needs a new model-based technical solution for generating user push information, a storage medium, and an electronic device to solve the above problems. Summary of the invention

[0005] In order to overcome at least one of the above-mentioned defects, the present application is proposed to provide a model-based user push information generation method, storage medium and electronic device that solves or at least partially solves the technical problem of the single form of push information generated in the prior art.

[0006] In a first aspect, the present application provides a model-based method for generating user push information, the method comprising: obtaining prompt word information and type information, wherein the type information represents the type of the push information, and the type information includes at least one of text, image, audio, and video; based on each type of the type information, selecting a target model corresponding to the type information in a preset model library, wherein the preset model library includes at least one of a text model, an image model, an audio model, and a video model; for each of the target models, generating a push information of a corresponding type based on the prompt word information and the target model.

[0007] In a technical solution of the above-mentioned model-based user push information generation method, for each of the target models, based on the prompt word information and the target model, generating a corresponding type of push information includes: parsing the prompt word information to obtain a parsing result; based on the parsing result, selecting target data in a preset database; and generating the push information based on the target data and the target model.

[0008] In a technical solution of the above-mentioned model-based user push information generation method, before selecting the target data in the preset database based on the analysis result, the method also includes: verifying the analysis result to determine whether the prompt word information meets the preset conditions, and if so, continuing to execute the step of determining the target data in the preset database based on the request information.

[0009] In a technical solution of the above-mentioned model-based user push information generation method, the method also includes: performing quality inspection and compliance inspection on the push information; if the quality or compliance of the push information fails the inspection, determining that the push information is unqualified.

[0010] In a technical solution of the above-mentioned model-based user push information generation method, if the quality and compliance of the push information are verified, the push information will be displayed. While displaying the push information, the method also includes: obtaining data related to the push information, the related data including at least traffic data and feedback data; based on the related data, adjusting the push information.

[0011] In a technical solution of the above-mentioned model-based user push information generation method, the adjustment of the push information based on the relevant data includes: updating the prompt word information, the parameters of the model in the preset model library, and at least one of the type information based on the relevant data; re-executing the step of generating push information to obtain updated push information.

[0012] In a technical solution of the above-mentioned model-based method for generating user push information, the method further includes: generating and displaying an analysis report based on the data related to the push information.

[0013] In a second aspect, the present application provides a model-based user push information generation device, the device comprising: an acquisition module, the acquisition module is configured to acquire prompt word information and type information, wherein the type information represents the type of the push information, and the type information includes at least one of text, image, audio, and video; an analysis module, the analysis module is configured to select a target model corresponding to the type information in a preset model library based on each type of the type information, wherein the preset model library includes at least one of a text model, an image model, an audio model, and a video model; a processing module, the processing module is configured to generate a corresponding type of push information for each target model based on the prompt word information and the target model.

[0014] In a third aspect, a computer-readable storage medium is provided, characterized in that the computer-readable storage medium includes a stored program, wherein when the program is run, the model-based user push information generation method described in any one of the technical solutions of the above-mentioned model-based user push information generation method is executed.

[0015] In a fourth aspect, an electronic device is provided, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the model-based user push information generation method described in any one of the technical solutions of the above-mentioned model-based user push information generation method through the computer program.

[0016] The above one or more technical solutions of the present application have at least one or more of the following beneficial effects:

[0017] In the technical solution of implementing this application, the preset model library integrates various types of large models, obtains the type of push information to be generated while obtaining the prompt word information, and calls the corresponding type of large model in the preset model library based on the type information to generate the corresponding type of push information. Through this application, various types of push information can be generated to meet the needs of diversified push content forms.

[0018] Furthermore, in the implementation of the technical solution of the present application, the prompt word information is first parsed, the spoken language expressions in the prompt word information are converted into normative standard fields, and then based on the parsing results, the target data is selected in the preset database. By selecting the template data in the preset database, the efficiency of the model generating the answer result is improved, and the quality of the generated content is guaranteed.

[0019] Furthermore, in the implementation of the technical solution of the present application, the parsing result is also verified to determine whether the prompt word information meets the preset conditions, so as to analyze whether the acquired prompt word information has clear semantics and whether there are any illegal sensitive words.

[0020] Furthermore, in implementing the technical solution of the present application, quality inspection and compliance inspection are performed on the generated push information to ensure that the push information is of high quality and complies with relevant specifications.

[0021] Furthermore, in implementing the technical solution of this application, while displaying the push information that has passed the inspection for quality and compliance, data related to the push information, such as traffic data and feedback data, is also obtained. By obtaining relevant data, data support can be provided for analyzing the effect of push information delivery and subsequent content improvement.

[0022] Furthermore, in the implementation of the technical solution of this application, the prompt word information, model parameters, generation type, etc. are updated based on relevant data, and then the updated push information is regenerated. Through this application, the prompt word, i.e., the specific content contained in the push information, model parameters, and the form of the push information, such as changing from text to video, can be updated or revised based on the delivery effect, feedback data, etc., so as to adapt to the actual needs of the outside world that are constantly changing, and ultimately improve the content accuracy and delivery effect of the push information. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0025] Figure 1 is a schematic diagram of a hardware environment of a method for generating user push information based on a model according to an embodiment of the present application;

[0026] Figure 2 is a schematic diagram of an application scenario of a method for generating user push information based on a model according to an embodiment of the present application;

[0027] Figure 3 It is a flowchart of the main steps of a method for generating user push information based on a model according to an embodiment of the present application;

[0028] Figure 4 It is a flowchart of the main steps of a method for generating user push information based on a model according to an embodiment of the present application;

[0029] Figure 5 It is a schematic diagram of the main structural block diagram of a model-based user push information generation device according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. "Module" and "processor" may include hardware, software or a combination of the two. A module may include hardware circuits, various suitable sensors, communication ports, memory, and may also include software parts, such as program code, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, hardware or a combination of the two. The non-transitory computer-readable storage medium includes any suitable medium that can store program code, such as a magnetic disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The term "at least one A or B" or "at least one of A and B" has a similar meaning to "A and / or B" and may include only A, only B, or A and B. The singular terms "a", "the" and "the" may also include plural forms.

[0032] According to one aspect of an embodiment of the present application, a model-based method for generating user push information is provided. The model-based method for generating user push information is widely used in smart homes, smart homes, smart home device ecosystems, smart residential (Intelligence House) ecosystems, and other scenarios including intelligent digital control applications. Optionally, in this embodiment, the above-mentioned model-based method for generating user push information can be applied to Figure 1 In the hardware environment composed of the terminal device 102 and the server 104 shown in FIG. Figure 1As shown, the server 104 is connected to the terminal device 102 via a network, and can be used to provide services (such as application services, etc.) for the terminal or a client installed on the terminal. A database can be set on the server or independently of the server to provide data storage services for the server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data computing services for the server 104.

[0033] The network may include but is not limited to at least one of the following: wired network, wireless network. The wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, local area network, and the wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal device 102 may be but is not limited to a PC, a mobile phone, a tablet computer, a smart air conditioner, a smart range hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing device, a smart dishwasher, a smart projection device, a smart TV, a smart clothes drying rack, a smart curtain, a smart audio and video, a smart socket, a smart speaker, a smart fresh air device, a smart kitchen and bathroom device, a smart bathroom device, a smart sweeping robot, a smart window cleaning robot, a smart mopping robot, a smart air purification device, a smart steamer, a smart microwave oven, a smart kitchen treasure, a smart purifier, a smart water dispenser, a smart door lock, etc.

[0034] In an example of an application scenario of this application, please refer to the attached Figure 2 , Figure 2 FIG. 1 is a schematic diagram of an application scenario of a method for generating user push information based on a model according to an embodiment of the present application. Figure 2 As shown in the figure, user roles can be designers, planning engineers, operation engineers, brand / marketing personnel, e-commerce marketing personnel, Haier customers, etc. Different application platforms are provided for different roles, such as various self-media platform APPs, Hwork, POP e-commerce system, nesting applet, Haier Smart Home APP, Sanyi Bird APP, etc. The above APPs can obtain functions such as copywriting generation, image generation, video generation, audio generation, etc. by connecting to the multi-layer distributed architecture based on cloud computing to generate push information using models to meet various practical needs. Based on the generation type selected by the user, the corresponding model is dispatched to generate the corresponding answer.

[0035] Please see attached Figure 3 , Figure 3 FIG. 1 is a flow chart of the main steps of a method for generating user push information based on a model according to an embodiment of the present application. Figure 3 As shown, the model-based user push information generation method in the embodiment of the present application mainly includes the following steps S1-S3.

[0036] Step S1: Obtain prompt word information and type information;

[0037] In this embodiment, the prompt word is a key word, phrase or sentence used to guide or trigger the content generation process. Type information is a specific information or instruction provided based on the type of content to be generated, which represents the type of push information, and the type information includes at least one of text, image, audio and video.

[0038] Step S2: Based on each type of information, select a target model corresponding to the type information in a preset model library;

[0039] In this embodiment, the preset model library has large models that can generate various types of answers, including but not limited to text models, image models, audio models and video models, among which the text model is used to generate text-type push content, the image model is used to generate image-type push content, the audio model is used to generate audio-type push content, and the video model is used to generate video-type push content. In addition, the image model and the audio model can be used as two sub-parts of the video model, that is, the video model can also generate image-type push content or audio-type push content. The preset model library provides the function of calling each target model interface based on type information.

[0040] Step S3: For each target model, based on the prompt word information and the target model, push information of the corresponding type is generated.

[0041] In this embodiment, the process of generating push information using the target model can be iterated and adjusted multiple times, and a more accurate answer result can be output through continuous optimization. If the type information contains multiple types at the same time, that is, if the type of push information expected to be generated is text, audio, and video at the same time, it is necessary to use the text model to generate text push information, use the audio model to generate audio push information, and use the video model to generate video push information.

[0042] In one embodiment, in combination with Figure 4 The main steps of the method for generating user push information based on a model according to an embodiment of the present application are shown in FIG. Figure 4 As shown, step S3 may also include the following steps S31-S33.

[0043] Step S31: Analyze the prompt word information to obtain the analysis result.

[0044] In this embodiment, the process of parsing the prompt word information may include, but is not limited to: segmenting the prompt word, extracting keywords or key phrases from the prompt word, attempting to identify the intent of the keyword, configuring parameters required for generating content, etc. The parsing result is the data information obtained after parsing the prompt word.

[0045] Step S32: based on the analysis result, select target data in the preset database;

[0046] In this embodiment, the data stored in the preset database includes but is not limited to material template data. Corresponding to the generation type information, the type of the material template data may include but is not limited to text data, image data, audio data, video data, etc.

[0047] Step S33: Generate push information based on target data and target model;

[0048] In this embodiment, the target data is passed as input to the corresponding target model, the model generates preliminary content according to the input data and its own parameters, and then outputs the answer result after several iterations.

[0049] In one embodiment, after obtaining the parsing result, the model-based user push information generation method of the present application may further include: verifying the parsing result to determine whether the prompt word information meets the preset conditions, and if so, continuing to perform the step of determining the target data in the preset database based on the request information. In this embodiment, the process of verifying the parsing result may include byte length, character type, illegal sensitive words, etc.

[0050] In one embodiment, the generated push information can also be subjected to quality inspection and compliance inspection. If the quality or compliance of the push information fails to pass the inspection, the push information is determined to be unqualified. In this embodiment, a pre-trained inspection model can be used for inspection. If any of the quality or compliance of the push information fails to pass the inspection, the generated content is determined to be unqualified, and subsequent operations such as deletion and prohibition of output display can be taken.

[0051] In one embodiment, while displaying the push information that has passed the quality and compliance inspection, data related to the push information, such as traffic data and feedback data, are also obtained to adjust the push information based on these related data. In this embodiment, the traffic data may include the number of visits, the number of views, the dwell time, etc., and the feedback data may include satisfaction evaluation, content quality evaluation, etc. Specifically, the step of adjusting the push information may include: based on the relevant data, updating at least one of the prompt word information, the parameters of the model in the preset model library, and the type information; re-executing the step of generating the push information to obtain the updated push information. In this embodiment, if the relevant data reflects that customers generally want to change the push content from text to pictures, the type information is updated, and the image model is selected to generate image-type push information.

[0052] In one embodiment, the model-based user push information generation method of the present application may also include: generating and displaying an analysis report based on data related to the push information. By generating and displaying the analysis report, the delivery effect of the push information can be displayed visually, so that the user can adjust the corresponding push strategy based on the analysis report.

[0053] Based on the above description, the model-based user push information generation method of the present application has been described in detail. It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art can understand that in order to achieve the effect of the present application, the different steps do not have to be executed in such an order, and they can be executed simultaneously (in parallel) or in other orders, and these changes are within the scope of protection of the present application.

[0054] Furthermore, the present application also provides a model-based user push information generation device.

[0055] Please see attached Figure 5 , Figure 5 FIG. 1 is a main structural block diagram of a device for generating user push information based on a model according to an embodiment of the present application. Figure 5As shown, the model-based user push information generation device in the embodiment of the present application mainly includes an acquisition module 11, an analysis module 12 and a processing module 13. In some embodiments, one or more of the acquisition module 11, the analysis module 12 and the processing module 13 can be combined into one module. In some embodiments, the acquisition module 11 can be configured to acquire prompt word information and type information, wherein the type information represents the type of push information, and the type information includes at least one of text, image, audio, and video. The analysis module 12 can be configured to select a target model corresponding to the type information in a preset model library based on each type of the type information, wherein the preset model library includes at least one of a text model, an image model, an audio model, and a video model. The processing module 13 can be configured to generate a corresponding type of push information for each target model based on the prompt word information and the target model. In one embodiment, the description of the specific implementation function of the acquisition module 11 can refer to step S1. In one embodiment, the description of the specific implementation function of the analysis module 12 can refer to step S2. In one embodiment, the description of the specific implementation function of the processing module 13 can refer to step S3.

[0056] The analysis module 12 can also be configured to perform quality inspection and compliance inspection on the push information; if the quality or compliance of the push information fails to pass the inspection, the push information is determined to be unqualified. The processing module 13 can also be configured to display the push information if both the quality and compliance of the push information pass the inspection. The acquisition module 11 can also be configured to acquire data related to the push information, and the related data includes at least traffic data and feedback data. The processing module 13 can also be configured to adjust the push information based on the related data. The processing module 13 can also be configured to generate and display an analysis report based on the data related to the push information.

[0057] The above-mentioned model-based user push information generating device is used to execute Figure 3 The model-based user push information generation method embodiment shown in the figure has similar technical principles, technical problems solved and technical effects produced. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process and related instructions of the model-based user push information generation device can refer to the contents described in the embodiment of the model-based user push information generation method, which will not be repeated here. It should be understood that since the setting of each module is only to illustrate the functional unit of the device of the present application, the physical devices corresponding to these modules can be the processor itself, or a part of the software in the processor, a part of the hardware, or a part of the combination of software and hardware. Therefore, the number of each module in the figure is only schematic.

[0058] It is understood by those skilled in the art that all or part of the processes in the method for implementing the above-mentioned embodiment of the present application can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal and software distribution medium, etc. that can carry the computer program code.

[0059] Furthermore, the present application also provides a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present application, the computer-readable storage medium can be configured to store a program for executing the model-based user push information generation method of the above-mentioned method embodiment, and the program can be loaded and run by the processor to implement the above-mentioned model-based user push information generation method. For ease of explanation, only the parts related to the embodiment of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present application. The computer-readable storage medium can be a memory device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present application is a non-temporary computer-readable storage medium.

[0060] Furthermore, the present application also provides an electronic device. In an electronic device embodiment according to the present application, the electronic device includes a processor and a memory, the memory can be configured to store a program for executing the model-based user push information generation method of the above method embodiment, and the processor can be configured to execute the program in the memory, which includes but is not limited to the program for executing the model-based user push information generation method of the above method embodiment. For ease of explanation, only the parts related to the embodiment of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present application. The electronic device can be an electronic device device formed by various electronic devices.

[0061] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for generating user push information based on a model, characterized in that: include: Acquire prompt word information and type information, wherein the type information represents the type of the push information, and the type information includes at least one of text, image, audio, and video; Based on each type of the type information, selecting a target model corresponding to the type information in a preset model library, wherein the preset model library includes at least one of a text model, an image model, an audio model, and a video model; For each of the target models, push information of a corresponding type is generated based on the prompt word information and the target model.

2. The method for generating user push information based on a model according to claim 1, characterized in that: For each of the target models, based on the prompt word information and the target model, generating push information of a corresponding type includes: Parsing the prompt word information to obtain a parsing result; Based on the analysis result, selecting target data in a preset database; The push information is generated based on the target data and the target model.

3. The method for generating user push information based on a model according to claim 2, characterized in that: Before selecting target data in a preset database based on the analysis result, the method further includes: The analysis result is verified to determine whether the prompt word information meets the preset condition. If so, the step of determining the target data in the preset database based on the request information is continued.

4. The method for generating user push information based on a model according to claim 1, characterized in that: The method further comprises: Performing quality inspection and compliance inspection on the pushed information; If the quality or compliance of the push information fails to pass the inspection, the push information is determined to be unqualified.

5. The method for generating user push information based on a model according to claim 4, characterized in that: If the quality and compliance of the push information are both verified, the push information is displayed. While displaying the push information, the method further includes: Acquire data related to the push information, wherein the related data at least includes flow data and feedback data; Based on the relevant data, the push information is adjusted.

6. The method for generating user push information based on a model according to claim 5, characterized in that: The adjusting the push information based on the relevant data includes: Based on the relevant data, updating at least one of the prompt word information, the parameters of the model in the preset model library, and the type information; Re-execute the step of generating push information to obtain updated push information.

7. The method for generating user push information based on a model according to claim 5 or 6, characterized in that: The method further comprises: Based on the data related to the pushed information, an analysis report is generated and displayed.

8. A user push information generation device based on a model, characterized in that: include: an acquisition module, the acquisition module being configured to acquire prompt word information and type information, wherein the type information represents the type of the push information, and the type information includes at least one of text, image, audio, and video; An analysis module, wherein the analysis module is configured to select a target model corresponding to each type of the type information from a preset model library based on each type of the type information, wherein the preset model library includes at least one of a text model, an image model, an audio model, and a video model; A processing module is configured to generate corresponding type of push information for each target model based on the prompt word information and the target model.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the model-based user push information generation method according to any one of claims 1 to 7 is executed when the program is run.

10. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to execute the model-based user push information generation method according to any one of claims 1 to 7 through the computer program.

Images