Prompt information generation method and device and related equipment

By obtaining the query information entered by the user and the feature information obtained in advance, prompt information is generated, which solves the problem that users find it difficult to determine the solution, improves the accuracy and efficiency of the solution, and helps users better respond to challenges.

CN118916468APending Publication Date: 2024-11-08SOUNDAI TECH CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411186545.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

It is difficult for users to determine the solution accurately and quickly when encountering problems, resulting in poor solution determination results.

Method used

By obtaining the query information input by the user and the feature information obtained in advance, prompt information is generated to represent the solution information of the target problem. The feature information is used to represent the processing style of the target object to solve the problem that the user expects, thereby improving the accuracy of the solution.

Benefits of technology

Improve the accuracy and efficiency of the solution, allowing users to better respond to challenges and difficulties and quickly determine solutions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118916468A_ABST
    Figure CN118916468A_ABST
Patent Text Reader

Abstract

The invention provides a prompt information generation method and device and related equipment.The prompt information generation method comprises the steps that query information input by a first user is obtained, and the query information is used for querying solution information of a target problem; prompt information is generated according to the query information and feature information obtained in advance, the prompt information is used for representing solution information of the target problem, and the feature information is used for representing a processing style of a target object expected by the first user for solving the target problem. Therefore, the solution information of the target problem can be generated according to the processing style of the target object expected by the first user for solving the target problem, so that the accuracy of the determined solution information is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the field of electronic technology, and in particular, to a prompt information generating method, device and related equipment. Background Art

[0002] With the continuous advancement of science and technology, people's living standards are constantly improving, but at the same time people are encountering more and more problems. Currently, many people often feel confused when encountering problems. They often feel that they have no idea where to start and cannot accurately and quickly determine solutions to the problems they encounter. It can be seen that the current users' determination of solutions to problems is poor. Summary of the invention

[0003] The embodiments of the present application provide a prompt information generation method, apparatus and related equipment to solve the problem that the current user's determination of a solution to a problem is poor.

[0004] To solve the above problems, this application is implemented as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for generating prompt information, the method comprising:

[0006] Acquire query information input by a first user, where the query information is used to query solution information of a target problem;

[0007] Prompt information is generated according to the query information and pre-acquired feature information, wherein the prompt information is used to represent solution information of the target problem, and the feature information is used to represent the processing style of the target object expected by the first user to solve the target problem.

[0008] In a second aspect, an embodiment of the present application provides a prompt information generating device, including:

[0009] A first acquisition module, used to acquire query information input by a first user, where the query information is used to query solution information of a target problem;

[0010] The first generating module is used to generate prompt information according to the query information and pre-acquired feature information, wherein the prompt information is used to represent the solution information of the target problem, and the feature information is used to represent the processing style of the target object expected by the first user to solve the target problem.

[0011] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a memory, a processor, and a program stored in the memory and executable on the processor; the processor is used to read the program in the memory to implement the steps in the method described in the first aspect above.

[0012] In a fourth aspect, an embodiment of the present application further provides a readable storage medium for storing a program, which, when executed by a processor, implements the steps in the method described in the first aspect above.

[0013] In a fifth aspect, an embodiment of the present application further provides a computer program product, comprising computer instructions, which, when executed by a processor, implement the steps in the method described in the first aspect above.

[0014] In an embodiment of the present application, prompt information is generated based on query information and pre-acquired feature information, the prompt information is used to represent solution information of the target problem, and the feature information is used to represent the processing style of the target object that the first user expects to solve the target problem. In this way, solution information of the target problem can be generated based on the processing style of the target object that the first user expects to solve the target problem, thereby improving the accuracy of the determined solution information. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0016] Figure 1 This is one of the flow charts of the prompt information generating method provided in the embodiment of the present application;

[0017] Figure 2 This is the second flowchart of the prompt information generating method provided in the embodiment of the present application;

[0018] Figure 3 This is the third flowchart of the prompt information generating method provided in the embodiment of the present application;

[0019] Figure 4 This is the fourth flowchart of the prompt information generating method provided in the embodiment of the present application;

[0020] Figure 5 It is a structural schematic diagram of a prompt information generating device provided in an embodiment of the present application;

[0021] Figure 6 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are 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 are within the scope of protection of this application.

[0023] The terms "first", "second" etc. in the embodiments of the present application are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. In addition, the terms "include" and "have" and any variation thereof are intended to cover non-exclusive inclusions, for example, the process, method, system, product or equipment comprising a series of steps or units need not be 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 equipment. In addition, "and / or" is used in the present application to represent at least one of connected objects, such as A and / or B and / or C, representing the inclusion of separate A, separate B, separate C, and A and B all exist, B and C all exist, A and C all exist, and 7 situations that A, B and C all exist.

[0024] See also Figure 1 , Figure 1 It is a flowchart of the prompt information generation method provided in an embodiment of the present application. Figure 1 The prompt information generating method shown can be executed by an electronic device.

[0025] like Figure 1 As shown, the prompt information generating method may include the following steps:

[0026] Step 101: Acquire query information input by a first user, where the query information is used to query solution information for a target problem.

[0027] The specific method in which the first user inputs the query information is not limited here. Optionally, the first user may input the query information through touch input, sliding input, or voice input.

[0028] The content of the target problem is not limited here. Optionally, the target problem may be a problem of how to choose among different options, or the target problem may be a problem for which no solution information can be found.

[0029] Step 102: Generate prompt information according to the query information and pre-acquired feature information, wherein the prompt information is used to indicate solution information of the target problem, and the feature information is used to indicate the processing style of the target object expected by the first user to solve the target problem.

[0030] Among them, the target object expected by the first user can be referred to as the role model object of the first user, and the target object can be an actual person, a virtual person, or a virtual anthropomorphic animal, etc. The actual person can refer to a real person who has appeared in history, the virtual person can refer to a virtual character created by literary works or film works, etc., and the virtual anthropomorphic animal can refer to a cartoon anthropomorphic animal created by literary works or film works, such as an anthropomorphic cat or an anthropomorphic mouse.

[0031] Among them, the characteristic information is used to represent the processing style of the target object that the first user expects to solve the target problem, which can be understood as: substituting into the perspective of the target object, and proposing solution information for the target problem according to the style of the target object in processing the problem. In this way, since the target object can be a role model object for the first user, and solution information for the target problem can be proposed according to the processing style of the role model object of the first user, and the prompt information is used to represent the solution information for the target problem, the target object can be guided in the process of generating the prompt information, thereby making the generated solution information more accurate and making the generated solution information more in line with the processing style expected by the first user.

[0032] The specific content of the prompt information is not limited here. Optionally, the prompt information may include at least one of the following: behavioral guidance, psychological motivation, actual operation steps and other information.

[0033] In an embodiment of the present application, according to steps 101 to 102, prompt information is generated based on the query information and pre-acquired feature information, the prompt information is used to represent the solution information of the target problem, and the feature information is used to represent the processing style of the target object that the first user expects to solve the target problem. In this way, the solution information of the target problem can be generated based on the processing style of the target object that the first user expects to solve the target problem, thereby improving the accuracy of the determined solution information.

[0034] At the same time, when the first user solves the target problem according to the solution information determined by the prompt information, the solving efficiency and accuracy of the target problem can be improved, and the notification can also enable the first user to better cope with challenges and difficulties.

[0035] An optional application scenario is that when the first user is hesitant about the target problem, he thinks about how his role model (i.e., the target object) would deal with the target problem, and thus can input query information on the electronic device so that the electronic device generates prompt information (i.e., solution information of the target problem) based on the query information and pre-acquired characteristic information of the target object (i.e., the target object's processing style for solving the target problem). In this way, under the guidance of the role model, the solution information of the target problem can be accurately and quickly determined, thereby achieving the effect of the role model object guiding the first user to make decisions on the target problem.

[0036] As an optional implementation manner, generating prompt information according to the query information and the pre-acquired feature information includes:

[0037] Inputting the query information into a preset language model to generate the prompt information;

[0038] The preset language model is a neural network model trained according to the feature information acquired in advance.

[0039] Among them, the preset language model can be called a large language model, and the training process of the preset language model is not limited here. Optionally, multiple feature information of the target object can be obtained from the sample pool, and the above-mentioned multiple feature information can be labeled information with high accuracy. The multiple feature information is input into the neural network model. When the neural network model converges, the converged neural network model can be determined as the preset language model.

[0040] The types of characteristic information are not specifically limited here. Optionally, the characteristic information may include at least one of the following: personality traits, behavioral style, values ​​and other key information.

[0041] In the implementation manner of the present application, query information is input into a preset language model to generate prompt information. In this way, prompt information is generated by using the preset language model, thereby improving the accuracy and generation efficiency of prompt information generation results.

[0042] See Figure 3 , Figure 3 The user in the example may refer to the first user. When the user encounters a target problem, he needs to seek a decision (i.e., the solution information of the target problem). The large model (which may refer to the preset language model) combines the example information (i.e., the characteristic information of the target object) to give suggestions (i.e., prompt information).

[0043] As an optional implementation manner, before generating prompt information according to the query information and the pre-acquired feature information, the method further includes:

[0044] Acquire initial information of the target object in a target manner, wherein the initial information is used to represent historical events of the target object from different sources;

[0045] Analyzing the initial information of the target object to generate the feature information;

[0046] The target method includes at least one of the following: web crawler acquisition, application programming interface (API) acquisition, and database acquisition.

[0047] The specific type of initial information is not limited here. Optionally, the initial information includes at least one of the following: speech, deeds, biography, etc. For example: Figure 2 , Figure 2 The role model information in the sentence can be understood as the identification information of the target object, the role model can refer to the target object, the speeches, deeds, biographies, etc. can be understood as the initial information, the big model can refer to the preset language model, and the key information such as personality traits, behavioral style, and values ​​can refer to the characteristic information.

[0048] The initial information of the target object is analyzed to generate characteristic information, which can be understood as: the initial information can be summarized and extracted and analyzed to obtain the characteristic information.

[0049] In the implementation manner of the present application, initial information of the target object is acquired in a targeted manner, and the initial information of the target object is analyzed to generate feature information, so that the accuracy of the result of the generated feature information can be further improved.

[0050] As an optional implementation manner, after generating prompt information according to the query information and the pre-acquired feature information, the method further includes:

[0051] receiving target information input by the first user, wherein the target information is used to indicate a preset target that the first user wants to achieve and a deadline for achieving the preset target;

[0052] Action plan information is generated according to the prompt information and the target information.

[0053] The preset goals may include long-term goals and short-term goals, and the deadline information may include deadline information of the long-term goals and deadline information of the short-term goals.

[0054] For example: See Figure 4 , Figure 4 The target in the above sentence refers to the preset target. Figure 4 The term in may refer to term information, Figure 4The plan table in the text may refer to action plan information, while Figure 4 The personalized incentives or suggestions in the action plan information may refer to the information stored in the action plan information. In this way, the implementation mode of the present application can effectively use the large language model (i.e., the preset language model) to analyze the user's role model information (i.e., the characteristic information of the target object), and provide personalized role model solutions and incentives (i.e., prompt information) according to the questions or needs (i.e., the query information) raised by the user, effectively stimulate the user's motivation and drive, and help them better achieve their goals and dreams.

[0055] In the implementation mode of the present application, the first user can set his / her own long-term and short-term goals and generate corresponding action plan information. In this way, the user can be regularly reminded to execute the action plan information according to the deadline information, so as to ensure that the first user can continue to maintain the action force, thereby ensuring the smooth completion of the action plan information.

[0056] As an optional implementation manner, after generating the action plan information according to the prompt information and the target information, the method further includes:

[0057] receiving first feedback information input by the first user, where the first feedback information is used to indicate the execution progress of the action plan information;

[0058] The action plan information is modified according to the first feedback information.

[0059] The type of the first feedback information is not limited here. Optionally, the first feedback information may be text information, or the first feedback information may be voice information.

[0060] Among them, the action plan information is corrected according to the first feedback information. It can be understood that the deadline information in the action plan information can be corrected according to the first feedback information to ensure that it will not be exceeded; or, the action steps of the action plan information can be corrected according to the first feedback information to improve the action efficiency, thereby ensuring that the action plan information can be successfully completed according to the deadline information.

[0061] In the implementation manner of the present application, the action plan information can be adjusted according to the first feedback information input by the first user to ensure that the user can continue to maintain motivation and action.

[0062] As an optional implementation manner, after generating the action plan information according to the prompt information and the target information, the method further includes:

[0063] Sending second feedback information to the server, where the second feedback information is used to indicate the execution progress of the action plan information;

[0064] Receiving suggestion information from a second user in response to the second feedback information;

[0065] The action plan information is modified according to the suggestion information.

[0066] The server may be a server corresponding to a community application, and the first user and the second user may both be registered users in the community application.

[0067] In the implementation manner of the present application, the first user can modify the action plan information according to the suggestion information replied by the second user, so as to further improve the accuracy of the action plan information.

[0068] In addition, by allowing the first user to share his or her progress and experience and communicate and interact with other users (second users), the first user can post questions, seek advice, and share experiences in the community application, and can also encourage and support each other with the second user to grow and progress together.

[0069] See also Figure 5 , Figure 5 : is a structural diagram of a prompt information generating device provided in an embodiment of the present application, wherein the prompt information generating device 500 comprises:

[0070] A first acquisition module 501 is used to acquire query information input by a first user, where the query information is used to query solution information of a target problem;

[0071] The first generating module 502 is used to generate prompt information according to the query information and the pre-acquired feature information, wherein the prompt information is used to represent the solution information of the target problem, and the feature information is used to represent the processing style of the target object expected by the first user to solve the target problem.

[0072] As an optional implementation, the first generating module 502 is further configured to input the query information into a preset language model to generate the prompt information;

[0073] The preset language model is a neural network model trained according to the feature information acquired in advance.

[0074] As an optional implementation manner, the prompt information generating device 500 further includes:

[0075] A second acquisition module, used for acquiring initial information of the target object in a target manner, wherein the initial information is used for representing historical events of the target object from different sources;

[0076] A second generating module, used for analyzing the initial information of the target object to generate the feature information;

[0077] Among them, the target method includes at least one of the following: web crawler acquisition, API acquisition, and database acquisition.

[0078] As an optional implementation manner, the prompt information generating device 500 further includes:

[0079] A first receiving module, configured to receive target information input by the first user, wherein the target information is used to indicate a preset target that the first user wants to achieve and a deadline for achieving the preset target;

[0080] The third generating module is used to generate action plan information according to the prompt information and the target information.

[0081] As an optional implementation manner, the prompt information generating device 500 further includes:

[0082] A second receiving module, configured to receive first feedback information input by the first user, wherein the first feedback information is used to indicate the execution progress of the action plan information;

[0083] The first correction module is used to correct the action plan information according to the first feedback information.

[0084] As an optional implementation manner, the prompt information generating device 500 further includes:

[0085] A sending module, used for sending second feedback information to the server, where the second feedback information is used for indicating the execution progress of the action plan information;

[0086] A third receiving module is used to receive suggestion information replied by the second user in response to the second feedback information;

[0087] The second correction module is used to correct the action plan information according to the suggestion information.

[0088] The prompt information generating device 500 can realize the embodiment of the present application Figure 1 The various processes of the method embodiment and the same beneficial effects are achieved, and will not be described again here to avoid repetition.

[0089] The present application also provides an electronic device. Figure 6 , the electronic device may include a processor 601, a memory 602, and a program 6021 stored in the memory 602 and executable on the processor 601. When the program 6021 is executed by the processor 601, Figure 1 Any steps in the corresponding method embodiments and achieving the same beneficial effects will not be repeated here.

[0090] A person skilled in the art can understand that all or part of the steps of implementing the above-mentioned embodiment method can be completed by hardware related to program instructions, and the program can be stored in a readable medium. The present application also provides a readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned Figure 1 Any steps in the corresponding method embodiments can achieve the same technical effect and will not be repeated here to avoid repetition.

[0091] The storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0092] The present application also provides a computer program product, including computer instructions, which can achieve the above-mentioned Figure 1 Any steps in the corresponding method embodiments can achieve the same technical effect and will not be repeated here to avoid repetition.

[0093] The above is a preferred implementation of the embodiment 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 described in 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 prompt information, characterized in that: The method comprises: Acquire query information input by a first user, where the query information is used to query solution information of a target problem; Prompt information is generated according to the query information and pre-acquired feature information, wherein the prompt information is used to represent solution information of the target problem, and the feature information is used to represent the processing style of the target object expected by the first user to solve the target problem.

2. The method according to claim 1, characterized in that The generating prompt information according to the query information and the pre-acquired characteristic information includes: Inputting the query information into a preset language model to generate the prompt information; The preset language model is a neural network model trained according to the feature information acquired in advance.

3. The method according to claim 1 or 2, characterized in that: Before generating prompt information according to the query information and the pre-acquired feature information, the method further includes: Acquire initial information of the target object in a target manner, wherein the initial information is used to represent historical events of the target object from different sources; Analyzing the initial information of the target object to generate the feature information; The target method includes at least one of the following: web crawler acquisition, application programming interface API acquisition, and database acquisition.

4. The method according to claim 1 or 2, characterized in that: After generating prompt information according to the query information and the pre-acquired feature information, the method further includes: receiving target information input by the first user, wherein the target information is used to indicate a preset target that the first user wants to achieve and a deadline for achieving the preset target; Action plan information is generated according to the prompt information and the target information.

5. The method according to claim 4, characterized in that After generating the action plan information according to the prompt information and the target information, the method further includes: receiving first feedback information input by the first user, where the first feedback information is used to indicate the execution progress of the action plan information; The action plan information is modified according to the first feedback information.

6. The method according to claim 4, characterized in that After generating the action plan information according to the prompt information and the target information, the method further includes: Sending second feedback information to the server, where the second feedback information is used to indicate the execution progress of the action plan information; Receiving suggestion information from a second user in response to the second feedback information; The action plan information is modified according to the suggestion information.

7. A prompt information generating device, characterized in that: include: A first acquisition module, used to acquire query information input by a first user, where the query information is used to query solution information of a target problem; The first generating module is used to generate prompt information according to the query information and pre-acquired feature information, wherein the prompt information is used to represent the solution information of the target problem, and the feature information is used to represent the processing style of the target object expected by the first user to solve the target problem.

8. An electronic device comprising: A memory, a processor, and a program stored in the memory and executable on the processor; wherein the processor is used to read the program in the memory to implement the steps in the prompt information generating method as described in any one of claims 1 to 6.

9. A readable storage medium for storing a program, characterized in that: When the program is executed by a processor, the steps of the prompt information generating method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, implement the steps in the prompt information generating method according to any one of claims 1 to 6.

Citation Information

Patent Citations

  • LLM model-based customizable identity question and answer robot device

    CN116992096A

  • Dialogue processing method and device based on large language model and electronic equipment

    CN117251552A

  • Application method of dialogue system based on human big language model in industrial scene

    CN117932012A