Information acquisition method and device

Abstract

The invention provides an information acquisition method, which can be applied to the field of information processing, and comprises the following steps: in response to received input information, determining at least one first object tag associated with the input information in object attribute information, the object attribute information comprising a plurality of object tags and attribute information corresponding to the object tags; under the condition that the attribute information corresponding to the first object tag does not meet the requirement, response information is generated and sent; and in response to feedback information received after the response information is sent, updating the attribute information of the first object tag.

Description

Technical Field

[0001] The present disclosure relates to the field of information processing, and more specifically, to an information acquisition method and device. Background Art

[0002] With the rapid development of artificial intelligence, large models are applied to various electronic devices. For large models running on the end, it is very important to capture user preferences, build user portraits, and become the user's intelligent avatar. However, for large models on the end, their model capabilities are limited. They cannot accurately extract user preferences, personality and other information from the user's historical conversations, nor do they fully utilize user feedback or provide users with more feedback opportunities. This makes the construction of user portraits of large models on the end have certain defects. Summary of the invention

[0003] In view of this, the present disclosure provides an information acquisition method, device, electronic device and medium.

[0004] One aspect of the present disclosure provides an information acquisition method, including: in response to received input information, determining at least one first object tag associated with the input information in object attribute information, wherein the object attribute information includes multiple object tags and attribute information corresponding to the object tags; if the attribute information corresponding to the first object tag does not meet the requirements, generating and sending response information; and in response to feedback information received after sending the response information, updating the attribute information of the first object tag.

[0005] According to an embodiment of the present disclosure, when the attribute information corresponding to the first object tag does not meet the requirements, a response message is generated and sent, including: when the attribute information corresponding to the first object tag in the object attribute information is empty, a first query message is generated and sent according to the first object tag; in response to feedback information received after sending the response message, the attribute information of the first object tag is updated, including: in response to feedback information received after sending the first query message, the attribute information of the first object tag is updated; the information acquisition method also includes: generating target output information based on at least the updated attribute information and the input information.

[0006] According to an embodiment of the present disclosure, when the attribute information corresponding to the first object tag does not meet the requirements, a response message is generated and sent, including: when the attribute information corresponding to the first object tag in the object attribute information is empty and the first object tag has at least two attribute information, at least two target output information are generated and sent according to the at least two attribute information of the first object tag and input information; in response to feedback information received after sending the response message, the attribute information of the first object tag is updated, including: in response to feedback information received after sending the target output information, the attribute information of the first object tag is updated.

[0007] According to an embodiment of the present disclosure, the information acquisition method also includes: generating target output information based on the attribute information and input information when the attribute information corresponding to the first object tag meets the requirements; generating reference information based on the feedback information in response to feedback information received after sending the target output information; and updating the object attribute information based on the reference information in response to the reference information meeting the update condition.

[0008] According to an embodiment of the present disclosure, the reference information includes at least one object information group, the object information group includes an object tag and attribute information corresponding to the object tag, and in response to the reference information satisfying an update condition, the object attribute information is updated according to the reference information, including: in response to the existence of identical object information groups in the reference information, and the number of identical object information groups is greater than a threshold, updating the object attribute information according to the identical object information groups.

[0009] According to an embodiment of the present disclosure, feedback information includes feedback content and feedback duration, and the feedback duration represents the time from sending response information to receiving feedback data; updating the attribute information of the first object tag includes: updating the attribute information of the first object tag according to the feedback content and feedback duration; or generating reference information includes: generating reference information according to the feedback content and feedback duration.

[0010] According to an embodiment of the present disclosure, the information acquisition method also includes: determining the association relationship between multiple object tags in the object attribute information; updating the attribute information of at least one third object tag based on the attribute information and the association relationship of the second object tag among the multiple object tags, wherein the second object tag is an object tag among the multiple object tags whose attribute information meets the requirements, and the third object tag is an object tag among the multiple object tags whose attribute information does not meet the requirements.

[0011] According to an embodiment of the present disclosure, the information acquisition method also includes: in response to the existence of object tags that meet the requirements in the object attribute information, generating and sending second query information according to the attribute information of each object tag that meets the requirements; in response to feedback information received after sending the second query information, updating the object attribute information.

[0012] Another aspect of the present disclosure provides an information acquisition device, including: a first determination module, used to determine at least one first object tag associated with the input information in the object attribute information in response to received input information, wherein the object attribute information includes multiple object tags and attribute information corresponding to the object tags; a first generation and sending module, used to generate and send response information when the attribute information corresponding to the first object tag does not meet the requirements; and a first update module, used to update the attribute information of the first object tag in response to feedback information received after sending the response information.

[0013] Another aspect of the present disclosure provides an electronic device, including: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.

[0014] Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above method when executed.

[0015] Another aspect of the present disclosure provides a computer program product, which includes computer executable instructions, and when the instructions are executed, are used to implement the method as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0017] Figure 1 Schematically shows an application scenario diagram in which the information acquisition method according to an embodiment of the present disclosure can be applied;

[0018] Figure 2 The flowchart of the information acquisition method according to the embodiment of the present disclosure is schematically shown;

[0019] Figure 3 A flowchart of generating and sending response information in the information acquisition method according to an embodiment of the present disclosure is schematically shown;

[0020] Figure 4 Another flowchart of generating and sending response information in the information acquisition method according to an embodiment of the present disclosure is schematically shown;

[0021] Figure 5 Another flow chart of the information acquisition method according to an embodiment of the present disclosure is schematically shown;

[0022] Figure 6Another flow chart of the information acquisition method according to an embodiment of the present disclosure is schematically shown;

[0023] Figure 7 Another flow chart of the information acquisition method according to an embodiment of the present disclosure is schematically shown;

[0024] Figure 8 Another flow chart of the information acquisition method according to an embodiment of the present disclosure is schematically shown;

[0025] Fig. 9 A block diagram of an information acquisition system according to an embodiment of the present disclosure is schematically shown;

[0026] Fig.10 A block diagram schematically shows an information acquisition device according to an embodiment of the present disclosure; and

[0027] Fig.11 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0028] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0029] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0030] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0031] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0032] In the embodiments of the present disclosure, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage, etc. of the data involved (for example, including but not limited to user personal information) are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information, network security, and national security.

[0033] In the embodiments of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0034] An embodiment of the present disclosure provides an information acquisition method, comprising: in response to received input information, determining at least one first object tag associated with the input information in object attribute information, wherein the object attribute information includes multiple object tags and attribute information corresponding to the object tags; if the attribute information corresponding to the first object tag does not meet the requirements, generating and sending response information; and in response to feedback information received after sending the response information, updating the attribute information of the first object tag.

[0035] Figure 1 The following schematically shows an application scenario diagram to which the information acquisition method according to an embodiment of the present disclosure can be applied. It should be noted that: Figure 1 What is shown is merely an example of an application scenario diagram to which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0036] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a terminal device 110, a network 120 and a server 130. The network 110 is used to provide a medium for a communication link between the terminal device 110 and the server 130. The network 120 may include various connection types, such as wired and / or wireless communication links, etc.

[0037] The terminal device 110 is provided with a terminal-side big model 111. Based on the terminal-side big model, users can perform functions including but not limited to daily task management, information organization, and personalized content recommendation. The terminal-side big model has the ability to build user portraits. The terminal-side big model can respond to the needs of users based on the built user portraits. The terminal-side big model 111 can be an independent application, a functional module embedded in an application, or a functional module embedded in the terminal device system to provide big model functions for various applications in the terminal device 110.

[0038] The terminal device 110 may be any electronic device having a display screen and supporting web browsing, including but not limited to a smart phone, a tablet computer, a laptop computer, a desktop computer, and the like.

[0039] The server 130 may be a server that provides various services, such as updating and modifying the user portrait browsed and constructed by the terminal device 110 (for example only). The server may analyze and process the data in the connected terminal device, and feed back the processing results to the terminal device.

[0040] It should be noted that the information acquisition method provided in the embodiment of the present disclosure can generally be executed by the terminal device 110. The information acquisition method provided in the embodiment of the present disclosure can also be executed by a server or other terminal device that is different from the terminal device 110 and can communicate with the terminal device 110. Correspondingly, or alternatively, the information acquisition method provided in the embodiment of the present disclosure can also be jointly executed by the terminal device 110 and the server 130.

[0041] For example, the object attribute information may be originally stored in the terminal device 110, or may be stored on an external storage device and may be imported into the first terminal device 110. Then, the first terminal device 110 may locally execute the information acquisition method provided by the embodiment of the present disclosure, or send the data to be processed to other terminal devices, servers, or server clusters, and the other terminal devices, servers, or server clusters that receive the image to be processed may execute the information acquisition method provided by the embodiment of the present disclosure.

[0042] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0043] Figure 2 The flowchart of the information acquisition method according to the embodiment of the present disclosure is schematically shown.

[0044] like Figure 2 As shown, the method may include operations S210 to S220.

[0045] In operation S210, in response to received input information, at least one first object tag associated with the input information in object attribute information is determined, wherein the object attribute information includes a plurality of object tags and attribute information corresponding to the object tags.

[0046] It should be noted that, before operation S210, a pre-constructed object portrait system, that is, object attribute information, may also be included, and the object attribute information includes multiple object tags and attribute information corresponding to the object tags. In the pre-construction process, the object attribute information may only contain object tags, and the attribute information corresponding to the object tags is empty.

[0047] Input information can be information or query requests (Query) provided by the user to the system through natural language or other forms of interaction (such as voice, text, click, etc.). This can be a question, command, preference statement, or other form of input. For example, a user sends a request to the client-side model: "I like spicy food, please recommend some dishes."

[0048] Object attribute information refers to a series of information stored within the system for a specific user, such as user portraits, which are used to describe the interests, preferences, habits, characteristics, etc. of the object. This information is composed of multiple object tags and attribute information corresponding to the object tags. For example, object tags: taste preference - "spicy", dish preference - "spicy chicken".

[0049] The first object tag refers to the tag that is most associated with the input information after receiving the user input information. This tag is used to represent a certain attribute that is most closely related to the current user query. The user inputs: "I want to read a few science fiction novels." Then the object tag associated with the user's "reading preference" will be identified as the first object tag, which may include the user's reading preferences. If the user enters "recommend a restaurant", related tags such as "food preferences" will be identified as the first object tag.

[0050] In operation S220, when the attribute information corresponding to the first object tag does not meet the requirements, response information is generated and sent. For example, when the attribute information of the first object tag is empty, or the attribute information of the first object tag is an initial default value, or the attribute information of the first object tag is not specific and detailed enough to generate an accurate output, it is considered that the attribute information corresponding to the first object tag does not meet the requirements.

[0051] When the attribute information corresponding to the first object tag does not meet the requirements, a response message is generated and sent. The response message can be text, voice, or pictures associated with the first object tag, so that the user can know the response of the big model to the user's request. It should be noted that the response here can be an answer response to the user's request content, or it can be a further communication response to the user's request content.

[0052] In operation S230, in response to feedback information received after sending the response information, attribute information of the first object tag is updated.

[0053] The feedback information may be additional information, instructions or operations provided by the user in response to the system response information. According to the feedback information provided by the user, the attribute information corresponding to the first object tag may be analyzed and obtained, and updated accordingly according to the obtained attribute information.

[0054] Figure 3 The flowchart of generating and sending response information in the information acquisition method according to an embodiment of the present disclosure is schematically shown.

[0055] like Figure 3 As shown, based on the foregoing embodiment, operation S220 may include operation S310, in which, when the attribute information corresponding to the first object tag in the object attribute information is empty, first query information is generated and sent according to the first object tag.

[0056] The first inquiry information may be a direct question about the attribute information corresponding to the first object tag. For example, the input information is: "Recommend a few dishes", and the corresponding first object tag is "taste preference", and its attribute information is empty. Then, the first inquiry information "What is your taste preference?" may be generated to directly ask for the answer to the empty attribute information.

[0057] On this basis, operation S230 may include operation S320, in response to feedback information received after sending the first query information, updating the attribute information of the first object tag. Specifically, determine whether the feedback information is related to the first object tag. If so, generate the attribute information of the first object tag according to the feedback information and update it accordingly. In operation S310, the end-side large model directly asks questions about the attribute information of the empty value. The user generally gives an answer containing the attribute information content of the first object tag. For example, "I like spicy food", then the attribute information corresponding to the label "taste preference" can be obtained according to the user's feedback information, which should be "spicy".

[0058] In some cases, the feedback information provided by the user is not related to the first object tag. For example, the user does not answer the question provided by the client-side large model, but changes the topic. For example, the input information is "Recommend me a few dishes", and after sending the first inquiry information, the feedback information received is: "Recommend me a scenic spot". The feedback information obtained cannot obtain content related to the first object tag. At this time, the attribute information of the first object tag is not updated, and the operation returns to S210, and the user's feedback information at this time is used as the input information in S210, and the solution is re-executed.

[0059] In the case where the feedback information is related to the first object tag, and the attribute information corresponding to the first object tag has been updated according to the feedback information, the information acquisition method further includes: generating target output information according to at least the updated attribute information and the input information. The target output information is the response information made to the user input information, that is, the initial request in this round of dialogue. The target output information can be understood as a direct, positive and complete answer to the user's request.

[0060] After the attribute information corresponding to the first object tag is updated, the user's initial request still fails to be responded to. Therefore, the target output information is generated at least based on the updated attribute information and the input information. For example, after the user answers the first inquiry information "What is your taste preference?" of the end-side big model, the user gives the feedback "I like spicy food". The attribute information of the object tag "taste preference" is updated to "spicy", and the target output information can be generated based on the attribute information of the updated first object tag and the input information, for example, "hot pot". In some embodiments, the target output information can be generated based on the updated attribute information and other first object tags that already have attribute information. For example, the attribute information of the object tag "taste preference" is updated to "spicy", and the object tag "ingredient preference" already has the attribute information "chicken", so the target output information "spicy chicken" can be generated accordingly.

[0061] In some embodiments, one inquiry may not be able to obtain the attribute information of the first object tag, and multiple rounds of questions may be required to accurately obtain the information. In this case, the information acquisition method may also include: in response to the feedback information being related to the first inquiry information, and the attribute information corresponding to the first object tag cannot be obtained according to the feedback information, then updating the content of the first inquiry information according to the feedback information and the first object tag and sending it until the attribute information corresponding to the first object tag can be obtained according to the received feedback information.

[0062] Figure 4 Another flowchart of generating and sending response information in the information acquisition method according to an embodiment of the present disclosure is schematically shown.

[0063] like Figure 4 As shown, in Figure 2On the basis of the illustrated embodiment, operation S220 may include operation S410, in which, when the attribute information corresponding to the first object tag in the object attribute information is empty and the first object tag has at least two attribute information, at least two target output information is generated and sent according to the at least two attribute information of the first object tag and the input information. Specifically, in the case where the attribute information corresponding to the first object tag in the object attribute information is empty and the first object tag has at least two attribute information, and the number of attribute information is less than or equal to a preset threshold, at least two target output information is generated and sent according to each attribute information of the first object tag and the input information, and each generated target output information corresponds to each attribute information one-to-one.

[0064] The first object tag has at least two attribute information. The "having" here does not mean that the attribute information corresponding to the first object tag exists, but rather that the attribute information corresponding to the first object tag has at least two values. For example, in the object attribute information, the attribute information corresponding to the gender tag is empty, while the gender tag can have two attribute information: male and female.

[0065] When the attribute information corresponding to the first object tag is empty, and the first object tag can have more than one attribute information and the number is small, the end-side large model can generate corresponding target output information based on each possible attribute information and input information. For example, the user's input information is: "What material is better for chopsticks?" The corresponding first object tag can be "material preference". The attribute information corresponding to the object tag "material preference" is empty. Assuming that in the pre-set setting, its value can only be "wood" or "iron", then, according to the attribute information of "wood", a target output information "wooden chopsticks have the following advantages..., so chopsticks are suitable for wood" can be generated, and according to the attribute information of "iron", a target output information "iron chopsticks have the following advantages..., so chopsticks are suitable for iron" can be generated. The two target output information are output for the user to judge.

[0066] The output method can be to seek feedback by asking questions after outputting multiple target output information. For example, after outputting two target output information, "Wooden chopsticks have the following advantages..., so wooden chopsticks are suitable", and "Iron chopsticks have the following advantages..., so iron chopsticks are suitable", add a question "After giving their respective advantages, which one do you think is more suitable for you?" and wait for feedback answers. Multiple target output information can also be output as an interactive UI, and users can perform interactive operations such as clicking on multiple target output information to obtain user feedback information.

[0067] On this basis, operation S230 may include operation S420: in response to feedback information received after sending the target output information, updating the attribute information of the first object tag. Specifically, if the user gives feedback information for the multiple target output information after learning the multiple target output information, then the corresponding attribute information is obtained and updated according to the feedback information. For example, based on the above example, the user inputs "I think wooden chopsticks are good", or the user clicks on the interactive UI of the target output information related to wooden chopsticks, then it can be known that the attribute information corresponding to the user's "material preference" label should be "wood".

[0068] It should be noted that Figure 3 The content of the embodiment shown is similar, and the feedback information received here needs to be related to the target output information so that the corresponding attribute information can be obtained according to the feedback information. If the feedback information is not related to each target output information output, the feedback information is regarded as input information to start a new round of communication.

[0069] Figure 5 Another flow chart of the information acquisition method according to an embodiment of the present disclosure is schematically shown.

[0070] like Figure 5 As shown, based on any of the foregoing embodiments, the information acquisition method may further include operations S510 to S530.

[0071] In operation S510, when the attribute information corresponding to the first object tag meets the requirements, target output information is generated according to the attribute information and the input information. For example, if the attribute information corresponding to the first object tag exists and is complete and detailed, then it can be considered that the attribute information corresponding to the first object tag meets the requirements. The situation where the requirements are met may include: after the input information is obtained, the attribute information corresponding to the first object tag meets the requirements; after the attribute information corresponding to the first object tag is updated according to the update operation in the above embodiment, the attribute information corresponding to the first object tag meets the requirements.

[0072] In operation S520, in response to feedback information received after sending the target output information, reference information is generated according to the feedback information. For example, when the received feedback information does not contain negative content about the target output information, the target output information outputted previously is deemed to meet the user's needs, and accordingly, the attribute information of the corresponding first object tag is also deemed to meet the requirements. At this time, the first object tag and the corresponding attribute information are stored as reference information.

[0073] It should be noted that, unlike the feedback information in the aforementioned embodiment that needs to be related to the first inquiry information and / or the target output information, the feedback information here may be related to or unrelated to the first inquiry information and / or the target output information: related, for example, the feedback information contains positive feedback content for the first inquiry information and / or the target output information, such as "yes", "right", "I do like spicy food", etc. Unrelated, for example, "I have another question...", etc. When the feedback information is not negative content for the first inquiry information and / or the target output information, such as "you are wrong", "I actually like sweet food", etc., it is deemed that the target output information outputted previously meets the user's needs, and accordingly, the attribute information of the corresponding first object tag is also deemed to meet the requirements. At this time, the first object tag and the corresponding attribute information are stored as reference information.

[0074] In some embodiments, the reference information may also be other object tags and corresponding attribute information other than the first object tag. For example, the feedback information includes the feedback content for the first query information and / or the target output information, as well as other information. Object tags and attribute information corresponding to object tags may also be extracted from other information. For example, the first object tag corresponding to "recommend a few dishes to me" is "taste preference". After the update in the aforementioned embodiment, the attribute information "spicy" corresponding to "taste preference" is obtained. If the user gives feedback "I am in Sichuan now, spicy food is indeed suitable for me", the attribute information "Sichuan" corresponding to the object tag "address" may be obtained. At this time, the object tag "address" and the corresponding attribute information "Sichuan" may also be stored as reference information.

[0075] Accordingly, in other embodiments, in the input information of the aforementioned embodiments, in addition to the actual request part, some other information may also exist in the input information. Accordingly, in the case where other information exists in the input information, reference information can be generated based on the other information in the input information. For example, the input information is "The weather is sunny and I am in a good mood. Please recommend a few songs to me", and the actual request part is "Recommend a few songs", so the first object tag corresponding to this input can be "Music Preference", and the input information also includes other information "The weather is sunny and I am in a good mood". Based on this other information, the attribute information "Sunny" corresponding to the object tag "Weather Preference" can be obtained, and then the object tag "Weather Preference" and the corresponding attribute information "Sunny" can be stored as reference information.

[0076] In some embodiments, the object tag and the attribute information of the object tag stored as reference information, in the object attribute information (such as a user portrait), the attribute information corresponding to the object tag is not empty. The attribute information corresponding to the object tag stored as reference information is different from the attribute information corresponding to the same object tag in the object attribute information (such as a user portrait). For example, in the object attribute information, the attribute information corresponding to "taste preference" is not empty and is "sweet", then in the generated reference information, the attribute information corresponding to "taste preference" is different from "sweet", for example, it may be "spicy", "sour", etc. If the same attribute information as that recorded in the object attribute information is stored as reference information, and the two are already the same, then there is no need to update the attribute information according to the reference information. Such object tags and corresponding attribute information obtained through feedback information are not stored as reference information to save resource overhead.

[0077] In operation S530, in response to the reference information satisfying the update condition, the object attribute information is updated according to the reference information. When the stored reference information satisfies the update condition, the object attribute information is updated according to the object tag recorded in the reference information and the corresponding attribute information. For example, the attribute information corresponding to the "taste preference" in the object attribute information is updated from "sweet" to "spicy".

[0078] According to an embodiment of the present disclosure, the reference information includes at least one object information group, the object information group includes an object tag and attribute information corresponding to the object tag, and operation S530 may include: in response to the existence of the same object information group in the reference information, and the number of the same object information groups is greater than a threshold, updating the object attribute information according to the same object information group. For example, in the reference information, there are multiple object information groups of "taste preference" and corresponding attribute information "spicy". When the number is greater than or equal to the number threshold, it can be regarded that the attribute information of the object tag "taste preference" of the object has changed, and the attribute information needs to be replaced with "spicy". By judging by the threshold of the object information group, and then determining whether to update, the influence caused by the accidental / special case of the object can be avoided. For example, the user's taste preference is "sweet", but one day he suddenly wants to eat sour, and this preference is known by the large model through feedback information or input information. Then, it is inappropriate to replace the attribute information corresponding to "taste preference" with "sour" at this time, because the object still likes to eat sweet in the macro sense, but there is only one special case at a specific time. However, by referring to the number of the same object information groups in the information, it can be determined whether a certain label of the object has changed at a macro level. This updating method will be more accurate.

[0079] According to an embodiment of the present disclosure, based on any of the foregoing embodiments, the feedback information may include feedback content and feedback duration, and the feedback duration represents the duration from sending the response information to receiving the feedback information. On this basis, updating the attribute information of the first object tag may include: updating the attribute information of the first object tag according to the feedback content and the feedback duration. Alternatively, generating reference information may include: generating reference information according to the feedback content and the feedback duration.

[0080] In some cases, the feedback duration can also reflect the emotional tendency towards the first query information and / or the target output information. When the feedback duration is short, it can be considered that the feedback party is emotionally firm and the emotional tendency towards the attribute information is enhanced. When the feedback duration is long, it can be considered that the feedback party is hesitant and the emotional tendency towards the attribute information is weak. According to the emotional tendency, more detailed attribute information can be obtained. For example, when the first query information is: "Is your taste heavy or light?", although the user gives the feedback content of "heavy", the feedback duration is long. It can be considered that the user prefers "heavy" to "light", but the tendency towards the attribute information of "heavy" is weak. Then, the attribute information "slightly heavy" can be obtained as the basis for updating or stored as reference information. In this way, the attribute information corresponding to the object label can be obtained more accurately and fine-grained.

[0081] Figure 6 Another flow chart of the information acquisition method according to an embodiment of the present disclosure is schematically shown.

[0082] like Figure 6 As shown, based on any of the foregoing embodiments, the information acquisition method further includes operations S610 to S620.

[0083] In operation S610, in response to received input information, attribute information of a first object tag is determined according to the input information.

[0084] In operation S620, when the attribute information corresponding to the first object tag does not meet the requirement, the attribute information of the first object tag is updated according to the input information.

[0085] In some cases, the received input information already contains the relevant content of the attribute information corresponding to the first object tag, and the attribute information corresponding to the first object tag can be directly determined based on the input information. For example, if the input information is: "I like to eat sweet food, recommend me a few dishes", the attribute information corresponding to "taste preference" can be determined to be "sweet" based on the input information "I like to eat sweet food", and the actual requirement of this input information is "recommend a few dishes". Based on this requirement, the first object tag such as "taste preference" can be determined. If the attribute information corresponding to the first object tag "taste preference" does not meet the requirements, it can be updated based on the attribute information "sweet" obtained from the input information.

[0086] Correspondingly, the object tag and the corresponding attribute information that can be obtained from the input information can also be other object tags other than the first object tag. In this case, the information acquisition method also includes: in response to the received input information, determining the attribute information of the fourth object tag according to the input information, and the fourth object tag is different from the first object tag. In the case where the attribute information corresponding to the fourth object tag does not meet the requirements, the attribute information of the fourth object tag is updated according to the input information. For example, the input information is "The weather is sunny, I am in a good mood, recommend me a few songs", then the actual demand part is "recommend a few songs", and the corresponding first object tag is "music preference", while the other part of the input information "The weather is sunny, I am in a good mood" can obtain the attribute information "Sunny" corresponding to "Weather Preference". In the case that the fourth object tag "Weather Preference" does not meet the requirements, its attribute information can be updated to "Sunny".

[0087] This embodiment can be used with Figure 6 The embodiments shown are executed in parallel, in which case the information acquisition method further includes: in response to the received input information, determining the attribute information of the first object tag and / or the attribute information of the fourth object tag according to the input information, the fourth object tag being different from the first object tag. If the attribute information corresponding to the first object tag and / or the fourth object tag does not meet the requirements, updating the attribute information of the first object tag and / or the fourth object tag according to the input information.

[0088] Correspondingly, in the aforementioned embodiment, there is also relevant content of received feedback information. Based on the same principle, the information acquisition method may also include: in response to receiving feedback information, including other information that is not related to the first query information and / or the target output information in the feedback information, determining attribute information of at least one fourth object tag based on the other information, and when the attribute information corresponding to the fourth object tag does not meet the requirements, updating the attribute information of the fourth object tag based on the other information.

[0089] Figure 7Another flow chart of the information acquisition method according to an embodiment of the present disclosure is schematically shown.

[0090] like Figure 7 As shown, based on any of the foregoing embodiments, the information acquisition method may further include operations S710 to S720.

[0091] Operation S710: determining association relationships between multiple object tags in object attribute information.

[0092] Operation S720, updates the attribute information of at least one third object tag according to the attribute information and association relationship of the second object tag among the multiple object tags, wherein the second object tag is an object tag among the multiple object tags whose attribute information meets the requirements, and the third object tag is an object tag among the multiple object tags that has an association relationship with the second object tag, and the attribute information corresponding to the third object tag does not meet the requirements.

[0093] Among object attributes, some object labels may have intrinsic correlations with each other. For example, users from different regions tend to have roughly the same taste. For example, users in Sichuan tend to have spicy taste, while users in the southeast coastal areas tend to have light taste.

[0094] Based on this kind of intrinsic association relationship, the object tag with empty attribute information can be updated through the object tag with non-empty attribute information. For example, the attribute information corresponding to the "address" tag is "southeast coast", then based on the association relationship between "address" and "taste preference", the attribute information of "taste preference" can be updated to "light".

[0095] In the disclosed embodiment, the association relationship between each object label can be established a priori through the cloud model or recommendation system deployed on the server. After the terminal-side model establishes communication with the server, the association relationship between the object labels can be obtained through the cloud model or recommendation system in the server, and the attribute information corresponding to the label can be updated. The object attribute information can also be uploaded to the server, and after the object attribute information is updated in the server based on the association relationship between the object labels, it is synchronized to the terminal-side large model.

[0096] Figure 8 Another flow chart of the information acquisition method according to an embodiment of the present disclosure is schematically shown.

[0097] like Figure 8 As shown, based on any of the foregoing embodiments, the information acquisition method may further include operations S810 to S820.

[0098] In operation S810, in response to the existence of object tags that meet the requirements in the object attribute information, second query information is generated and sent according to the attribute information of each object tag that meets the requirements.

[0099] In operation S820, object attribute information is updated in response to feedback information received after sending the second query information.

[0100] After the attribute information is updated by the method in any of the above embodiments, further confirmation can be performed based on the attribute information of the object tags that meet the requirements in the object attribute information. For example, second query information can be generated and sent based on the attribute information of each object tag that meets the requirements, so that the user can know whether the object attribute information generated by the client-side large model is correct. After the user knows and gives corresponding feedback information, if the feedback information contains the modified content of the attribute information of the object tag, then the corresponding object attribute information can be updated according to the modified content in the feedback information.

[0101] For example, in the object attribute information, "taste preference" is "sweet", "reading preference" is "science fiction", and "music preference" is "jazz", then this information can be integrated to generate and send a second inquiry message "Do you like sweet food? Do you like science fiction books? Do you like jazz music?" The user confirms based on the second inquiry information. If he is not satisfied with the content recorded therein, he can give feedback information, such as "No, my favorite music is pop music". Then, according to the modified content in the feedback information "My favorite music is pop music", the attribute information corresponding to the object label "music preference" can be updated to "pop music".

[0102] In summary, the embodiments of the present disclosure provide an information acquisition system framework. Fig. 9 The block diagram of the information acquisition system according to the embodiment of the present disclosure is schematically shown.

[0103] like Fig. 9As shown, after the user makes a request, the object attribute information can be updated according to the input content of the request, and its processing route is the arrow line marked with 1 in the figure. When the attribute information corresponding to the first object tag corresponding to the request is empty, the corresponding attribute information can be determined and updated through inquiry and feedback, and its processing route is the arrow line marked with 2 in the figure. After obtaining the input information and feedback information, the corresponding reference information can be generated. When the reference information meets the update condition, the object attribute information is updated based on the reference information, and its processing route is the arrow line marked with 3 in the figure. The user's input information and feedback information can also be saved as the knowledge base data of the end-side large model at the same time, and its processing route is the arrow line marked with 4 in the figure. The object attribute information can be self-updated according to the association relationship between each object tag in the object attribute information, and its processing route is the arrow line marked with 5 in the figure. The data in the knowledge base and the object attribute information can be used as the prompt content of the end-side large model to assist the large model in generating a reply to the request, and its processing route is the arrow line marked with 6 in the figure. In this way, the object attribute information is dynamically updated in the process of communicating with the user.

[0104] Fig.10 The block diagram schematically shows an information acquisition device according to an embodiment of the present disclosure.

[0105] like Fig.10 As shown, the information acquisition device 1000 includes a first determination module 1010 , a first generation and sending module 1020 and a first update module 1030 .

[0106] The first determination module 1010 is used to determine at least one first object tag associated with the input information in the object attribute information in response to the received input information, wherein the object attribute information includes multiple object tags and attribute information corresponding to the object tags; in some embodiments, the first determination module 1010 can be used to perform operation S210 in the aforementioned method, which is not repeated here.

[0107] The first generation and sending module 1020 is used to generate and send response information when the attribute information corresponding to the first object tag does not meet the requirements; in some embodiments, the first generation and sending module 1020 can be used to execute operation S220 in the aforementioned method, which is not repeated here.

[0108] The first updating module 1030 is used to update the attribute information of the first object tag in response to the feedback information received after sending the response information. In some embodiments, the updating module 1030 can be used to perform the operation S230 in the above method, which will not be described in detail here.

[0109] According to an embodiment of the present disclosure, the first generation and sending module 1020 may include a first sub-generation and sending module. The first sub-generation and sending module is used to generate and send a first query information according to the first object tag when the attribute information corresponding to the first object tag in the object attribute information is empty. In some embodiments, the first sub-generation and sending module can be used to perform operation S310 in the aforementioned method, which is not repeated here. The first update module 1030 may include a first sub-update module, and the first sub-update module is used to update the attribute information of the first object tag in response to feedback information received after sending the first query information. The information acquisition device 1000 may also include a first generation module, and the first generation module is used to generate target output information based on at least the updated attribute information and the input information.

[0110] According to an embodiment of the present disclosure, the first generation and sending module 1020 may include a second sub-generation and sending module, and the second sub-generation and sending module is used to generate and send at least two target output information according to the at least two attribute information of the first object tag and the input information when the attribute information corresponding to the first object tag in the object attribute information is empty and the first object tag has at least two attribute information. In some embodiments, the second sub-generation and sending module can be used to perform operation S410 in the aforementioned method, which is not described in detail here. The first update module 1030 may include a second sub-update module, and the second sub-update module is used to update the attribute information of the first object tag in response to feedback information received after sending the target output information.

[0111] According to an embodiment of the present disclosure, the information acquisition device may further include a second generation module, a third generation module, and a second update module. The second generation module is used to generate target output information according to the attribute information and input information when the attribute information corresponding to the first object tag meets the requirements. In some embodiments, the second generation module can be used to perform operation S510 in the aforementioned method, which is not described in detail here. The third generation module is used to generate reference information according to the feedback information received after sending the target output information. In some embodiments, the third generation module can be used to perform operation S520 in the aforementioned method, which is not described in detail here. The second update module is used to update the object attribute information according to the reference information in response to the reference information satisfying the update condition. In some embodiments, the second update module can be used to perform operation S530 in the aforementioned method, which is not described in detail here.

[0112] According to an embodiment of the present disclosure, the reference information includes at least one object information group, and the object information group includes an object tag and attribute information corresponding to the object tag. The second update module may include a third sub-update module. The third sub-update module is used to update the object attribute information according to the same object information group in response to the same object information group existing in the reference information and the number of the same object information groups being greater than a threshold.

[0113] According to an embodiment of the present disclosure, the first update module may include a fourth sub-update module. The fourth sub-update module is used to update the attribute information of the first object tag according to the feedback content and the feedback duration. The third generation module may include a first sub-generation module, and the first sub-generation module is used to generate reference information according to the feedback content and the feedback duration.

[0114] According to an embodiment of the present disclosure, the information acquisition device may further include a second determination module and a third update module. The second determination module is used to determine the attribute information of the first object tag according to the input information in response to the received input information. In some embodiments, the second determination module can be used to perform operation S610 in the aforementioned method, which is not described in detail here. The third sub-update module is used to update the attribute information of the first object tag according to the input information when the attribute information corresponding to the first object tag does not meet the requirements. In some embodiments, the third sub-update module can be used to perform operation S620 in the aforementioned method, which is not described in detail here.

[0115] According to an embodiment of the present disclosure, the information acquisition device may further include a third determination module and a fourth update module. The third determination module is used to determine the association relationship between multiple object tags in the object attribute information. In some embodiments, the third determination module can be used to perform operation S710 in the aforementioned method, which is not described in detail here. The fourth update module is used to update the attribute information of at least one third object tag based on the attribute information and association relationship of the second object tag among the multiple object tags, wherein the second object tag is an object tag among the multiple object tags whose attribute information meets the requirements, and the third object tag is an object tag among the multiple object tags whose attribute information does not meet the requirements. In some embodiments, the fourth update module can be used to perform operation S720 in the aforementioned method, which is not described in detail here.

[0116] According to an embodiment of the present disclosure, the information acquisition device may further include a second generation and sending module and a fifth update module. The second generation and sending module is used to generate and send second query information in response to the existence of object tags that meet the requirements in the object attribute information according to the attribute information of each object tag that meets the requirements. In some embodiments, the second generation and sending module can be used to perform operation S810 in the aforementioned method, which is not described in detail here. The fifth update module is used to update the object attribute information in response to feedback information received after sending the second query information. In some embodiments, the fifth update module can be used to perform operation S820 in the aforementioned method, which is not described in detail here.

[0117] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging circuits, or can be implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

[0118] For example, any of the first determination module 1010, the first generation and transmission module 1020, and the first update module 1030 can be combined in one module / unit / sub-unit for implementation, or any of the modules / units / sub-units can be split into multiple modules / units / sub-units. Alternatively, at least part of the functions of one or more of these modules / units / sub-units can be combined with at least part of the functions of other modules / units / sub-units and implemented in one module / unit / sub-unit. According to an embodiment of the present disclosure, at least one of the first determination module 1010, the first generation and transmission module 1020, and the first update module 1030 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or by any one of the three implementation methods of software, hardware, and firmware, or by a suitable combination of any of them. Alternatively, at least one of the first determining module 1010, the first generating and sending module 1020, and the first updating module 1030 may be at least partially implemented as a computer program module, and when the computer program module is executed, a corresponding function may be performed.

[0119] It should be noted that the data processing system part in the embodiments of the present disclosure corresponds to the data processing method part in the embodiments of the present disclosure. The description of the data processing system part specifically refers to the data processing method part, which will not be repeated here.

[0120] Fig.11 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present disclosure is schematically shown. Fig.11 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0121] like Fig.11 As shown, the electronic device 1100 according to an embodiment of the present disclosure includes a processor 1101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage part 1108 to a random access memory (RAM) 1103. The processor 1101 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 1101 may also include an onboard memory for caching purposes. The processor 1101 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0122] In RAM 1103, various programs and data required for the operation of electronic device 1100 are stored. Processor 1101, ROM 1102 and RAM 1103 are connected to each other through bus 1104. Processor 1101 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 1102 and / or RAM 1103. It should be noted that the program can also be stored in one or more memories other than ROM 1102 and RAM 1103. Processor 1101 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0123] According to an embodiment of the present disclosure, the electronic device 1100 may further include an input / output (I / O) interface 1105, which is also connected to the bus 1104. The electronic device 1100 may further include one or more of the following components connected to the input / output (I / O) interface 1105: an input portion 1106 including a keyboard, a mouse, etc.; an output portion 1107 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 1108 including a hard disk, etc.; and a communication portion 1109 including a network interface card such as a LAN card, a modem, etc. The communication portion 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the input / output (I / O) interface 1105 as needed. A removable medium 1111, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1110 as needed, so that a computer program read therefrom is installed into the storage portion 1108 as needed.

[0124] According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1109, and / or installed from the removable medium 1111. When the computer program is executed by the processor 1101, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0125] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0126] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include, but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0127] For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 1102 and / or the RAM 1103 described above and / or one or more memories other than the ROM 1102 and the RAM 1103 .

[0128] An embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method provided by the embodiment of the present disclosure. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the information acquisition method provided by the embodiment of the present disclosure.

[0129] When the computer program is executed by the processor 1101, the above functions defined in the system / device of the embodiment of the present disclosure are executed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0130] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 1109, and / or installed from a removable medium 1111. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0131] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0132] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It can be understood by those skilled in the art that the features recorded in the various embodiments of the present disclosure can be combined and / or combined in a variety of ways, even if such a combination or combination is not explicitly recorded in the present disclosure. In particular, without departing from the spirit and teaching of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0133] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for obtaining information, comprising: In response to the received input information, determining at least one first object tag associated with the input information in the object attribute information, wherein the object attribute information includes a plurality of object tags and attribute information corresponding to the object tags; If the attribute information corresponding to the first object tag does not meet the requirements, generate and send response information; In response to feedback information received after sending the response information, the attribute information of the first object tag is updated.

2. The method according to claim 1, wherein when the attribute information corresponding to the first object tag does not meet the requirements, generating and sending response information comprises: When the attribute information corresponding to the first object tag in the object attribute information is empty, generating and sending first query information according to the first object tag; The updating of the attribute information of the first object tag in response to the feedback information received after sending the response information includes: In response to feedback information received after sending the first query information, updating attribute information of the first object tag; The method further comprises: Target output information is generated based on at least the updated attribute information and the input information.

3. The method according to claim 1, wherein when the attribute information corresponding to the first object tag does not meet the requirement, generating and sending the response information comprises: When the attribute information corresponding to the first object tag in the object attribute information is empty and the first object tag has at least two attribute information, generating and sending at least two target output information according to the at least two attribute information of the first object tag and the input information; The updating of the attribute information of the first object tag in response to the feedback information received after sending the response information includes: In response to feedback information received after sending the target output information, attribute information of the first object tag is updated.

4. The method according to claim 1, further comprising: When the attribute information corresponding to the first object tag meets the requirement, generating target output information according to the attribute information and the input information; In response to feedback information received after sending the target output information, generating reference information according to the feedback information; In response to the reference information satisfying an update condition, the object attribute information is updated according to the reference information.

5. The method according to claim 4, wherein the reference information comprises at least one object information group, the object information group comprises an object tag and attribute information corresponding to the object tag, and in response to the reference information satisfying an update condition, updating the object attribute information according to the reference information comprises: In response to the existence of identical object information groups in the reference information, and the number of the identical object information groups being greater than a threshold, the object attribute information is updated according to the identical object information groups.

6. According to the method of any one of claims 1 to 4, the feedback information includes feedback content and feedback duration, and the feedback duration represents the duration from sending the response information to receiving the feedback data; The updating of the attribute information of the first object tag includes: updating the attribute information of the first object tag according to the feedback content and the feedback duration; Alternatively, the generating of reference information includes: The reference information is generated according to the feedback content and the feedback duration.

7. The method according to claim 1, further comprising: In response to the received input information, determining attribute information of the first object tag according to the input information; When the attribute information corresponding to the first object tag does not meet the requirement, the attribute information of the first object tag is updated according to the input information.

8. The method according to claim 1, further comprising: Determining an association relationship between multiple object tags in the object attribute information; According to the attribute information of the second object tag among the multiple object tags and the association relationship, the attribute information of at least one third object tag is updated, wherein the second object tag is an object tag among the multiple object tags whose attribute information meets the requirements, and the third object tag is an object tag among the multiple object tags whose attribute information does not meet the requirements.

9. The method according to claim 1, further comprising: In response to the existence of object tags meeting the requirements in the object attribute information, generating and sending second query information according to the attribute information of each object tag meeting the requirements; In response to feedback information received after sending the second query information, the object attribute information is updated.

10. An information acquisition device, comprising: a first determining module, configured to determine, in response to received input information, at least one first object tag associated with the input information in the object attribute information, wherein the object attribute information includes a plurality of object tags and attribute information corresponding to the object tags; A first generating and sending module, configured to generate and send response information when the attribute information corresponding to the first object tag does not meet the requirement; and The first updating module is configured to update the attribute information of the first object tag in response to feedback information received after sending the response information.

Images