Interaction information processing method and device, equipment and storage medium

Abstract

The embodiment of the invention provides an interaction information processing method and device, equipment and a storage medium. The method comprises the following steps: acquiring dialogue input information to be replied; obtaining candidate information and a hierarchical relationship of the candidate information; matching the dialogue input information with candidate information according to the hierarchical relationship to obtain target information corresponding to the dialogue input information; and generating dialogue input reply information according to the target information and the dialogue input information, and displaying the dialogue input reply information. According to the embodiment of the invention, the problems of low retrieval efficiency, missed matching and mismatching in a mode of replying by triggering an index through a keyword can be solved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to data processing technology, and more particularly to an interactive information processing method, apparatus, device and storage medium. Background Art

[0002] The interactive robot analyzes large amounts of text data and learns patterns in language usage to provide corresponding answers to questions.

[0003] Current interactive robots match keywords in conversation input information with pre-built index dictionaries, and respond by triggering indexes based on keywords, or provide guidance based on keywords in conversation input information through large language models. This results in low retrieval efficiency, and missed matches or incorrect matches may occur because the expressions of words similar to keywords in the index dictionary are different from the keywords. Summary of the invention

[0004] The embodiments of the present disclosure provide an interactive information processing method, apparatus, device and storage medium, which can improve retrieval efficiency and solve the problems of missed matching and false matching.

[0005] In a first aspect, an embodiment of the present disclosure provides an interactive information processing method, including:

[0006] Get the conversation input information to be replied;

[0007] Acquire candidate information and a hierarchical relationship of the candidate information, wherein the candidate information is determined based on semantic features of the historical information, and the hierarchical relationship is determined based on a hierarchical structure corresponding to a topic of the historical information;

[0008] Matching the dialogue input information with candidate information according to the hierarchical relationship to obtain target information corresponding to the dialogue input information;

[0009] Generate dialogue input reply information according to the target information and the dialogue input information, and display the dialogue input reply information.

[0010] In a second aspect, an embodiment of the present disclosure further provides an interactive information processing device, the device comprising:

[0011] An information acquisition module, used to acquire the dialogue input information to be replied;

[0012] A hierarchical acquisition module, used to acquire candidate information and hierarchical relationships of the candidate information, wherein the candidate information is determined based on semantic features of historical information, and the hierarchical relationships are determined based on hierarchical structures corresponding to the topics of the historical information;

[0013] a content matching module, configured to match the dialogue input information with candidate information according to the hierarchical relationship to obtain target information corresponding to the dialogue input information;

[0014] The reply information generating module is used to generate dialogue input reply information according to the target information and the dialogue input information, and to display the dialogue input reply information.

[0015] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0016] one or more processors;

[0017] a storage device for storing one or more programs,

[0018] When the one or more programs are executed by the one or more processors, the one or more processors implement the interactive information processing method as described in any embodiment of the present disclosure.

[0019] In a fourth aspect, an embodiment of the present disclosure further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the interactive information processing method as described in any embodiment of the present disclosure.

[0020] The disclosed embodiments provide an interactive information processing method, apparatus, device and storage medium, which obtain target information corresponding to the dialogue input information by matching dialogue input information with candidate information according to the hierarchical relationship of the candidate information, and generate dialogue input reply information corresponding to the dialogue input information in combination with the target information, thereby solving the problems of low retrieval efficiency, missed matches and wrong matches in the method of replying by using keyword-triggered index. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0022] Figure 1 A flowchart of an interactive information processing method provided by an embodiment of the present disclosure;

[0023] Figure 2 A schematic diagram of the structure of a knowledge base provided in an embodiment of the present disclosure;

[0024] Figure 3 A structural block diagram of a knowledge vector library provided in an embodiment of the present disclosure;

[0025] Figure 4A flowchart of another interactive information processing method provided by an embodiment of the present disclosure;

[0026] Figure 5 A flowchart of another interactive information processing method provided by an embodiment of the present disclosure;

[0027] Figure 6 A schematic diagram of the structure of an interactive information processing device provided by an embodiment of the present disclosure;

[0028] Figure 7 A schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0030] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0031] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0032] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0033] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0034] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0035] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0036] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0037] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0038] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0039] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0040] Figure 1 A flow chart of an interactive information processing method provided in an embodiment of the present disclosure. The embodiment of the present disclosure is applicable to intelligent dialogue situations based on interactive robots. The method can be executed by an interactive information processing device, which can be implemented in the form of software and / or hardware. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, a PC or a server, etc.

[0041] like Figure 1 As shown, the method includes:

[0042] S110: Acquire the dialogue input information to be replied.

[0043] The dialogue input information may represent dialogue text information input into the interactive robot. The dialogue input vector may represent a vector corresponding to the dialogue input information. For example, the dialogue input information may include a question text or a statement text. The dialogue input information may be directly input through an interactive interface provided by a terminal device, or the voice information input by the user may be converted into text information, which is not specifically limited in the embodiments of the present disclosure.

[0044] After obtaining the dialogue input information, the server preprocesses the dialogue input information to implement semantic segmentation of the dialogue input information, and maps the semantically segmented dialogue input information into a vector format, namely, a dialogue input vector.

[0045] In some embodiments, the dialogue input information is input into a pre-trained Embedding model to convert the dialogue input information into a dialogue input vector. It should be noted that the embodiments of the present disclosure may also use other methods of mapping the dialogue input information into vector features to achieve the conversion of the dialogue input information into the dialogue input vector, which is not specifically limited in the embodiments of the present disclosure.

[0046] S120: Obtain candidate information and the hierarchical relationship of the candidate information.

[0047] The candidate information is determined based on the semantic features of the historical information, and the hierarchical relationship is determined based on the hierarchical structure corresponding to the subject of the historical information.

[0048] In some embodiments, the historical information includes historical knowledge documents, the candidate information includes candidate knowledge content, and the hierarchical structure includes a structure of a directory corresponding to the subject of the historical knowledge document. The historical information may be a historical knowledge document generated during an enterprise service process, etc. The candidate knowledge content may represent semantic features obtained by semantically summarizing the historical knowledge document.

[0049] For example, historical knowledge documents may include business documents, personnel documents, product documents, etc. The database composed of historical knowledge documents may be a knowledge base. In the knowledge base, historical knowledge documents of the same subject correspond to the same directory, and there may be an inclusion relationship between the directories, that is, the directory may contain subdirectories. Figure 2 A schematic diagram of the structure of a knowledge base provided in an embodiment of the present disclosure, such as Figure 2 As shown, historical knowledge documents a, b, and c are of the same subject and can be placed under directory A. Historical knowledge documents e and f are of the same subject and can be placed under directory R, ​​and target A is a subdirectory of target R. It should be noted that the directory structure represents the hierarchical structure of the directory in the knowledge base, and can change as the user places historical knowledge documents into the knowledge base.

[0050] Semantic features can represent the summary of the content expressed by historical information. The historical information can be semantically understood and summarized through a large language model to obtain corresponding semantic features. For example, for historical knowledge documents, the historical knowledge documents are segmented according to separators such as carriage returns or periods to obtain several sentences containing set words. Each sentence can be preprocessed by removing stop words, punctuation marks, and irrelevant characters, and the preprocessed sentences are formatted. Then, the sentence vector corresponding to the formatted sentence is determined, and the sentence vector is input into the large language model. The semantic features of the sentence vector are determined by the large language model according to the content represented by the sentence vector. The semantic features of the corresponding historical knowledge document are determined based on the semantic features of the sentence vector. If the directory does not contain subdirectories, the semantic features of all historical knowledge documents in the directory are used as candidate knowledge content for the directory itself.

[0051] If the directory contains subdirectories, the directory features of the directory are determined by combining the subdirectory features and the semantic features of all historical knowledge documents under the target. The semantic features of all historical knowledge documents under the subdirectory can be merged to obtain a merged text, and the semantic features corresponding to the merged text can be determined by a large language model, and the semantic features corresponding to the merged text can be used as subdirectory features.

[0052] The candidate knowledge corresponding to the directory is formed according to one or more of the directory features corresponding to the directory, the semantic features of the historical knowledge documents corresponding to the directory, and the content of the historical knowledge documents corresponding to the directory, and then the hierarchical relationship of the candidate knowledge content is determined according to the directory structure. Optionally, the candidate knowledge content is stored according to the hierarchical relationship to obtain a knowledge vector library.

[0053] Exemplarily, after obtaining the input vector of the dialogue to be replied, a knowledge vector library is obtained, wherein the knowledge vector library represents the candidate knowledge contents and the hierarchical relationship between the candidate knowledge contents.

[0054] Figure 3 This is a structural block diagram of a knowledge vector library provided by an embodiment of the present disclosure. Figure 3As shown, the knowledge vector library includes 3 levels, among which the first level is represented as level 1, which corresponds to directory R, ​​and level 1 stores candidate knowledge content corresponding to directory R, ​​including directory features corresponding to directory A, semantic features of historical knowledge document e, and semantic features of historical knowledge document f. In addition, the content of historical knowledge document e and the content of historical knowledge document f are respectively candidate knowledge content of the next level corresponding to directory R. The second level is represented as level 2, which corresponds to directory A, and directory A is a subdirectory of the next level corresponding to directory R. Level 2 stores candidate knowledge content corresponding to directory A, including semantic features of historical knowledge document a under directory B, semantic features of historical knowledge document b, and semantic features of historical knowledge document c. In addition, the content vector of historical knowledge document a, the content vector of historical knowledge document b, and the content vector of historical knowledge document c are respectively candidate knowledge content of the next level corresponding to directory A.

[0055] S130: Match the dialogue input information with candidate information according to the hierarchical relationship to obtain target information corresponding to the dialogue input information.

[0056] In the disclosed embodiment, the dialogue input vector is matched with the candidate information in the knowledge vector library to determine the context information related to the dialogue input information, thereby assisting the large language model to generate a dialogue input response in combination with the context information related to the dialogue input information.

[0057] Since the candidate information in the knowledge vector library is stored hierarchically according to the directory structure, the dialogue input vector can be matched with the candidate information starting from the first level (ie, the root directory).

[0058] Exemplarily, matching the dialogue input information with candidate information according to the hierarchical relationship to obtain target information corresponding to the dialogue input information includes:

[0059] For the current level determined according to the hierarchical relationship, the dialogue input information is matched with the candidate information corresponding to the current level; and the target information corresponding to the dialogue input information is determined according to the matching result. The dialogue input information and the candidate information may be matched by vector matching. The current level may represent the level to which the candidate information being matched with the dialogue input vector belongs. For example, the dialogue input vector is matched with the candidate information starting from the first level, and the first level is taken as the current level. The dialogue input vector is matched with the candidate information included in the first level for similarity, and if the candidate information whose similarity with the dialogue input vector exceeds the set similarity threshold is matched, the candidate information whose similarity exceeds the set similarity threshold is taken as the target information corresponding to the dialogue input vector.

[0060] Further, if there is candidate information matching the dialogue input information at the current level, the candidate information matching the dialogue input information is used as the target information corresponding to the dialogue input information.

[0061] Optionally, if candidate information matching the dialogue input information exists at the current level, matching the dialogue input information with candidate information corresponding to the target information at a level below the current level;

[0062] If the current level does not have candidate information matching the dialogue input information, the dialogue input information is matched with content of historical information corresponding to a level below the current level.

[0063] If there is content matching the dialogue input information in the history information corresponding to the next level, the content matching the dialogue input information is used as the target information corresponding to the dialogue input information.

[0064] by Figure 3 Taking the provided knowledge vector library as an example, matching starts from directory R, ​​taking directory R as the current level, and matching the conversation input vector with the sub-directory features corresponding to directory R (i.e., the directory features of directory A), the semantic features of historical knowledge document e, and the semantic features of historical knowledge document f.

[0065] The directory features of directory A may be determined by combining the semantic features of historical knowledge document a, the semantic features of historical knowledge document b, and the semantic features of historical knowledge document c. For example, the combined text obtained by combining the semantic features of historical knowledge document a, the semantic features of historical knowledge document b, and the semantic features of historical knowledge document c is input into the large language model to obtain the directory features corresponding to directory A output by the large language model.

[0066] In some embodiments, if there are directory features and semantic features matching the dialogue input vector at the current level, and they are the directory features corresponding to directory A and the semantic features corresponding to historical knowledge document e, that is, the vector similarity between the directory features corresponding to directory A and the semantic features corresponding to historical knowledge document e and the dialogue input information exceeds a set similarity threshold, the directory features corresponding to directory A and the semantic features corresponding to historical knowledge document e are determined as the target information corresponding to the dialogue input vector at the current level.

[0067] Then, level 2 corresponding to directory A and historical knowledge document e is used as the new current level. The dialogue input vector is matched with the semantic features of historical knowledge document a, the semantic features of historical knowledge document b, and the semantic features of historical knowledge document c corresponding to directory A. The dialogue input vector is matched with the semantic features corresponding to historical knowledge document e.

[0068] If it is determined through matching that the similarity between the semantic features of historical knowledge document a and the dialogue input vector exceeds the set similarity threshold, the semantic features of historical knowledge document a are used as the first target information, and the level 3 corresponding to historical knowledge document a is used as the new current level. The content of historical knowledge document a is matched with the dialogue input vector, and the text content whose similarity with the dialogue input vector exceeds the set similarity threshold is obtained as the second target information.

[0069] Optionally, the importance of the first target information can be set higher than that of the second target information. The first target information can be organized according to the path and related content in the matching process. For example, if relevant content is found in target A: aaaa, then relevant content is found in historical knowledge document 1: cccaa. The second target information can be organized by listing numbers. For example, 1. There is relevant content in historical knowledge document: bbbbb; 2. There is relevant content in historical knowledge document f: ccbbbb.

[0070] In some other embodiments, if there is no candidate information matching the dialogue input vector at the current level, and there is historical information of the next level (e.g., historical knowledge documents e and f under directory R) at the current level, the dialogue input vector is vector matched with the content vector of historical knowledge document e and the content vector of historical knowledge document f respectively. If there is a content vector in historical knowledge document f whose similarity with the dialogue input vector exceeds a similarity threshold, the content vector matching the dialogue input vector is used as the second target information corresponding to the dialogue input vector. If there is no content vector in historical knowledge documents e and f whose similarity with the dialogue input vector exceeds a similarity threshold, the dialogue input vector is similarly matched with the content vectors of the historical knowledge documents in the knowledge vector library respectively to obtain the target information.

[0071] It should be noted that the matching in the embodiments of the present disclosure not only includes one-to-one correspondence of texts based on retrieval, traversal, etc., but also includes semantic features matched based on context information using a large language model.

[0072] S140: Generate dialogue input reply information according to the target information and the dialogue input information, and display the dialogue input reply information.

[0073] The dialogue input reply information may be an answer corresponding to the dialogue input information.

[0074] Exemplarily, a prompt word is generated according to the target information and the dialogue input information, and dialogue input reply information is generated according to the prompt word; and the dialogue input reply information and the target information are displayed.

[0075] Among them, the prompt words are used to limit the interaction logic of the large language model. For example, the prompt words are used to limit the content that the answer generation depends on, and the prompt words are used to specify the answer content when the answer cannot be answered.

[0076] For example, a prompt word is generated according to the target information and the dialogue input information according to the prompt word generation template, and the prompt word is input into the large language model, and the dialogue input information is understood by the large language model and dialogue input response information combined with the target information is generated. The dialogue input information and the dialogue input response information are displayed in the form of question and answer pairs.

[0077] Optionally, the target information may also be displayed as attachment information so that the user can learn more context information.

[0078] The technical solution of the disclosed embodiment matches the dialogue input vector with the candidate information according to the hierarchical relationship of the candidate information to obtain the target information corresponding to the dialogue input vector, and generates dialogue input reply information corresponding to the dialogue input information in combination with the target information. Since the candidate information is determined based on the semantic features of the historical information, the semantics of the historical information is expressed in a general way, the amount of matching data is reduced, and the retrieval efficiency is improved. Moreover, by matching the dialogue input vector with the candidate information layer by layer, missed matches and wrong matches can be avoided, thereby solving the problems of low retrieval efficiency, missed matches and wrong matches in the method of replying by triggering indexes with keywords.

[0079] Figure 4 This is a flow chart of another interactive information processing method provided by an embodiment of the present disclosure. Based on the above embodiment, the embodiment of the present disclosure additionally defines the steps of determining candidate information and the hierarchical relationship of the candidate information.

[0080] like Figure 4 As shown, the method includes:

[0081] S410: Obtain historical information and a directory structure corresponding to the historical information.

[0082] The directory structure represents the hierarchical structure in the knowledge base corresponding to the subject of the historical information, see Figure 2 . Historical knowledge documents a, b, c are on the same subject and can be placed in directory A. Historical knowledge documents e and f are on the same subject and can be placed in directory R, ​​and target A is a subdirectory of target R.

[0083] S420: Determine semantic features of the historical information corresponding to the directory, and determine candidate information corresponding to the directory according to the semantic features.

[0084] Exemplarily, for the historical information corresponding to the directory, the semantic features of the historical information are determined according to the content of the historical information. For example, historical information is obtained directory by directory according to the directory structure as the historical information corresponding to the directory. Document segmentation is performed on the historical information corresponding to the directory to obtain several sentences containing set words. Each sentence is preprocessed, and the preprocessed sentences are formatted. Then, the sentence vector corresponding to the formatted sentence is determined, and the sentence vector is input into the large language model, and the semantic features of the sentence vector are determined by the large language model according to the content represented by the sentence vector. The semantic features of the corresponding historical information are determined according to the semantic features of the sentence vector.

[0085] If the target does not contain a subdirectory, the semantic features of the historical information corresponding to the target are used as the directory features of the directory itself.

[0086] If the target contains a subdirectory, the semantic features of the historical information corresponding to the target are merged to obtain a merged text, the merged text is input into the large language model, and the subdirectory features of the subdirectory are determined according to the merged text by the large language model.

[0087] Acquire a subdirectory feature corresponding to the directory, and determine a directory feature corresponding to the directory according to the subdirectory feature corresponding to the directory and the semantic feature of the historical information, wherein the subdirectory feature is determined based on the semantic feature of the historical information included in the subdirectory.

[0088] Determine candidate information corresponding to the directory according to the semantic features, the directory features and the content of the historical information.

[0089] S430: Determine the hierarchical relationship of the candidate information according to the directory structure.

[0090] For example, for the historical knowledge document at the bottom layer, the content vector of the historical knowledge document is used as the corresponding candidate information. For a directory that does not contain subdirectories, the semantic features of all historical knowledge documents under the directory are used as the corresponding candidate information. For a directory that contains subdirectories, the subdirectory features corresponding to the directory and the semantic features of all historical knowledge documents under the directory are used as the corresponding candidate information. Then, the hierarchical relationship of the candidate information corresponding to each directory is determined according to the directory structure, see Figure 3 . Construct a knowledge vector library according to the hierarchical relationship of candidate information.

[0091] The technical solution of the disclosed embodiment determines the semantic vectors of historical information in the knowledge base and stores the semantic vectors in layers according to the directory structure in the knowledge base, thereby reducing the amount of data required to match the dialogue input vector. Hierarchical retrieval can also improve missed matches and false matches, thereby improving retrieval efficiency.

[0092] Figure 5 A flowchart of another interactive information processing method provided by the embodiment of the present disclosure. Based on the above embodiment, the embodiment of the present disclosure defines the process of constructing a knowledge vector library and the process of generating dialogue input reply information. Figure 5 As shown, the process of constructing a knowledge vector library includes obtaining a historical knowledge document 501, formatting the historical knowledge document 501 to obtain a formatted document 502. The formatted document 502 is semantically summarized according to different levels to obtain a semantic feature 503 of the historical knowledge document. Candidate knowledge content is determined according to the semantic feature 503, and the candidate knowledge content is stored in a vector database according to the hierarchical relationship to obtain a knowledge vector library 504. The historical knowledge document may include documents and question and answer pairs.

[0093] The process of generating dialogue input reply information includes: obtaining dialogue input information to be replied 505. Performing semantic segmentation and vectorization processing on dialogue input information 505 to obtain dialogue input vector 506. Matching target candidate content 507 from the knowledge vector library according to dialogue input vector 506. Combining dialogue input information 505 and target candidate content 507 to form prompt word 508. Inputting prompt word 508 into large language model 509, and obtaining dialogue input reply information 510 output by large language model 509.

[0094] Figure 6 This is a schematic diagram of the structure of an interactive information processing device provided in an embodiment of the present disclosure. The device can be implemented in the form of software and / or hardware. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, a PC or a server.

[0095] like Figure 6 As shown, the device includes: an information acquisition module 610, a level acquisition module 620, a content matching module 630 and a reply information generation module 640.

[0096] The information acquisition module 610 is used to acquire the dialogue input information to be replied;

[0097] A hierarchical acquisition module 620, configured to acquire candidate information and hierarchical relationships of the candidate information, wherein the candidate information is determined based on semantic features of the historical information, and the hierarchical relationships are determined based on a hierarchical structure corresponding to a topic of the historical information;

[0098] A content matching module 630, configured to match the dialogue input information with candidate information according to the hierarchical relationship to obtain target information corresponding to the dialogue input information;

[0099] The reply information generating module 640 is used to generate dialogue input reply information according to the target information and the dialogue input information, and display the dialogue input reply information.

[0100] Optionally, it also includes a level determination module;

[0101] The hierarchical determination module is used to obtain historical information and a directory structure corresponding to the historical information, wherein the directory structure represents a hierarchical structure corresponding to the subject of the historical information; determine semantic features of the historical information corresponding to the directory, and determine candidate information corresponding to the directory based on the semantic features; and determine the hierarchical relationship of the candidate information based on the directory structure.

[0102] Optionally, the determining the semantic features of the historical information corresponding to the directory, and determining the candidate information corresponding to the directory according to the semantic features, includes:

[0103] For the historical information corresponding to the directory, determining the semantic features of the historical information according to the content of the historical information;

[0104] Acquire a subdirectory feature corresponding to the directory, and determine a directory feature corresponding to the directory according to the subdirectory feature corresponding to the directory and the semantic feature of the historical information, wherein the subdirectory feature is determined based on the semantic feature of the historical information included in the subdirectory;

[0105] Determine candidate information corresponding to the directory according to the semantic features, the directory features and the content of the historical information.

[0106] Optionally, the content matching module 630 includes:

[0107] a matching unit, configured to match the dialogue input vector dialogue input information with candidate information corresponding to the current level determined according to the hierarchical relationship;

[0108] The content determination unit is used to determine the target information corresponding to the dialogue input information of the dialogue input vector according to the matching result.

[0109] Furthermore, the content determination unit is specifically used for:

[0110] If there is candidate information matching the dialogue input information of the dialogue input vector at the current level, the candidate information matching the dialogue input information of the dialogue input vector is used as the target information corresponding to the dialogue input information of the dialogue input vector.

[0111] Furthermore, the matching unit is specifically used for:

[0112] If there is candidate information matching the dialogue input information at the current level, matching the dialogue input information with candidate information corresponding to the target information at a level below the current level;

[0113] If there is no candidate information matching the dialogue input vector at the current level, the dialogue input vector dialogue input information is matched with the content of the historical information corresponding to the next level of the current level.

[0114] Furthermore, the content determination unit is specifically used for:

[0115] If there is content matching the dialogue input vector dialogue input information in the history information corresponding to the next level, the content matching the dialogue input vector dialogue input information is used as the target information corresponding to the dialogue input vector dialogue input information.

[0116] Optionally, the reply information generating module 640 is specifically used for:

[0117] Generate prompt words according to the target information and the dialogue input information, and generate dialogue input reply information according to the prompt words;

[0118] The dialogue input reply information and target information are displayed.

[0119] Optionally, the historical information includes historical knowledge documents, the candidate information includes candidate knowledge content, and the hierarchical structure includes a structure of a directory corresponding to a subject of the historical knowledge document.

[0120] The interactive information processing device provided in the embodiments of the present disclosure can execute the interactive information processing method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0121] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

[0122] Figure 7 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Figure 7 , which shows an electronic device (eg, Figure 7The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 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.

[0123] like Figure 7 As shown, the electronic device 700 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage device 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 are also stored. The processing device 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An edit / output (I / O) interface 705 is also connected to the bus 704.

[0124] Typically, the following devices may be connected to the I / O interface 705: an input device 706 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 707 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 708 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 709. The communication device 709 may allow the electronic device 700 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 The electronic device 700 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0125] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart 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 non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 709, or installed from a storage device 708, or installed from a ROM 702. When the computer program is executed by the processing device 701, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0126] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0127] The electronic device provided by the embodiment of the present disclosure and the interactive information processing method provided by the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0128] The embodiment of the present disclosure provides a computer storage medium on which a computer program is stored. When the program is executed by a processor, the interactive information processing method provided by the above embodiment is implemented.

[0129] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. 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, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0130] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0131] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0132] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

[0133] Get the conversation input information to be replied;

[0134] Acquire candidate information and a hierarchical relationship of the candidate information, wherein the candidate information is determined based on semantic features of the historical information, and the hierarchical relationship is determined based on a hierarchical structure corresponding to a topic of the historical information;

[0135] Matching the dialogue input information with candidate information according to the hierarchical relationship to obtain target information corresponding to the dialogue input information;

[0136] Generate dialogue input reply information according to the target information and the dialogue input information, and display the dialogue input reply information.

[0137] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0138] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square 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 square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart 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.

[0139] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0140] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0141] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0142] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0143] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0144] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A method for processing interactive information, characterized in that: include: Get the conversation input information to be replied; Acquire candidate information and a hierarchical relationship of the candidate information, wherein the candidate information is determined based on semantic features of the historical information, and the hierarchical relationship is determined based on a hierarchical structure corresponding to a topic of the historical information; Matching the dialogue input information with candidate information according to the hierarchical relationship to obtain target information corresponding to the dialogue input information; Generate dialogue input reply information according to the target information and the dialogue input information, and display the dialogue input reply information.

2. The method according to claim 1, characterized in that The method also includes determining candidate information and the hierarchical relationship of the candidate information by the following steps: Acquire historical information and a directory structure corresponding to the historical information, wherein the directory structure represents a hierarchical structure corresponding to a subject of the historical information; Determine semantic features of historical information corresponding to the directory, and determine candidate information corresponding to the directory according to the semantic features; The hierarchical relationship of the candidate information is determined according to the directory structure.

3. The method according to claim 2, characterized in that The determining of the semantic features of the historical information corresponding to the directory, and determining the candidate information corresponding to the directory according to the semantic features, includes: For the historical information corresponding to the directory, determining the semantic features of the historical information according to the content of the historical information; Acquire a subdirectory feature corresponding to the directory, and determine a directory feature corresponding to the directory according to the subdirectory feature corresponding to the directory and the semantic feature of the historical information, wherein the subdirectory feature is determined based on the semantic feature of the historical information included in the subdirectory; Determine candidate information corresponding to the directory according to the semantic features, the directory features and the content of the historical information.

4. The method according to claim 1, characterized in that: The step of matching the dialogue input information with candidate information according to the hierarchical relationship to obtain target information corresponding to the dialogue input information includes: For a current level determined according to the hierarchical relationship, matching the dialogue input information with candidate information corresponding to the current level; The target information corresponding to the dialogue input information is determined according to the matching result.

5. The method according to claim 4, characterized in that The determining, according to the matching result, the target information corresponding to the dialogue input information comprises: If candidate information matching the dialogue input information exists at the current level, the candidate information matching the dialogue input information is used as target information corresponding to the dialogue input information.

6. The method according to claim 5, characterized in that The matching the dialogue input information with the candidate information corresponding to the current level includes: If candidate information matching the dialogue input information exists at the current level, matching the dialogue input information with candidate information corresponding to the target information at a level below the current level; If the current level does not have candidate information matching the dialogue input information, the dialogue input information is matched with content of historical information corresponding to a level below the current level.

7. The method according to claim 6, characterized in that The determining, according to the matching result, the target information corresponding to the dialogue input information comprises: If there is content matching the dialogue input information in the history information corresponding to the next level, the content matching the dialogue input information is used as the target information corresponding to the dialogue input information.

8. The method according to claim 1, characterized in that The step of generating dialogue input reply information according to the target information and the dialogue input information, and displaying the dialogue input reply information includes: Generate prompt words according to the target information and the dialogue input information, and generate dialogue input reply information according to the prompt words; The dialogue input reply information and target information are displayed.

9. The method according to any one of claims 1 to 8, characterized in that The historical information includes historical knowledge documents, the candidate information includes candidate knowledge content, and the hierarchical structure includes a structure of a directory corresponding to a subject of the historical knowledge document.

10. An interactive information processing device, characterized in that: include: An information acquisition module, used to acquire the dialogue input information to be replied; A hierarchical acquisition module, used to acquire candidate information and hierarchical relationships of the candidate information, wherein the candidate information is determined based on semantic features of historical information, and the hierarchical relationships are determined based on hierarchical structures corresponding to the topics of the historical information; a content matching module, configured to match the dialogue input information with candidate information according to the hierarchical relationship to obtain target information corresponding to the dialogue input information; The reply information generating module is used to generate dialogue input reply information according to the target information and the dialogue input information, and to display the dialogue input reply information.

11. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the interactive information processing method as described in any one of claims 1 to 9.

12. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the interactive information processing method as described in any one of claims 1 to 9 when executed by a computer processor.

Images