Method, apparatus, device and storage medium for information retrieval

Abstract

According to embodiments of the present disclosure, methods, apparatuses, devices and storage media for information retrieval are provided. In one method, input content indicative of a retrieval demand is received; and a result page is presented, the result page showing a set of retrieval elements determined based on the input content and a set of retrieval results for the retrieval demand, wherein the set of retrieval results comprises at least one retrieval result matching at least part of the set of retrieval elements. Thus, embodiments of the present disclosure can intuitively present a factor disassembly of a natural language search to a user, so as to facilitate the user to understand a response process of the natural language search request.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and particularly to methods, apparatuses, devices, and computer-readable storage media for information retrieval. Background Technology

[0002] With the rapid development of internet technology, the internet has become an important platform for people to access and share content. Users can access the internet through terminal devices to enjoy various internet services. Internet platforms also provide users with the ability to retrieve various types of information. How to improve the efficiency of such information retrieval has become a focus of attention. Summary of the Invention

[0003] In a first aspect of this disclosure, an information retrieval method is provided. The method includes: receiving input content indicating a retrieval request; and presenting a results page displaying a set of search elements determined based on the input content and a set of search results for the retrieval request, wherein the set of search results includes at least one search result that matches at least some of the search elements in the set of search elements.

[0004] In a second aspect of this disclosure, an apparatus for information retrieval is provided. The apparatus includes: a text receiving module configured to receive input content indicating a retrieval request; and a page rendering module configured to render a results page displaying a set of search elements determined based on the input content and a set of search results for the retrieval request, wherein the set of search results includes at least one search result that matches at least some of the search elements in the set of search elements.

[0005] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect.

[0006] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program that can be executed by a processor to implement the method of the first aspect.

[0007] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0008] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0009] Figure 1 A schematic diagram of an example environment in which embodiments of the present disclosure can be implemented is shown;

[0010] Figure 2 A flowchart of a method for information retrieval according to some embodiments of the present disclosure is shown;

[0011] Figures 3A to 3D Example interfaces according to some embodiments of this disclosure are shown;

[0012] Figure 4 Block diagrams of an apparatus for information retrieval according to some embodiments of the present disclosure are shown; and

[0013] Figure 5 A block diagram of an apparatus capable of implementing several embodiments of the present disclosure is shown. Detailed Implementation

[0014] It is understood that before using the technical solutions disclosed in the embodiments of this disclosure, relevant users should be informed of the type, scope of use, and usage scenarios of the information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and their authorization should be obtained. Relevant users may include any type of rights holder, such as individuals, enterprises, or groups.

[0015] For example, upon receiving a user's active request, a prompt message is sent to the relevant user to explicitly inform them that the requested operation will require access to and use of their information. This allows the relevant user to autonomously choose, based on the prompt message, whether to provide information to the software or hardware such as the electronic device, application program, server, or storage medium performing the operations of this disclosed technical solution.

[0016] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, which can display the prompt message in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0017] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0018] It is understood that when adopting this technical solution, the data involved (including but not limited to the data itself, the acquisition, use, storage and transmission of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0019] The term "in response to" as used herein refers to a state in which a corresponding event occurs or a condition is satisfied. It will be understood that the timing of subsequent actions performed in response to such event or condition is not necessarily strongly correlated with the time when the event occurs or the condition is met. For example, in some cases, subsequent actions may be performed immediately upon the occurrence of the event or the fulfillment of the condition; while in others, they may be performed some time after the occurrence of the event or the fulfillment of the condition.

[0020] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0021] It should be noted that the headings of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and embodiments of any type may be included under any section / subsection. Furthermore, embodiments described in any section / subsection may be combined in any way with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0022] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0023] As used herein, the term "model" refers to a system that learns the relationship between inputs and outputs from training data, enabling it to generate corresponding outputs for a given input after training. The generation and use of models can be based on technologies permitted by laws and regulations, such as machine learning, referred to as available technologies. For example, deep learning is a machine learning algorithm that uses multiple layers of processing units to process inputs and provide corresponding outputs. In this document, "model" may also be referred to as a "machine learning model," a "machine learning network," or simply a "network," and these terms are used interchangeably. A model can also include different types of processing units or networks.

[0024] As briefly mentioned earlier, people can already use various types of information retrieval tools to improve the efficiency of information retrieval. However, traditional information retrieval tools are usually based on keyword filtering and matching to find matching search results for users, and such information retrieval tools are difficult to support users' needs for natural language search.

[0025] Embodiments of this disclosure provide a scheme for information retrieval. Specifically, it can receive input content indicating a retrieval request and present a results page. The results page can display a set of search elements determined based on the input content and a set of search results for the retrieval request, wherein the set of search results includes at least one search result that matches at least some of the search elements in the set of search elements.

[0026] Therefore, the embodiments of this disclosure can intuitively present the element breakdown of natural language search to users, so as to facilitate users' understanding of the response process of natural language search requests.

[0027] Example embodiments of this disclosure are described below with reference to the accompanying drawings.

[0028] Example Environment

[0029] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. For example... Figure 1 As shown, in environment 100, terminal device 110 can be used to provide digital assistant 102 to target object 150. Such target object may include users or organizations, where the organization may be a company, group, department, etc.

[0030] For example, such a digital assistant 102 could also be called a digital assistant or a digital robot. It should be understood that, although in Figure 1The digital assistant 102 is shown to be included in the terminal device 110, but some of the processing capabilities of the digital assistant 102 may also be at least partially based on the server 120. For example, the front-end portion of the digital assistant 102 (e.g., the presentation portion) may be included in the terminal device 110, but the back-end portion of the digital assistant 102 (e.g., the information retrieval portion) may be included in the server 120.

[0031] In some examples, digital assistant 102 may be a digital assistant that assists target object 150 in its work, or it may be any other suitable physical form. Digital assistant 102 may also operate independently or be integrated into a specific application.

[0032] In some embodiments, the digital assistant 102 can be activated by an appropriate means (e.g., a shortcut key, a button, or voice), such as being invoked or woken up. If the digital assistant 102 is active, the terminal device 110 can present an interface 104 associated with the digital assistant 102. The interface 104 can be a conversational user interface (also referred to as a conversational interface or conversational window) or any other suitable interface form. As will be described in detail below, such an interface 104 may also include interface elements for information interaction, such as message input boxes, message lists, message bubbles, etc. Through the interface 104, the digital assistant 102 can obtain information input by the target object 150.

[0033] Such input information can include any appropriate type of message, such as text messages, image messages, voice messages, form messages, link messages, and other appropriate types of messages.

[0034] Furthermore, server 120 may allow target object 150 to interact with digital assistant 102 to obtain information generated by digital assistant 102. Alternatively, as will be detailed below, with authorization from target object 150, the information generated by digital assistant 102 may also be based on historical interactions between target object 150 and at least one business component 115.

[0035] Such business components may include components capable of providing appropriate types of business services to the target object 150, examples of which may include, but are not limited to, office-related components, tool-related components, etc. In some embodiments, such business components may be installed on the same terminal device 110. Alternatively or additionally, such business components may also be installed on other terminal devices or provided as cloud services.

[0036] In some embodiments, such a business component 115 may include multiple office components within an office suite. An office suite can be a set of office components developed to improve office efficiency, such as office components for creating and editing documents, office components for creating and editing tables, office components for charting, and so on.

[0037] In some embodiments, the multiple office components include a number of the following: chat components, document components, audio and video conferencing components, email components, calendar components, schedule components, task components, Objectives and Key Results (OKR) components, and / or appropriate office components that are currently available or may be developed in the future.

[0038] In some embodiments, digital assistant 102 may be a separate application from business component 115. Alternatively, digital assistant 102 may also be a function or component appropriately integrated into business component 115.

[0039] In some embodiments, historical interaction information 130 may be maintained as needed on appropriate electronic devices, such as terminal device 110, server 120, and / or other appropriate electronic devices. Historical interaction information 130 may include, for example, interaction information stored on terminal device 110 or interaction information uploaded to server 120.

[0040] As will be detailed below, historical interaction information 130 can be provided to process information retrieval requests from target object 150.

[0041] In some embodiments, terminal device 110 communicates with server 120 to provide services to digital assistant 102. Terminal device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, terminal device 110 can also support any type of interface for target object 150 (such as "wearable" circuitry). Server 120 can be various types of computing systems / servers capable of providing computing power, including but not limited to mainframes, edge computing nodes, computing devices in cloud environments, etc.

[0042] Despite Figure 1Only one server 120 is shown, but environment 100 may include multiple servers 120. For example, historical interaction information 130 may be stored locally or on a second server 120 as needed and with relevant user authorization. It should be understood that this is merely an exemplary description and does not imply any limitation on the scope of this disclosure.

[0043] It should be understood that the structure and function of environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0044] Example process

[0045] Figure 2 A flowchart of a process 200 for information retrieval according to some embodiments of the present disclosure is shown. Process 200 may be implemented by suitable electronic devices or a combination of electronic devices (e.g., Figure 1 (This refers to server 120, terminal device 110, or a combination of server 120 and terminal device 110). For ease of description, terminal device 110 is used as an example below, and references are also provided. Figure 1 To describe process 200.

[0046] As shown in the figure, in box 210, terminal device 110 receives input content indicating retrieval needs.

[0047] In some embodiments, the terminal device 110 may, for example, receive user input in a search control to obtain input content indicating a search request. Figure 3A As shown, terminal device 110 can provide users with an interface 300A as shown in the figure.

[0048] Interface 300A may include a search control 305 for receiving input. Terminal device 110 may, for example, receive input content 310 entered by the user using the search control 305. Exemplarily, the user may directly type the input content 310, such as text content, into the search control 305. Alternatively, the user may input voice content, which will then be transcribed into text content by terminal device 110.

[0049] In some embodiments, the terminal device 110 may also receive input indicating a retrieval request through other suitable means, for example. As an example, see reference... Figure 1 As discussed, terminal device 110 may provide, for example, an interactive interface between target object (e.g., user) 150 and digital assistant 102, such an interface may display, for example, a conversation between target object 150 and digital assistant 102. Furthermore, terminal device 110 may acquire input content entered by target object 150 into the conversation indicating retrieval needs.

[0050] For ease of description, the following will use a retrieval control as an example to describe the sample interface according to this disclosure. It should be understood that such features can also be used in scenarios such as information retrieval triggered in a session.

[0051] Continue to refer to Figure 2 In box 220, terminal device 110 presents a results page, which displays a set of search elements determined based on the input content and a set of search results for the search requirements, wherein the set of search results includes at least one search result that matches at least some of the search elements in the set of search elements.

[0052] In some embodiments, terminal device 110 may present the parsing results of input content 310 on a results page. Such parsing results may, for example, include a set of search elements determined based on input content 310. For example, terminal device 110 may present the parsing results of input content 310 before the search results are fully loaded to indicate that the search request is being processed.

[0053] For example, such as Figure 3B As shown, after receiving a search command triggered by the user, the terminal device 110 presents the interface 300B as shown in the figure. In the interface 300B, the terminal device 110 can present instruction information 315, which can describe a set of search elements determined based on the input content 310, such as search element 320-1, search element 320-2, search element 320-3, and search element 320-4 (referred to individually or collectively as search element 320).

[0054] The following will describe the specific process for determining search element 320.

[0055] In some embodiments, before presenting the retrieval element 320, the terminal device 110 may determine whether the input content 310 corresponds to a natural language search scenario. Specifically, the terminal device 110 may provide the input content 310 to the target model to determine whether the input content indicates a natural language search scenario. If it is determined that the input content 310 indicates a natural language search scenario, the terminal device 110 may further obtain the parsing result of the input content 310.

[0056] For example, such a target model can be implemented based on an appropriate machine learning model to determine the search scenario of the input content 310. For instance, if the input content 310 is a simple keyword expression, the terminal device 110 may not trigger the parsing of the input content 310. Conversely, if the input content 310 corresponds to a natural language search scenario, the terminal device 110 may trigger the parsing of one or more search elements 320 indicated in the input content 310.

[0057] In some embodiments, one or more retrieval elements 320 indicated in the input content 310 may be parsed by a suitable electronic device (including, but not limited to, terminal device 110, server 120, or a combination thereof).

[0058] In some embodiments, the electronic device may determine the first set of search elements indicated in the input content 310 based on a first search mode. Such a first search mode may, for example, include a search mode based on the historical interaction information 130 mentioned above.

[0059] The generation process of historical interaction information 130 will be briefly described below. In some embodiments, when the target object 150 interacts with the business component 115, the business component 115 can generate log records and send the log records to the recording module. Further, the recording module can generate corresponding record entries based on the received log records, as the corresponding historical interaction information 130. In some embodiments, such record entries may include knowledge elements to describe the business object corresponding to the historical interaction event.

[0060] In some embodiments, such business objects may include business objects generated by the target object 150 during its interaction with the business component 115, edited business objects, referenced business objects, shared business objects, etc. Taking a document component as an example, the historical interaction events may include the creation event of a specific document in the document component by the target object 150; correspondingly, the business object corresponding to the document creation event may include that specific document. As another example, taking an audio / video conferencing component as an example, the historical interaction events may include an audio / video conferencing event attended by the target object 150; correspondingly, the business object corresponding to that audio / video conferencing event may include the audio / video conferencing itself.

[0061] In some embodiments, the knowledge element may be a natural language description of the business object, designed to abstract and / or compress the content of the business object. For example, using a document object as an example of a business object, the knowledge element may be used to describe the document object's topic, completion status, audience, language, and expression style, etc. Using an audio / video conference as an example of a business object, the knowledge element may be used to describe the audio / video conference's topic, agenda, a summary of the conference content, etc.

[0062] It should be understood that different dimensions of information can be selected to generate knowledge elements that describe the business object, depending on the type of the business object. For example, taking a conversation as an example of a business object, knowledge elements could be used to describe the type of conversation (e.g., whether it is a one-on-one chat), an overview of the conversation content, etc.

[0063] Therefore, by maintaining knowledge elements in the record entries, embodiments of this disclosure can describe or characterize the business objects involved in the corresponding historical interaction events with a limited content length.

[0064] In some embodiments, record entries may also include a time element indicating when a historical interaction event occurred. For example, continuing with the example of document creation as a historical interaction event, such a time element could indicate the document's creation time.

[0065] In some other embodiments, the record entry may also include an action element that indicates the type of the historical interaction event. Continuing with the example of creating a document as a historical interaction event, such an action element could indicate, for example, that the type of the historical interaction event is "create document".

[0066] It should be understood that event types can be appropriately categorized according to the needs of the scenario. Taking a document as an example of a business object, its corresponding types may include: document production events (e.g., creation), document consumption events (e.g., browsing), document circulation events (e.g., sharing), and document management events (e.g., permission settings), etc.

[0067] In some embodiments, a record entry may further include a payload element for indexing a business object corresponding to a relevant historical interaction event. Taking a document as an example of a business object, the payload element may include, for example, a document number or document identifier for indexing the document.

[0068] Therefore, in some scenarios, after the target object 150 interacts with the business component 115, the recording module can generate corresponding record entries. Such record entries can be represented as {time element, action element, knowledge element, payload element} to describe the historical interaction event from multiple preset dimensions.

[0069] In some embodiments, in a first retrieval mode, the electronic device can parse the indicated action element or knowledge element from the input content 310. Such action elements can be used, for example, to match action elements included in the historical interaction information 130. Such knowledge elements can be used, for example, to match knowledge elements included in the historical interaction information 130.

[0070] by Figure 3B As an example, the electronic device may parse the action element corresponding to the input content 310 (e.g., action: share in a meeting) as a retrieval element in a first retrieval mode.

[0071] For another example, if input 310 is “documents on topic A”, the electronic device can, for example, determine that its corresponding knowledge element is “knowledge: topic A” and use it as a search element.

[0072] In some embodiments, the electronic device may use, for example, a suitable machine learning model to determine the corresponding knowledge elements or action elements from the input content 310. Such a machine learning model may be trained, for example, on a corresponding training dataset, which may include test retrieval text generated based on multiple knowledge elements and / or action elements included in historical interaction information, with their corresponding knowledge elements and / or action elements as labeled values. Thus, the trained machine learning model is able to extract the corresponding knowledge elements and / or action elements from the retrieval text.

[0073] In some embodiments, the first set of search elements corresponding to the first search mode may further include, for example, user elements associated with the business object to be searched. Figure 3B As an example, retrieval element 320-1 may indicate user information (e.g., user "XX") associated with the business object to be retrieved.

[0074] In some embodiments, the first set of search elements corresponding to the first search mode may further include, for example, a time element associated with the business object to be searched. Figure 3B As an example, retrieval element 320-2 can indicate time information (e.g., "last week") associated with the business object to be retrieved.

[0075] In some embodiments, the first set of search elements corresponding to the first search mode may further include, for example, the type element of the business object to be searched. Figure 3B As an example, retrieval element 320-3 can indicate the type information of the business object to be retrieved (e.g., "document").

[0076] In this way, embodiments of this disclosure can parse a first set of search elements corresponding to the first search mode from the input content for use in subsequent search processes. It should be understood that in some scenarios, the content of some search elements may be empty. For example, the user may not have indicated time information in the input content 310.

[0077] In some embodiments, the electronic device may determine a second set of search elements indicated in the input content 310 based on a second search mode. Such a second search mode may, for example, include performing information retrieval using a set of preset filters. Accordingly, the second set of search elements may correspond to the set of preset filters.

[0078] In some embodiments, such a filter may include a first filter associated with the result type. For example, the first filter may indicate that the search results should be of the document type.

[0079] In some embodiments, such a filter may include a second filter associated with a time range. For example, the second filter may indicate that the document was shared within the time range of "last week".

[0080] In some embodiments, such a filter may include a third filter associated with a user. For example, the third filter may indicate that the user who shared the document is "XX".

[0081] In some embodiments, such a filter may include a fourth filter associated with a session. For example, the fourth filter may indicate that a document was shared in a particular session.

[0082] In some embodiments, such a filter is associated with a fifth filter that includes keywords. For example, a fourth filter may indicate that the document to be searched may include specific keywords.

[0083] In this manner, embodiments of this disclosure can also utilize preset filters to perform the parsing of search elements. In some embodiments, the terminal device 110 can provide a set of search results tailored to the search requirements on the results page. For example, after the set of search results has been loaded, the terminal device 110 can display the set of search results.

[0084] like Figure 3C As shown, terminal device 110 may provide search results 325, 335, and 345 in interface 300C, for example. Accordingly, the indication information 315 in interface 300C may be updated accordingly to indicate that the search is complete.

[0085] As another example, terminal device 110 may also directly present interface 300C in response to a user's search request. For example, terminal device 110 can provide, for instance, an interface 300C. Figure 3C The results page shown displays the search results and indication information 315.

[0086] Furthermore, at least one of such search results 325, 335, and 345 may be determined, for example, based on a set of search elements 320 described by the indication information 315. Figure 3C As an example, search result 325 could be determined based on the set of search elements 320.

[0087] Specifically, for example, the server 120 or a suitable electronic device may determine the search results 325 that match the set of search elements 320 based on the set of search elements 320 and the historical interaction information 130 discussed above.

[0088] As an example, when the retrieval element 320-4 corresponding to the action element is parsed, the server 120 may, for example, compare the retrieval element 320-4 with the action elements of each historical interaction event maintained in the historical interaction information 130, and may, for example, determine one or more action elements that satisfy the retrieval element 320-4 based on vector matching.

[0089] Additionally, server 120 can perform filtering and other processing based on other search elements, and combine action elements to determine the final matching search results, for example, search result 325.

[0090] In some embodiments, at least one of search result 325, search result 335, and search result 345 may be determined, for example, from a set of candidate results. Server 120 may, for example, maintain index information associated with the set of candidate results. Such index information may, for example, correspond to the first set of search elements and / or the second set of search elements discussed above, enabling server 120 to filter matching search results based on the acquired search elements.

[0091] In some embodiments, such as Figure 3C As shown, the terminal device 110 can also associate each search result with corresponding descriptive information. In some embodiments, if the search result 325 includes a business object (e.g., document A) that matches an action element (e.g., corresponding to search element 320-4), and the business object is not determined based on knowledge elements, then the descriptive information 330 corresponding to the search result 325 may include a description of a first event associated with the business object (e.g., document A). As an example, such descriptive information 330 may be generated based on the portion of the action elements in the historical interaction information 130 that matches the action element (e.g., search element 320-4).

[0092] In another example, if a business object in a particular search result is identified based on a knowledge element (e.g., "Topic A"), and that particular search result is not based on any action element, then the descriptive information corresponding to that business object may include the portion of the business object's description that matches the knowledge element. As an example, such descriptive information could be generated based on the portion of the knowledge elements in the historical interaction information 130 that matches that knowledge element.

[0093] In another example, if a business object in a particular search result is determined based on both knowledge elements and action elements, the descriptive information corresponding to that business object may include a description of a second event associated with that business object. As an example, such descriptive information could be generated based on the portion of the action elements in the historical interaction information 130 that matches the action elements.

[0094] Therefore, based on this method, description information 330, description information 340 and description information 350 can be used to intuitively show the reasons why the corresponding search results 325, search results 335 and search results 345 are determined to match the input content 310.

[0095] In some embodiments, such as Figure 3C As shown, search result 345 may, for example, not match at least one search element. Accordingly, terminal device 110 may also associate search result 345 with matching information 355. Matching information 355 may indicate one or more elements in a set of search elements 320 that do not match search result 345. Additionally or alternatively, matching information 355 may also list one or more elements in the set of search elements 320 that match search result 345.

[0096] In some embodiments, terminal device 110 can also sort multiple search results. Continuing with the first search mode as an example, if the set of search results includes a first search result and a second search result (e.g., search result 325 and search result 335) determined based on action elements (e.g., search elements 320-4), then terminal device 110 can sort search result 325 and search result 335, for example, based on the time of the events corresponding to search result 325 and search result 335.

[0097] For example, if the event indicated in the description information 330 of search result 325 is later than the event indicated in the description information 340 of search result 335, then terminal device 110 may, for example, prioritize displaying search result 325.

[0098] In some embodiments, if the set of search results includes at least a third search result and a fourth search result determined based on knowledge elements, the terminal device 110 may also sort the third search result and the fourth search result based on the matching degree between the third search result and the fourth search result and the knowledge elements.

[0099] Continuing with the example of "Topic A" as a knowledge element, if the document corresponding to the third search result matches "Topic A" more closely than the document corresponding to the fourth search result, then the terminal device 110 may, for example, prioritize displaying the third search result.

[0100] In some embodiments, for the second retrieval mode based on a preset filter, the terminal device 110 may obtain and present the corresponding retrieval results in a similar manner, which will not be elaborated further in this disclosure.

[0101] In some embodiments, the terminal device 110 may also determine multiple search results to be provided based on a first search mode and a second search mode simultaneously. In some examples, if the most matching first search result is determined based on the first search mode, the indication information 315 may be used to describe a first set of search elements corresponding to the first search mode. Conversely, if the most matching first search result is determined based on the second search mode, the indication information 315 may be used to describe a second set of search elements corresponding to the second search mode.

[0102] It should be understood that, although Figures 3A to 3C It describes the process of presenting search elements and search results in conjunction with a specific search page, but such a process also applies to searches triggered in conversations with digital assistants, as described above.

[0103] In some embodiments, unlike interface 300C, terminal device 110 may also utilize, for example, such as Figure 3D The interface shown is 300D, which provides search results.

[0104] like Figure 3D As shown, terminal device 110 may provide, for example, a feature management component 360. Similar to instruction information 315, feature management component 360 may also present one or more search features determined based on input content, such as search feature 365-1, search feature 365-2, and search feature 365-3.

[0105] In some embodiments, the terminal device 110 may also provide a feature addition entry 370 in the feature management component 360 for adding one or more additional search features. For example, if a user triggers the feature addition entry 370, the terminal device 110 may obtain one or more additional search features through the feature management component 360. As an example, the terminal device 110 may provide a feature input entry in the feature management component 360 for inputting "Topic A" as an additional search feature.

[0106] Based on this approach, the embodiments of this disclosure can further support users in refining the search text, thereby improving the efficiency of information retrieval.

[0107] In some embodiments, when a user triggers the feature addition entry 370, the terminal device 110 may, for example, present a conversation window with the digital assistant 102, which may be integrated into the feature management component 360. The user can enter one or more additional search features through the conversation window with the digital assistant.

[0108] For example, a digital assistant can proactively ask, "Could you describe the topic of this document?" Correspondingly, the user can enter "Topic A" as a new search element. Based on this approach, embodiments of this disclosure can further support users in refining their natural language search needs through dialogue, thereby improving the efficiency of information retrieval.

[0109] Example devices and equipment

[0110] Figure 4 A schematic structural block diagram of an apparatus 400 for information retrieval according to certain embodiments of the present disclosure is shown. The apparatus 400 may be implemented as or included in... Figure 1 The various modules / components in the device 400 can be implemented by hardware, software, firmware, or any combination thereof.

[0111] As shown in the figure, the device 400 includes a text receiving module 410 configured to receive input content indicating a search requirement; and a page presentation module 420 configured to present a results page, the results page displaying a set of search elements determined based on the input content and a set of search results for the search requirement, wherein the set of search results includes at least one search result that matches at least some of the search elements in the set of search elements.

[0112] In some embodiments, the page rendering module 420 is further configured to: present the parsing results of the input content on the results page, the parsing results including the set of search elements determined based on the input content; and provide the set of search results for the search requirements on the results page.

[0113] In some embodiments, the apparatus 400 further includes a determination module configured to: provide input content to the target model to determine whether the input content indicates a natural language search scenario; and in response to determining that the input content indicates a natural language search scenario, obtain the parsing result of the input content.

[0114] In some embodiments, the text receiving module 410 is further configured to: receive input content received by the user in the retrieval control; or receive input content entered by the user into the digital assistant during a session between the user and the digital assistant.

[0115] In some embodiments, a set of search elements includes a first set of search elements corresponding to a first search mode. The first set of search elements includes at least: an action element for describing an event associated with the business object to be searched; and / or a knowledge element for describing the content of the business object.

[0116] In some embodiments, the first set of retrieval elements further includes at least one of the following: user elements associated with the business object, time elements associated with the business object, and type elements of the business object.

[0117] In some embodiments, at least one search result is determined from a set of candidate results, and the set of candidate results is associated with a set of index information corresponding to the first set of search elements.

[0118] In some embodiments, the apparatus 400 further includes an information description module configured to: in response to at least one search result including a first business object matching an action element, present first description information of the first business object, the first description information including a description of a first event associated with the first business object, the first event matching an action element; in response to at least one search result including a second business object matching a knowledge element, present second description information of the second business object, the second description information including a portion of the description content of the second business object matching a knowledge element; or in response to at least one search result including a third business object matching both an action element and a knowledge element, present third description information of the third business object, the third description information including a description of a second event associated with the third business object, the second event matching an action element.

[0119] In some embodiments, the apparatus 400 further includes a sorting module configured to: in response to a set of search results including at least a first search result and a second search result determined based on action elements, sort the first search result and the second search result based on the time of the events corresponding to the first search result and the second search result; or in response to a set of search results including at least a third search result and a fourth search result determined based on knowledge elements, sort the third search result and the fourth search result based on the matching degree between the third search result and the fourth search result and the knowledge elements.

[0120] In some embodiments, a set of search elements includes a second set of search elements corresponding to a second search mode, wherein the second set of search elements corresponds to a set of preset filters used for retrieval.

[0121] In some embodiments, a set of preset filters includes at least one of the following: a first filter associated with the result type; a second filter associated with the time range; a third filter associated with the user; a fourth filter associated with the session; and a fifth filter associated with the keyword.

[0122] In some embodiments, the apparatus 400 further includes an element addition module configured to: acquire at least one additional search element based on the selection of the element addition entry to update a set of search elements; and provide updated search results determined based on the set of search elements.

[0123] In some embodiments, the feature addition module is further configured to: present a conversation window with the digital assistant based on the selection of the feature addition entry; and obtain at least one additional search feature based on the conversation window.

[0124] In some embodiments, the apparatus 400 further includes an element matching module configured to: present matching information associated with at least one search result, the matching information indicating: a first element in a set of search elements that matches at least one search result, and / or a second element in a set of search elements that does not match at least one search result.

[0125] Figure 5 A block diagram is shown illustrating an electronic device 500 in which one or more embodiments of the present disclosure may be implemented. It should be understood that... Figure 5 The electronic device 500 shown is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. Figure 5 The electronic device 500 shown can be used to achieve Figure 1 The server 120, the terminal device 110, or a combination of the server 120 and the terminal device 110.

[0126] like Figure 5 As shown, electronic device 500 is in the form of a general-purpose electronic device. Components of electronic device 500 may include, but are not limited to, one or more processors or processing units 510, memory 520, storage device 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. Processing unit 510 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 520. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 500.

[0127] Electronic device 500 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 520 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 530 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 500.

[0128] Electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 5 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 520 may include computer program product 525 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0129] Communication unit 540 enables communication with other electronic devices via a communication medium. Additionally, the functionality of components of electronic device 500 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, electronic device 500 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0130] Input device 550 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 560 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 500 can also communicate with one or more external devices (not shown) via communication unit 540 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 500, or with any device that enables electronic device 500 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0131] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0132] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0133] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0134] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0135] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0136] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. An information retrieval method, comprising: Receive input content indicating a retrieval request, wherein the input content is entered by the target object; as well as In response to the search scenario indicated by the input content, a natural language search scenario is displayed on the results page. This includes a set of search elements determined based on the input content and a set of search results tailored to the search requirements. The set of search results includes at least one search result that matches at least some of the search elements in the set. The set of search results is determined based on historical interaction information generated from logs of interactions between the target object and business components. The set of search elements includes at least: action elements describing events associated with the business object to be searched; and / or knowledge elements describing the content of the business object. The method further includes: associating the set of search results with corresponding descriptive information, wherein the descriptive information is used to show the reason why the corresponding search result is determined to match the input content.

2. The method according to claim 1, wherein displaying the set of search elements determined based on the input content and the set of search results for the search requirement on the results page includes: The results page displays the parsing results of the input content, including the set of search elements determined based on the input content; as well as The results page provides the set of search results for the stated search requirements.

3. The method according to claim 2, further comprising: The input content is provided to the target model to determine whether the input content indicates a natural language search scenario; as well as In response to determining that the input content indicates a natural language search scenario, the parsing result of the input content is obtained.

4. The method of claim 1, wherein receiving input indicating a search request comprises: Receive the input content received by the user in the search control; or During a conversation between a user and a digital assistant, the user inputs the information into the digital assistant.

5. The method of claim 1, wherein the set of search elements further comprises at least one of the following: User elements associated with the business object, The time element associated with the business object; The type element of the business object.

6. The method of claim 5, wherein the at least one search result is determined from a set of candidate results, and the set of candidate results is associated with a set of index information corresponding to the set of search elements.

7. The method according to claim 1, further comprising: In response to the at least one search result including a first business object that matches the action element, first description information of the first business object is presented, the first description information including a description of a first event associated with the first business object, the first event matching the action element; In response to the fact that the at least one search result includes a second business object that matches the knowledge element, second description information of the second business object is presented, the second description information including the part of the description content of the second business object that matches the knowledge element; or In response to the at least one search result including a third business object that matches the action element and the knowledge element, third description information of the third business object is presented, the third description information including a description of a second event associated with the third business object, the second event matching the action element.

8. The method according to claim 1, further comprising: In response to the set of search results including at least a first search result and a second search result determined based on the action element, the first search result and the second search result are sorted based on the time of the events corresponding to the first search result and the second search result; or In response to the set of search results including at least a third search result and a fourth search result determined based on the knowledge elements, the third search result and the fourth search result are sorted based on the matching degree between the third search result and the fourth search result and the knowledge elements.

9. The method according to claim 1, further comprising: Based on the selection of the entry point for adding elements, at least one additional search element is obtained to update the set of search elements; as well as Provide updated search results based on the set of search elements.

10. The method of claim 9, wherein obtaining at least one additional search element comprises: Based on the selection of the entry point for the aforementioned element, a conversation window with the digital assistant is presented; as well as Based on the session window, obtain the at least one additional search element.

11. The method according to claim 1, further comprising: Matching information is presented in association with the at least one search result, the matching information being used to indicate: a first element in the set of search elements that matches the at least one search result, and / or a second element in the set of search elements that does not match the at least one search result.

12. An apparatus for information retrieval, comprising: The text receiving module is configured to receive input content indicating a retrieval request, the input content being entered by the target object; The page presentation module is configured to respond to a natural language search scenario indicated by the input content, and display a set of search elements determined based on the input content and a set of search results for the search requirement on the results page. The set of search results includes at least one search result that matches at least some of the search elements in the set of search elements. The set of search results is determined based on historical interaction information, which is generated based on log records of the interaction between the target object and the business component. The set of search elements includes at least one action element, which describes an event associated with the business object to be searched. and / or knowledge elements, used to describe the content of the business object, The device further includes an information presentation module, configured to: associate with the set of search results and present corresponding descriptive information, the descriptive information being used to show the reason why the corresponding search result was determined to match the input content.

13. An electronic device, comprising: At least one processing unit; as well as At least one memory, coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, which, when executed by the at least one processing unit, cause the electronic device to perform the method according to any one of claims 1 to 11.

14. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 11.

Images