Method, apparatus, device, medium and program product for article retrieval

Abstract

According to an embodiment of the present disclosure, a method, apparatus, device, medium and program product for article retrieval are provided. The method includes: obtaining retrieval indication information indicating article retrieval requirements; based on the retrieval indication information and the prompt articles associated with the retrieval indication information, using a first machine learning model, obtaining at least one type of article retrieval information for the retrieval indication information; and based on the at least one type of article retrieval information, obtaining at least one target article as at least a part of the target article set. Through this method, the accuracy and comprehensiveness of article retrieval can be improved.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, devices, apparatuses, media, and program products for article retrieval. Background Art

[0002] With the development of information technology, various terminal devices can provide various services to people in work and life. Applications that provide services can be deployed in terminal devices. Terminal devices present corresponding content and interact with users through the user interface of the application to meet various needs of users. In some cases, terminal devices can use digital assistants to communicate with users, thereby providing search results for users based on their article search needs. Summary of the invention

[0003] In a first aspect of the present disclosure, an article retrieval method is provided. The method includes: obtaining retrieval indication information indicating article retrieval requirements; obtaining at least one type of article retrieval information for the retrieval indication information using a first machine learning model based on the retrieval indication information and a prompt article associated with the retrieval indication information; and obtaining at least one target article as at least part of a target article set based on the at least one type of article retrieval information.

[0004] In a second aspect of the present disclosure, a device for article retrieval is provided. The device includes: an indication information acquisition module configured to acquire retrieval indication information indicating article retrieval requirements; a retrieval information acquisition module configured to acquire at least one type of article retrieval information for the retrieval indication information based on the retrieval indication information and a prompt article associated with the retrieval indication information, using a first machine learning model; and a target article acquisition module configured to acquire at least one target article as at least part of a target article set based on at least one type of article retrieval information.

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

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0007] In a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method according to the first aspect of the present disclosure is implemented.

[0008] It should be understood that the content described in this section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above and other features, advantages and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram showing an example environment in which embodiments according to the present disclosure may be implemented;

[0011] Figure 2 A flowchart showing a process for article retrieval according to some embodiments of the present disclosure is shown;

[0012] Figure 3 A flowchart of a process for iteratively performing article retrieval according to some embodiments of the present disclosure is shown;

[0013] Figure 4 A schematic structural block diagram showing an example apparatus for article retrieval according to some embodiments of the present disclosure; and

[0014] Figure 5 A block diagram of an electronic device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0015] 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. On the contrary, these embodiments are provided to provide 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.

[0016] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part 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.

[0017] Herein, unless explicitly stated, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0018] 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.

[0019] 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.

[0020] 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, so that the user can independently choose whether to provide personal information to software or hardware such as electronic devices, applications, servers or storage media that execute operations of the technical solution of the present disclosure based on the prompt message.

[0021] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information is sent to the user in a manner such as a pop-up window, in which the prompt information can be presented in text form. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0022] 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 relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0023] As used herein, the term "model" can learn the association between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for a given input. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multi-layer processing units. A neural network model is an example of a model based on deep learning. In this article, "model" may also be referred to as "machine learning model", "learning model", "machine learning network" or "learning network", and these terms are used interchangeably in this article.

[0024] As mentioned above, with the development of information technology, various terminal devices can provide various services to people in work and life. Applications that provide services can be deployed in terminal devices. The terminal device presents the corresponding content through the user interface of the application and interacts with the user to meet the various needs of the user. In some cases, the terminal device can use a digital assistant to communicate with the user, obtain the user's retrieval requirements for articles (such as papers), and call the search engine for retrieval, thereby providing the user with the retrieved target articles. However, the current retrieval method still needs to be improved in terms of the depth of retrieval and the comprehensiveness of retrieval.

[0025] In view of this, an embodiment of the present disclosure proposes an improved solution for article retrieval. In the solution, retrieval indication information indicating article retrieval requirements is obtained. Based on the retrieval indication information and the prompt articles associated with the retrieval indication information, at least one type of article retrieval information for the retrieval indication information is obtained using a first machine learning model. Based on at least one type of article retrieval information, at least one target article is obtained as at least a part of a target article set.

[0026] In an embodiment of the present disclosure, the prompt article associated with the retrieval indication information is provided to the machine learning model together with the retrieval indication information. As a result, the machine learning model can obtain more sufficient article retrieval information from the prompt article. Further, based on this more sufficient article retrieval information, the target article is retrieved, which can improve the accuracy and comprehensiveness of the retrieval results.

[0027] Various example implementations of the solution are described in detail below in conjunction with the accompanying drawings. Example Environment

[0028] Figure 1 A schematic diagram of an example environment 100 in which an embodiment of the present disclosure can be implemented is shown. The environment 100 involves a dialogue system 110, which can support interaction with a user 145. In some examples, in an article retrieval scenario, the dialogue system 110 can support the user 145 to propose a retrieval requirement for an article in natural language and / or by specifying relevant articles (e.g., uploading attachments of relevant articles, providing links to relevant articles), etc. In an embodiment of the present disclosure, an article can refer to a document, file, or material including one or more modal data (e.g., text, charts, formulas, images, etc.). The article can be of various suitable types and genres. Exemplarily, the article can include a paper (e.g., for academic research), a news report, etc. The dialogue system 110 can provide the user 145 with retrieval results for the retrieval requirement, such as a target article set, etc. The user 145 can be referred to as an end user of the dialogue system 110.

[0029] In some embodiments, the dialogue system 110 may include or be implemented as a digital assistant 122. The digital assistant 122 may be configured to have an intelligent dialogue. As an example, the digital assistant 122 may be configured as an independently running application, such as a web application or other types of applications. As another example, the digital assistant 122 may be configured within the application as part of the application. In such an example, the digital assistant 122 and the application may be considered to be the same application. The digital assistant 122 is provided to assist users in various task processing requirements in different applications and scenarios. During the interaction with the digital assistant 122, the user inputs an interactive message, and the digital assistant 122 provides a response message in response to the user input. Typically, the digital assistant 122 is able to support users to input questions in a natural language, and perform tasks and provide responses based on the understanding of natural language input and logical reasoning ability.

[0030] For each user 145, the client of the dialogue system 110 can present an interaction window 142 of the digital assistant 122 in the client interface, such as a dialogue window with the digital assistant 122. The user 145 can enter a message in the dialogue window, and the object system 110 can determine the response message of the digital assistant 122 and present it to the user 145 in the interaction window 142. In some embodiments, the interaction message of the dialogue system 110 may include messages in multimodal forms, such as text messages (e.g., natural language text), voice messages, image messages, video messages, and the like.

[0031] The dialogue system 110 may be deployed locally on the terminal device of each user 145, and / or may be supported by a server device. For example, the terminal device of the user 145 may run a client of the dialogue system 110, which may support the interaction between the user and the part provided by the server. In the case where the dialogue system 110 runs locally on the user's terminal device, the user 145 may directly interact with the local dialogue system 110 using the terminal device. In the case where the dialogue system 110 runs on the server device, the server device may provide services to the client running in the terminal device based on the communication connection with the terminal device. The dialogue system 110 may present a corresponding interface to the user 145 based on the operation of the user 145, so as to output and / or receive relevant information to the user 145.

[0032] In some embodiments, the implementation of at least part of the functions of the dialogue system 110 and / or the implementation of at least part of the functions of the digital assistant 122 in the dialogue system 110 can be implemented based on the machine learning model 155. During the operation of the dialogue system 110, one or more machine learning models can be called, such as machine learning model 155-1, machine learning model 155-2, ..., machine learning model 155-N, and so on, where N is a positive integer. For the convenience of description, one or more machine learning models are collectively referred to as machine learning models 155 in this document. In the dialogue system 110, the digital assistant 122 can use the machine learning model 155 to understand the user input and provide a response to the user based on the output of the machine learning model 155. It should be noted that although in Figure 1 The machine learning model 155 is shown as being independent of the dialogue system 110, but one or more machine learning models 155 may run on the dialogue system 110, or other remote servers.

[0033] The machine learning model 155 can be a model of different types. In some embodiments, one or more machine learning models 155 can be built based on a language model (LM), for example, based on a large language model (LLM). The machine learning model used is a content generation model that can generate corresponding outputs based on model inputs. In some embodiments, a multimodal machine learning model can receive model inputs of textual modalities (e.g., natural language and / or machine language) and / or model inputs of non-textual modalities (e.g., images, voice, video, etc.), and can generate desired outputs based on model inputs and prompts. The prompts here are used to guide the machine learning model to generate user needs that can solve the model inputs. In an application scenario for supporting user dialogue, the input of user 145 can be provided to the machine learning model 155 as at least a part of the model input (other parts can include prompts). The user input is considered a question. Based on the model output, a corresponding response can be generated to provide to the user 145.

[0034] The dialogue system 110 can run on appropriate electronic devices. The electronic devices here can be any type of device with computing capabilities, including terminal devices or server devices. The terminal device 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 systems (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio broadcast receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The server device can include, for example, a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like. In some embodiments, the dialogue system 110 can be implemented based on a cloud service.

[0035] It should be understood that the structure and functionality of environment 100 are described for exemplary purposes only and does not imply any limitation on the scope of the present disclosure. Example Process

[0036] Some example embodiments of the present disclosure will be described below with continued reference to the accompanying drawings. Figure 2 A flowchart of a process 200 for article retrieval according to some embodiments of the present disclosure is shown. Part or all of the process 200 may be implemented by the dialogue system 110 or may be implemented by other devices independent of the dialogue system 110, for example, may be implemented by other remote devices (terminal devices or service devices) with computing capabilities. In the following, for ease of discussion, the execution of the process 200 is described from the perspective of the dialogue system 110, but this is only exemplary.

[0037] In box 210, the dialogue system 110 obtains retrieval indication information indicating article retrieval requirements. Taking papers as an example, article retrieval requirements can represent retrieval requirements determined by the user 145 in order to find relevant papers in the process of conducting academic research or writing papers. Retrieval indication information can represent information obtained directly or indirectly based on the article retrieval requirements of the user 145. In some embodiments, the dialogue system 110 can directly use the query input by the user 145 as retrieval indication information. For example, the query can be "the latest research progress in autonomous driving". Alternatively or additionally, the dialogue system 110 can use the first machine learning model to obtain key information in the article based on one or more indicated articles specified by the user 145 as retrieval indication information. The user 145 can specify the indicated article by uploading an article attachment, providing an article link, or other suitable methods. For example, if the user 145 uploads a paper on autonomous driving technology research, the dialogue system 110 can extract key information in the paper by calling the first machine learning model, and infer that the user 145 wants to retrieve papers in the field of autonomous driving. That is, in this case, the dialogue system 110 indirectly obtains the retrieval indication information by understanding the article specified by the user 145. The first machine learning model may be a large language model. The first machine learning model may be referred to as a crawling model.

[0038] In box 220, the dialogue system 110 uses the first machine learning model to obtain at least one type of article retrieval information for the retrieval indication information based on the retrieval indication information and the prompt articles associated with the retrieval indication information. Article retrieval information refers to information that can be used to obtain articles. For example, article retrieval information can be information such as keywords, search statements, Boolean logic operators, etc. provided to the search engine. In the current article retrieval method, the article retrieval information is obtained by extracting keywords, rewriting, etc. after obtaining the user's query. Since the information contained in the query is limited, the article retrieval information obtained in this way is also relatively limited.

[0039] Prompt articles refer to one or more articles provided to the first machine learning model as a source for obtaining article retrieval information. The prompt articles associated with the retrieval indication information may, for example, be articles in the same or similar fields as the query. For example, if the query is "the latest research progress in autonomous driving", the prompt articles may be some papers in the field of autonomous driving. In some embodiments, the prompt articles may be provided by the user 145 to the dialogue system 110. Alternatively or additionally, the prompt article may be a target article obtained by retrieval, and the specific acquisition method will be described in detail later. Since the amount of information contained in the prompt article is usually large, the article retrieval information obtained based on both the retrieval indication information and the prompt article will be more comprehensive.

[0040] In some embodiments, at least one type of article retrieval information may include key information for article retrieval (such as keywords, search statements, etc.). Alternatively or additionally, at least one type of article retrieval information may also include information about articles cited by the article (such as the title, article number, author, etc. of the cited article).

[0041] In block 230, the dialog system 110 obtains at least one target article as at least a part of the target article set based on at least one type of article retrieval information. Specifically, depending on the specific type of the article retrieval information, the dialog system 110 may call a corresponding service or tool (e.g., a search engine, a database) to obtain the at least one target article.

[0042] In some embodiments, if at least one type of article retrieval information includes target key information for article retrieval, the dialogue system 110 may use a search engine to obtain one or more target articles from at least one target article based on the target key information. For example, a keyword or a search statement may be input into the search engine to obtain the target article.

[0043] In some embodiments, the target key information may include information contained in the retrieval indication information. In one example, the dialogue system 110 may use the first machine learning model to obtain the first key information in the retrieval indication information as part of the target key information. Alternatively or additionally, the target key information may include information in the prompt article that is associated with the retrieval indication information. In one example, the dialogue system 110 may use the first machine learning model to obtain the second key information in the prompt article that is associated with the retrieval indication information as part of the target key information.

[0044] In some embodiments, the target key information may also include reference information associated with the first key information or the second key information, that is, other information derived from the first or second key information. For example, when the first key information includes "autonomous driving", reference information such as "unmanned driving" and "assisted driving" may be derived. In some embodiments, the dialogue system 110 may use the first machine learning model to obtain reference information associated with the first key information or the second key information. By obtaining reference information as a supplement to the target key information, the coverage of article retrieval can be further expanded.

[0045] In some embodiments, if at least one type of article search information includes information about cited articles, the dialogue system 110 can retrieve the article from a search engine or database as a target article based on the information about the article cited by the prompt article (e.g., the title of the article). Taking a paper as an example, the cited articles can include articles in the reference list and can also include articles cited in other parts of the paper. Since the cited articles are usually highly correlated with the original article, including them in the search results can improve the accuracy of article retrieval.

[0046] In some embodiments, the dialogue system 110 may use a first machine learning model to determine at least one article part related to the retrieval indication information from multiple article parts of the prompt article. The article part may include, for example, an abstract, an introduction, a chapter or paragraph in the text, etc. In one example, if the retrieval indication information is "the latest research progress in autonomous driving" and the prompt article is a cutting-edge paper in the automotive field, the dialogue system 110 may use a first machine learning model to determine the chapter related to autonomous driving in the paper as at least one article part related to the retrieval indication information. After determining at least one article part related to the retrieval indication information, the dialogue system 110 may generate information about the cited article based on the articles cited in the at least one article part. For example, the dialogue system 110 may extract the title of an article cited in a certain chapter of the prompt article as information about the cited article. An article (especially an academic paper) may cite many articles, but these articles may not all be related to the user's query purpose or needs. In this embodiment, the machine learning model can be used to understand the meaning of each part of the article to select the part (for example, a paragraph) related to the query purpose or needs. In this way, the articles cited in the selected part are more relevant to the query purpose or needs. In this way, the accuracy of article retrieval can be further improved.

[0047] In some embodiments, one or more target articles among at least one target article obtained in any search may be used as prompt articles for the next search, thereby performing multiple rounds of searches in an iterative manner. Figure 3 An iterative article retrieval process 300 is shown.

[0048] In some embodiments, Figure 3As shown, obtaining at least one type of article retrieval information and obtaining at least one target article are performed in multiple rounds of iterations. In one round, the dialogue system 110 can determine the prompt article in the current round iteration based on at least one target article obtained in the previous round iteration of the current iteration. In some embodiments, the dialogue system 110 can use all of the at least one target article obtained in the previous round iteration as the prompt article in the current round iteration. For example, each target article is combined with the query for the next round of retrieval. Alternatively, the dialogue system 110 can also use part of the target articles in the at least one target article obtained in the previous round iteration as the prompt article in the current round iteration. Then, the dialogue system 110 can use the first machine learning model 310 to obtain at least one type of article retrieval information in the current round iteration based on the retrieval indication information and the prompt article in the current round iteration. It can be understood that although the content of the at least one type of article retrieval information obtained in each iteration may be different, the acquisition principle is the same, so it will not be repeated here.

[0049] At the end of the round, the dialogue system 110 may retrieve at least one target article in the current iteration based on at least one type of article retrieval information in the current iteration, as part of the target article set 330. Specifically, Figure 3 As shown, at least one type of article retrieval information is provided to the environment service 320. The environment service 320 may include or call various suitable tools (e.g., search engines or databases) to obtain target articles. For different types of article retrieval information, the environment service 320 may call corresponding tools. For example, for key information used for article retrieval, the environment service 320 may call a search engine to perform article retrieval based on the key information. For another example, for information on a cited article, the environment service 320 may call a database to query the cited article in the database.

[0050] Similarly, at least one target article obtained in the current iteration round can be used to determine the prompt article for the next iteration round. It is understandable that when the first round of article retrieval begins, there is no target article. Therefore, the retrieval can be performed based only on the retrieval indication information, or based on the retrieval indication information and the prompt article input by the user.

[0051] In some embodiments, the dialogue system 110 may terminate multiple iteration rounds in response to the target article set satisfying a preset retrieval stop condition. In one example, the retrieval stop condition may include: the number of target articles in the target article set reaches a preset number, such as 100 articles. In one example, the retrieval stop condition may include: the correlation between the target article newly added in the target article set and the retrieval indication information is lower than the preset correlation. As the iteration rounds increase, the correlation between the retrieved target article and the retrieval indication information may become lower and lower. Therefore, when the correlation between the newly added target article and the retrieval indication information is lower than the preset correlation, the dialogue system 110 may determine to terminate the iteration. In one example, the retrieval stop condition may include: the iteration round for obtaining the newly added target article in the target article set reaches the preset round. That is, when a certain search depth is reached, the dialogue system 110 may determine to terminate the iteration. In some embodiments, the dialogue system 110 may also preset multiple retrieval stop conditions, and terminate the iteration when any retrieval stop condition is met.

[0052] In some embodiments, the first machine learning model 310 can be trained to enable the model to determine whether it is necessary to enter the next iteration round.

[0053] After the iteration is terminated, the dialogue system 110 can obtain a target article set based on all target articles retrieved in multiple rounds. In some embodiments, the retrieved target articles can also be screened to remove some articles that do not meet the requirements.

[0054] In the above scheme, by iteratively performing article retrieval in multiple rounds, the accuracy and comprehensiveness of the retrieval results can be improved. By setting the retrieval stop condition, it can be further ensured that the retrieval is performed efficiently within a limited number of rounds.

[0055] In some embodiments, Figure 3 As shown, the dialogue system 110 can use the second machine learning model 340 (i.e., the sorting model) to determine the corresponding relevance between each target article in the target article set and the retrieval indication information. Based on the corresponding relevance of each target article, the dialogue system 110 can sort each target article to obtain a sorted target article set 350. According to the order of the corresponding relevance, the dialogue system 110 can present at least a portion of the target articles in the sorted target article set. In one example, based on the sorting result, the dialogue system 110 can present each target article in the target article set in order from high to low relevance. The dialogue system 110 can present all target articles in full, or it can present part of the target articles (e.g., the articles with the top 100 relevance).

[0056] In some embodiments, the dialogue system 110 may score and sort each target article in the target article set based on other criteria, such as the publication time, citation frequency, download volume, etc. of the article.

[0057] By ranking the articles in the target article collection, more accurate retrieval results can be provided to users. Example devices and equipment

[0058] The embodiments of the present disclosure also provide corresponding devices for implementing the above methods or processes. Figure 4 A schematic structural block diagram of an example apparatus 400 for article retrieval according to some embodiments of the present disclosure is shown. The apparatus 400 may be implemented as or included in the dialogue system 110. Each module / component in the apparatus 400 may be implemented by hardware, software, firmware, or any combination thereof.

[0059] like Figure 4 As shown, the device 400 includes: an indication information acquisition module 410, a retrieval information acquisition module 420 and a target article acquisition module 430. The indication information acquisition module 410 is configured to acquire retrieval indication information indicating article retrieval requirements. The retrieval information acquisition module 420 is configured to acquire at least one type of article retrieval information for the retrieval indication information based on the retrieval indication information and the prompt articles associated with the retrieval indication information using a first machine learning model. The target article acquisition module 430 is configured to acquire at least one target article as at least part of the target article set based on at least one type of article retrieval information.

[0060] In some embodiments, obtaining at least one type of article retrieval information and obtaining at least one target article are performed in one iteration round of multiple iteration rounds, and for the current iteration round of multiple iteration rounds, the device 400 also includes a prompt article determination module, which is configured to determine the prompt article in the current iteration round based on at least one target article obtained in the previous iteration round of the current iteration round. The retrieval information acquisition module 420 is also configured to obtain at least one type of article retrieval information in the current iteration round using the first machine learning model based on the retrieval indication information and the prompt article in the current iteration round. The target article acquisition module 430 is also configured to obtain at least one target article in the current iteration round as part of the target article set based on at least one type of article retrieval information in the current iteration round.

[0061] In some embodiments, the apparatus 400 further includes an iteration termination module configured to terminate multiple iteration rounds in response to the target article set satisfying a preset retrieval stop condition.

[0062] In some embodiments, the retrieval stop condition includes at least one of the following: the number of target articles in the target article set reaches a preset number, the correlation between the most recently added target article in the target article set and the retrieval indication information is lower than a preset correlation, or the number of iteration rounds for obtaining the most recently added target article in the target article set reaches a preset round.

[0063] In some embodiments, at least one type of article retrieval information includes target key information for article retrieval, and the target article acquisition module 430 is further configured to retrieve one or more target articles from at least one target article using a search engine based on the target key information retrieval.

[0064] In some embodiments, the retrieval information acquisition module 420 is also configured to use the first machine learning model to obtain the first key information in the retrieval indication information as part of the target key information; and use the first machine learning model to obtain the second key information associated with the retrieval indication information in the prompt article as part of the target key information.

[0065] In some embodiments, the retrieval information acquisition module 420 is further configured to utilize the first machine learning model to acquire reference information associated with the first key information or the second key information as part of the target key information.

[0066] In some embodiments, at least one type of article retrieval information includes information of cited articles, and the target article acquisition module 430 is further configured to acquire the cited articles as one or more target articles of at least one target article based on the information of the cited articles.

[0067] In some embodiments, the retrieval information acquisition module 420 is also configured to use a first machine learning model to determine at least one article part related to the retrieval indication information from multiple article parts of the prompt article; and generate information of the cited article based on the article cited in at least one article part.

[0068] In some embodiments, the device 400 also includes: a correlation acquisition module, configured to use a second machine learning model to determine the corresponding correlation between each target article in the target article set and the retrieval indication information; a sorting module, configured to sort each target article based on the corresponding correlation of each target article to obtain a sorted target article set; and a presentation module, configured to present at least a part of the target articles in the sorted target article set according to the order of the corresponding correlation.

[0069] In some embodiments, the indication information acquisition module 410 is also configured to acquire one or more retrieval indication articles indicating article retrieval requirements based on user input; and to use a first machine learning model to acquire key information in the one or more retrieval indication articles as retrieval indication information.

[0070] The units and / or modules included in the device 400 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units and / or modules can be implemented using software and / or firmware, such as machine executable instructions stored on a storage medium. In addition to or as an alternative to machine executable instructions, some or all of the units and / or modules in the device 400 can be implemented at least in part by one or more hardware logic components. As an example and not limitation, exemplary types of hardware logic components that can 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.

[0071] Figure 5 1 shows a block diagram of 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 constitute any limitation on the functionality and scope of the embodiments described herein. Figure 5 The electronic device 500 shown may include or be implemented as Figure 1 The dialogue system 110, or Figure 4 Device 400.

[0072] like Figure 5 As shown, the electronic device 500 is in the form of a general electronic device. The components of the electronic device 500 may include, but are not limited to, one or more processors or processing units 510, a memory 520, a storage device 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. The processing unit 510 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 520. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 500.

[0073] The electronic device 500 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 520 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 530 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 500.

[0074] The electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 5 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 520 may include a computer program product 525 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0075] The communication unit 540 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 500 can be implemented in a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 500 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0076] The input device 550 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 560 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 500 may also communicate with one or more external devices (not shown) through the communication unit 540 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 500, or communicate with any device that allows the electronic device 500 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0077] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0078] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0079] 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 device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0080] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0081] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse 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 realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0082] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. An article retrieval method, comprising: Acquire search indication information indicating article search requirements; Based on the search indication information and the prompt articles associated with the search indication information, using a first machine learning model, obtaining at least one type of article search information for the search indication information; as well as Based on the at least one type of article retrieval information, at least one target article is obtained as at least a part of the target article set.

2. The method according to claim 1, wherein obtaining the at least one type of article retrieval information and obtaining the at least one target article are performed in one iteration round of multiple iteration rounds, and for a current iteration round of the multiple iteration rounds, the method comprises: Determine the prompt article in the current iteration based on the at least one target article obtained in the previous iteration of the current iteration; Based on the search indication information and the prompt articles in the current round iteration, using the first machine learning model, obtaining the at least one type of article search information in the current round iteration; as well as Based on the at least one type of article retrieval information in the current round iteration, the at least one target article in the current round iteration is obtained as a part of the target article set.

3. The method according to claim 2, further comprising: In response to the target article set satisfying a preset retrieval stop condition, the multiple iteration rounds are terminated.

4. The method according to claim 3, wherein the retrieval stop condition comprises at least one of the following: The number of target articles in the target article set reaches a preset number, The relevance between the target article newly added to the target article set and the search indication information is lower than the preset relevance, or The iteration round for obtaining the latest added target article in the target article set reaches a preset round.

5. The method according to claim 1, wherein the at least one type of article retrieval information includes target key information for article retrieval, and obtaining at least one target article includes: Based on the target key information, one or more target articles in the at least one target article are acquired using a search engine.

6. The method according to claim 5, wherein the target key information is obtained by: Using the first machine learning model, obtaining first key information in the search indication information as part of the target key information; and Utilizing the first machine learning model, second key information associated with the retrieval indication information in the prompt article is obtained as part of the target key information.

7. The method according to claim 6, wherein the target key information can also be obtained by: Using the first machine learning model, obtain reference information associated with the first key information or the second key information as part of the target key information.

8. The method according to claim 1, wherein the at least one type of article retrieval information includes information of cited articles, and obtaining at least one target article comprises: Based on the information of the cited article, the cited article is obtained as one or more target articles of the at least one target article.

9. The method according to claim 8, wherein the information of the cited articles is obtained by: Determine, by using the first machine learning model, at least one article part related to the search indication information from a plurality of article parts of the prompt article; and Based on the articles cited in the at least one article part, information of the cited articles is generated.

10. The method according to claim 1, further comprising: Determine, by using a second machine learning model, a corresponding degree of association between each target article in the target article set and the search indication information; Based on the corresponding relevance of each target article, sorting each target article to obtain a sorted set of target articles; as well as At least a portion of the target articles in the sorted target article set are presented according to the order of the corresponding relevances.

11. The method according to claim 1, further comprising: Acquire one or more search indication articles indicating the article search requirement based on user input; as well as Utilize the first machine learning model to obtain key information from the one or more retrieval indication articles as the retrieval indication information.

12. A device for article retrieval, comprising: An indication information acquisition module, configured to acquire retrieval indication information indicating article retrieval requirements; A search information acquisition module is configured to acquire at least one type of article search information for the search indication information by using a first machine learning model based on the search indication information and the prompt articles associated with the search indication information; as well as The target article acquisition module is configured to acquire at least one target article as at least a part of the target article set based on the at least one type of article retrieval information.

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

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

15. A computer program product, comprising a computer program, wherein the computer program implements the method according to any one of claims 1 to 11 when executed by a processor.

Images