Information query method, device, electronic device and storage medium

Abstract

The present disclosure discloses an information query method, device, electronic device, storage medium and program product, and relates to the field of data processing technology, and in particular to the field of intelligent search. The specific implementation scheme of the information query method is: identifying the query information to obtain target entity information and associated entity information; wherein the associated entity information indicates an entity associated with the target entity; based on the target entity information, determining the target text from the text information set; and based on the associated entity information, determining the target annotation from the entity information set.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, in particular to the field of intelligent search, and specifically to an information query method, device, electronic device, storage medium, and program product. Background Art

[0002] With the popularization of the Internet, intelligent search has become one of the important tools of the Internet. Intelligent search can provide information query, retrieval and other services. In the process of providing these services, it can continuously optimize its advantages such as intelligence, personalization, interactivity and initiative, and strive to enable users to quickly and accurately find the information they need. Summary of the invention

[0003] The present disclosure provides an information query method, device, electronic device, storage medium and program product.

[0004] According to one aspect of the present disclosure, there is provided an information query method, comprising: identifying query information to obtain target entity information and associated entity information; wherein the associated entity information indicates an entity associated with the target entity; based on the target entity information, determining a target text from a text information set; and based on the associated entity information, determining a target annotation from the entity information set.

[0005] According to another aspect of the present disclosure, an information query device is provided, including: an identification module, used to identify query information to obtain target entity information and associated entity information; wherein the associated entity information indicates an entity associated with the target entity; a first determination module, used to determine a target text from a text information set based on the target entity information; and a second determination module, used to determine a target annotation from the entity information set based on the associated entity information.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method as described above.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method as described above.

[0008] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the method described above when executed by a processor.

[0009] It should be understood that the content described in this section is not intended to identify the key 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

[0010] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0011] Figure 1 An exemplary system architecture to which the information query method and device according to an embodiment of the present disclosure can be applied is schematically shown;

[0012] Figure 2 A flowchart of an information query method according to an embodiment of the present disclosure is schematically shown;

[0013] Figure 3 A flowchart of an information query method according to another embodiment of the present disclosure is schematically shown;

[0014] Figure 4 The application scenario diagram of the information query method according to the embodiment of the present disclosure is schematically shown;

[0015] Figure 5 A schematic diagram of displaying target annotation according to an embodiment of the present disclosure is schematically shown;

[0016] Figure 6 A block diagram schematically shows an information query device according to an embodiment of the present disclosure; and

[0017] Figure 7 A block diagram of an electronic device suitable for implementing an information query method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0018] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0019] In medical search scenarios, user queries are naturally short, and users often fail to accurately express their needs. For short or inaccurate query information, the system cannot provide accurate feedback that is close to the user's intention, which can easily lead to a poor user experience.

[0020] The present disclosure provides an information query method, an apparatus, an electronic device, a storage medium, and a program product.

[0021] According to an embodiment of the present disclosure, an information query method may include: identifying query information to obtain target entity information and associated entity information; wherein the associated entity information indicates an entity associated with the target entity; based on the target entity information, determining a target text from a text information set; and based on the associated entity information, determining a target annotation from the entity information set.

[0022] According to the embodiments of the present disclosure, not only the target text as feedback information can be displayed to the user, but also the target annotation that can be refined and supplemented as a selection candidate can be provided to the user. The target text and the target annotation realize a two-way function, intelligently guiding the user to achieve accurate matching of feedback content that is consistent with the actual situation, and better meet the user's medical search needs.

[0023] It should be noted that in the technical solution of the present disclosure, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0024] It should be noted that, for ease of description, the following examples describe the embodiments of the present disclosure using medical inquiry as an example scenario. Those skilled in the art can understand that the technical solutions of the embodiments of the present disclosure can be applied to any other inquiry or query scenarios.

[0025] Figure 1 An exemplary system architecture to which the information query method and device according to an embodiment of the present disclosure can be applied is schematically shown.

[0026] It should be noted that Figure 1 The examples shown are only examples of system architectures to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios. For example, in another embodiment, the exemplary system architecture to which the information query method and apparatus can be applied may include a terminal device, but the terminal device may implement the information query method and apparatus provided by the embodiments of the present disclosure without interacting with the server.

[0027] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0028] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as knowledge reading applications, web browser applications, search applications, instant messaging tools, email clients and / or social platform software, etc. (only as examples).

[0029] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0030] The server 105 may be a server that provides various services, such as a background management server (only an example) that provides support for the content browsed by the user using the terminal devices 101, 102, and 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0031] It should be noted that the information query method provided in the embodiment of the present disclosure can generally be executed by the terminal device 101, 102, or 103. Accordingly, the information query device provided in the embodiment of the present disclosure can also be set in the terminal device 101, 102, or 103.

[0032] Alternatively, the information query method provided in the embodiment of the present disclosure may also be generally executed by the server 105. Accordingly, the information query device provided in the embodiment of the present disclosure may generally be arranged in the server 105. The information query method provided in the embodiment of the present disclosure may also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the information query device provided in the embodiment of the present disclosure may also be arranged in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0033] For example, when a user enters query information in a medical search scenario, the terminal devices 101, 102, and 103 can obtain the query information entered by the user, and then send the obtained query information to the server 105, which analyzes the query information to determine the target entity information and associated entity information of the query information; and determines the target text and target annotation based on the target entity information and associated entity information. Alternatively, a server or server cluster that can communicate with the terminal devices 101, 102, 103 and / or the server 105 analyzes the query information and finally determines the target text and target annotation.

[0034] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0035] Figure 2 The flowchart of the information query method according to the embodiment of the present disclosure is schematically shown.

[0036] like Figure 2 As shown, the method includes operations S210 to S230.

[0037] In operation S210, the query information is identified to obtain target entity information and associated entity information; wherein the associated entity information indicates entities associated with the target entity.

[0038] In operation S220 , a target text is determined from the text information set based on the target entity information.

[0039] In operation S230 , a target annotation is determined from the entity information set based on the associated entity information.

[0040] According to the embodiments of the present disclosure, the type of query information is not limited. For example, it can be a phrase, a piece of text, or text converted from a recognized speech. No further details are given here, as long as it is information input by the user based on the intention of query or retrieval.

[0041] According to the embodiments of the present disclosure, the type of entity information is not limited. For example, it can be a proper noun in the field of medical consultation, a proper noun in the field of weather forecast, or other entity information with specific meanings used in the field of intelligent search.

[0042] According to an embodiment of the present disclosure, the target entity information may be entity information that is the same as or similar to the entity in the query information. The target entity information is mainly used to characterize key information or basic information in the query information.

[0043] According to an embodiment of the present disclosure, the associated entity information may be entity information associated with the entity information in the query information. The associated entity information is mainly used to characterize the associated information in the query information.

[0044] According to the embodiments of the present disclosure, the type of text information set is not specifically limited. For example, it can be a text type information set or a conversation record type information set, as long as it is an information set with text description content.

[0045] According to the embodiments of the present disclosure, the type of the target text is not specifically limited. For example, it can be a text description, one or more records in a conversation record, or a text with image content.

[0046] According to the embodiments of the present disclosure, the type of entity information set is not specifically limited. For example, it can be a set of target entities, a set of associated entities, or a set of target entities and associated entities.

[0047] According to an embodiment of the present disclosure, the target annotation may be an entity that supplements the description associated with an entity in the query information. The target annotation may be a target entity similar to the entity in the query information, or an associated entity, or may include both the target entity and the associated entity. As long as it can assist in guiding the query and provide further supplementary description, it can be used.

[0048] According to the embodiments of the present disclosure, not only the target entity information of the query information is identified, but also the related entities in the query information are identified and predicted, so that the query information can be mined more fully and deeply.

[0049] According to the embodiments of the present disclosure, not only is the target text determined from the text information set based on the target entity information, but the target text is used as feedback information for the query information. The target annotation is also determined from the entity information set based on the associated entity information, guiding the user to perform a more accurate secondary search based on the target annotation. The user is intelligently guided to perform a refined and supplementary expression search from the target annotation, making the query results richer and more accurate, and improving the user's search demand experience.

[0050] Reference below Figure 3 to Figure 6 , combined with specific embodiments Figure 2 The method shown is further explained.

[0051] Figure 3 The flowchart of an information query method according to another embodiment of the present disclosure is schematically shown.

[0052] like Figure 3 As shown, in response to a query request for requesting query information about a user input, query information 310 input by a user is obtained. The query information is identified to obtain target entity information 320 and associated entity information 330 respectively. Based on the target entity information 320, a target text 360 is determined from a text information set 340. Based on the associated entity information 330, a target annotation 370 is determined from an entity information set 350. The target text 360 and the target annotation 370 are displayed so that the user can perform a secondary query or search based on the target text 360 or the target annotation 370.

[0053] According to an embodiment of the present disclosure, the query information may be identified using the first named entity recognition model to obtain target entity information.

[0054] According to an embodiment of the present disclosure, the first named entity recognition model may be trained by using historical text information and a first label corresponding to the historical text information as training samples, wherein the first label is used to characterize target entity information in the historical text information.

[0055] According to an embodiment of the present disclosure, the second named entity recognition model may be used to perform named entity recognition on the query information to obtain associated entity information.

[0056] According to an embodiment of the present disclosure, the second named entity recognition model is trained by using historical text information and a second label corresponding to the historical text information as training samples, wherein the second label is used to characterize associated entity information in the historical text information.

[0057] According to an embodiment of the present disclosure, the first named entity recognition model and the second named entity recognition model can be trained using the same NER (Named Entity Recognition) naming recognition model as the initial model, but is not limited to this. The first named entity recognition model and the second named entity recognition model can also be trained using different recognition models.

[0058] According to the embodiments of the present disclosure, the query information is respectively identified using the first named entity recognition model and the second named entity recognition model, which is more targeted and makes the prediction and identification more accurate.

[0059] According to the embodiments of the present disclosure, different training samples are used to train the first named entity recognition model and the second named entity recognition model, respectively, which is conducive to obtaining the trained models quickly and efficiently.

[0060] According to the embodiments of the present disclosure, the query information is respectively identified using the first named entity recognition model and the second named entity recognition model, the user's search request is mapped to relevant entities through the named entity recognition model, and in-depth mining is performed to obtain not only the target entity information but also the associated entity information.

[0061] According to an embodiment of the present disclosure, a text information set includes a plurality of text information, wherein each of the plurality of text information includes entity information.

[0062] According to an embodiment of the present disclosure, the entity information may be information that is identical to, similar to, or associated with the target entity information.

[0063] According to an embodiment of the present disclosure, the target text may be determined through the following operations.

[0064] For example, a first matching degree between entity information in each text information and target entity information is calculated; and corresponding text information whose first matching degree is greater than or equal to a first matching degree threshold is determined as the target text.

[0065] According to the embodiments of the present disclosure, the calculation method of the first matching degree is not limited. For example, it can be determined by calculating the vector similarity, the distance similarity, or other correlation calculation methods.

[0066] According to the embodiment of the present disclosure, the first matching degree threshold is not specifically limited. For example, it can be 0.95, or 0.98, etc. It can be set according to the actual situation, as long as it helps to ensure that the number of target texts recalled is appropriate and the recall rate is high.

[0067] According to an embodiment of the present disclosure, the entity information set includes a plurality of entity information.

[0068] According to an embodiment of the present disclosure, multiple entity information in the entity information set may be identical to, similar to, or associated with multiple entity information in the text information set.

[0069] According to an embodiment of the present disclosure, the target annotation may be determined through the following operations.

[0070] For example, a second matching degree between each entity information in the plurality of entity information and the associated entity information is calculated; and entity information whose second matching degree is greater than or equal to a second matching degree threshold is determined as a target annotation.

[0071] According to the embodiment of the present disclosure, the calculation method of the second matching degree is not limited. For example, it can be determined by calculating the vector similarity or by calculating other correlations.

[0072] According to the embodiment of the present disclosure, the second matching degree threshold is not specifically limited. For example, it can be 0.95, or 0.98, etc. It can be set according to the actual situation, as long as it helps to ensure that the number of target annotations recalled is appropriate and the recall rate is high.

[0073] According to another embodiment of the present disclosure, the target annotation may also be determined through the following operations.

[0074] For example, determining the category of each entity information among multiple entity information in an entity information set; calculating the second matching degree between each entity information and the associated entity information; determining the entity weight of each entity information in the entity information set based on the category and the second matching degree; and determining an entity whose entity weight is greater than or equal to an entity weight threshold as a target annotation.

[0075] According to an embodiment of the present disclosure, the entity information set contains not only entity information that is the same as or similar to the entity information in the query information, but also some necessary attribute information. The attribute information is also an important component of the associated entity information. According to an embodiment of the present disclosure, simply using correlation cannot effectively recall the associated attribute information. In this case, a weight can be assigned to the category of each entity information in the entity information set, and the target annotation can be determined by combining the category and the second matching degree.

[0076] For example, when "high blood pressure" is used as query information to determine the target annotation, the related entity information such as antihypertensive drugs and blood pressure can be matched and determined based on the matching degree. However, although attribute information such as age and gender is also important, it is difficult to determine it through correlation matching.

[0077] In this case, combining the category and the second matching degree by assigning weights is conducive to the mining and determination of attribute information such as age and gender, and more effectively guiding users to express their demands in a refined manner.

[0078] According to an embodiment of the present disclosure, the target text and the target annotation may be sorted to obtain a sorting result; and the target text and the target annotation may be displayed according to the sorting result.

[0079] According to the embodiments of the present disclosure, the target text and the target annotation can be sorted separately to obtain the sorting results of the target text and the sorting results of the target annotation, and then the target text and the target annotation are displayed respectively according to their respective sorting results, but it is not limited to this. It is also possible to sort the target text and the target annotation together to obtain a comprehensive sorting result, and display the target text and the target annotation in the order of the comprehensive sorting result.

[0080] According to the embodiments of the present disclosure, sorting is performed first, and then the target text and target annotations are displayed in the order of the sorting results, which is more biased, helps users obtain effective information more quickly, and improves user experience.

[0081] According to an embodiment of the present disclosure, when it is determined that both the target text and the target annotation are plural, for example, the target text includes plural items and the target annotation includes plural items.

[0082] According to an embodiment of the present disclosure, when it is determined that there are at least two identical target texts and / or at least two identical target annotations, deduplication is performed; a first number of identical target texts and / or a second number of identical target annotations are calculated; a weight of the target text is determined based on the first number and a first degree of matching; a weight of the target annotation is determined based on the second number and a second degree of matching; and the target text and the target annotation are sorted using the weight of the target text and the weight of the target annotation to obtain a sorting result.

[0083] According to an embodiment of the present disclosure, the at least two identical target texts may be understood as at least two identical or similar target texts. The degree of similarity may be controlled by a text similarity threshold.

[0084] According to an embodiment of the present disclosure, the at least two identical target annotations may be understood as at least two identical or similar target annotations. The degree of similarity may be controlled by an annotation similarity threshold.

[0085] According to the embodiments of the present disclosure, not only the matching degree is considered to sort the target text and the target annotation, but also the number of the same ones. That is, not only the relevance is considered to ensure the query intent is close to the user, but also the popularity is considered to be more practical. Therefore, combining the two can better reach the real needs of users.

[0086] According to an embodiment of the present disclosure, the information query method may further include an operation of constructing an entity information set.

[0087] For example, historical text information is obtained; a second named entity recognition model is used to perform named entity recognition on the historical text information to obtain primary entity information; impurity filtering and normalization are performed on the primary entities to obtain entity information; and based on the entity information, an entity information set is obtained.

[0088] According to the embodiment of the present disclosure, the impurity filtering process can be a process of screening and removing irrelevant entity information. Through the impurity filtering process of the embodiment of the present disclosure, useless information can be deleted and filtered, thereby improving the efficiency of subsequent processing.

[0089] According to the embodiments of the present disclosure, the normalization process may be a process of performing statistics and deduplication on the same or similar primary entity information. After the normalization process of the embodiments of the present disclosure, the same or similar content in the primary entity information can be deduplicated, thereby avoiding the output of a large number of the same or similar results during the recall. After the normalization process, the richness and diversity of the recall results are improved.

[0090] According to an embodiment of the present disclosure, before performing a deduplication operation on the same or similar primary entity information, the number of the same or similar primary entity information may be counted to obtain word frequency information (i.e., the same number of information), so that it can be considered as an important influencing factor when subsequently sorting the target annotations.

[0091] According to an embodiment of the present disclosure, the text information set may also be constructed in the same operation manner as that of constructing the entity information set.

[0092] For example, historical text information is obtained, and named entity recognition is performed on the historical text information using the first named entity recognition model to obtain entity information corresponding to the historical text information in the text information set, so that when performing subsequent retrieval queries, the corresponding target text can be obtained using the entity information corresponding to the historical text information in the text information set.

[0093] According to the embodiments of the present disclosure, the text information set and the entity information set may be designed as an offline database, but it is not limited thereto, and the text information set and the entity information set may also be designed as an online database.

[0094] According to the embodiments of the present disclosure, the text information set and the entity information set are designed in the form of an online database, which can change in real time based on actual changes, reflecting real-time performance and better reflecting the popularity of word frequency.

[0095] The information query method provided by the embodiments of the present disclosure can be applied to intelligent retrieval scenarios in medical consultation.

[0096] According to an embodiment of the present disclosure, the query information may be a phrase, a keyword, or a paragraph of text input by a user on an input interface for querying about a disease, a symptom, a treatment, or a drug.

[0097] According to an embodiment of the present disclosure, the target entity information may include entities that are the same as or similar to entities in the query information.

[0098] For example, if the entity in the query information is a disease entity, the target entity information may be one or more of disease entity information, symptom entity information, drug entity information, and treatment entity information.

[0099] According to an embodiment of the present disclosure, the related entity information may include entities related to the entity in the query information.

[0100] For example, if the entity in the query information is a disease entity, the associated entity information may be one or more of concurrent disease entity information, concurrent symptom entity information, age entity information, and gender entity information.

[0101] Figure 4 A schematic diagram of an application scenario of the information query method according to an embodiment of the present disclosure is schematically shown.

[0102] like Figure 4 As shown, the query information 410 may be "the difference between kidney yin deficiency and kidney yang deficiency". Based on the query information 410, the feedback information displayed on the page may include both target text and target annotation. The target text includes the first conversation record text 420 and the second conversation record text 430. The target annotation includes a term 440 in the form of a question and answer.

[0103] The target entity information identified by the content in the query information 410 may be disease entity information such as kidney yin deficiency, kidney yin deficiency, and other types of entity information such as difference. The first matching degree between each entity information in the text information set and the target entity information can be calculated through the target entity information, and the text information with the first matching degree greater than or equal to the first matching degree threshold is determined as the target text, such as the first dialogue record text 420 and the second dialogue record text 430. Among them, the first dialogue record text 420 and the second dialogue record text 430 may include a title, and a dialogue record (i.e., patient questions and expert answers, etc.). In the title, patient questions or expert answers, entity information such as "kidney yin deficiency", "kidney yang deficiency" and the like that is the same as the target entity information may be included.

[0104] like Figure 4 As shown, it can also be seen that the target annotation can be displayed in the form of an entry 440 or a link. The entry 440 may reflect entity category keywords such as "population", "associated symptoms" and "concurrent diseases". The detailed content of the target annotation can be further displayed after the user selects the entry 440.

[0105] According to an embodiment of the present disclosure, the target text and target annotation can be displayed on the interface according to the sorting result. For example, if the entry 440 is ranked first, the first conversation record text 420 and the second conversation record text 430 are ranked second and third respectively, then the display order is entry 440 first, the first conversation record text 420 and the second conversation record text 430 second and third respectively.

[0106] Figure 5 A schematic diagram of displaying target annotations according to an embodiment of the present disclosure is schematically shown.

[0107] The associated entity information associated with the target entity information may be, for example, accompanying symptom entity information and concurrent disease entity information. By using these associated entity information, target annotations matching these associated entity information may be matched from the entity information set, such as backache, fear of cold, fatigue, insomnia, kidney yin deficiency, kidney yang deficiency, yin deficiency, and yang deficiency. In addition, entity information such as gender, age, etc. may be determined as target annotations by setting the entity weight of the category of each entity information in the entity information set.

[0108] like Figure 5 As shown, the content in the target annotation can be entity information of accompanying symptoms such as low back pain, fear of cold, fatigue, insomnia, etc., or gender such as male and female, or entity information of concurrent diseases such as kidney yin deficiency, kidney yang deficiency, yin deficiency and yang deficiency, etc.

[0109] The user can select the entry of the target annotation. After entering the entry, the user can make a guided selection based on the candidate content provided. For example, the user can make an accurate selection of males and females in the population, and can also make an accurate selection of accompanying symptoms such as backache, fear of cold, fatigue, insomnia, etc. according to the actual situation. The user can also make an accurate selection of concurrent diseases such as kidney yin deficiency, kidney yang deficiency, yin deficiency, and yang deficiency according to the actual situation. After selecting, click OK, and the system can perform a secondary query based on the accurate selection of the target annotation.

[0110] According to the embodiments of the present disclosure, users can be intelligently guided to refine and supplement their expressions through target annotation, so as to accurately match the feedback content that best matches the user's situation and better meet the user's medical search needs.

[0111] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0112] Figure 6 A block diagram of an information query device according to an embodiment of the present disclosure is schematically shown.

[0113] like Figure 6 As shown, the information query device 600 may include an identification module 610 , a first determination module 620 , and a second determination module 630 .

[0114] The identification module 610 is used to identify the query information and obtain target entity information and associated entity information; wherein the associated entity information indicates entities associated with the target entity.

[0115] The first determination module 620 is used to determine the target text from the text information set based on the target entity information.

[0116] The second determination module 630 is used to determine a target annotation from the entity information set based on the associated entity information.

[0117] According to an embodiment of the present disclosure, the text information set includes a plurality of text information, wherein each of the plurality of text information includes entity information.

[0118] According to an embodiment of the present disclosure, the first determining module 620 may include a first calculating unit and a first determining unit.

[0119] The first calculation unit is used to calculate a first matching degree between the entity information in each text information and the target entity information.

[0120] The first determining unit is configured to determine the corresponding text information having a first matching degree greater than or equal to a first matching degree threshold as the target text.

[0121] According to an embodiment of the present disclosure, the entity information set includes multiple entity information.

[0122] According to an embodiment of the present disclosure, the second determining module 630 may include a second calculating unit and a second determining unit.

[0123] The second calculation unit is used to calculate a second matching degree between each entity information in the plurality of entity information and the associated entity information.

[0124] The second determining unit is used to determine the entity information with a second matching degree greater than or equal to a second matching degree threshold as a target annotation.

[0125] According to an embodiment of the present disclosure, the information query device 600 may further include a sorting module and a display module.

[0126] The sorting module is used to sort the target text and target annotation to obtain the sorting result.

[0127] The display module is used to display the target text and target annotation according to the sorting results, so as to perform a secondary query based on the target text or target annotation.

[0128] According to an embodiment of the present disclosure, the target text includes multiple; wherein the target annotation includes multiple.

[0129] According to an embodiment of the present disclosure, the sorting module may include a deduplication unit, a third calculation unit, a third determination unit, a fourth determination unit, and a sorting unit.

[0130] The deduplication unit is used to perform deduplication when it is determined that there are at least two identical target texts and / or at least two target annotations.

[0131] The third calculating unit is used to calculate a first number of identical target texts and / or a second number of identical target annotations.

[0132] The third determining unit is used to determine the weight of the target text based on the first number and the first matching degree.

[0133] The fourth determining unit is used to determine the weight of the target annotation based on the second number and the second matching degree.

[0134] The sorting unit is used to sort the target text and the target annotation by using the weight of the target text and the weight of the target annotation to obtain a sorting result.

[0135] According to an embodiment of the present disclosure, the recognition module may include a first recognition unit and a second recognition unit.

[0136] A first recognition unit, used to recognize the query information using a first named entity recognition model to obtain a target entity;

[0137] The first named entity recognition model is trained by using historical text information and a first label corresponding to the historical text information as training samples, wherein the first label is used to represent target entity information in the historical text information.

[0138] A second recognition unit, configured to perform named entity recognition on the query information using a second named entity recognition model to obtain associated entity information;

[0139] The second named entity recognition model is trained by using historical text information and a second label corresponding to the historical text information as training samples, wherein the second label is used to represent associated entity information in the historical text information.

[0140] According to an embodiment of the present disclosure, the information query device 600 may further include an acquisition module, a primary identification module, a pre-processing module and a obtaining module.

[0141] The acquisition module is used to obtain historical text information.

[0142] The primary recognition module is used to perform named entity recognition on historical text information using a second named entity recognition model to obtain primary entity information.

[0143] The preprocessing module is used to perform impurity filtering and normalization processing on the primary entities to obtain entity information.

[0144] The obtaining module is used to obtain an entity information set based on the entity information.

[0145] According to an embodiment of the present disclosure, the target entity information may include entities that are the same as or similar to entities in the query information. For example, if the entity in the query information is a disease entity, the target entity information may be one or more of disease entity information, symptom entity information, drug entity information, and treatment entity information.

[0146] According to an embodiment of the present disclosure, the associated entity information may include entities related to the entity in the query information. For example, if the entity in the query information is a disease entity, the associated entity information may be one or more of concurrent disease entity information, concurrent symptom entity information, age entity information, and gender entity information.

[0147] According to an embodiment of the present disclosure, the second determining module 630 may include a fifth determining unit, a fourth calculating unit, a sixth determining unit, and a seventh determining unit.

[0148] The fifth determining unit is configured to determine a category of each piece of entity information in the plurality of entity information in the entity information set.

[0149] The fourth calculation unit is used to calculate the second matching degree between each entity information and the associated entity information.

[0150] The sixth determining unit is used to determine the entity weight of each entity information in the entity information set based on the category and the second matching degree.

[0151] The seventh determination unit is used to determine an entity whose entity weight is greater than or equal to an entity weight threshold as a target annotation.

[0152] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0153] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method as described above.

[0154] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute the method as described above.

[0155] According to an embodiment of the present disclosure, a computer program product includes a computer program, and when the computer program is executed by a processor, the computer program implements the method as described above.

[0156] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0157] like Figure 7As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0158] A number of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0159] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as the information query method. For example, in some embodiments, the information query method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the information query method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the information query method in any other appropriate manner (e.g., by means of firmware).

[0160] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0161] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0162] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0163] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0164] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0165] A computer system may include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises through computer programs running on respective computers and having a client-server relationship to each other. The server may be a cloud server, a server in a distributed system, or a server combined with a blockchain.

[0166] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0167] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An information query method, comprising: Identify the query information to obtain target entity information and associated entity information; wherein the associated entity information indicates entities associated with the target entity; Based on the target entity information, determining a target text from a text information set; and Based on the associated entity information, a target annotation is determined from the entity information set, wherein the target annotation includes an entity associated with the entity in the query information for supplementary description, and the target annotation is displayed in the form of an entry or a link, so as to perform a secondary query according to the user's precise selection of the target annotation; Wherein, determining the target annotation from the entity information set based on the associated entity information includes: Determine a category of each entity information in the plurality of entity information in the entity information set; Calculating a second matching degree between each entity information and the associated entity information; Determining an entity weight of each entity information in the entity information set based on the category and the second matching degree; An entity whose entity weight is greater than or equal to an entity weight threshold is determined as the target annotation.

2. The method according to claim 1, wherein: The text information set includes a plurality of text information, wherein each text information in the plurality of text information includes entity information; The determining the target text from the text information set based on the target entity information includes: Calculating a first matching degree between the entity information in each text information and the target entity information; The corresponding text information whose first matching degree is greater than or equal to the first matching degree threshold is determined as the target text.

3. The method according to claim 2, further comprising: Sorting the target text and the target annotation to obtain a sorting result; The target text and the target annotation are displayed according to the sorting result, so as to perform a secondary query based on the target text or the target annotation.

4. The method according to claim 3, wherein: The target text includes multiple; wherein the target annotation includes multiple; The sorting of the target text and the target annotation to obtain the sorting result includes: In the case where it is determined that there are at least two identical target texts and / or at least two identical target annotations, performing deduplication; Calculating a first number of the same target texts and / or a second number of the same target annotations; Determining a weight of the target text based on the first number and the first matching degree; Determining a weight of the target annotation based on the second number and the second matching degree; The target text and the target annotation are sorted using the weight of the target text and the weight of the target annotation to obtain a sorting result.

5. The method according to claim 1, wherein: The identifying of the query information to obtain the target entity information and the associated entity information includes: Using the first named entity recognition model to recognize the query information, and obtain the target entity; The first named entity recognition model is obtained by training with historical text information and a first label corresponding to the historical text information as training samples, wherein the first label is used to represent target entity information in the historical text information; and Using the second named entity recognition model to perform named entity recognition on the query information to obtain related entity information; The second named entity recognition model is trained by using historical text information and a second label corresponding to the historical text information as training samples, wherein the second label is used to represent associated entity information in the historical text information.

6. The method according to claim 1, further comprising: Get historical text information; Using a second named entity recognition model to perform named entity recognition on the historical text information to obtain primary entity information; Performing impurity filtering and normalization processing on the primary entity to obtain the entity information; Based on the entity information, the entity information set is obtained.

7. The method according to claim 1, wherein: The target entity information includes at least one of the following: disease entity information, symptom entity information, drug entity information, and treatment entity information; The associated entity information includes at least one of the following: concurrent disease entity information, concurrent symptom entity information, age entity information, and gender entity information.

8. An information query device, comprising: An identification module, used to identify the query information and obtain target entity information and associated entity information; wherein the associated entity information indicates entities associated with the target entity; A first determination module is used to determine a target text from a text information set based on the target entity information; and A second determination module is used to determine a target annotation from the entity information set based on the associated entity information, wherein the target annotation includes an entity associated with the entity in the query information for supplementary description, and the target annotation is displayed in the form of an entry or a link so as to perform a secondary query according to a user's selection of the target annotation; Wherein, the second determining module includes: a fifth determining unit, configured to determine a category of each entity information in the plurality of entity information in the entity information set; a fourth calculation unit, configured to calculate a second matching degree between each entity information and the associated entity information; a sixth determining unit, configured to determine an entity weight of each entity information in the entity information set based on the category and the second matching degree; A seventh determining unit is used to determine an entity whose entity weight is greater than or equal to an entity weight threshold as the target annotation.

9. The device according to claim 8, wherein: The text information set includes a plurality of text information, wherein each text information in the plurality of text information includes entity information; The first determining module comprises: A first calculation unit, configured to calculate a first matching degree between the entity information in each text information and the target entity information; The first determining unit is configured to determine the corresponding text information having a first matching degree greater than or equal to a first matching degree threshold as the target text.

10. The apparatus according to claim 9, further comprising: A sorting module, used for sorting the target text and the target annotation to obtain a sorting result; A display module is used to display the target text and the target annotation according to the sorting result, so as to perform a secondary query based on the target text or the target annotation.

11. The device according to claim 10, wherein: The target text includes multiple; wherein the target annotation includes multiple; The sorting module comprises: a deduplication unit, configured to perform deduplication when it is determined that there are at least two identical target texts and / or at least two identical target annotations; A third calculation unit, configured to calculate a first number of the same target texts and / or a second number of the same target annotations; A third determining unit, configured to determine a weight of the target text based on the first number and the first matching degree; a fourth determining unit, configured to determine a weight of the target annotation based on the second number and the second matching degree; A sorting unit is used to sort the target text and the target annotation by using the weight of the target text and the weight of the target annotation to obtain a sorting result.

12. The device according to claim 8, wherein: The identification module comprises: A first recognition unit, used to recognize the query information using a first named entity recognition model to obtain a target entity; The first named entity recognition model is obtained by training with historical text information and a first label corresponding to the historical text information as training samples, wherein the first label is used to represent target entity information in the historical text information; and A second recognition unit, configured to perform named entity recognition on the query information using a second named entity recognition model to obtain associated entity information; The second named entity recognition model is trained by using historical text information and a second label corresponding to the historical text information as training samples, wherein the second label is used to represent associated entity information in the historical text information.

13. The apparatus according to claim 8, further comprising: Acquisition module, used to obtain historical text information; A primary recognition module, used to perform named entity recognition on the historical text information using a second named entity recognition model to obtain primary entity information; A preprocessing module, used for performing impurity filtering and normalization processing on the primary entity to obtain the entity information; The obtaining module is used to obtain the entity information set based on the entity information.

14. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

15. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

16. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images