Mail content dynamic retrieval method and device, electronic equipment, medium and program product

Abstract

The invention provides a dynamic retrieval method and device for mail content, electronic equipment, a storage medium and a program product, can be applied to the technical field of artificial intelligence and big data, and relates to application of a large model in a financial science and technology scene. The method comprises the following steps: acquiring a retrieval mode and a retrieval formula determined by a user; under the condition that the retrieval mode is advanced retrieval, performing first accurate retrieval in the user mail content according to the retrieval formula; if the retrieval result of the first accurate retrieval is null, a selection interface is provided, and the selection interface comprises relaxed retrieval conditions and semantic association options; if the selection operation of relaxing the retrieval condition option is received, performing fuzzy retrieval in the mail content by removing at least one of a plurality of limiting conditions; and if a selection operation on semantic association is received, performing semantic association on at least one of the plurality of limiting conditions based on a pre-constructed personal retrieval knowledge base of the user to obtain associative knowledge, and performing semantic retrieval according to the associative knowledge.

Description

Technical Field

[0001] This application relates to the fields of artificial intelligence and big data technology, and to the application of large models in fintech scenarios, specifically to a method, device, electronic device, medium, and program product for dynamic retrieval of email content. Background Technology

[0002] In today's corporate office environment, email systems have become a core medium for office collaboration and information retention due to their advantages such as traceable communication records, long-term content retention, and high security. As enterprises expand and their digitalization levels increase, email systems support numerous office scenarios, including approval processes, task collaboration, and internal announcements, resulting in a rapidly growing volume of historical email data accumulated by users.

[0003] Existing search methods suffer from low efficiency and poor user experience due to repeated trial and error after initial failures. On one hand, while keyword-based search is simple to use, it often returns multiple matches when processing massive amounts of historical data, requiring manual filtering and thus reducing efficiency. On the other hand, while multi-field combination search methods can theoretically achieve precise retrieval, their effectiveness depends entirely on the user's accurate memory of email metadata. When the user's memory is flawed, empty results are returned, leading to a poor user experience. Summary of the Invention

[0004] In view of the above problems, this application provides a method, apparatus, electronic device, medium and program product for dynamic retrieval of email content, which can solve the problems of low efficiency and low success rate of first-time retrieval of massive historical emails in the prior art.

[0005] According to a first aspect of this application, a dynamic retrieval method for email content is provided. The method includes: obtaining a user-defined retrieval mode and retrieval formula; the retrieval mode includes simple retrieval and advanced retrieval; the retrieval formula includes multiple limiting conditions; when the retrieval mode is advanced retrieval, performing a first precise retrieval within the user's email content based on the retrieval formula; if the first precise retrieval result is empty, providing the user with a selection interface, the selection interface including a broadened retrieval option and a semantic association option; if a selection operation for the broadened retrieval option is received, performing a fuzzy retrieval within the email content by removing at least one of the multiple limiting conditions; if a selection operation for the semantic association option is received, performing semantic association based on at least one of the multiple limiting conditions using a pre-built user's personal retrieval knowledge base to obtain associated knowledge, and performing a semantic retrieval within the email content based on the associated knowledge.

[0006] According to an embodiment of the present application, the method further comprises: when the search mode is simple search, performing a second accurate search in the mail content according to the search formula; if the result of the second accurate search is empty, performing word segmentation processing on the search formula to obtain a word segmentation result; and performing search in the mail content based on the word segmentation result.

[0007] According to an embodiment of the present application, the second accurate search comprises: determining a search type according to the search formula; determining at least one target search range for priority search in the mail content according to the search type; and performing search in the target search range according to the search formula.

[0008] According to an embodiment of the present application, the determination of the search type according to the search formula comprises: when the search formula contains time information, determining the search type as text search; when the search formula contains an email address feature symbol, determining the search type as sender / recipient search; and when the search formula does not contain time and email address feature symbols, determining the search type as keyword search.

[0009] According to an embodiment of the present application, the determination of the target search range for priority search in the mail content according to the search type comprises: when the search type is text search, determining the target search range as a text range; when the search type is sender / recipient search, determining the target search range as a sender field range or a recipient field range; and when the search type is keyword search, determining the target search range as a subject range and a text range, and the search priority of the subject range is higher than that of the text range.

[0010] According to an embodiment of the present application, the personal search knowledge base is constructed in the following manner: recording a plurality of historical search formulas of the user, constructing a first part knowledge base based on the plurality of historical search formulas; analyzing a plurality of historical mail contents of the user by using a large model, constructing a second part knowledge base based on the analysis result; and fusing the first part knowledge base and the second part knowledge base to form the personal search knowledge base; wherein the first part knowledge base comprises a replacement condition pair and a replacement weight of the replacement condition pair; and the second part knowledge base comprises an association condition pair and an association strength of the association condition pair.

[0011] According to an embodiment of the present application, the construction of the first part knowledge base based on the plurality of historical search formulas comprises: when there is only one pair of different limited conditions in the plurality of historical search formulas, taking the different limited conditions as a replacement condition pair; analyzing a replacement weight of the replacement condition pair; and storing the replacement condition pair and the replacement weight to the first part knowledge base.

[0012] According to an embodiment of the present application, the plurality of historical email contents of the user are analyzed by using the large model, and a second part of the knowledge base is constructed based on the analysis result, including: identifying, by using the large model, a plurality of limitation conditions with the same meaning, belonging to a subordinate relationship or belonging to a parallel relationship in the plurality of historical email contents, to form a pair of associated conditions; analyzing the association strength of the pair of associated conditions; and storing the pair of associated conditions and the association strength to the second part of the knowledge base.

[0013] According to an embodiment of the present application, after the semantic retrieval in the email content according to the association knowledge, the method further includes: recording the selection of the user on the retrieval result of the semantic retrieval; and updating the replacement weight and the association strength by using the selection.

[0014] The second aspect of the present application provides a dynamic retrieval device for email content, the device comprising: an acquisition module configured to acquire a retrieval mode and a retrieval formula determined by a user, the retrieval mode comprising simple retrieval and advanced retrieval, and the retrieval formula comprising a plurality of limitation conditions; an advanced retrieval module configured to, when the retrieval mode is advanced retrieval, perform first accurate retrieval in the email content of the user according to the retrieval formula; if the retrieval result of the first accurate retrieval is empty, providing a selection interface to the user, the selection interface comprising a relaxed retrieval condition option and a semantic association option; a condition relaxation module configured to, if a selection operation on the relaxed retrieval condition option is received, perform fuzzy retrieval in the email content by removing at least one limitation condition in the plurality of limitation conditions; and a semantic association module configured to, if a selection operation on the semantic association option is received, perform semantic association on at least one limitation condition in the plurality of limitation conditions based on a pre-constructed personal retrieval knowledge base of the user to obtain association knowledge, and perform semantic retrieval in the email content according to the association knowledge.

[0015] The third aspect of the present application provides an electronic device, comprising: one or more processors; a memory configured to store one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0016] The fourth aspect of the present application further provides a computer-readable storage medium having a computer program or instructions stored thereon, wherein the computer program or instructions are executed by a processor to implement the steps of the above method.

[0017] The fifth aspect of the present application further provides a computer program product comprising a computer program or instructions, wherein the computer program or instructions are executed by a processor to implement the steps of the above method. BRIEF DESCRIPTION OF DRAWINGS

[0018] The above and other objects, features and advantages of the present application will become more apparent from the following description of embodiments of the present application taken with reference to the accompanying drawings, in which:

[0019] Figure 1 An application scenario diagram of the dynamic retrieval method, device, equipment, medium and program product of the mail content according to the embodiments of the present application is schematically shown;

[0020] Figure 2 One of the flowcharts of the dynamic retrieval method of the mail content according to the embodiments of the present application is schematically shown;

[0021] Figure 3 The second of the flowcharts of the dynamic retrieval method of the mail content according to the embodiments of the present application is schematically shown;

[0022] Figure 4 The flowchart of the second accurate retrieval in the simple retrieval according to the embodiments of the present application is schematically shown;

[0023] Figure 5 The flowchart of the personal retrieval knowledge base construction in the dynamic retrieval method of the mail content according to the embodiments of the present application is schematically shown;

[0024] Figure 6 The structural block diagram of the dynamic retrieval device of the mail content according to the embodiments of the present application is schematically shown; and

[0025] Figure 7 The block diagram of the electronic equipment suitable for implementing the dynamic retrieval method of the mail content according to the embodiments of the present application is schematically shown. DETAILED DESCRIPTION

[0026] Hereinafter, the embodiments of the present application will be described with reference to the accompanying drawings. However, it is to be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present application. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to one skilled in the art that one or more embodiments can be practiced without these specific details. In other instances, well-known structures and techniques have been omitted in order to avoid obscuring the concepts of the present application.

[0027] The terms used herein are merely used to describe specific embodiments and are not intended to limit the present application. The terms "include", "comprise" and the like used herein indicate the presence of the described features, steps, operations and / or components, but do not exclude the presence or addition of one or more other features, steps, operations or components.

[0028] All terms used herein (including technical and scientific terms) have meanings commonly understood by one of ordinary skill in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having meanings consistent with the context of the specification, and should not be interpreted in an idealized or overly formal manner.

[0029] In the case of using expressions similar to "at least one of A, B, and C, etc.", it is generally intended to include any of A, B, and C alone, a combination of at least two of A, B, and C, etc.

[0030] In the technical solutions of the present application, the user information (including but not limited to user personal information, user image information, user equipment information, such as location information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved are information and data authorized by the user or authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of related data comply with relevant laws, regulations and standards, necessary security measures are taken, do not violate public order and good customs, and provide corresponding operation portal for user to choose authorization or refusal.

[0031] In the scenario of using personal information for automated decision-making, the method, device and system provided by the embodiments of the present application all provide corresponding operation portal for the user to choose to agree or refuse the automated decision-making result; if the user chooses to refuse, the expert decision-making process is entered. The expression "automated decision-making" here refers to the activity of automatically analyzing, evaluating the behavior habits, interests and hobbies or economic, health, credit status of individuals, etc. by computer programs, and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by personnel who are engaged in a certain field of work, have special experience, knowledge and skills, and reach a certain professional level.

[0032] Figure 1 The application scenario of the dynamic retrieval method, device, equipment, medium and program product of the mail content according to the embodiments of the present application is schematically shown.

[0033] As Figure 1 shown, the application scenario 100 according to the embodiments can include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104 and a server 105. The network 104 is used as a medium to provide a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0034] The user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be installed with various communication client applications, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0035] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smartphones, tablet computers, laptop computers, desktop computers, etc.

[0036] In some embodiments, the first terminal device 101, the second terminal device 102, and the third terminal device 103 run email clients or web-based email systems accessible through browsers.

[0037] The server 105 can be a server providing various services, such as a background management server supporting websites browsed by the user using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (only as an example). The background management server can analyze and process received user requests and other data, and feed back the processing results to the terminal device.

[0038] It should be noted that the dynamic retrieval method of the email content provided by the embodiments of the present application can generally be executed by the server 105. Correspondingly, the dynamic retrieval device of the email content provided by the embodiments of the present application can generally be arranged in the server 105. The dynamic retrieval method of the email content provided by the embodiments of the present application can also be executed by the first terminal device 101, the second terminal device 102, or the third terminal device 103. Correspondingly, the dynamic retrieval device of the email content provided by the embodiments of the present application can also be arranged in the first terminal device 101, the second terminal device 102, or the third terminal device 103.

[0039] It should be understood that Figure 1 The number of terminal devices, networks, and servers in the above description is only illustrative. According to the needs of implementation, there can be any number of terminal devices, networks, and servers.

[0040] It should be noted that the present application relates to the field of artificial intelligence and big data technology, and specifically relates to the application of natural language processing and intelligent information retrieval technology in the financial technology scene. For example, in the daily operation of financial institutions, the mail system carries a large amount of important information such as transaction confirmation letters, risk warning notifications, compliance review opinions, and customer communication records. By applying the dynamic retrieval method of mail content proposed in the present application, the contextual differences of financial practitioners using professional terms such as "extension", "continuation", and "delay" can be intelligently understood, and associated concepts can be automatically associated, so that in the scenes of risk control review and customer service tracing, key business information can be quickly and accurately located from a large number of historical emails, significantly improving the efficiency and accuracy of financial business queries, while meeting the high standard requirements of the financial industry for information traceability.

[0041] It should be noted that the dynamic retrieval method of mail content and the like in the embodiments of the present application can be widely applied in the field of financial technology and other related technologies. In particular, in the financial technology scene, the mail system carries a large amount of key financial business data, including but not limited to transaction confirmation, risk warning, compliance review, customer service records, and other core business processes.

[0042] The following will be based on Figure 1 The described scene, through Figures 2-7 The dynamic retrieval method of mail content of the disclosed embodiments will be described in detail.

[0043] Figure 2 An example of a flowchart of a dynamic retrieval method of mail content according to an embodiment of the present application is schematically shown.

[0044] As Figure 2 shown, the dynamic retrieval method of mail content of this embodiment includes operation S210~operation S240.

[0045] In operation S210, the retrieval mode and the retrieval formula determined by the user are obtained; the retrieval mode includes simple retrieval and advanced retrieval; the retrieval formula includes a plurality of limiting conditions.

[0046] In the embodiments of the present application, for the mail content of the user, the user can select the retrieval mode of the mail content retrieval and input the retrieval formula through the mail client or the browser mailbox interface. Among them, the retrieval mode includes simple retrieval and advanced retrieval; the retrieval formula can include one or more limiting conditions, such as keywords, time, sender, recipient, email address features, etc.

[0047] In the embodiments of the present application, the simple search can be represented as a search input box, in which the user can input any keyword or phrase; the advanced search can provide multiple input fields or drop-down menus for the user to specify multiple limiting conditions such as sender, recipient, subject, content, time range, whether there are attachments, specific tags, etc.

[0048] In the embodiments of the present application, if the search mode is advanced search, the user inputs a search formula in the search box in the simple search interface, which can be a string; if the search mode is advanced search, the user inputs limiting conditions in multiple specified condition boxes through the advanced search interface, thereby forming a search formula.

[0049] For example, in the case of advanced search, the user inputs “xxx@xxx.com” in the “sender” box, “Q1 budget” in the “subject” box, and “2025” in the “time” box, and checks the “with attachments” option, and these limiting conditions collectively constitute a structured search formula.

[0050] In operation S220, in the case of advanced search, a first accurate search is performed in the user's mail content according to the search formula; if the search result of the first accurate search is empty, a selection interface is provided to the user, including a relaxed search condition option and a semantic association option.

[0051] In the embodiments of the present application, according to the search formula input by the user in the advanced search mode, a first accurate search is performed in the user's mail content, which is a strict match, i.e., only the mail content that meets all the limiting conditions contained in the search formula is returned.

[0052] In the embodiments of the present application, if no mail content that meets the search formula is searched, i.e., the search result of the first accurate search is empty, a selection interface is popped up to the user operation interface, prompting “the search result is empty, you can:”, and providing “relaxed search condition” and “semantic association” options.

[0053] In operation S230, if a selection operation on the relaxed search condition option is received, a fuzzy search is performed in the mail content by removing at least one of the multiple limiting conditions.

[0054] In the embodiments of the present application, if the user selects the “relaxed search condition” option, the system performs a fuzzy search in the mail content by removing one or more limiting conditions in the search formula. For example, the “with attachments” condition checked by the user can be removed first, and the remaining limiting conditions are used for searching; if the search result is still empty at this time, the time range is further relaxed (e.g., from “2023” to “2022 and 2023”).

[0055] In operation S240, if a selection operation for semantic association options is received, semantic association is performed on at least one of the multiple limiting conditions based on the user's pre-built personal retrieval knowledge base to obtain associated knowledge, and semantic retrieval is performed within the email content based on the associated knowledge.

[0056] In this embodiment of the application, if the user selects the "semantic association" option, semantic association is performed based on the user's pre-built personal retrieval knowledge base and at least one limiting condition in the search query entered by the user to obtain associated knowledge, and the user's email content is searched based on the associated knowledge.

[0057] For example, if the user's input search query contains "Q1 budget", and the personal search knowledge base stores semantic associations between "Q1" and "first quarter" and "budget" and "expense plan", then new search conditions (such as the subject or body containing "first quarter" or "expense plan") are generated based on these semantic associations, which is the associative knowledge; and the search is performed in the email content based on this associative knowledge.

[0058] Through the embodiments of this application, in the advanced search mode, when no results are found on the first search, the user is proactively offered two different search strategies: a relaxed search criteria option and semantic association. For the relaxed search criteria option, the search is performed after removing at least one of the multiple limiting conditions from the search expression. For the semantic association option, the search is performed after semantically associating at least one of the multiple limiting conditions from the search expression. In this way, advanced search is transformed from mechanical execution to intelligent collaboration. When a user's search operation fails due to overly strict limiting conditions in the input search expression or inaccurate wording, it does not passively return empty results but proactively provides two search strategies. This not only improves the user experience after the first failed search and avoids the user getting bogged down in repeated trial and error, but also enhances search capabilities and efficiency by introducing semantic association based on the user's personal search knowledge base.

[0059] Figure 3 The flowchart illustrating the second method for dynamically retrieving email content according to an embodiment of this application is shown in the illustration.

[0060] like Figure 3 As shown, the dynamic retrieval method for email content in this embodiment further includes: performing operations S320 to S330 after the above operation S210.

[0061] When operating the S320, in the simple search mode, a second precise search is performed within the email content based on the search query.

[0062] In this embodiment of the application, when the search mode is simple search, the user enters a search query in the search box of the simple search interface, and a second precise search is performed on the user's email content based on the search query. For example, the search query entered in the search box can be "11:20 Zhang Sanzhoubao".

[0063] In operation S330, if the result of the second precise search is empty, the search query is segmented to obtain the segmentation result; based on the segmentation result, a search is performed within the email content.

[0064] For example, if the second precise search in the user's email content based on the search query "11:20 Zhang San's Weekly Report" yields no results, then the search query "11:20 Zhang San's Weekly Report" is segmented into words to obtain word segmentation results such as "11:20", "Zhang San", and "weekly report". These word segmentation results are then used to perform fuzzy searches within the email content.

[0065] Figure 4 A flowchart illustrating a second precise search in a simple search according to an embodiment of this application is shown.

[0066] like Figure 4 As shown, in some embodiments, the second precise retrieval in operation S320 may further include operations S410 to S430.

[0067] In operation S410, the search type is determined based on the search query.

[0068] In the embodiments of this application, when the search query contains time information, the search type is determined to be a text search; when the search query contains email address characteristics, the search type is determined to be a sender / recipient search; when the search query does not contain time or email address characteristics, the search type is determined to be a keyword search.

[0069] For example, if the user inputs the search query "11:20 Zhang Sanzhoubao", regular expression matching can be used to identify that "11:20" is time information, thus determining the search type as text search.

[0070] For example, when a user enters the search term "@Zhang San", the search type can be determined to be a sender / recipient search by recognizing the email address feature "@" in the search term.

[0071] For example, if a user enters the search term "Zhang San's Weekly Report", the search type is determined to be a keyword search because no time information or email address feature is recognized.

[0072] In operation S420, according to the search type, at least one target search range of the priority search is determined within the mail content.

[0073] In the embodiment of the present application, in the case that the search type is the body search, the target search range is determined as the body range; in the case that the search type is the sender / recipient search, the target search range is determined as the sender field range or the recipient field range; in the case that the search type is the keyword search, the target search range is determined as the subject range and the body range, and the search priority of the subject range is higher than that of the body range.

[0074] Exemplarily, when the search type of the search expression "11:20 Zhang San's Weekly" input by the user is determined as the body search, the target search range of the priority search is determined as the body range of the mail.

[0075] Exemplarily, when the search type of the search expression "Zhang San's Weekly" input by the user is determined as the keyword search, the target search range of the priority search is determined as the subject range and the body range of the mail, and the search priority of the subject range is higher than that of the body range.

[0076] In operation S430, according to the search expression, search is performed in the target search range.

[0077] Exemplarily, when the search expression input by the user is "11:20 Zhang San's Weekly", the regular expression matching can be used to identify that "11:20" is time information, and the search type is determined as the body search, so that the target search range of the priority search is determined as the body range of the mail; then, in the body range of the mail, the mail content containing the complete sequence of the search expression "11:20 Zhang San's Weekly" is searched, to implement the second accurate search; if the search result of the second accurate search is empty, the search expression is processed by word segmentation, to obtain the word segmentation results such as "11:20", "Zhang San", "Weekly", and then the word segmentation results are used to search in the mail body.

[0078] Figure 5 A flowchart of the construction of the personal search knowledge base in the dynamic search method of the mail content according to the embodiment of the present application is schematically shown.

[0079] As shown in Figure 5 In the embodiment, the personal search knowledge base of the user can be constructed in advance according to the following operations S510-S530.

[0080] In operation S510, a plurality of historical search expressions of the user are recorded, and a first part of the knowledge base is constructed based on the plurality of historical search expressions.

[0081] In the embodiment of the present application, the data source of the first part of the knowledge base is a plurality of historical search expressions input by the user in the historical search process. For example, the string input by the user in the search box in the simple search mode and the search expression composed of a plurality of limiting conditions input by the user in the plurality of condition boxes in the advanced search mode. By analyzing these recorded historical search expressions, the user's personalized search habits and word preferences can be identified, thereby constructing the first part of the user's personal search knowledge base, which can reflect the user's explicit search logic.

[0082] In the embodiment of the present application, when there is only one pair of different limiting conditions in the plurality of historical search expressions, the pair of different limiting conditions is taken as a replacement condition pair; the replacement weight of the replacement condition pair is analyzed; and the replacement condition pair and the replacement weight are stored in the first part of the knowledge base.

[0083] For example, in the case where there are two search expressions "11:20 Zhang San weekly meeting" and "11:20 Zhang San meeting" in the historical search expressions, "weekly meeting" and "meeting" can be taken as a replacement condition pair; the replacement weight is analyzed based on the search success of the replacement condition pair; and then the replacement condition pair "weekly meeting" and "meeting" and the replacement weight are stored in the first part of the knowledge base.

[0084] In operation S520, the plurality of historical email contents of the user are analyzed by using the large model, and the second part of the knowledge base is constructed based on the analysis result.

[0085] In the embodiment of the present application, the plurality of historical email contents of the user are analyzed by using the large model, and the second part of the knowledge base is constructed based on the analysis result.

[0086] In the embodiment of the present application, the plurality of historical email contents of the user are analyzed by using the large model, and the second part of the knowledge base is constructed based on the analysis result.

[0087] Exemplarily, in the case that "Please attend the weekly meeting, the monthly meeting and the temporary meeting" appears in the mail body, it can be recognized that "weekly meeting", "monthly meeting" and "temporary meeting" are in parallel relation, and then they can be regarded as two pairs of associated condition pairs respectively, and the association strength can be calculated according to the co-occurrence frequency.

[0088] In operation S530, the first part of the knowledge base and the second part of the knowledge base are fused to form the personal retrieval knowledge base.

[0089] Further, based on the pre-constructed personal retrieval knowledge base of the user, the semantic association is performed on at least one of the multiple limitation conditions in the retrieval formula to obtain the associated knowledge, and after the semantic retrieval in the mail content according to the associated knowledge, the following steps are further included: recording the selection of the user on the retrieval result of the semantic retrieval; and updating the replacement weight of the replacement condition pair and the association strength of the associated condition pair in the personal retrieval knowledge base of the user by using the selection.

[0090] Based on the above-mentioned dynamic retrieval method of the mail content, the application further provides a dynamic retrieval device of the mail content. The following will be combined with the Figure 6 The device will be described in detail.

[0091] Figure 6 The structure block diagram of the dynamic retrieval device of the mail content according to the embodiment of the application is schematically shown.

[0092] As Figure 6 shown, the dynamic retrieval device 600 of the mail content of the embodiment includes an acquisition module 610, a high-level retrieval module 620, a condition relaxation module 630 and a semantic association module 640.

[0093] The acquisition module 610 is used for acquiring the retrieval mode and the retrieval formula determined by the user, the retrieval mode includes simple retrieval and high-level retrieval, and the retrieval formula includes multiple limitation conditions. In an embodiment, the acquisition module 610 can be used for performing the operation S210 described above, and here will not be repeated.

[0094] The high-level retrieval module 620 is used for performing the first accurate retrieval in the mail content of the user according to the retrieval formula in the case that the retrieval mode is high-level retrieval, and if the retrieval result of the first accurate retrieval is empty, a selection interface is provided to the user, the selection interface includes a relaxation retrieval condition option and a semantic association option. In an embodiment, the high-level retrieval module 620 can be used for performing the operation S220 described above, and here will not be repeated.

[0095] The condition relaxing module 630 is configured to perform the first fuzzy search in the mail content by removing at least one of the multiple defined conditions if a selection operation on the relaxing search condition option is received. In an embodiment, the condition relaxing module 630 can be configured to perform the operation S230 described above, and thus repeated details are not provided herein.

[0096] The semantic association module 630 is configured to perform semantic association on at least one of the multiple defined conditions based on the pre-constructed personal search knowledge base of the user to obtain associated knowledge, and perform semantic search in the mail content according to the associated knowledge if a selection operation on the semantic association option is received. In an embodiment, the semantic association module 630 can be configured to perform the operation S240 described above, and thus repeated details are not provided herein.

[0097] According to an embodiment of the present application, any of the acquisition module 610, the advanced search module 620, the condition relaxing module 630 and the semantic association module 640 can be combined in one module, or any of the modules can be split into multiple modules. Alternatively, at least part of the function of one or more of the modules can be combined with at least part of the function of other modules, and implemented in one module. According to an embodiment of the present application, at least one of the acquisition module 610, the advanced search module 620, the condition relaxing module 630 and the semantic association module 640 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on board, a system in package, an application specific integrated circuit (ASIC), or any other reasonable manner of integrating or packaging a circuit, etc. or implemented by hardware or firmware, or implemented in any one of software, hardware and firmware or in a proper combination of any of them. Alternatively, at least one of the acquisition module 610, the advanced search module 620, the condition relaxing module 630 and the semantic association module 640 can be at least partially implemented as a computer program module which can perform the corresponding function when the computer program module is run.

[0098] Figure 7 A block diagram of an electronic device suitable for implementing the method of dynamically searching mail content according to an embodiment of the present application is schematically shown.

[0099] As Figure 7As shown, the electronic device 700 according to the embodiments of the present application includes a processor 701 which can perform various appropriate actions and processes according to a program stored in a read only memory (ROM) 702 or a program loaded into a random access memory (RAM) 703 from a storage section 708. The processor 701 can include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor, and / or a related chipset, and / or a dedicated microprocessor (e.g., an application specific integrated circuit (ASIC)), and so on. The processor 701 can also include an on-board memory for cache use. The processor 701 can include a single processing unit or multiple processing units for executing different actions of the method processes according to the embodiments of the present application.

[0100] In the RAM 703, various programs and data required for the operation of the electronic device 700 are stored. The processor 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. The processor 701 performs various operations of the method processes according to the embodiments of the present application by executing the programs in the ROM 702 and / or the RAM 703. Note that the programs can also be stored in one or more memories other than the ROM 702 and the RAM 703. The processor 701 can also perform various operations of the method processes according to the embodiments of the present application by executing the programs stored in the one or more memories.

[0101] According to the embodiments of the present application, the electronic device 700 can further include an input / output (I / O) interface 705 which is also connected to the bus 704. The electronic device 700 can further include one or more of the following components connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as necessary. A removable recording medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 710 as necessary, so that a computer program read therefrom is installed into the storage section 708 as necessary.

[0102] The present application also provides a computer readable storage medium, which can be included in the device / apparatus / system described in the above embodiments; or can exist separately without being assembled into the device / apparatus / system. The above computer readable storage medium carries one or more programs, which when executed, implement the method according to the embodiments of the present application.

[0103] According to an embodiment of the present application, the computer readable storage medium can be a non-transitory computer readable storage medium, for example, can include but not limited to: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this application, a computer readable storage medium can be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present application, the computer readable storage medium can include one or more of the above-described ROM 702 and / or RAM 703 and / or memories other than the ROM 702 and the RAM 703.

[0104] Embodiments of the present application also include a computer program product, which includes a computer program containing program codes for executing the methods shown in the flowcharts. When the computer program product is run in a computer system, the program codes are used to make the computer system implement the dynamic retrieval method of mail content provided by the embodiments of the present application.

[0105] The above-described functions defined in the system / device / apparatus of the embodiments of the present application are performed when the computer program is executed by the processor 701. According to an embodiment of the present application, the above-described system, device, module, unit, etc. can be implemented by computer program modules.

[0106] In one embodiment, the computer program can rely on tangible storage media such as optical storage media, magnetic storage media, etc. In another embodiment, the computer program can also be transmitted, distributed, and downloaded in the form of signals on network media. The computer program is downloaded and installed through the communication part 709, and / or installed from the detachable medium 711. The program codes contained in the computer program can be transmitted by any appropriate network media, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

[0107] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the detachable medium 711. When the computer program is executed by the processor 701, the above-described functions defined in the system of the embodiments of the present application are performed. According to an embodiment of the present application, the above-described system, device, apparatus, module, unit, etc. can be implemented by computer program modules.

[0108] According to embodiments of the present application, program code for implementing the computer programs provided by embodiments of the present application can be written in any combination of one or more programming languages, and can be implemented in a high-level procedural and / or object-oriented programming language, and / or in assembly / machine language. Programming languages include, but are not limited to, Java, C++, python, "C", or the like. Program code can execute entirely on a user's computing device, partly on the user's device, as a stand-alone software package, partly on a remote computing device, or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider.

[0109] The computer program instructions can also be loaded onto a computer or other programmable information processing apparatus to cause a series of operations to be performed on the computer or other programmable information processing apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable information processing apparatus implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0110] Those skilled in the art will appreciate that features recited in the various embodiments of the present application can be combined and / or integrated in various combinations, even if such combinations have not been explicitly recited in the present application. In particular, the features recited in the various embodiments of the present application can be combined and / or integrated in various combinations, without departing from the spirit and teachings of the present application. All such combinations are within the scope of the present application.

Claims

1. A method for dynamic retrieval of email content, characterized in that, The method includes: Obtain the user-defined search mode and search formula, wherein the search mode includes simple search and advanced search; and the search formula includes multiple limiting conditions. When the search mode is the advanced search, a first precise search is performed on the user's email content according to the search formula; if the search result of the first precise search is empty, a selection interface is provided to the user, the selection interface including the option to relax the search conditions and the semantic association option; If a selection operation for the relaxed search criteria option is received, a fuzzy search is performed within the email content by removing at least one of the multiple limiting conditions; If a selection operation for the semantic association option is received, then based on the user's pre-built personal retrieval knowledge base, semantic association is performed on at least one of the multiple limiting conditions to obtain associated knowledge, and semantic retrieval is performed within the email content based on the associated knowledge.

2. The dynamic retrieval method for email content according to claim 1, characterized in that, The method further includes: When the search mode is the simple search, a second precise search is performed within the email content according to the search formula. If the result of the second precise search is empty, then the search expression is segmented to obtain the segmentation result; and the search is performed within the email content based on the segmentation result.

3. The dynamic retrieval method for email content according to claim 2, characterized in that, The second precise retrieval includes: Determine the search type based on the search query; Based on the search type, at least one priority search target scope is determined within the email content; Within the target search scope, a search is performed according to the search query.

4. The dynamic retrieval method for email content according to claim 3, characterized in that, Determining the search type based on the search query includes: If the search query contains time information, the search type is determined to be a text search. If the search query contains email address identifiers, the search type is determined to be a sender / recipient search. If the search query does not contain time or email address characteristics, the search type is determined to be a keyword search.

5. The dynamic retrieval method for email content according to claim 4, characterized in that, The step of determining at least one priority search target scope within the email content based on the search type includes: When the search type is the text search, the target search scope is determined to be the text scope; If the search type is the sender / recipient search, then the target search range is determined to be either the sender field range or the recipient field range. When the search type is the keyword search, the target search scope is determined to be the topic scope and the text scope, and the search priority of the topic scope is higher than that of the text scope.

6. The dynamic retrieval method for email content according to claim 1, characterized in that, The personal retrieval knowledge base is constructed in the following manner: Record multiple historical search queries of the user, and construct a first part of the knowledge base based on the multiple historical search queries; The large model is used to analyze the content of multiple historical emails of the user, and the second part of the knowledge base is constructed based on the analysis results; The first part of the knowledge base and the second part of the knowledge base are merged to form the personal retrieval knowledge base; The first part of the knowledge base includes replacement condition pairs and their replacement weights; the second part of the knowledge base includes association condition pairs and their association strengths.

7. The dynamic retrieval method for email content according to claim 6, characterized in that, The construction of the first part of the knowledge base based on multiple historical search queries includes: When there is only one pair of different limiting conditions among multiple historical search terms, the different limiting conditions are used as the replacement condition pair; Analyze the replacement weights of the replacement condition pairs; The replacement condition pairs and the replacement weights are stored in the first part of the knowledge base.

8. The dynamic retrieval method for email content according to claim 6, characterized in that, The process involves analyzing multiple historical emails of the user using a large model, and constructing a second knowledge base based on the analysis results, including: The large model is used to identify multiple limiting conditions in the content of the historical emails that have the same meaning, belong to a subordinate relationship, or belong to a parallel relationship, and form the associated condition pairs; Analyze the association strength of the association condition pairs; The association condition pairs and the association strength are stored in the second part of the knowledge base.

9. The dynamic retrieval method for email content according to claim 6, characterized in that, After performing semantic retrieval within the email content based on the associative knowledge, the method further includes: Record the user's selection of search results for the semantic search; The replacement weight and the association strength are updated based on the selection criteria.

10. A dynamic retrieval device for email content, characterized in that, The device includes: The acquisition module is used to acquire the search mode and search formula determined by the user. The search mode includes simple search and advanced search; the search formula includes multiple limiting conditions. An advanced search module is used to perform a first precise search on the user's email content according to the search formula when the search mode is the advanced search; if the search result of the first precise search is empty, a selection interface is provided to the user, the selection interface including a relaxation of search conditions option and a semantic association option; The condition relaxation module is used to perform a first fuzzy search within the email content by removing at least one of the multiple limiting conditions if a selection operation for the relaxed search condition option is received. The semantic association module is used to, upon receiving a selection operation for the semantic association option, perform semantic association on at least one of the multiple limiting conditions based on the user's pre-built personal retrieval knowledge base, obtain associated knowledge, and perform semantic retrieval within the email content based on the associated knowledge.

11. An electronic device, comprising: One or more processors; Memory, used to store one or more computer programs. The characteristic feature is that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 9.

13. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 9.

Images