Information inquiry method, device, electronic apparatus, storage medium and program
The information inquiry method leverages large-scale language models to generate input parameters directly for query interfaces, addressing complexity and service failures, thereby enhancing query efficiency and stability in digital offices.
Patent Information
- Application Number
- JP2024099632
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-03-13
- Filing Date
- 2024-06-20
- Publication Date
- 2024-11-19
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In digitalized office environments, information inquiries face challenges due to increased traffic and complexity, leading to reduced processing speed and potential interruptions from network abnormalities or proxy service failures.
An information inquiry method utilizing large-scale language models to directly generate input parameters for query interfaces, reducing dependence on message queues and proxy services by processing data format text to obtain target parameters, and employing a fallback strategy to ensure accurate information retrieval.
Enhances information query efficiency by minimizing reliance on message queues and proxy services, improving processing speed and stability through accurate parameter generation and fallback strategies.
Smart Images

Figure 2024161346000001_ABST
Abstract
Description
[Technical field]
[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to the technical fields of large-scale language models, information processing, smart offices, etc., and in particular to information query methods, devices, electronic devices, storage media, and programs. [Background technology]
[0002] With the wide application of information technology, artificial intelligence technology, and natural language processing technology based on large-scale language models in various fields, the digital office mode has become widespread in all aspects of the work of an enterprise's daily management and operation.
[0003] In the digitalized office world, as traffic increases, the flow of information inquiries and processing gradually becomes more complex, and the amount of information to be processed also increases. Therefore, a fast and efficient information inquiry method is required to reduce the impact of information inquiries on the processing speed of other processes. Summary of the Invention
[0004] The present disclosure provides an information query method, a device, an electronic device, a storage medium, and a program.
[0005] According to one aspect of the present disclosure, an information query method is provided, which includes: in response to a received information query request from a target object, obtaining a period to be queried, a number of items to be queried, and a target identifier corresponding to the information query request; processing the period to be queried, the number of items to be queried, the target identifier, and a predetermined parameter format text to obtain target parameters representing input parameters of a query interface of an information query system; and obtaining target information from the information query system by invoking the query interface based on the target parameters.
[0006] According to another aspect of the present disclosure, an information query device is provided, including a first acquisition module, a processing module, and a query module. The first acquisition module acquires a period to be queried, a number of items to be queried, and a target identifier corresponding to the information query request in response to a received information query request from a target object. The processing module processes the period to be queried, the number of items to be queried, the identifier of the target object, and a predetermined parameter format text to acquire target parameters representing input parameters of a query interface of an information query system. The query module acquires target information from the information query system by calling the query interface based on the target parameters.
[0007] According to another aspect of the present disclosure, there is provided an electronic device including at least one processor and a memory communicatively connected to the at least one processor, the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to cause the at least one processor to perform the above-mentioned method.
[0008] According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the above-described method.
[0009] According to another aspect of the present disclosure, there is provided a computer program product which, when executed by a processor, implements the above method.
[0010] It should be understood that the subject matter described in this section is not intended to identify key or important features of the embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the disclosure will be readily apparent from the following specification. [Brief description of the drawings]
[0011] The drawings are provided for a better understanding of the invention and are not intended to limit the disclosure.
[0012] [Figure 1] FIG. 1 illustrates a schematic diagram of an exemplary system architecture to which the information query method and apparatus according to the embodiments of the present disclosure can be applied. [Diagram 2] FIG. 2 illustrates a flowchart of an information query method according to an embodiment of the present disclosure. [Diagram 3] FIG. 3 illustrates a schematic diagram of information processing and storage flow according to an embodiment of the present disclosure. [Figure 4] FIG. 4 illustrates a schematic diagram of an information query method according to an embodiment of the present disclosure. [Diagram 5] FIG. 5 illustrates a schematic diagram of an information query method according to another embodiment of the present disclosure. [Figure 6] FIG. 6 is a schematic block diagram of an information inquiry device according to an embodiment of the present disclosure. [Figure 7] FIG. 7 is a schematic block diagram of an electronic device suitable for implementing an information query method according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0013] Hereinafter, exemplary embodiments of the present disclosure will be described with reference to the drawings, and various details of the embodiments of the present disclosure will be included for ease of understanding, which are merely illustrative. Therefore, it should be understood that those skilled in the art can make various changes and modifications to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for clarity and conciseness, the following description will omit the description of known functions and structures.
[0014] In the digital office model, current information query is usually realized based on the distributed message queue Kafka. However, if a network abnormality occurs and the message queue is clogged or there are no messages to be consumed in the message queue, the information query service will be interrupted, affecting the normal operation of subsequent processes.
[0015] In addition, the information query in the related example can call the information query system based on a multi-proxy service, and if an abnormality occurs in any of the proxy services, the information query service is interrupted.
[0016] In view of this, an embodiment of the present disclosure provides an information query method, which processes the period to be queried, the number of items to be queried, and the object identifier of the target object based on a predetermined parameter format text, obtains target parameters for calling up the query interface of an information query system, makes full use of the natural language processing capability using a large-scale language model, does not need to perform multi-proxy services, directly generates parameters that can be input into the query interface, and calls the query interface to perform information query, reduces the dependency of information query flow on message queues and proxy services, and improves the efficiency of information query.
[0017] FIG. 1 illustrates a schematic diagram of an exemplary system architecture to which the information query method and apparatus according to the embodiments of the present disclosure can be applied.
[0018] In order for those skilled in the art to understand the technical content of the present disclosure, Fig. 1 is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, and does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenes. For example, in another embodiment, an exemplary system architecture to which the information query method and device can be applied may include a terminal device, but the terminal device does not need to interact with a server and can realize the information query method and device according to the embodiments of the present disclosure.
[0019] As shown in FIG. 1, the system architecture 100 according to the embodiment may include a client 110, an information query system 120, and a large model platform 130.
[0020] The user can select an information file that needs to be inquired on the information management page 111 of the client 110, for example, by selecting "select inquire / all inquire" 112.
[0021] The information inquiry system 120 may be configured to process historical download information with the client 110 to inquire of the client.
[0022] For example, in the application of form information, there are multiple forms of different types and formats for different orders and different customers, and the variety of forms brings certain difficulties to information inquiries. Therefore, in order to improve the efficiency of information inquiries, different types of form contents can be processed and stored collectively.
[0023] In an embodiment of the present disclosure, the information inquiry system 120 establishes a processing task upon receiving an information processing request sent from the client 110, and at this time, the state of the processing task is the initial state 1201. Then, the processing task is executed, and information is filled to generate an Excel file 121. For example, an Excel file can be generated by filling the content of the form information in an image format with information. If the processing task is executed successfully, an Excel file 1202 is generated. If the processing task fails to be executed, it goes back and retries, and if it still fails after three retries, the state of the processing task is task failed 1204. If the state of the processing task exceeds a predetermined time limit, and all states within the predetermined time limit are task failed 1204, the state of the processing task is task expired 1205.
[0024] After the processing task is successfully executed, a file transfer task is executed, and the generated Excel file is uploaded to the cloud 122, and the Excel file is stored in the cloud 123. If the file transfer task is successfully executed, the task status at this time is Upload Success 1203. If the file transfer task fails to be executed, it goes back and retries, and if it still fails after the retry, the file transfer task status at this time is Task Failed 1204.
[0025] The large scale model platform 130 receives a query request from the client 110, inputs the query request into the large scale language model, performs large scale model recognition 131, and outputs target parameters. The target parameters are matched with the query request through parameter analysis and validation 132.
[0026] If the target parameters match the query request, it indicates that the recognition result of the large-scale language model is accurate, the output target parameters match the parameters in the query request, and the parameters 133 in the query request can be used to call the information query plug-in 135 to query the target information from the information query system 120.
[0027] If the target parameters do not match the query request, it indicates that the recognition result of the large-scale language model is incorrect, and the output target parameters do not match the parameters in the query request, and the parameter call information query plug-in 135 in the fallback strategy 134 can be applied to query the target information from the information query system 120.
[0028] In the embodiment of the present disclosure, after the information query plug-in 135 undergoes the plug-in registration configuration review 1351, it realizes the release 1353 of the plug-in application, and uses the information query plug-in 135 to take the parameters output by the large-scale language model as input parameters of the query interface of the information query system, and directly calls the query interface of the information query system to complete the information query operation.
[0029] In an embodiment of the present disclosure, the plug-in registration configuration review 1351 registers the Open API (Open Application Programming Interface, an open platform application programming interface) profile of the information query plug-in 135 in the plug-in library of the large-scale model platform, and after being reviewed by the large-scale model platform, the release 1353 of the plug-in application can be realized.
[0030] In addition, since the parameters output by the large-scale language model may not match the query request, tuning 1352 can be performed on the recognition effect of the large-scale language model to optimize the result output by the large-scale language model. For example, based on a loss function, a loss value can be calculated based on the result output by the large-scale language model and the initial input request information, and based on the loss value, the parameters of the large-scale language model can be fine-tuned until the loss value converges, thereby improving the accuracy of the information query result.
[0031] It should be noted that the information query method according to the embodiment of the present disclosure may generally be performed by the large-scale model platform 130. Accordingly, the information query device provided by the embodiment of the present disclosure may be installed in the large-scale model platform 130.
[0032] It should be understood that the number of clients, information inquiry systems and large-scale model platforms in Figure 1 is merely an example. According to the needs of implementation, there may be any number of clients, information inquiry systems and large-scale model platforms.
[0033] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision, disclosure, application and other processing of such user personal information shall all comply with the provisions of relevant laws and regulations, take necessary security measures, and not violate public order and morals.
[0034] In the technical solution disclosed herein, the user's approval or consent is obtained before obtaining or collecting the user's personal information.
[0035] FIG. 2 illustrates a flowchart of an information query method according to an embodiment of the present disclosure.
[0036] As shown in FIG. 2, the method 200 includes operations S210-S230.
[0037] In operation S210, in response to the received information inquiry request from the target object, a period to be inquired, a number of items to be inquired, and an object identifier of the target object corresponding to the information inquiry request are obtained.
[0038] In operation S220, the period to be queried, the number of items to be queried, the object identifier and the predefined parameter format text are processed to obtain the target parameters.
[0039] In operation S230, obtain target information from an information query system by invoking a query interface based on the target parameters.
[0040] According to an embodiment of the present disclosure, an information query request may be generated based on a selection operation for a query period and a query number of items on a target page by a target subject. The target page may be configured according to a query scene demand of a specific item.
[0041] For example, the item to be queried may be an operation log record, the selected period to be queried may be January 2-3, and the number of items to be queried may be 5. The information query request may be to query five operation logs that occurred on January 2-3.
[0042] According to an embodiment of the present disclosure, the information query request may be in text format or obtained by voice recognition. For example, the information query request may be "Please query the derived records of 10 forms from 8:00 to 10:00 today", the period to be queried may be "from 8:00 to 10:00 today", and the number of items to be queried may be "10".
[0043] According to an embodiment of the present disclosure, the identifier of the target object may indicate an identity identifier of the target object in an information query system, may be used to verify whether the target object has query authority, and may be used to determine the scope of files that can be queried.
[0044] For example, a form of inquiry authority may be arranged, and a number of identifiers having inquiry authority may be recorded in the form. If it is determined that the identifier of the target object belongs to the form, it may be determined that the target object has the inquiry authority of the information inquiry system.
[0045] For example, the queryable scope of the target object in the information query system may be determined by configuring a mapping relationship between the identifier and the query file identifier, thereby realizing physical separation of the queryable data of different query objects and ensuring data security.
[0046] According to an embodiment of the present disclosure, the target parameter represents an input parameter of the query interface of the information query system. The predetermined parameter format text can represent a parameter format text that matches the parameter format needs of the query interface, thereby ensuring that the parameter format of the target parameter matches the query interface, and can directly input the query interface.
[0047] For example, the predefined parameter format text may include a period to query-query start time field, a period to query-query end time field, an identifier field, and a number of items field.
[0048] According to an embodiment of the present disclosure, by utilizing the natural language processing capability of the large-scale language model, the period to be queried, the number of items to be queried, the identifier of the target object and the entire predetermined parameter format text can be input into the large-scale language model as input text, so that the large-scale language model outputs target parameters for invoking a query interface according to the predetermined parameter format text based on the context information of the input text.
[0049] For example, an information query request for a target object T may be “Please query the derivation records of 10 forms from 8:00 to 10:00 today”, and the target parameters output by the large-scale language model may be “···beginTime:\20XX-01-03 08:00:00\ endTime: \20XX-01-03 10:00:00 \FileCount\10\query“Please query the derivation records of 10 forms from 8:00 to 10:00 today”, T\…”.
[0050] According to an embodiment of the present disclosure, the above target parameters can be used as input parameters of a query interface, and the query interface can be invoked to query the target information from the information query system.
[0051] According to an embodiment of the present disclosure, the period to be queried, the number of items to be queried, and the identifier of the target object are processed based on a predetermined parameter format text to obtain target parameters for calling up the query interface of the information query system, making full use of the natural language processing capability of the large-scale language model, and eliminating the need for multi-proxy services, directly generating parameters that can be input into the query interface, and calling up the query interface to perform information query, thereby reducing the dependency of the information query flow on message queues and proxy services, reducing the impact of the information query flow on the speed of other processing flows, and improving the efficiency of information query.
[0052] Since the basis of information query requires first constructing an information file with a unified format, the above method further includes obtaining content information of the target item and a predetermined template including a filling position, a name field and a content field corresponding to the content, and filling the content information into the content field corresponding to the name field according to the filling position to generate information of the target item.
[0053] According to an embodiment of the present disclosure, the predetermined template corresponds to a target item and may be pre-arranged according to the content of the target item. The target item may be, for example, a form, a document, an operation history, or other item that can be queried and has a diversified information format. The information of the target item may be an information file with a unified format.
[0054] According to an embodiment of the present disclosure, information of a target item is processed according to a predetermined template to generate an information file with a unified format, thereby reducing the redundant process of secondary processing for information with different formats in the information query process, and further improving information processing efficiency.
[0055] Hereinafter, with reference to FIG. 3, the method shown in FIG. 2 will be further described with reference to a specific embodiment.
[0056] FIG. 3 illustrates a schematic diagram of information processing and storage flow according to an embodiment of the present disclosure.
[0057] As shown in FIG. 3, in the embodiment 300, a flow of processing and storage for form information is illustrated by way of example, taking an application scene of form information as an example.
[0058] In the application scenario of form information, users usually download electronic forms already issued from third-party applications, and the types and formats of the electronic forms are different, which makes it inconvenient to inquire. Therefore, by constructing a form template, the form contents of electronic forms of different formats can be represented in the same format, for example, an Excel file.
[0059] According to an embodiment of the present disclosure, a form template 302 can be created based on the open source code function library of Apache POI (Por Obfuscation Implementation). The form template 302 may include a name field 302_1, a column coordinate 302_2, and a content field 302_3. The name field may include a form ID field, a serial number field, an issue time field, etc. The content field corresponds to the name field, for example, the form ID is XXX in the target form 301, and the content field corresponding to the name field "form ID" in the content field is "XXX". The column coordinate may indicate a filling position corresponding to the content to realize the correspondence between the name and the content.
[0060] For example, the content field "XXX" is filled into the name field "report ID" at column coordinate "0" to generate report ID column information 303_1. The content field "YYY" is filled into the name field "serial number" at column coordinate "1" to generate serial number information 303_2. The content field "ZZZ" is filled into the name field "issue time" at column coordinate "2" to generate issue time information 303_3. Report information 303 in Excel file format is obtained.
[0061] According to an embodiment of the present disclosure, the form information 303 can be stored in the cloud 123 by locating a storage address in the form information.
[0062] According to the embodiment of the present disclosure, a target storage address can be arranged according to the download target identifier of the target item, and information of the target item can be stored according to the target storage address.
[0063] According to an embodiment of the present disclosure, the download target identifier of the target item can correspond to the content information of the target item, and in the profile, a mapping relationship between the download target identifier and the target storage address can be set, so as to realize a one-to-one correspondence relationship between the information of the target item and the storage address, thereby facilitating the query and further improving the query efficiency.
[0064] For example, the information of the target item can be converted into bytes of information and uploaded to the cloud 123 for storage.
[0065] According to the embodiment of the present disclosure, different types of content information are processed based on a predetermined template to realize unified information format, and a storage address is set and the processed information file is stored in the cloud to reduce the storage space occupation rate of the terminal device.
[0066] According to an embodiment of the present disclosure, the above operation S220 can include an operation of constructing a suggested text based on the period to be queried, the number of items to be queried, the identifier of the target object and a predetermined parameter format text, and an operation of processing the suggested text using a generative large-scale model to obtain target parameters.
[0067] FIG. 4 illustrates a schematic diagram of an information query method according to an embodiment of the present disclosure.
[0068] 4, in the embodiment 400, the information query request 420 may be "Please query five derived information items between 10:00 and 14:00 today". The period 421 to be queried that can be obtained from the information query request 420 may be "10:00 and 14:00 today", and the number of items 422 to be queried may be "five". The predetermined parameter format text 423 may be determined based on the corresponding item type in the information query request.
[0069] According to an embodiment of the present disclosure, a period to be queried 421, a number of items to be queried 422 and a predetermined parameter format text 423 can be constructed as a presented text 424. Then, the presented text 424 is input to a generative large-scale model 426, and the generative large-scale model 426 is used to understand the context information in the presented text 424, and the target parameters 425 are output based on the natural language processing capability of the generative large-scale model 426.
[0070] According to an embodiment of the present disclosure, by constructing a presentation text including a predetermined parameter format text, the generative large-scale model can generate parameters that meet the needs of the input format of the information query interface according to the predetermined parameter format, so that the output result of the generative large-scale model can be directly used to call the query interface, thereby further improving the information query efficiency.
[0071] At present, the processing accuracy of the generative large-scale model is high, but there may still be recognition errors, such as the format of the target parameter is incorrect, or the content of some parameters of the target parameter is incorrect, etc. Therefore, a proper fallback strategy can be set to ensure the normal execution of the query task.
[0072] According to an embodiment of the present disclosure, the above operation S230 may include: analyzing the target parameters to obtain an analysis result including a target query period, a target item number, and a target identifier; obtaining query attribute information based on the analysis result; obtaining the target information from the information query system based on the query attribute information; in response to the analysis result matching with the information query request, the query attribute information including the target query period, the target item number, and the target identifier; and in response to the analysis result not matching with the information query request, the query attribute information including a predetermined query period, a predetermined number of query items, and the target identifier.
[0073] For example, the information query request 420 sent by the target object T may be "Please query five derived information between 10:00 and 14:00 today". The target query period included in the analysis result obtained by analyzing the target parameters may be "10:00-14:00 today", the number of target items may be "five derived information", and the identifier of the target object may be "T". Execute the operation S430 to match the target query period in the analysis result with the period to be queried in the information query request, the number of target items in the analysis result, and the number of items to be queried and the identifier of the target object in the information query request one by one. Determine whether the target parameters and the query request match. Through verification, it is determined that the target parameters 425 match the information query request 420, execute the operation S440, and call up the query interface with the input parameters of the target parameters "five derived information between 10:00-14:00 today", and query the first target information 431 from the information query system.
[0074] For example, the information inquiry request 420 sent by the target object T may be "Please inquire about five derived information between 10:00 and 14:00 today". The target inquiry period included in the analysis result obtained by analyzing the target parameters may be "10:00-13:00 today", the number of target items may be "four derived information", and the identifier of the target object may be "T". Execute the operation S430 to match the target inquiry period in the analysis result with the period to be inquired in the information inquiry request, the number of target items in the analysis result with the number of items to be inquired and the identifier of the target object in the information inquiry request one by one. Determine whether the target parameters and the inquiry request match. By verification, it is determined that the target parameters 425 and the information inquiry request 420 do not match, and execute the operation S450 to call the inquiry interface with the input parameter of the predetermined parameter "the latest one derived information today", and inquire the second target information 432 from the information inquiry system.
[0075] According to the embodiment of the present disclosure, the creation of the fallback strategy can be determined based on the item type and item content in the actual application scenario. For example, in the case of a form inquiry, the latest one piece of downloaded / derived information on the day is highly likely to be queried, so when the target parameters output from the large-scale language model are incorrect, the latest one piece of derived information can be used as the fallback strategy for the information inquiry.
[0076] According to the embodiment of the present disclosure, the matching degree between the output result of the large-scale language model and the information query request can be verified through the analysis and verification of the target parameters, and the accuracy of the information query can be improved under the premise of realizing the simplified resource scheduling flow of the information query process. At the same time, the impact of the error detection of the information query system on the processing process can be reduced by setting appropriate predetermined parameters as a fallback strategy, and the stable operation of the system can be further improved.
[0077] FIG. 5 illustrates a schematic diagram of an information query method according to another embodiment of the present disclosure.
[0078] As shown in Fig. 5, in the embodiment 500, for the ID of the target object in the target parameters output from the large-scale language model, first, perform operation S510 to verify whether the target object has the authority to access the information query system. If it is determined that the target object has the access authority, determine the history download information 512 of the target object from the history item download information of the multiple target objects according to the identifier of the target object. If it is determined that the target object does not have the access authority, perform operation S520 to process the next request.
[0079] According to an embodiment of the present disclosure, the information inquiry system includes history item download information of at least two target objects. Obtaining target information from the information inquiry system according to the inquiry attribute information can include: determining target history item download information corresponding to an object identifier from the history item download information of the at least two target objects; and determining target information corresponding to the inquiry attribute information from the target history item download information.
[0080] An operation S530 can be performed on the target parameters output by the large-scale language model to determine whether the target parameters 531 match the query request. Based on the target query period and the target number of items, target information can be determined from the target history item download information. For example, based on the query period T1 and the number of items Nu1 532, item information M1 533 is determined from the history item download information 512 of the target object. The query period T1 and the number of items Nu1 indicate the same period to be queried and the number of items to be queried as the information query request.
[0081] Otherwise, a fallback strategy can be implemented to determine target information from the target history item download information based on a predetermined query period and a predetermined number of items inquired. For example, item information M2 537 of the target target is determined from the history item download information 512 based on the query period T2 and the number of items Nu2 536. The query period T2 and the number of items Nu2 indicate a period to be queried and a number of items to be queried that are completely different or at least partially different from the information query request.
[0082] For example, the information query request may be "query the latest 5 derived records today", and the target parameter may be "what are the latest 5 derived records today", it can be determined that the target parameter and the information query request do not match, and the current parameter is directly input into the query interface of the information query system, and the parameter is incorrect, so that the information query system may have an error and cannot continue to execute the query task. In this case, a fallback strategy can be implemented, and the predetermined query period may be the current period of today, and the number of predetermined query items may be one. The predetermined parameters in the fallback strategy are used as input parameters of the query interface, and it can be found that the query result can at least partially satisfy the initial information query request, and the query information is still valid for the target object.
[0083] According to the embodiment of the present disclosure, the historical download record of the target object is first determined according to the identifier of the target object, so as to realize the physical separation of the stored data between different target objects and improve the data security.Furthermore, by setting a fallback strategy, when the target parameters are incorrect, valid information can still be queried, so as to reduce the error rate of the information query system and further improve the stable operation of the system.
[0084] According to an embodiment of the present disclosure, the information query system includes a mapping relationship between information and information storage address, so that based on the mapping relationship, it can determine storage address information of the target information, obtain network environment information of the target object, and stitch the storage address information and the network environment information to generate target link information for the target object to download the target information.
[0085] 5, based on the mapping relationship, a storage address Me1534 can be determined based on the item information M1533, and the network environment En1513 and the storage address Me1534 can be stitched together to generate a link L1535 for the target object to download the item information M1. Based on the mapping relationship, a storage address Me2538 can be determined based on the item information M2537, and the network environment En1513 and the storage address Me2538 can be stitched together to generate a link L2539 for the target object to download the item information M2.
[0086] According to an embodiment of the present disclosure, there is a one-to-one correspondence between the network environment information of a target object and the identifier of the target object, and by setting a mapping relationship between the network environment information and the identifier in advance, the network environment information of the target object can be determined based on the identifier of the target object.
[0087] According to an embodiment of the present disclosure, the target link information includes the network environment of the target object and also includes the storage address of the target information, so that when a user clicks on the target link information, the user can directly jump to an information download interface, so as to timely download the target information and improve information query efficiency.
[0088] According to an embodiment of the present disclosure, in addition to returning link information for downloading the target information, a rendering template can be arranged to return and display the target information to the client in the form of a visualization interface, thereby improving the user experience.
[0089] FIG. 6 is a schematic block diagram of an information inquiry device according to an embodiment of the present disclosure.
[0090] As shown in FIG. 6 , the information query device 600 may include a first obtaining module 610 , a processing module 620 and a query module 630 .
[0091] The first acquisition module 610 acquires a period to be inquired, a number of items to be inquired, and an object identifier of the target object corresponding to the information inquiry request in response to the received information inquiry request.
[0092] The processing module 620 processes the period to be inquired, the number of items to be inquired, the object identifier and the predefined parameter format text to obtain target parameters, which represent the input parameters of the query interface of the information query system.
[0093] The query module 630 obtains the target information from the information query system by invoking a query interface based on the target parameters.
[0094] According to an embodiment of the present disclosure, the query module may include an analysis sub-module, an acquisition sub-module, and a query sub-module.
[0095] The analysis sub-module analyzes the goal parameters and obtains an analysis result, where the analysis result includes a goal query period, a goal item number, and a target identifier.
[0096] The acquisition sub-module acquires the query attribute information based on the analysis result.
[0097] The query submodule obtains target information from the information query system based on the query attribute information. In response to the analysis result matching the information query request, the query attribute information includes a target query period, a target item number, and a target identifier. In response to the analysis result not matching the information query request, the query attribute information includes a predetermined query period, a predetermined query item number, and a target object identifier.
[0098] According to an embodiment of the present disclosure, the information query system includes history item download information of at least two target objects, and the first query sub-module may include a first determining unit and a second determining unit.
[0099] The first determining unit determines, from the history item download information of the at least two target objects, the target history item download information corresponding to the object identifier.
[0100] The second determining unit determines, from the target history item download information, first target information corresponding to the query attribute information.
[0101] According to an embodiment of the present disclosure, the information query system includes a mapping relationship between information and a storage address of the information, and the above apparatus further includes a determination module, a second acquisition module, and a first generation module.
[0102] The determination module determines, based on the mapping relationship, the storage address information corresponding to the target information.
[0103] The second acquiring module acquires network environment information of the target object.
[0104] The first generating module stitches the storage address information and the network environment information to generate target link information for the target object to download the target information.
[0105] According to an embodiment of the present disclosure, the processing module may include a construction sub-module and a processing sub-module.
[0106] The construction submodule constructs the presentation text based on the time period to be queried, the number of items to be queried, the identifier of the target object, and the predetermined parameter format text. The processing submodule processes the presentation text using the generative large-scale model to obtain the target parameters.
[0107] According to an embodiment of the present disclosure, the apparatus may further include a third acquisition module and a third generation module.
[0108] A third obtaining module obtains content information of the target item and a predefined template, where the predefined template includes a filling position, a name field and a content field corresponding to the content.
[0109] The third generating module fills the content information into the content field corresponding to the name field according to the filling position, and generates information of the target item.
[0110] According to an embodiment of the present disclosure, the above-mentioned device may further include a configuration module and a storage module, the configuration module configures a target storage address according to a download target identifier of the target item, and the storage module stores information of the target item according to the target storage address.
[0111] According to an embodiment of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium, and a computer program.
[0112] 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, the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor such that the at least one processor performs the above-described method.
[0113] According to an embodiment of the present disclosure, there is provided a non-transitory computer-readable storage medium having computer instructions stored thereon, the computer instructions causing a computer to perform the above-described method.
[0114] According to an embodiment of the present disclosure, a computer program, when executed by a processor, implements the above method.
[0115] 7 shows an exemplary block diagram for implementing an exemplary electronic device 700 according to an embodiment of the present disclosure. The electronic device is intended to represent various types of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various types of mobile devices, such as personal digital assistants, mobile phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely exemplary and are not intended to limit the implementation of the present disclosure as described and / or claimed herein.
[0116] 7, the device 700 includes a computing unit 701, which can perform various appropriate operations and processes based on a computer program stored in a read-only memory (ROM) 702 or loaded from a storage unit 708 into a random access memory (RAM) 703. The RAM 703 can further store various programs and data necessary for the operation of the device 700. The computing unit 701, the ROM 702, and the RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.
[0117] The components in the device 700 are connected to an 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 magnetic 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 enables the device 700 to exchange information / data with other devices via a computer network, such as the Internet, and / or various types of electrical communication networks.
[0118] The computing unit 701 may be various general-purpose and / or dedicated processing modules having 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, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 executes each of the 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 tangibly embodied in a machine-readable medium, such as the storage unit 708. In some embodiments, some or all of the computer program may be loaded and / or installed in the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, it may perform one or more steps of the web page identification method described above. Alternatively, in another embodiment, the computing unit 701 may be configured to perform the information query method in any other suitable manner (eg, via firmware).
[0119] Various embodiments of the systems and techniques described herein may be realized in digital electronic circuitry systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may be embodied in one or more computer programs that may be executed and / or interpreted by a programmable system that includes at least one programmable processor, which may be a special purpose or general purpose programmable processor, and may include a processor that is capable of receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
[0120] The program codes for implementing the methods 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 apparatus, so that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are performed. The program codes may be fully executed on the device, partially executed on the device, partially executed on the device as a separate software package and partially executed on a remote device or fully executed on a remote device or server.
[0121] In the context of this disclosure, a machine-readable medium may be a tangible medium, and may include or store a program for use in or in combination with an instruction execution system, apparatus, or device. 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, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections through one or more wires, portable computer disks, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), optical fibers, compact disk read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0122] A computer may implement the systems and techniques described herein to provide interaction with a user, and may include a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user, and a keyboard and pointing device (e.g., a mouse or trackball) through which a user may provide input to the computer. Other types of devices may also provide interaction with a user, for example, the feedback provided to the user may be any form of sensing feedback (e.g., visual feedback, auditory feedback, or tactile feedback) and may receive input from the user in any form (including voice input, speech input, or tactile input).
[0123] The systems and techniques described herein may be implemented in a computing system including background components (e.g., a data server), or a computing system including middleware components (e.g., an application server), or a computing system including front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user may interact with embodiments of the systems and techniques described herein), or a computing system including any combination of such background, middleware, or front-end components. The components of the system may be connected to each other by any form or medium of digital data communication (e.g., a communications network). Examples of communications networks illustratively include a local area network (LAN), a wide area network (WAN), and the Internet.
[0124] The computer system may include clients and servers. The clients and servers are generally remote and typically interact through a communication network. The relationship between clients and servers is created by computer programs running on the corresponding computers and having a client-server relationship. The server may be a cloud server, a server of a distributed system, or a server in combination with a blockchain.
[0125] It should be understood that various types of flows shown above may be used, and steps may be rearranged, added, or deleted. For example, each step described in the present invention may be performed in parallel, sequentially, or in a different order, and the present specification is not limited thereto as long as the desired results of the technical solution of the present disclosure can be achieved.
[0126] The specific embodiments described above do not limit the scope of protection of the present disclosure. Those skilled in the art should understand that various modifications, combinations, subcombinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principle of the present disclosure should be included within the scope of protection of the present disclosure.
Claims
1. In response to the received information inquiry request from the target object, acquiring a period to be inquired, a number of items to be inquired, and an object identifier of the target object corresponding to the information inquiry request; Processing the time period to be queried, the number of items to be queried, the object identifier and the predetermined parameter format text to obtain target parameters representing input parameters of a query interface of an information query system; and obtaining target information from the information query system by invoking the query interface based on the target parameters.
23. An information inquiry method comprising:
2. obtaining target information from the information query system by invoking the query interface based on the target parameters; analyzing the target parameters to obtain an analysis result including a target query period, a target item number, and the object identifier; obtaining query attribute information based on the analysis result; Obtaining the target information from the information inquiry system based on the inquiry attribute information; In response to the analysis result matching the information query request, the query attribute information includes the target query period, the target item number, and the object identifier; In response to the analysis result not matching the information query request, the query attribute information includes a predetermined query period, a predetermined number of query items, and the target identifier. The method of claim 1.
3. The information inquiry system includes history item download information of at least two of the target objects; Obtaining the target information from the information inquiry system based on the inquiry attribute information includes: determining a target history item download information corresponding to the object identifier from history item download information of at least two of the target objects; determining the target information corresponding to the query attribute information from the target history item download information. The method of claim 2.
4. The information query system includes a mapping relationship between information and information storage address; The method comprises: determining storage address information of the target information based on the mapping relationship; Obtaining network environment information of the target object; stitching the storage address information and the network environment information to generate target link information for the target object to download the target information. The method according to any one of claims 1 to 3.
5. Processing the time period to be queried, the number of items to be queried, the object identifiers of the target objects, and predetermined parameter format text to obtain target parameters, constructing a presentation text based on the time period to query, the number of items to query, the object identifier, and the predetermined parameter format text; and processing the presentation text utilizing a generative large-scale model to obtain the target parameters. The method of claim 1.
6. The method comprises: Obtaining content information of the target item and a predefined template including a filling position, a name field and a content field corresponding to the content; and filling the content information into a content field corresponding to the name field according to the filling position to generate information of the target item. The method of claim 1.
7. The method comprises: locating a target storage address according to a download target identifier of the target item; storing information of the target item according to the target storage address. The method according to claim 6.
8. a first acquisition module for acquiring a period to be inquired, a number of items to be inquired, and an object identifier of the target object corresponding to the information inquiry request in response to the information inquiry request; a processing module for processing the time period to be queried, the number of items to be queried, the object identifier and a predetermined parameter format text to obtain target parameters representing input parameters of a query interface of an information query system; a query module for obtaining target information from the information query system by invoking the query interface based on the target parameters. Information inquiry device.
9. The query module includes: an analysis sub-module for analyzing the target parameters to obtain an analysis result including a target query period, a target item number, and the object identifier; an acquisition submodule for acquiring query attribute information based on the analysis result; a query submodule for obtaining the target information from the information query system according to the query attribute information; In response to the analysis result matching the information query request, the query attribute information includes the target query period, the target item number, and the object identifier; In response to the analysis result not matching the information query request, the query attribute information includes a predetermined query period, a predetermined number of query items, and the target identifier.
9. The apparatus of claim 8.
10. The information query system includes at least two of the target object's history item download information, and the query submodule: A first determination unit for determining a target history item download information corresponding to the object identifier from history item download information of at least two of the target objects; a second determining unit for determining target information corresponding to the query attribute information from the target history item download information.
10. The apparatus of claim 9.
11. The information query system includes a mapping relationship between information and information storage address, and the device includes: a determining module for determining storage address information corresponding to the target information based on the mapping relationship; A second acquisition module for acquiring network environment information of the target object; and a first generating module for generating target link information for the target object to download the target information by stitching the storage address information and the network environment information. An apparatus according to any one of claims 8 to 10.
12. The processing module includes: a construction sub-module for constructing a presentation text based on the time period to be queried, the number of items to be queried, the object identifier and the predetermined parameter format text; a processing submodule for processing the presented text using a generative large-scale model to obtain the target parameters.
9. The apparatus of claim 8.
13. The apparatus comprises: A third acquisition module acquires content information of the target item and a predefined template including a filling position, a name field and a content field corresponding to the content; and a third generating module for filling the content information into a content field corresponding to the name field according to the filling position, and generating information of the target item.
9. The apparatus of claim 8.
14. The apparatus comprises: A configuration module for configuring a target storage address according to a download target identifier of the target item; a storage module for storing the information of the target item according to the target storage address.
14. The apparatus of claim 13.
15. At least one processor; a memory in communication with the at least one processor; The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor such that the at least one processor can perform the method of any one of claims 1-3. electronic equipment.
16. A non-transitory computer-readable storage medium having computer instructions stored thereon, comprising: The computer instructions cause a computer to carry out the method according to any one of claims 1 to 3. A non-transitory computer-readable storage medium having computer instructions stored thereon.
17. A computer program which, when executed by a processor, implements the method according to any one of claims 1 to 3.
