Information acquisition method, device and electronic equipment

Abstract

The present disclosure provides an information acquisition method and device and electronic equipment, relates to the technical field of artificial intelligence, specifically to the technical field of intelligent search and large language model, and a specific implementation scheme is as follows: a plurality of historical search requests related to an enterprise are acquired, wherein each historical search request comprises a candidate job attribute and a candidate document topic corresponding to the candidate job attribute; a candidate outline document matched with the candidate job attribute and the candidate document topic is acquired according to a large language model (LLM) and the historical search request; a target search request sent by a user device is received, a target outline document matched with the target search request is acquired from the candidate outline document, and the target outline document is fed back to the user device, so that the present disclosure can provide the target outline document matched with the job attribute and the document topic for a user in an enterprise, the user can subsequently fill in content based on the target document outline, the writing efficiency of the user is improved, and meanwhile, the quality level of the document is improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of artificial intelligence, in particular to the technical field of intelligent search and large language model, and more particularly to an information acquisition method and device, an electronic device and a storage medium. BACKGROUND

[0002] At present, in an enterprise, users will write various types of documents, and correspondingly, users of different types of work will also write different types of documents. A high-quality document first needs an outline document, and users can fill in their own content information based on the outline document. However, the method for obtaining an outline document in the related art has the problem of being unable to provide the required outline document for users of different types of work. SUMMARY

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

[0004] According to a first aspect, an information acquisition method is provided, comprising: obtaining a plurality of historical search requests related to an enterprise, wherein each historical search request comprises a candidate work attribute and a candidate document topic corresponding to the candidate work attribute; obtaining a candidate outline document matched with the candidate work attribute and the candidate document topic according to a large language model (LLM) and the historical search requests; receiving a target search request sent by a user device, and obtaining a target outline document matched with the target search request from the candidate outline document and feeding back to the user device.

[0005] According to a second aspect, an information acquisition device is provided, comprising: a first obtaining module configured to obtain a plurality of historical search requests related to an enterprise, wherein each historical search request comprises a candidate work attribute and a candidate document topic corresponding to the candidate work attribute; a second obtaining module configured to obtain a candidate outline document matched with the candidate work attribute and the candidate document topic according to a large language model (LLM) and the historical search requests; and a third obtaining module configured to receive a target search request sent by a user device, obtain a target outline document matched with the target search request from the candidate outline document, and feed back to the user device.

[0006] According to a third aspect, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the information acquisition method according to the first aspect of the present disclosure.

[0007] According to a fourth aspect, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to perform the information acquisition method according to the first aspect of the present disclosure.

[0008] According to a fifth aspect, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the information acquisition method according to the first aspect of the present disclosure.

[0009] It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0010] The accompanying drawings are used to better understand the present scheme, and do not limit the present disclosure. Among them:

[0011] Figure 1 is a flowchart of an information acquisition method according to a first embodiment of the present disclosure;

[0012] Figure 2 is a flowchart of an information acquisition method according to a second embodiment of the present disclosure;

[0013] Figure 3 is a flowchart of an information acquisition method according to a third embodiment of the present disclosure;

[0014] Figure 4 is a flowchart of an information acquisition method according to a fourth embodiment of the present disclosure;

[0015] Figure 5 is a flowchart of an information acquisition method according to a fifth embodiment of the present disclosure;

[0016] Figure 6 is a flowchart of an information acquisition method according to an embodiment of the present disclosure;

[0017] Figure 7 is a block diagram of an information acquisition device for implementing an embodiment of the present disclosure;

[0018] Figure 8 is a block diagram of an electronic device for implementing an information acquisition method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0019] Exemplary embodiments of the present disclosure are described herein with reference to the accompanying drawings, which are included to provide a thorough understanding of embodiments of the present disclosure and are not intended to be inclusive of all aspects of the present disclosure. Accordingly, those of ordinary skill in the art will recognize that various changes in the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted for clarity and conciseness.

[0020] Artificial Intelligence (AI) is a technology science that studies and develops theories, methods, techniques, and application systems for simulating, extending, and expanding human intelligence. Currently, AI technology has the advantages of high automation, high accuracy, and low cost, and has been widely applied.

[0021] Intelligent search, an intelligent search engine, is a new generation of search engine combined with artificial intelligence technology. It can provide traditional fast retrieval, relevance sorting, and other functions, as well as user role registration, automatic identification of user interests, semantic understanding of content, intelligent information filtering and pushing, and other functions.

[0022] Large Language Model (LLM) refers to a deep learning model trained using a large amount of text data, which can generate natural language text or understand the meaning of language text. Large language models can handle a variety of natural language tasks such as text classification, question answering, and dialogue, and are an important way to artificial intelligence.

[0023] A method for obtaining information according to an embodiment of the present disclosure is described below with reference to the accompanying drawings.

[0024] Figure 1 is a flowchart of a method for obtaining information according to the first embodiment of the present disclosure.

[0025] As shown in Figure 1 , the method for obtaining information according to the embodiment of the present disclosure can specifically include the following steps:

[0026] S101, obtaining a plurality of historical search requests related to the enterprise, wherein each historical search request includes a candidate job attribute and a candidate document topic corresponding to the candidate job attribute.

[0027] Wherein, the candidate job attribute refers to each type of work contained in the enterprise.

[0028] Wherein, the type of work refers to the type of work divided according to the needs of labor management, according to the nature of production labor, the characteristics of technological process or the characteristics of service activities.

[0029] It should be noted that the specific way of obtaining the candidate job attribute and the candidate document topic corresponding to the candidate job attribute is not limited in the present disclosure, and can be selected according to actual conditions.

[0030] Optionally, according to the actual situation of the staff of the enterprise, the candidate job attributes (job types) in the enterprise can be determined, the document topics of each candidate job attribute during writing can be obtained, and for each candidate job attribute, the document topics of each candidate job attribute during writing can be summarized to obtain the candidate document topic corresponding to the candidate job attribute.

[0031] For example, when the candidate job attribute is an algorithm engineer, the corresponding candidate document topic can be an experimental report document and a technical scheme document; when the candidate job attribute is a test engineer, the corresponding candidate document topic can be a test report document and a test case design document.

[0032] S102, according to the large language model LLM and the historical search request, obtaining a candidate outline document matched with the candidate job attribute and the candidate document topic.

[0033] The large language model (Large Language Model, LLM for short) refers to a kind of language model based on neural network with large-scale parameters.

[0034] In the disclosed embodiment, according to the large language model and the historical search request, a candidate outline document matched with the candidate job attribute and the candidate document topic can be obtained.

[0035] Optionally, an initial outline guide template prompt can be obtained, the outline guide template is edited according to the candidate job attribute, the candidate document topic and the historical search request, a first outline guide template is obtained, the first outline guide template is input into the large language model LLM, and a candidate outline document matched with the candidate job attribute and the candidate document topic is obtained.

[0036] For example, when the candidate job attribute is an algorithm engineer and the candidate document topic is an experimental report document, the candidate outline document is A1; when the candidate job attribute is an algorithm engineer and the candidate document topic is a technical scheme document, the candidate outline document is A2.

[0037] In the embodiment of the present application, through the large language model LLM and the historical search request, all candidate outline documents matched with the candidate job attribute and the candidate document topic in the enterprise can be obtained.

[0038] S103, receiving the target search request sent by the user equipment, and obtaining the target outline document matched with the target search request from the candidate outline document, and feeding back to the user equipment.

[0039] It should be noted that after receiving the target search request query sent by the user equipment, the target search request can be parsed to obtain the target document topic and the user identifier information corresponding to the user equipment, obtain the target work attribute corresponding to the user identifier information, and obtain the target outline document from the candidate outline document according to the target document topic and the target work attribute.

[0040] For example, when the target search request sent by the user equipment is "I want to write a document about the topic of experimental report now, please help me generate the outline of the document.", the target search request can be parsed to obtain the target document topic "experimental report" and the target work attribute "algorithm engineer", and the target outline document A1 can be obtained.

[0041] To sum up, the information acquisition method of the embodiment of the present disclosure can obtain a plurality of historical search requests related to an enterprise, wherein each historical search request includes a candidate work attribute and a candidate document topic corresponding to the candidate work attribute; and according to a large language model LLM and the historical search request, a candidate outline document matching the candidate work attribute and the candidate document topic is obtained; receiving a target search request sent by a user equipment, and obtaining a target outline document matching the target search request from the candidate outline document, and feeding back to the user equipment, the present disclosure can provide the target outline document matching the work attribute and the document topic for the users in the enterprise, and the users can fill in the content based on the target document outline in the future, which improves the writing efficiency of the users, and at the same time, improves the quality level of the document.

[0042] Figure 2 is a flowchart of the information acquisition method according to the second embodiment of the present disclosure.

[0043] As shown in Figure 2 based on the embodiment shown in Figure 1 The information acquisition method of the embodiment of the present disclosure can specifically include the following steps:

[0044] S201, obtaining a plurality of historical search requests related to an enterprise, wherein each historical search request includes a candidate work attribute and a candidate document topic corresponding to the candidate work attribute.

[0045] The step S201 "candidate work attribute corresponding to candidate document topic" in the above embodiment can include the following steps S301 and S303.

[0046] S301, for each candidate work attribute, obtaining the document title of the candidate work attribute.

[0047] Optionally, the document title written by each candidate work attribute in the enterprise can be obtained in advance.

[0048] For example, for the candidate job attribute of algorithm engineer, the document titles are "graph algorithm model research document" and "text classification model research document".

[0049] S302, information extraction is performed on the document title of the candidate job attribute to obtain an initial document theme of the candidate job attribute.

[0050] Optionally, after obtaining the document title of the candidate job attribute, information extraction can be performed on the document title of the candidate job attribute by using the trained model to obtain an initial document title of the candidate job attribute.

[0051] Optionally, the information extraction model Monet can be used to perform information extraction on the document title of the candidate job attribute to obtain an initial document title of the candidate job attribute. The information extraction model Monet having a theme extraction function can be trained by using labeled training data.

[0052] For example, by using the information extraction model Monet, the themes of the above-mentioned documents can be obtained as "model research" for the document titles of "graph algorithm model research document" and "text classification model research document".

[0053] S303, a candidate document theme corresponding to the candidate job attribute is selected from the initial document theme of the candidate job attribute.

[0054] The step S303 "selecting a candidate document theme corresponding to the candidate job attribute from the initial document theme of the candidate job attribute" in the above-mentioned embodiment can include the following steps S401 and S402.

[0055] S401, the occurrence frequency of the initial document theme of the candidate job attribute and the occurrence frequency threshold are obtained.

[0056] It should be noted that the initial document theme and the occurrence frequency of the initial document theme of each candidate job attribute can be obtained by using the information extraction model Monet.

[0057] It should be noted that the disclosure does not limit the setting of the occurrence frequency threshold, which can be set according to actual conditions.

[0058] Optionally, the occurrence frequency threshold can be set as 3.

[0059] S402, according to the occurrence frequency of the initial document theme and the occurrence frequency threshold, a candidate document theme corresponding to the candidate job attribute is selected from the initial document theme of the candidate job attribute.

[0060] Optionally, from the initial document topics of the candidate job attributes, the first initial document topic with an occurrence frequency less than the occurrence frequency threshold is filtered out, and the second initial document topic remaining in the initial document topics of the candidate job attributes is taken as the candidate document topic corresponding to the candidate job attribute.

[0061] The step S102 in the above embodiment can specifically include the following steps S202 and S204.

[0062] S202, obtaining an initial outline guide template.

[0063] It should be noted that the disclosure does not limit the setting of the initial outline guide template, which can be set according to actual conditions.

[0064] Optionally, the initial outline guide template prompt can be "I am an XXX (job attribute), and I want to write a document about XX topic now. Please help me generate the outline of the document."

[0065] It should be noted that the initial outline guide template can specify the writing paradigm of natural language, so that the large language model LLM can more accurately understand the search intent.

[0066] S203, editing the outline guide template according to the candidate job attribute, the candidate document topic and the historical search request to obtain a first outline guide template.

[0067] In the embodiments of the disclosure, the outline guide template can be edited according to the candidate job attribute, the candidate document topic and the historical search request to obtain the first outline guide template.

[0068] For example, based on the initial outline guide template, the first outline guide template can be "I am an algorithm engineer, and I want to write a document about the topic of the test report now. Please help me generate the outline of the document."

[0069] S204, inputting the first outline guide template into the large language model LLM to obtain the candidate outline document matching the candidate job attribute and the candidate document topic.

[0070] In the embodiments of the disclosure, after obtaining the first outline guide template, the first outline guide template can be input into the large language model LLM, and the large language model LLM can generate the candidate outline document matching the candidate job attribute and the candidate document topic according to the input first outline guide template.

[0071] In the embodiments of the present disclosure, after the candidate outline document matching the candidate work attribute and the candidate document topic is acquired, a mapping relationship between the candidate outline document and the document topic and the work attribute corresponding to the candidate document outline can be established, and the mapping relationship is stored in the search engine.

[0072] Optionally, in order to facilitate subsequent user search, the mapping relationship can be stored in the search engine (ElasticSearch, referred to as ES).

[0073] S205, receiving a target search request sent by a user equipment.

[0074] The step S103 "acquiring a target outline document matching the target search request from the candidate outline document" in the above embodiment can specifically include the following steps S206 and S208.

[0075] S206, parsing the target search request to acquire a target document topic and user identity information corresponding to the user equipment.

[0076] It should be noted that after the target search request is received, the target search request can be parsed to obtain the target document topic in the target search request, and the user identity information (Identity document, referred to as ID) corresponding to the user equipment can be acquired.

[0077] S207, acquiring a target work attribute corresponding to the user identity information.

[0078] Optionally, a mapping relationship between the user identity information and the work attribute in the enterprise can be established in advance, and the target work attribute corresponding to the user identity information can be obtained by querying the mapping relationship according to the user identity information corresponding to the user equipment.

[0079] S208, acquiring a target outline document based on the target document topic and the target work attribute.

[0080] The step S208 "acquiring a target outline document based on the target document topic and the target work attribute" in the above embodiment can specifically include the following steps S501 and S502.

[0081] S501, querying the mapping relationship through the search engine according to the target document topic and the target work attribute to acquire a target candidate outline document matching the target search request.

[0082] Optionally, after the target document topic and the target work attribute are acquired, the mapping relationship can be queried through the search engine ES, that is, the mapping relationship between the candidate outline document and the document topic and the work attribute corresponding to the candidate document outline is queried through the ES to recall the target candidate outline document matching the target search request.

[0083] S502, obtaining the target outline document from the target candidate outline document according to the large language model LLM.

[0084] In the embodiments of the present disclosure, after obtaining the target candidate outline document, the outline document screening request can be generated based on the target candidate outline document, the second outline guide template is obtained by editing the initial outline guide template according to the target work attribute, the target document theme and the outline document screening request, and the target outline document is obtained from the target candidate outline document by inputting the second outline guide template into the large language model LLM.

[0085] For example, for the target candidate outline documents x1, x2 and x3, the second outline guide template can be "I am an algorithm engineer, and now I want to write a document on the topic of the test report. Please select the outline document that is most matched with the target document theme from the following documents: x1, x2 and x3."

[0086] Further, in order to improve the accuracy of obtaining the target outline document, after obtaining the second outline guide template, the second outline guide template can be input into the large language model LLM, and then the target outline document is selected from the target candidate outline document.

[0087] The specific process of the information obtaining method proposed in the present disclosure is explained below.

[0088] For example, as shown in FIG. 6, the target candidate outline document x1, x2 and x3 are obtained according to the target work attribute and the target document theme, and the second outline guide template is obtained by editing the initial outline guide template according to the target work attribute, the target document theme and the outline document screening request. Figure 6As shown, it can be divided into mining pipeline and retrieval (search) pipeline, first collect the document data in the enterprise, summarize the document title corresponding to each job attribute (job type), obtain the document title corresponding to each job attribute, for example: document title corresponding to job type 1 …… document title corresponding to job type n, can extract the topic of the document title corresponding to each job attribute based on the extraction model Monet, optionally, the document topics with frequency less than 3 can be filtered out in ascending order of frequency, and then the document topics (i.e. writing topics) corresponding to each job attribute are obtained, for example: document topics corresponding to job type 1 …… document topics corresponding to job type n, according to the obtained document topics, job attributes and historical search requests, edit the initial outline guide template, obtain the first outline guide template, input the first outline guide template into the large language model, and then obtain the outline document matched with the job attribute and the document topic (i.e. writing outline), store the generated outline document matched with the job attribute and the document topic in the search engine, that is, complete the mining pipeline, further, the target search request query sent by the user device can be received, the query can be parsed, the target document topic to be searched in the query can be extracted by using the extraction model Monet, and the user identifier information corresponding to the user device is obtained. Obtain the target job attribute corresponding to the user identifier information, according to the target document topic, the target job attribute, recall the candidate outline document matched with the target document topic and the target job attribute through ES, generate an outline document screening request based on the target candidate outline document, edit the initial outline guide template according to the target job attribute, the target document topic and the outline document screening request, obtain the second outline guide template, input the second outline guide template into the large language model LLM, obtain the target outline document from the target candidate outline document, and finally return the target outline document to the user device.

[0089] In summary, the information acquisition method of the embodiment of the present disclosure combines the search engine and the large language model, which can more accurately and reliably provide the target outline document matched with the job attribute and the document topic for the users in the enterprise. The user can subsequently fill in the content based on the target document outline, improving the writing efficiency of the user, and improving the quality level of the document.

[0090] It should be noted that in the technical solution of the present disclosure, the acquisition, storage and application of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0091] Figure 7 is a structural schematic diagram of an information acquisition device according to an embodiment of the present disclosure.

[0092] As Figure 7As shown, the information acquisition device 700 comprises a first acquisition module 710, a second acquisition module 720, and a third acquisition module 730.

[0093] The first acquisition module 710 is configured to acquire a plurality of historical search requests related to an enterprise, wherein each historical search request comprises a candidate job attribute and a candidate document topic corresponding to the candidate job attribute.

[0094] The second acquisition module 720 is configured to acquire, according to a large language model LLM and the historical search requests, a candidate outline document matching the candidate job attribute and the candidate document topic.

[0095] The third acquisition module 730 is configured to receive a target search request sent by a user device, acquire, from the candidate outline document, a target outline document matching the target search request, and feed back to the user device.

[0096] The first acquisition module 710 is configured to: for each candidate job attribute, acquire a document title of the candidate job attribute; perform information extraction on the document title of the candidate job attribute to obtain an initial document topic of the candidate job attribute; and filter, from the initial document topic of the candidate job attribute, a candidate document topic corresponding to the candidate job attribute.

[0097] The first acquisition module 710 is configured to: acquire an occurrence frequency of the initial document topic of the candidate job attribute and an occurrence frequency threshold; and according to the occurrence frequency of the initial document topic and the occurrence frequency threshold, filter, from the initial document topic of the candidate job attribute, the candidate document topic corresponding to the candidate job attribute.

[0098] The first acquisition module 710 is configured to: filter out, from the initial document topic of the candidate job attribute, a first initial document topic with an occurrence frequency less than the occurrence frequency threshold; and take a second initial document topic remaining in the initial document topic of the candidate job attribute as the candidate document topic corresponding to the candidate job attribute.

[0099] The second acquisition module 720 is configured to: acquire an initial outline guide template; edit the outline guide template according to the candidate job attribute, the candidate document topic, and the historical search request to acquire a first outline guide template; and input the first outline guide template into the large language model LLM to acquire the candidate outline document matching the candidate job attribute and the candidate document topic.

[0100] The device 700 is further configured to: establish a mapping relationship between the candidate outline document and a document theme and a work attribute corresponding to the candidate document outline; and store the mapping relationship in a search engine.

[0101] The third obtaining module 730 is configured to: parse the target search request to obtain a target document theme and user identification information corresponding to the user device; obtain a target work attribute corresponding to the user identification information; and obtain the target outline document based on the target document theme and the target work attribute.

[0102] The third obtaining module 730 is configured to: query a mapping relationship based on the target document theme and the target work attribute through a search engine to obtain a target candidate outline document matched with the target search request; and obtain the target outline document from the target candidate outline document based on the large language model LLM.

[0103] The third obtaining module 730 is configured to: generate an outline document screening request based on the target candidate outline document; edit an initial outline guide template based on the target work attribute, the target document theme and the outline document screening request to obtain a second outline guide template; and input the second outline guide template into the large language model LLM to obtain the target outline document from the target candidate outline document.

[0104] It should be noted that the above explanation and description of the information obtaining method embodiment also applies to the information obtaining device of the present disclosure, and the specific process will not be repeated here.

[0105] To sum up, the information obtaining device of the present disclosure obtains a plurality of historical search requests related to an enterprise, wherein each historical search request includes a candidate work attribute and a candidate document theme corresponding to the candidate work attribute; and obtains a candidate outline document matched with the candidate work attribute and the candidate document theme based on a large language model LLM and the historical search request; receives a target search request sent by a user device, and obtains a target outline document matched with the target search request from the candidate outline document and feeds back to the user device. The present disclosure can provide a target outline document matched with a work attribute and a document theme for a user in an enterprise, and the user can fill in content based on the target document outline subsequently, which improves the writing efficiency of the user and improves the quality level of the document.

[0106] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0107] Figure 8A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0108] like Figure 8 As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0109] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0110] The computing unit 801 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized 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 801 performs various methods and processes described above, such as the information acquisition method. For example, in some embodiments, the information acquisition method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded onto the RAM 803 and executed by the computing unit 801, one or more steps of the information acquisition method described above can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform the information acquisition method by any other suitable means, such as by means of firmware.

[0111] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0112] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0113] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can 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 the machine-readable storage medium would include a lined- up electrical connection, 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), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0114] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0115] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0116] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0117] The present disclosure also provides a computer program product comprising a computer program which, when executed by a processor, implements the information acquisition method as described above.

[0118] It should be understood that the various forms of flow shown above can be re-ordered, added to, or have steps deleted, using the flow. For example, the steps described in the present disclosure can be executed in parallel, in series, or in a different order, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

[0119] The above detailed description does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An information acquisition method, wherein, The method comprises: obtaining a plurality of historical search requests related to an enterprise, wherein each of the historical search requests comprises a candidate job attribute and a candidate document topic corresponding to the candidate job attribute; editing an initial outline guide template according to the candidate job attribute, the candidate document topic and the historical search request to obtain a first outline guide template; inputting the first outline guide template into a large language model (LLM) to obtain a candidate outline document matching the candidate job attribute and the candidate document topic; receiving a target search request sent by a user device, and parsing the target search request to obtain a target document topic and user identification information corresponding to the user device; obtaining a target job attribute corresponding to the user identification information, and based on the target document topic and the target job attribute, obtaining a target outline document matching the target search request from the candidate outline document and feeding back to the user device.

2. The method of claim 1, wherein, The method comprises: for each candidate job attribute, obtaining a document title of the candidate job attribute; performing information extraction on the document title of the candidate job attribute to obtain an initial document topic of the candidate job attribute; from the initial document topic of the candidate job attribute, screening out a candidate document topic corresponding to the candidate job attribute.

3. The method of claim 2, wherein, The method comprises: obtaining a frequency and a frequency threshold of the candidate document topic of the candidate job attribute; according to the frequency and the frequency threshold of the initial document topic, screening out the candidate document topic corresponding to the candidate job attribute from the initial document topic of the candidate job attribute.

4. The method of claim 3, wherein, The method comprises: from the initial document topic of the candidate job attribute, screening out a first initial document topic with a frequency less than the frequency threshold; taking a second initial document topic remaining in the initial document topic of the candidate job attribute as the candidate document topic corresponding to the candidate job attribute.

5. The method of claim 1, wherein, After the candidate outline document matching the candidate job attribute and the candidate document topic is obtained, the method comprises: establishing a mapping relationship between the candidate outline document and a document topic and a job attribute corresponding to the candidate outline document; storing the mapping relationship in a search engine.

6. The method of claim 1, wherein, The method comprises: according to the target document topic and the target job attribute, querying the mapping relationship through a search engine to obtain a target candidate outline document matching the target search request; according to the large language model (LLM), obtaining the target outline document from the target candidate outline document.

7. The method of claim 6, wherein, The obtaining the target outline document from the target candidate outline document according to the large language model LLM further includes: generating an outline document screening request based on the target candidate outline document; editing an initial outline guide template according to the target work attribute, the target document theme, and the outline document screening request to obtain a second outline guide template; inputting the second outline guide template into the large language model LLM to obtain the target outline document from the target candidate outline document.

8. An information acquisition apparatus, wherein, The device includes: The first obtaining module is configured to obtain a plurality of historical search requests related to an enterprise, wherein each historical search request includes a candidate work attribute and a candidate document theme corresponding to the candidate work attribute; The second obtaining module is configured to edit an initial outline guide template according to the candidate work attribute, the candidate document theme, and the historical search request to obtain a first outline guide template, and input the first outline guide template into a large language model LLM to obtain a candidate outline document matching the candidate work attribute and the candidate document theme; The third obtaining module is configured to receive a target search request sent by a user device, parse the target search request to obtain a target document theme and user identification information corresponding to the user device, obtain a target work attribute corresponding to the user identification information, and obtain a target outline document matching the target search request from the candidate outline document based on the target document theme and the target work attribute, and feed back to the user device.

9. The apparatus of claim 8, wherein, The first obtaining module is configured to: obtain a document title of the candidate work attribute for each candidate work attribute; perform information extraction on the document title of the candidate work attribute to obtain an initial document theme of the candidate work attribute; screen a candidate document theme corresponding to the candidate work attribute from the initial document theme of the candidate work attribute.

10. The apparatus of claim 9, wherein, The first obtaining module is configured to: obtain an occurrence frequency of the initial document theme of the candidate work attribute and an occurrence frequency threshold; screen a candidate document theme corresponding to the candidate work attribute from the initial document theme of the candidate work attribute according to the occurrence frequency of the initial document theme and the occurrence frequency threshold.

11. The apparatus of claim 10, wherein, The first obtaining module is configured to: screen out a first initial document theme with an occurrence frequency less than the occurrence frequency threshold from the initial document theme of the candidate work attribute; retain a second initial document theme remaining in the initial document theme of the candidate work attribute as the candidate document theme corresponding to the candidate work attribute.

12. The apparatus of claim 8, wherein, The device is further configured to: establish a mapping relationship between the candidate outline document and a document theme and a work attribute corresponding to the candidate outline document; store the mapping relationship in a search engine.

13. The apparatus of claim 8, wherein, The third obtaining module is configured to: obtain a target candidate outline document matching the target search request by querying a mapping relationship through a search engine according to the target document theme and the target work attribute; According to the large language model LLM, the target outline document is obtained from the target candidate outline document.

14. The apparatus of claim 13, wherein, The third obtaining module is configured to: generate an outline document screening request based on the target candidate outline document; edit an initial outline guide template according to the target work attribute, the target document theme, and the outline document screening request, to obtain a second outline guide template; input the second outline guide template into the large language model LLM, and obtain the target outline document from the target candidate outline document.

15. An electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

16. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method according to any one of claims 1-7.

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

Images