Movatterモバイル変換


[0]ホーム

URL:


CN119961392A - Question and answer result output method, device, storage medium and program product - Google Patents

Question and answer result output method, device, storage medium and program product
Download PDF

Info

Publication number
CN119961392A
CN119961392ACN202411898163.6ACN202411898163ACN119961392ACN 119961392 ACN119961392 ACN 119961392ACN 202411898163 ACN202411898163 ACN 202411898163ACN 119961392 ACN119961392 ACN 119961392A
Authority
CN
China
Prior art keywords
data packet
service data
text information
user
knowledge base
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202411898163.6A
Other languages
Chinese (zh)
Inventor
林叶
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Seashell Housing Beijing Technology Co Ltd
Original Assignee
Seashell Housing Beijing Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Seashell Housing Beijing Technology Co LtdfiledCriticalSeashell Housing Beijing Technology Co Ltd
Priority to CN202411898163.6ApriorityCriticalpatent/CN119961392A/en
Publication of CN119961392ApublicationCriticalpatent/CN119961392A/en
Pendinglegal-statusCriticalCurrent

Links

Classifications

Landscapes

Abstract

Translated fromChinese

本公开实施例提供了一种问答结果输出方法、设备、存储介质及程序产品,涉及大模型技术领域。该方法包括:获取用户输入的文本信息,根据用户输入的文本信息确定初始业务数据包;获取预设的语义映射字典和索引字典,根据预设的语义映射字典和索引字典对初始业务数据包进行转换处理,得到目标业务数据包;将用户输入的文本信息、目标业务数据包、第一知识库和第二知识库输入至预设的大模型中,基于预设的大模型输出问答结果。采用本技术方案,能够实时查询业务数据信息,并提高了业务数据信息的响应速度以及响应内容的准确率。

The disclosed embodiments provide a method, device, storage medium and program product for outputting question and answer results, and relate to the field of big model technology. The method includes: obtaining text information input by a user, and determining an initial business data packet according to the text information input by the user; obtaining a preset semantic mapping dictionary and an index dictionary, and converting and processing the initial business data packet according to the preset semantic mapping dictionary and the index dictionary to obtain a target business data packet; inputting the text information input by the user, the target business data packet, the first knowledge base and the second knowledge base into a preset big model, and outputting question and answer results based on the preset big model. The adoption of this technical solution enables real-time query of business data information, and improves the response speed of business data information and the accuracy of response content.

Description

Question and answer result output method, device, storage medium and program product
Technical Field
The embodiment of the disclosure relates to the technical field of large models, in particular to a question and answer result output method, equipment, a storage medium and a program product.
Background
During business operations, business personnel often feed back private data problems in the group to seek consultation. Since the problem-solving process is complex and time-consuming, it is important to introduce AI technology to solve these high-frequency problems intelligently.
But currently mainstream large models are often dependent on a fixed conventional knowledge base in combination with private data. However, the content of the conventional knowledge base is static text, and cannot flexibly adapt to continuously changing business data.
Therefore, a method for outputting a question-answer result is needed, which can query service data information in real time and improve the response speed of the service data information and the accuracy of response content.
Disclosure of Invention
To solve or at least partially solve the above technical problems, embodiments of the present disclosure provide a question and answer result output method, apparatus, storage medium, and program product.
A first aspect of an embodiment of the present disclosure provides a question-answer result output method, including:
Acquiring text information input by a user, and determining an initial service data packet according to the text information input by the user, wherein the initial service data packet is used for representing service data information associated with the text information input by the user;
Acquiring a preset semantic mapping dictionary and an index dictionary, and converting the initial service data packet according to the preset semantic mapping dictionary and the index dictionary to obtain a target service data packet;
Inputting the text information input by the user, the index dictionary, the target business data packet, a first knowledge base and a second knowledge base into a preset big model, and outputting a question-answer result based on the preset big model, wherein the first knowledge base is a basic knowledge base related to the text information input by the user, and the second knowledge base is a similar knowledge base related to the text information input by the user.
In one example, the converting the initial service data packet according to the preset semantic mapping dictionary and the index dictionary to obtain a target service data packet includes:
performing first conversion processing on the initial service data packet according to the preset semantic mapping dictionary to obtain an intermediate service data packet;
and performing second conversion processing on the intermediate service data packet according to the index dictionary to obtain the target service data packet.
In one example, the performing a first conversion process on the initial service data packet according to the preset semantic mapping dictionary to obtain an intermediate service data packet includes:
acquiring first semantic information and second semantic information in the preset semantic mapping dictionary, and searching the first semantic information in the initial service data packet, wherein the first semantic information and the second semantic information have a corresponding relation;
and replacing the first semantic information in the initial service data packet with the second semantic information to obtain the intermediate service data packet.
In one example, the performing, according to the index dictionary, a second conversion process on the intermediate service data packet to obtain the target service data packet includes:
Acquiring the second semantic information and the number information in the index dictionary, and searching the second semantic information in the intermediate service data packet, wherein the second semantic information and the number information have a corresponding relation;
And replacing the second semantic information in the intermediate service data packet with the number information to obtain the target service data packet.
In one example, the determining an initial service data packet according to the text information input by the user includes:
Inputting the text information input by the user into a classification model, and determining the business category to which the text information input by the user belongs based on the classification model;
and identifying keywords in the text information input by the user based on the classification model, and determining the initial service data packet in the service category according to the keywords.
In one example, the second knowledge base is a similar knowledge base associated with text information entered by the user, comprising:
Inputting the text information input by the user into an expansion knowledge base, and searching text information similar to the text information input by the user in the expansion knowledge base;
And determining the similar text information as the second knowledge base.
In one example, the determining the similar text information as the second knowledge base includes:
And combining the similar text information which is larger than a threshold value to obtain the second knowledge base.
A second aspect of the embodiments of the present disclosure provides a question-answer result output apparatus, including:
The system comprises an acquisition module, a service data processing module and a service data processing module, wherein the acquisition module is used for acquiring text information input by a user and determining an initial service data packet according to the text information input by the user, wherein the initial service data packet is used for representing service data information related to the text information input by the user;
The processing module is used for acquiring a preset semantic mapping dictionary and an index dictionary, and converting the initial service data packet according to the preset semantic mapping dictionary and the index dictionary to obtain a target service data packet;
The output module is used for inputting the text information input by the user, the index dictionary, the target business data packet, a first knowledge base and a second knowledge base into a preset big model, and outputting a question-answer result based on the preset big model, wherein the first knowledge base is a basic knowledge base associated with the text information input by the user, and the second knowledge base is a similar knowledge base associated with the text information input by the user.
A third aspect of the disclosed embodiments provides an electronic device comprising a processor and a memory, wherein the memory has stored therein a computer program which, when executed by the processor, performs the method of the first aspect described above.
A fourth aspect of the disclosed embodiments provides a computer readable storage medium having stored therein a computer program which, when executed by a processor, can implement the method of the first aspect described above.
A fifth aspect of the disclosed embodiments provides a computer program product comprising a computer program which, when executed by a processor, implements the method as described in the first aspect.
The embodiment of the disclosure provides a question and answer result output method, equipment, a storage medium and a program product, wherein the method comprises the steps of obtaining text information input by a user, determining an initial service data packet according to the text information input by the user, wherein the initial service data packet is used for representing service data information related to the text information input by the user, obtaining a preset semantic mapping dictionary and an index dictionary, converting the initial service data packet according to the preset semantic mapping dictionary and the index dictionary to obtain a target service data packet, inputting the text information input by the user, the target service data packet, a first knowledge base and a second knowledge base into a preset large model, and outputting a question and answer result based on the preset large model, wherein the first knowledge base is a basic knowledge base related to the text information input by the user, and the second knowledge base is a similar knowledge base related to the text information input by the user. By adopting the technical scheme, the service data information can be queried in real time, and the response speed of the service data information and the accuracy of response content are improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.
In order to more clearly illustrate the embodiments of the present disclosure or the solutions in the prior art, the drawings that are required for the description of the embodiments or the prior art will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
Fig. 1 is a flow chart of a question and answer result output method provided in an embodiment of the disclosure;
fig. 2a is a schematic flow chart of a question and answer result output method according to an embodiment of the disclosure;
FIG. 2b is a schematic diagram of a question and answer result output process provided by an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a question and answer result output device according to an embodiment of the disclosure;
fig. 4 is a schematic structural diagram of an electronic device in an embodiment of the disclosure.
Detailed Description
In order that the above objects, features and advantages of the present disclosure may be more clearly understood, a further description of aspects of the present disclosure will be provided below. It should be noted that, without conflict, the embodiments of the present disclosure and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced otherwise than as described herein, and it is apparent that the embodiments in the specification are only some, rather than all, of the embodiments of the present disclosure.
Fig. 1 is a flowchart of a question and answer result output method according to an embodiment of the disclosure, which may be performed by an electronic device. The electronic device may be understood as a device such as a mobile phone, tablet, notebook, desktop, smart television, etc., by way of example. As shown in fig. 1, the method provided in this embodiment includes the following steps:
S101, acquiring text information input by a user, and determining an initial service data packet according to the text information input by the user, wherein the initial service data packet is used for representing service data information associated with the text information input by the user.
The embodiment can be executed by an application program built in the electronic device, and specifically, can be executed by intelligent customer service in the application program. The text information input by the user is the business related questions to be consulted by the user. In this embodiment, text information input by a user is input to the intelligent customer service. The initial service data packet is used for representing service data information associated with text information input by a user, wherein the initial service data packet is a code file related to the service data.
S102, acquiring a preset semantic mapping dictionary and an index dictionary, and converting the initial service data packet according to the preset semantic mapping dictionary and the index dictionary to obtain a target service data packet.
In one example, the preset semantic mapping dictionary is a mapping relationship between different semantic information. For example, "name" corresponds to "name". The index dictionary is a mapping relation between semantic information and number information, for example, "name" corresponds to number information "1".
In one example, the data volume of the target traffic data packet is less than the data volume of the initial traffic data packet. And converting the initial service data packet through a preset semantic mapping dictionary and an index dictionary, so that the data volume of the initial service data packet is reduced, and a target service data packet is obtained.
S103, inputting text information input by a user, an index dictionary, a target business data packet, a first knowledge base and a second knowledge base into a preset large model, and outputting a question-answer result based on the preset large model, wherein the first knowledge base is a basic knowledge base associated with the text information input by the user, and the second knowledge base is a similar knowledge base associated with the text information input by the user.
In one example, the first knowledge base is a base knowledge base associated with text information entered by a user, wherein the base knowledge base is business related base data information. Such as the name of the service and basic data information of the service. The second knowledge base is a similar knowledge base associated with text information entered by the user.
In this embodiment, text information, an index dictionary, a target service data packet, a first knowledge base and a second knowledge base input by a user are input into a preset large model, so that the preset large model combines the text information, the index dictionary, the target service data packet, the first knowledge base and the second knowledge base input by the user to determine a question-answer result together.
The embodiment of the disclosure provides a question and answer result output method, which comprises the steps of obtaining text information input by a user, determining an initial service data packet according to the text information input by the user, wherein the initial service data packet is used for representing service data information related to the text information input by the user, obtaining a preset semantic mapping dictionary and an index dictionary, converting the initial service data packet according to the preset semantic mapping dictionary and the index dictionary to obtain a target service data packet, inputting the text information input by the user, the index dictionary, the target service data packet, a first knowledge base and a second knowledge base into a preset large model, and outputting a question and answer result based on the preset large model, wherein the first knowledge base is a basic knowledge base related to the text information input by the user, and the second knowledge base is a similar knowledge base related to the text information input by the user. By adopting the technical scheme, the service data information can be queried in real time, and the response speed of the service data information and the accuracy of response content are improved.
Fig. 2a shows a flowchart of a question and answer result output method according to an embodiment of the present disclosure. Embodiments of the present disclosure may be optimized based on the embodiments described above, and may be combined with various alternatives of one or more of the embodiments described above.
As shown in fig. 2a, the question and answer result output method may include the steps of:
S201, acquiring text information input by a user, and determining an initial service data packet according to the text information input by the user, wherein the initial service data packet is used for representing service data information associated with the text information input by the user.
In one example, determining an initial service data packet based on text information entered by a user includes:
Inputting text information input by a user into a classification model, and determining the business category to which the text information input by the user belongs based on the classification model;
and identifying keywords in text information input by a user based on the classification model, and determining an initial service data packet in the service category according to the keywords.
In one example, the classification model is used to make business class determinations for text information entered by a user. In this embodiment, different service data information belongs to different service classes, and the same service class includes a plurality of different initial service data packets.
In this embodiment, after determining, through the classification model, the service class to which the text information input by the user belongs, and then determining, in the service class, the initial service data packet associated with the text information input by the user through the keyword in the text information input by the user.
S202, acquiring a preset semantic mapping dictionary and an index dictionary.
In one example, this step may be referred to the content of step S102.
S203, performing first conversion processing on the initial service data packet according to a preset semantic mapping dictionary to obtain an intermediate service data packet.
In one example, performing a first conversion process on an initial service data packet according to a preset semantic mapping dictionary to obtain an intermediate service data packet, including:
Acquiring first semantic information and second semantic information in a preset semantic mapping dictionary, and searching the first semantic information in an initial service data packet, wherein the first semantic information and the second semantic information have a corresponding relation;
And replacing the first semantic information in the initial service data packet with the second semantic information to obtain an intermediate service data packet.
In one example, the first semantic information may be english semantic information and the second semantic information may be chinese semantic information. Specifically, the preset semantic mapping dictionary may be:
{
"name"; "name",
"Phone"; "phone",
"Sex"; "gender",
}
Wherein, "name", "phone", "sex" is first semantic information, and "name", "phone", "sex" is second semantic information.
In one example, the initial traffic data packet may be:
{
"name"; "Zhang san",
“phone”;“123456789”,
"Sex"; "man",
}
Wherein, "name", "phone", "sex" is the first semantic information. In this embodiment, the first semantic information "name" is found in the initial service data packet, then the first semantic information "name" is replaced with the second semantic information "name" in the initial service data packet, and other first semantic information is also replaced, so that the intermediate service data packet may be:
{
"name"; "Zhang san",
"Telephone"; "123456789",
"Sex"; "man",
}
Specifically, the english semantic information in the intermediate service data packet has been replaced with chinese semantic information.
S204, performing second conversion processing on the intermediate service data packet according to the index dictionary to obtain a target service data packet.
In one example, performing a second conversion process on the intermediate service data packet according to the index dictionary to obtain a target service data packet, including:
Acquiring second semantic information and numbering information in an index dictionary, and searching the second semantic information in an intermediate service data packet, wherein the second semantic information and the numbering information have a corresponding relation;
And replacing the second semantic information in the intermediate service data packet with the number information to obtain the target service data packet.
In one example, the numbering information is digital information, which may be 1,2, or 3, for example.
In this embodiment, the index dictionary may be:
{
"name"; "1",
"Telephone"; "2",
"Sex"; "3",
}
In one example, the second semantic information "name" is searched in the intermediate service data packet, the "name" is replaced by the number information "1", and other second semantic information is also replaced, so that the target service data packet is obtained:
{
"1"; "Zhang san",
“2”;“123456789”,
"3"; "Man",
}
Specifically, the chinese semantic information in the target service data packet has been replaced with numbering information. The advantage of this arrangement is that the cost of use of the pre-set large model can be effectively reduced.
S205, inputting text information input by a user, an index dictionary, a target business data packet, a first knowledge base and a second knowledge base into a preset large model, and outputting a question-answer result based on the preset large model, wherein the first knowledge base is a basic knowledge base associated with the text information input by the user, and the second knowledge base is a similar knowledge base associated with the text information input by the user.
In one example, the second knowledge base is a similar knowledge base associated with text information entered by a user, comprising:
Inputting text information input by a user into an expansion knowledge base, and searching text information similar to the text information input by the user in the expansion knowledge base;
And determining the similar text information as a second knowledge base.
In one example, the step may be parallel processed with step S201, specifically, the text information input by the user is expanded in the expansion knowledge base, so that more service data information related to the text information input by the user can be obtained, and then the second knowledge base is obtained.
In one example, determining similar text information as the second knowledge base includes:
and combining the similar text information which is larger than the threshold value to obtain a second knowledge base.
In one example, the threshold may be set in advance. In this embodiment, based on a preset similarity algorithm, similar text information greater than a threshold may be found, and all similar text information greater than the threshold may be combined to obtain a second knowledge base.
For a clearer illustration, reference may be made to a schematic illustration of a question and answer result output process shown in fig. 2 b.
The embodiment of the disclosure provides a question and answer result output method, which comprises the steps of obtaining text information input by a user, determining an initial service data packet according to the text information input by the user, obtaining a preset semantic mapping dictionary and an index dictionary, performing first conversion processing on the initial service data packet according to the preset semantic mapping dictionary to obtain a middle service data packet, and performing second conversion processing on the middle service data packet according to the index dictionary to obtain a target service data packet. Inputting text information input by a user, an index dictionary, a target service data packet, a first knowledge base and a second knowledge base into a preset large model, and outputting a question-answer result based on the preset large model, wherein the first knowledge base is a basic knowledge base associated with the text information input by the user, and the second knowledge base is a similar knowledge base associated with the text information input by the user. By adopting the technical scheme, the use cost of the large model is reduced, and the desensitization processing of the data is realized through simple field configuration.
Fig. 3 is a schematic structural diagram of a question-answer result output apparatus provided in an embodiment of the present disclosure, where the question-answer result output apparatus may be understood as the above-mentioned electronic device or a part of functional modules in the above-mentioned electronic device. As shown in fig. 3, the question-answer result output means 30 includes:
the acquiring module 301 is configured to acquire text information input by a user, and determine an initial service data packet according to the text information input by the user, where the initial service data packet is used to characterize service data information associated with the text information input by the user.
The processing module 302 is configured to obtain a preset semantic mapping dictionary and an index dictionary, and perform conversion processing on the initial service data packet according to the preset semantic mapping dictionary and the index dictionary to obtain a target service data packet.
The output module 303 is configured to input text information input by a user, an index dictionary, a target service data packet, a first knowledge base and a second knowledge base into a preset big model, and output a question-answer result based on the preset big model, where the first knowledge base is a basic knowledge base associated with the text information input by the user, and the second knowledge base is a similar knowledge base associated with the text information input by the user.
In one example, the processing module 302 includes:
the first processing sub-module is used for performing first conversion processing on the initial service data packet according to a preset semantic mapping dictionary to obtain an intermediate service data packet;
and the second processing sub-module is used for carrying out second conversion processing on the intermediate service data packet according to the index dictionary to obtain the target service data packet.
In one example, the first processing sub-module is specifically configured to:
Acquiring first semantic information and second semantic information in a preset semantic mapping dictionary, and searching the first semantic information in an initial service data packet, wherein the first semantic information and the second semantic information have a corresponding relation;
And replacing the first semantic information in the initial service data packet with the second semantic information to obtain an intermediate service data packet.
In one example, the second processing sub-module is specifically configured to:
Acquiring second semantic information and numbering information in an index dictionary, and searching the second semantic information in an intermediate service data packet, wherein the second semantic information and the numbering information have a corresponding relation;
And replacing the second semantic information in the intermediate service data packet with the number information to obtain the target service data packet.
In one example, the acquisition module 301 includes:
The first determining submodule is used for inputting text information input by a user into the classification model and determining the service class to which the text information input by the user belongs based on the classification model;
And the second determining sub-module is used for identifying keywords in text information input by a user based on the classification model and determining initial service data packets in service categories according to the keywords.
In one example, the second knowledge base is a similar knowledge base associated with text information entered by a user, comprising:
Inputting text information input by a user into an expansion knowledge base, and searching text information similar to the text information input by the user in the expansion knowledge base;
And determining the similar text information as a second knowledge base.
In one example, determining similar text information as the second knowledge base includes:
and combining the similar text information which is larger than the threshold value to obtain a second knowledge base.
The device provided in this embodiment can execute the method of any one of the above embodiments, and the execution mode and the beneficial effects thereof are similar, and are not described herein again.
The embodiment of the disclosure also provides electronic equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor is used for executing the computer program, and the method of any embodiment can be realized when the computer program is executed by the processor.
By way of example, fig. 4 is a schematic structural diagram of an electronic device in an embodiment of the present disclosure. Referring now in particular to fig. 4, a schematic diagram of an electronic device 1000 suitable for use in implementing embodiments of the present disclosure is shown. The electronic device 1000 in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 4 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.
As shown in fig. 4, the electronic device 1000 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 1001 that may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 1002 or a program loaded from a storage means 1008 into a Random Access Memory (RAM) 1003. In the RAM 1003, various programs and data necessary for the operation of the electronic apparatus 1000 are also stored. The processing device 1001, the ROM 1002, and the RAM 1003 are connected to each other by a bus 1004. An input/output (I/O) interface 1005 is also connected to bus 1004.
In general, devices including input devices 1006 such as a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc., output devices 1007 including a Liquid Crystal Display (LCD), speaker, vibrator, etc., storage devices 1008 including, for example, magnetic tape, hard disk, etc., and communication devices 1009 may be connected to the I/O interface 1005. The communication means 1009 may allow the electronic device 1000 to communicate wirelessly or by wire with other devices to exchange data. While fig. 4 shows an electronic device 1000 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs.
A fifth aspect of the disclosed embodiments provides a computer program product comprising a computer program which, when executed by a processor, implements a method as in the first aspect.
In such an embodiment, the computer program may be downloaded and installed from a network via the communication device 1009, or installed from the storage device 1008, or installed from the ROM 1002. The above-described functions defined in the method of the embodiment of the present disclosure are performed when the computer program is executed by the processing device 1001.
It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of a computer-readable storage medium may include, but are not limited to, an electrical connection having one or more wires, 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. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to electrical wiring, fiber optic cable, RF (radio frequency), and the like, or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol ), and may be interconnected with 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 (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.
The computer readable medium may be included in the electronic device or may exist alone without being incorporated into the electronic device.
The computer readable medium carries one or more programs, when the one or more programs are executed by the electronic equipment, the electronic equipment is caused to acquire text information input by a user, determine an initial business data packet according to the text information input by the user, wherein the initial business data packet is used for representing business data information related to the text information input by the user, acquire a preset semantic mapping dictionary and an index dictionary, convert the initial business data packet according to the preset semantic mapping dictionary and the index dictionary to obtain a target business data packet, input the text information input by the user, the target business data packet, a first knowledge base and a second knowledge base into a preset large model, output a question-answer result based on the preset large model, and the first knowledge base is a basic knowledge base related to the text information input by the user, and the second knowledge base is a similar knowledge base related to the text information input by the user. Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including, but not limited to, an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.
The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic that may be used include Field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems-on-a-chip (SOCs), complex Programmable Logic Devices (CPLDs), and the like.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The 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 a machine-readable storage medium would include an electrical connection based on one or more wires, 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.
The embodiments of the present disclosure further provide a computer readable storage medium, where a computer program is stored, where when the computer program is executed by a processor, the method of any of the foregoing embodiments may be implemented, and the implementation manner and the beneficial effects are similar, and are not repeated herein.
It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
The above is merely a specific embodiment of the disclosure to enable one skilled in the art to understand or practice the disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

Translated fromChinese
1.一种问答结果输出方法,其特征在于,所述方法包括:1. A method for outputting question and answer results, characterized in that the method comprises:获取用户输入的文本信息,根据所述用户输入的文本信息确定初始业务数据包;其中,所述初始业务数据包用于表征与所述用户输入的文本信息关联的业务数据信息;Acquire text information input by a user, and determine an initial service data packet according to the text information input by the user; wherein the initial service data packet is used to represent service data information associated with the text information input by the user;获取预设的语义映射字典和索引字典,根据所述预设的语义映射字典和所述索引字典对所述初始业务数据包进行转换处理,得到目标业务数据包;Obtaining a preset semantic mapping dictionary and an index dictionary, and converting the initial service data packet according to the preset semantic mapping dictionary and the index dictionary to obtain a target service data packet;将所述用户输入的文本信息、所述索引字典、所述目标业务数据包、第一知识库和第二知识库输入至预设的大模型中,基于所述预设的大模型输出问答结果;其中,所述第一知识库为与所述用户输入的文本信息关联的基础知识库;所述第二知识库为与所述用户输入的文本信息关联的相似知识库。The text information input by the user, the index dictionary, the target business data packet, the first knowledge base and the second knowledge base are input into a preset big model, and the question and answer results are output based on the preset big model; wherein the first knowledge base is a basic knowledge base associated with the text information input by the user; and the second knowledge base is a similar knowledge base associated with the text information input by the user.2.根据权利要求1所述的方法,其特征在于,所述根据所述预设的语义映射字典和所述索引字典对所述初始业务数据包进行转换处理,得到目标业务数据包,包括:2. The method according to claim 1, characterized in that the converting of the initial service data packet according to the preset semantic mapping dictionary and the index dictionary to obtain the target service data packet comprises:根据所述预设的语义映射字典对所述初始业务数据包进行第一转换处理,得到中间业务数据包;Performing a first conversion process on the initial service data packet according to the preset semantic mapping dictionary to obtain an intermediate service data packet;根据所述索引字典对所述中间业务数据包进行第二转换处理,得到所述目标业务数据包。The intermediate service data packet is subjected to a second conversion process according to the index dictionary to obtain the target service data packet.3.根据权利要求2所述的方法,其特征在于,所述根据所述预设的语义映射字典对所述初始业务数据包进行第一转换处理,得到中间业务数据包,包括:3. The method according to claim 2, wherein the first conversion process is performed on the initial service data packet according to the preset semantic mapping dictionary to obtain the intermediate service data packet, comprising:获取所述预设的语义映射字典中的第一语义信息和第二语义信息,在所述初始业务数据包中查找所述第一语义信息;其中,所述第一语义信息与所述第二语义信息具备对应关系;Acquire the first semantic information and the second semantic information in the preset semantic mapping dictionary, and search the first semantic information in the initial service data packet; wherein the first semantic information and the second semantic information have a corresponding relationship;将所述初始业务数据包中的所述第一语义信息替换为所述第二语义信息,得到所述中间业务数据包。The first semantic information in the initial service data packet is replaced with the second semantic information to obtain the intermediate service data packet.4.根据权利要求3所述的方法,其特征在于,所述根据所述索引字典对所述中间业务数据包进行第二转换处理,得到所述目标业务数据包,包括:4. The method according to claim 3, characterized in that the performing a second conversion process on the intermediate service data packet according to the index dictionary to obtain the target service data packet comprises:获取所述索引字典中的所述第二语义信息和编号信息,在所述中间业务数据包中查找所述第二语义信息;其中,所述第二语义信息与所述编号信息具备对应关系;Acquire the second semantic information and number information in the index dictionary, and search for the second semantic information in the intermediate service data packet; wherein the second semantic information and the number information have a corresponding relationship;将所述中间业务数据包中的所述第二语义信息替换为所述编号信息,得到所述目标业务数据包。The second semantic information in the intermediate service data packet is replaced with the numbering information to obtain the target service data packet.5.根据权利要求1所述的方法,其特征在于,所述根据所述用户输入的文本信息确定初始业务数据包,包括:5. The method according to claim 1, wherein determining the initial service data packet according to the text information input by the user comprises:将所述用户输入的文本信息输入至分类模型,基于所述分类模型确定所述用户输入的文本信息所属的业务类别;Inputting the text information input by the user into a classification model, and determining the business category to which the text information input by the user belongs based on the classification model;基于所述分类模型识别所述用户输入的文本信息中的关键字,根据所述关键字在所述业务类别中确定所述初始业务数据包。Keywords in the text information input by the user are identified based on the classification model, and the initial service data packet is determined in the service category according to the keywords.6.根据权利要求1所述的方法,其特征在于,所述第二知识库为与所述用户输入的文本信息关联的相似知识库,包括:6. The method according to claim 1, characterized in that the second knowledge base is a similar knowledge base associated with the text information input by the user, comprising:将所述用户输入的文本信息输入至拓展知识库中,在所述拓展知识库中查找与所述用户输入的文本信息相似的文本信息;Inputting the text information input by the user into an extended knowledge base, and searching the extended knowledge base for text information similar to the text information input by the user;将所述相似的文本信息确定为所述第二知识库。The similar text information is determined as the second knowledge base.7.根据权利要求6所述的方法,其特征在于,所述将所述相似的文本信息确定为所述第二知识库,包括:7. The method according to claim 6, characterized in that determining the similar text information as the second knowledge base comprises:将大于阈值的所述相似的文本信息进行合并处理,得到所述第二知识库。The similar text information greater than a threshold is merged to obtain the second knowledge base.8.一种电子设备,其特征在于,包括:8. An electronic device, comprising:处理器和存储器,其中,所述存储器中存储有计算机程序,当所述计算机程序被所述处理器执行时,所述处理器执行权利要求1-7中任一项所述的方法。A processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the method according to any one of claims 1 to 7.9.一种计算机可读存储介质,其特征在于,所述存储介质中存储有计算机程序,当所述计算机程序被处理器执行时,实现如权利要求1-7中任一项所述的方法。9. A computer-readable storage medium, characterized in that a computer program is stored in the storage medium, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.10.一种计算机程序产品,其特征在于,包括计算机程序,该计算机程序被处理器执行时实现如权利要求1-7中任一项所述的方法。10. A computer program product, characterized in that it comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
CN202411898163.6A2024-12-202024-12-20 Question and answer result output method, device, storage medium and program productPendingCN119961392A (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN202411898163.6ACN119961392A (en)2024-12-202024-12-20 Question and answer result output method, device, storage medium and program product

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN202411898163.6ACN119961392A (en)2024-12-202024-12-20 Question and answer result output method, device, storage medium and program product

Publications (1)

Publication NumberPublication Date
CN119961392Atrue CN119961392A (en)2025-05-09

Family

ID=95594663

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN202411898163.6APendingCN119961392A (en)2024-12-202024-12-20 Question and answer result output method, device, storage medium and program product

Country Status (1)

CountryLink
CN (1)CN119961392A (en)

Similar Documents

PublicationPublication DateTitle
CN111368185B (en)Data display method and device, storage medium and electronic equipment
CN111522927B (en) Entity query method and device based on knowledge graph
CN112906394B (en) Address identification method, device, equipment and storage medium
CN111400625B (en)Page processing method and device, electronic equipment and computer readable storage medium
CN110516159B (en)Information recommendation method and device, electronic equipment and storage medium
WO2022105775A1 (en)Search processing method and apparatus, model training method and apparatus, and medium and device
CN112148751B (en)Method and device for querying data
CN112819512A (en)Text processing method, device, equipment and medium
CN118964390A (en) Data query method, device, readable medium, electronic device and program product
CN109902726B (en) Resume information processing method and device
CN111737571B (en)Searching method and device and electronic equipment
WO2025087031A1 (en)Media data search method and apparatus, and storage medium and electronic device
CN119648818A (en) Image generation method, device, system, electronic device, and computer-readable medium
CN112084441A (en)Information retrieval method and device and electronic equipment
CN111782895B (en)Retrieval processing method and device, readable medium and electronic equipment
CN116431657A (en)Data query statement generation method, device, equipment, storage medium and product
CN115204124A (en) Word example generation method, device and electronic device
CN110619093B (en)Method, apparatus, electronic device, and computer-readable storage medium for determining an order of search items
CN119961392A (en) Question and answer result output method, device, storage medium and program product
CN115129845A (en) Text information processing method, device and electronic device
CN114970880A (en) Data screening method, device, storage medium and electronic device
CN114090832A (en)Method, device, equipment and storage medium for enquiring data of middle station
CN110598133A (en)Method, apparatus, electronic device, and computer-readable storage medium for determining an order of search items
CN114741407B (en)Condition query method and device and electronic equipment
CN120450036A (en) Output result determination method, device, client, server and storage medium

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination

[8]ページ先頭

©2009-2025 Movatter.jp