CN117492743A - Target application generation method and device based on large language model and storage medium - Google Patents
Target application generation method and device based on large language model and storage medium Download PDFInfo
- Publication number
- CN117492743A CN117492743A CN202311322085.0A CN202311322085A CN117492743A CN 117492743 A CN117492743 A CN 117492743A CN 202311322085 A CN202311322085 A CN 202311322085A CN 117492743 A CN117492743 A CN 117492743A
- Authority
- CN
- China
- Prior art keywords
- user
- target
- language model
- target application
- large language
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000006870 function Effects 0.000 claims abstract description 32
- 230000004044 response Effects 0.000 claims description 29
- 230000000694 effects Effects 0.000 claims description 26
- 238000012360 testing method Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 12
- 230000001172 regenerating effect Effects 0.000 claims description 4
- 230000001105 regulatory effect Effects 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 abstract description 7
- 238000013135 deep learning Methods 0.000 abstract description 4
- 238000003058 natural language processing Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 14
- 238000005516 engineering process Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/36—Software reuse
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
- G06F3/0482—Interaction with lists of selectable items, e.g. menus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04842—Selection of displayed objects or displayed text elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04847—Interaction techniques to control parameter settings, e.g. interaction with sliders or dials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/34—Graphical or visual programming
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Machine Translation (AREA)
Abstract
The disclosure provides a target application generation method, a target application generation device and a storage medium based on a large language model, and relates to the artificial intelligence fields of deep learning, the large language model, a generated dialogue, natural language processing and the like. The method may include: acquiring configuration information of a target application to be created, which is set by a user, wherein the configuration information comprises: the target large language model and auxiliary information, wherein the auxiliary information comprises: the target plug-in is matched with a specific function of the target application, the target large language model is a large language model used by the target application, and the specific function comprises a function which cannot be realized by the target large language model alone; and combining the auxiliary information with the target large language model to obtain the target application. By applying the scheme disclosed by the invention, the target application meeting the business requirements of the user can be simply and conveniently generated.
Description
Technical Field
The disclosure relates to the technical field of artificial intelligence, in particular to a target application generating method, device and storage medium based on a large language model in the fields of deep learning, large language model, generating type dialogue, natural language processing and the like.
Background
With the development of technology, large language models (LLM, large Language Model) are becoming more and more widely used in various scenarios. The large language model refers to a deep learning model trained using a large amount of text data, and can be used to generate natural language text, understand the meaning of the natural language text, and the like.
Disclosure of Invention
The disclosure provides a target application generation method, a target application generation device and a storage medium based on a large language model.
A target application generation method based on a large language model comprises the following steps:
acquiring configuration information of a target application to be created, which is set by a user, wherein the configuration information comprises: the target large language model and auxiliary information, wherein the auxiliary information comprises: a target plug-in matched with a specific function of the target application, wherein the target large language model is a large language model used by the target application, and the specific function comprises a function which cannot be realized by the target large language model alone;
and combining the auxiliary information with the target large language model to obtain the target application.
A large language model-based target application generation apparatus, comprising: the information acquisition module and the application generation module;
the information acquisition module is configured to acquire configuration information of a target application to be created, where the configuration information is set by a user and includes: the target large language model and auxiliary information, wherein the auxiliary information comprises: a target plug-in matched with a specific function of the target application, wherein the target large language model is a large language model used by the target application, and the specific function comprises a function which cannot be realized by the target large language model alone;
and the application generation module is used for combining the auxiliary information with the target large language model to obtain the target application.
An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as described above.
A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform a method as described above.
A computer program product comprising computer programs/instructions which when executed by a processor implement a method as described above.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a flow chart of an embodiment of a method for generating a target application based on a large language model according to the present disclosure;
FIG. 2 is a schematic diagram of an application configuration interface and an application effect test interface according to the present disclosure;
FIG. 3 is a schematic illustration of an insert presented in accordance with the present disclosure;
FIG. 4 is a schematic diagram of a manner in which a user creates and selects a knowledge base in accordance with the present disclosure;
FIG. 5 is a schematic diagram of a displayed alert word template according to the present disclosure;
FIG. 6 is a schematic diagram of the composition and structure of a first embodiment 600 of a target application generating device based on a large language model according to the present disclosure;
FIG. 7 is a schematic diagram of the composition and structure of a second embodiment 700 of a target application generating device based on a large language model according to the present disclosure;
fig. 8 shows a schematic block diagram of an electronic device 800 that may be used to implement embodiments of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of 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 in the following description for clarity and conciseness.
In addition, it should be understood that the term "and/or" herein is merely one association relationship describing the associated object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
FIG. 1 is a flow chart of an embodiment of a method for generating a target application based on a large language model according to the present disclosure. As shown in fig. 1, the following detailed implementation is included.
In step 101, configuration information of a target application to be created, which is set by a user, is obtained, where the configuration information includes: the target large language model and auxiliary information, wherein the auxiliary information comprises: and the target plug-in is matched with a specific function of the target application, wherein the target large language model is a large language model used by the target application, and the specific function comprises a function which cannot be realized by the target large language model alone.
In step 102, the auxiliary information is combined with the target large language model to obtain the target application.
For traditional large language models, it is often difficult to meet the business appeal of users in the vertical industry domain due to the limitations of their general knowledge.
By adopting the scheme of the embodiment of the method, a user can combine the corresponding plug-in capability with the large language model only by carrying out some simple configuration, so that a target application, namely a target application program, meeting the business requirements of the user in the vertical industry field is generated, and further, the requirement of the user for efficiently constructing a proprietary model application meeting the self requirements of enterprises is met, and the user can be an enterprise user.
In practical applications, the execution subject of the method embodiments of the present disclosure may be a predetermined tool platform.
In practical application, after acquiring a user creation instruction (such as clicking a predetermined button), an application configuration interface may be displayed for the user, and according to an operation performed by the user based on the application configuration interface, configuration information of a target application to be created may be determined.
Preferably, in response to obtaining a model selection instruction sent by a user, the selectable large language model can be presented to the user, and the large language model selected by the user can be used as a target large language model, in addition, in response to obtaining a plug-in selection instruction sent by the user, the selectable plug-in can be presented to the user, and one or all of the following plug-ins can be used as the target plug-in: and selecting the plug-ins from the displayed plug-ins by a user, and customizing the plug-ins.
The number, the types and the like of the large language models included in the selectable large language models can be determined according to actual needs, after a user sends a model selection instruction, the selectable large language models can be displayed to the user in a list form for selection by the user, accordingly, the user can select one large language model from the selectable large language models according to own needs, and the target large language model can be a knowledge enhancement large language model (ERNIE-Bot) for example, wherein ERNIE refers to a semantic representation model (Enhanced Representation through kNowledge IntEgration) with enhanced knowledge.
In addition, after the user sends the plug-in selection instruction, the selectable plug-ins can be displayed to the user, accordingly, the user can select to use the displayed plug-ins or not, specifically, if all the target plug-ins required by the user are included in the displayed plug-ins, the target plug-ins can be selected directly, or if all the target plug-ins are not included in the displayed plug-ins, the target plug-ins can be obtained in a self-defined manner, or if one part of the target plug-ins is included in the displayed plug-ins and the other part of the target plug-ins are not included in the displayed plug-ins, part of the target plug-ins included in the displayed plug-ins can be selected, and the other part of the target plug-ins can be obtained in a self-defined manner, so that the plug-in system is very flexible and convenient. The target plug-in is a plug-in matched with a specific function of the target application, namely, a plug-in capable of being used for realizing the specific function of the target application, wherein the specific function can be a function which cannot be realized by the target large language model alone.
Through the processing, a user can conveniently and quickly determine the required target large language model and the target plugin, so that a good foundation is laid for subsequent processing, and various capability plugins can be supported, and the plugin capability can be combined with the target large language model so as to quickly construct the target application conforming to the service requirements, wherein the plugin can be used for enriching some functions/capabilities which are not possessed by the target large language model, namely, the capability of the target large language model can be expanded, for example, the target large language model does not possess certain computing capability, and then the corresponding computing capability can be provided for the target large language model through the computing plugin.
Preferably, after the large language model selected by the user is used as the target large language model, M parameters which can be adjusted and correspond to the target large language model can be displayed, M is a positive integer, the specific value can be determined according to the actual requirement, parameter values which are respectively set by the user for each parameter can be obtained, and each parameter and the corresponding parameter value are added into the auxiliary information.
The target large language model usually corresponds to a plurality of different parameters, wherein one/some parameters are allowed to be adjusted, and the rest parameters are not allowed to be adjusted, accordingly, the parameters which are allowed to be adjusted/can be adjusted can be displayed to a user, so that the user can set corresponding parameter values according to the needs of the user, and further, the parameters which can be adjusted and the corresponding parameter values can be added into auxiliary information, so that the performance and the like of the obtained target application can be further improved.
Preferably, one or any combination of the following may also be performed:
1) Acquiring a knowledge base associated with a target large language model, and adding the knowledge base into auxiliary information, wherein the knowledge base is a knowledge base corresponding to the industry field to which a target application belongs;
2) Acquiring a prompt word (prompt) set by a user for a target large language model, and adding the prompt word into auxiliary information;
3) And acquiring an opening white set by a user, and adding the opening white into auxiliary information, wherein the opening white is used for displaying the initial position of a text part in a response result generated by a target application for input dialogue content.
Preferably, the knowledge base selected by the user from the created knowledge bases can be obtained and used as the knowledge base associated with the target large language model, and the number of the associated knowledge bases can be one or a plurality of knowledge bases. In addition, the method for obtaining the prompt word set by the user for the target large language model may include: the method comprises the steps of obtaining a user-defined prompt word input by a user and being used as the prompt word set by the user for a target large language model, or displaying an alternative prompt word template to the user and using the prompt word template selected by the user as the prompt word set by the user for the target large language model.
As previously described, the knowledge base may be a knowledge base corresponding to an industry domain to which the target application belongs, which may include various knowledge in the industry domain, such as various documents, and the like. The knowledge base can provide needed knowledge for the target large language model, namely, the target large language model can learn the content in the knowledge base, so that the performance of the target large language model is improved, and the like.
The user can set the prompt word for the target big language model, if the user does not set the prompt word, the target big language model can use the built-in prompt word, but the built-in prompt word is likely not to meet the actual requirement of the user, so that the user can set the prompt word without using the built-in prompt word, the accuracy of the prompt word is improved, in addition, the user can customize the prompt word, or for some non-professional users, the prompt word template provided by the platform can also be directly used, namely, the platform can display the alternative prompt word template to the user, so that the user can select one prompt word template from the alternative prompt word template as the prompt word set for the target big language model, and the use requirement of different types of users can be met.
In addition, the user can set a start white for displaying the initial position of the text part in the response result generated by the target application for the input dialogue content, namely, when the subsequent user performs dialogue with the target application, the start white can be placed at the forefront of the text part in the response result, so that the dialogue process is more humanized and the like.
In short, through the processing, the performance of the target application can be further improved through the association of a knowledge base, the setting of a prompt word, the setting of a start-up time and the like.
After the target large language model and various auxiliary information are determined, the auxiliary information can be combined with the target large language model to obtain the desired target application.
Preferably, the auxiliary information and the target large language model can be combined into a thinking chain, and the combined result is used as a required target application. The target large language model, the target plug-in, the associated knowledge base, the prompt words, the start of the scene and the like can be packaged into a whole in a preset mode, and the whole can serve as a target application, and the whole can provide services to the outside, such as generating a picture according to the input dialogue content (descriptive information) or generating a calculation result according to the input dialogue content (mathematical expression) and the like. The auxiliary information and the target large language model are combined into the thinking chain, so that the auxiliary information can be used for assisting the target large language model in carrying out chain thinking, and the capability and the like of the target large language model can be further expanded.
Preferably, after obtaining the target application, the following first process may be further performed: an application effect test interface of the target application is displayed for a user, and a corresponding response result is generated and displayed by the target application according to dialogue contents input by the user in a dialogue box of the application effect test interface; and responding to the determination that the user adjusts the configuration information of the target application according to the response result, regenerating the target application according to the adjusted configuration information, and repeatedly executing the first processing based on the regenerated target application.
In addition, preferably, in response to obtaining an online instruction sent by a user, the latest obtained target application is issued, where the online instruction is an instruction sent by the user after determining that the configuration information of the target application is not required to be adjusted according to a response result.
For example, if the dialog content input by the user in the dialog box of the application effect test interface is description information, a corresponding response result, such as a picture and a corresponding text description (text part), can be generated by using the target application according to the description information, then the user can manually evaluate whether the response result is satisfactory, if not, the description information can be adjusted, and the response result can be regenerated according to the adjusted description information, if the response result generated after adjusting the description information for a plurality of times is still not satisfactory, then the configuration information of the target application can be adjusted, correspondingly, the target application can be regenerated according to the adjusted configuration information, then the above-mentioned process can be repeated until the user is satisfactory for the current target application, i.e. the user considers that the configuration information of the target application is not required to be adjusted any more, further, the user can issue an online instruction, and thus the latest obtained target application can be issued.
The adjustment of the configuration information of the target application may refer to adjusting any information therein, that is, adjusting the target large language model and/or the auxiliary information, where one or more items of information may be adjusted when the auxiliary information is adjusted.
Through the processing, an application effect test function can be provided for the generated target application, so that a user can conveniently preview the application effect in real time, and the target application can be flexibly adjusted according to the application effect until the user is satisfied with the application effect, so that the operation steps from configuration to a test flow of the user are reduced, the black box reaction of the user to the actual effect in the process of configuring a model is avoided, and further the resource cost of the user for issuing the application is reduced.
In connection with the above description, fig. 2 is a schematic diagram of an application configuration interface and an application effect testing interface according to the present disclosure.
As shown in fig. 2, after the user clicks the selection box after "apply/model service", the selectable large language model may be displayed to the user in the form of a drop-down list, and if the user selects ERNIE-Bot as the target large language model, then 3 corresponding parameters for adjustment, that is, temperature, diversity and repetition penalty, may be further displayed, and the user may set the parameter values of the 3 parameters respectively. In addition, the user may click "+" corresponding to "plug-in" shown in the lower right corner, so that an alternative plug-in may be displayed for the user, fig. 3 is a schematic diagram of the illustrated plug-in described in this disclosure, where various available plug-ins may be included, such as a search plug-in, a text graph (Stable DiffusionV) plug-in, a weather forecast (weather feature) plug-in, a summary generation (chat file) plug-in based on a document, etc., the user may easily configure the plug-in capability to be combined with the target large language model by clicking "install", and in addition, if the user needs to adjust the plug-in, the previously selected plug-in may be removed by clicking "uninstall" and the user may also customize the plug-in according to his own needs.
As shown in FIG. 2, the user may also click on "associate knowledge bases" to associate the knowledge bases. Accordingly, FIG. 4 is a schematic diagram of a manner in which a user creates and selects a knowledge base as described in the present disclosure. As shown in FIG. 4, the user may create a knowledge base by himself and may select the created knowledge base to associate with the target large language model.
As shown in FIG. 2, the user may also enter a custom prompt, or the user may click on an "import template" so that an alternative prompt template may be presented to the user for selection by the user. Fig. 5 is a schematic diagram of a displayed alert word template according to the present disclosure. In addition, as shown in fig. 2, the user may set an open field, such as "hello, i is an x.
As shown in fig. 2, for the generated target application, a real-time application effect test function may be provided, that is, a user may preview and test the application effect in real time, so as to adjust configuration information of the target application, and the like. When it is determined that no adjustment is necessary, the "online" may be clicked to publish the latest obtained target application.
It should be noted that, for the sake of simplicity of description, the foregoing method embodiments are expressed as a series of combinations of actions, but it should be understood by those skilled in the art that the present disclosure is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present disclosure. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all of the preferred embodiments, and that the acts and modules referred to are not necessarily required by the present disclosure.
The foregoing is a description of embodiments of the method, and the following further describes embodiments of the present disclosure through examples of apparatus.
Fig. 6 is a schematic structural diagram of a first embodiment 600 of a target application generating device based on a large language model according to the present disclosure. As shown in fig. 6, includes: an information acquisition module 601 and an application generation module 602.
The information obtaining module 601 is configured to obtain configuration information of a target application to be created set by a user, where the configuration information includes: the target large language model and auxiliary information, wherein the auxiliary information comprises: and the target plug-in is matched with a specific function of the target application, wherein the target large language model is a large language model used by the target application, and the specific function comprises a function which cannot be realized by the target large language model alone.
The application generating module 602 is configured to combine the auxiliary information with the target large language model to obtain a target application.
By adopting the scheme of the embodiment of the device, a user can combine the corresponding plug-in capability with the large language model only by carrying out some simple configuration, so that a target application, namely a target application program, meeting the business requirements of the user in the vertical industry field is generated, and the requirement of the user for efficiently constructing a proprietary model application meeting the self requirements of enterprises is further met.
Preferably, the information obtaining module 601 may display an alternative large language model to the user in response to obtaining a model selection instruction sent by the user, and may use the large language model selected by the user as a target large language model, and in addition, in response to obtaining a plug-in selection instruction sent by the user, may display an alternative plug-in to the user, and may use one or all of the following plug-ins as the target plug-in: and selecting the plug-ins from the displayed plug-ins by a user, and customizing the plug-ins.
Preferably, after the large language model selected by the user is used as the target large language model, the information obtaining module 601 may further display M parameters that can be adjusted and correspond to the target large language model, where M is a positive integer, a specific value may be determined according to an actual requirement, and parameter values set by the user for each parameter may be obtained, and each parameter and the corresponding parameter value are added to the auxiliary information.
The target large language model usually corresponds to a plurality of different parameters, wherein some parameters or some parameters are allowed to be adjusted, and the rest parameters are not allowed to be adjusted, and accordingly, the parameters which are allowed to be adjusted/available for adjustment can be displayed to a user, so that the user can set corresponding parameter values according to own needs.
Preferably, the information obtaining module 601 may further obtain a knowledge base associated with the target large language model, add the knowledge base to the auxiliary information, where the knowledge base is a knowledge base corresponding to an industry domain to which the target application belongs, and/or obtain a prompt word set by a user for the target large language model, add the prompt word to the auxiliary information, and/or obtain an opening white set by the user, add the opening white to the auxiliary information, where the opening white is used to display a starting position of a text portion in a response result generated by the target application for the input dialog content.
Specifically, preferably, the information obtaining module 601 may obtain a knowledge base created and selected by the user as a knowledge base associated with the target large language model, and/or the information obtaining module 601 may obtain a custom prompt word input by the user as a prompt word set by the user for the target large language model, or display an alternative prompt word template to the user, and use the prompt word template selected by the user as a prompt word set by the user for the target large language model.
In addition, after determining the target large language model and various auxiliary information, the application generation module 602 may combine the auxiliary information with the target large language model to obtain the desired target application.
Preferably, the application generation module 602 may combine the auxiliary information with the target large language model into a mental chain, and use the combined result as the target application. The target large language model, the target plug-in, the associated knowledge base, the prompt words, the scene white and the like can be packaged into a whole to serve as a target application, and the whole provides services for the outside.
Fig. 7 is a schematic structural diagram of a second embodiment 700 of the target application generating device based on a large language model according to the present disclosure. As shown in fig. 7, includes: an information acquisition module 601, an application generation module 602, and an effect test module 603.
The information obtaining module 601 and the application generating module 602 are the same as those in the embodiment shown in fig. 6, and are not described again.
After obtaining the target application, the effect test module 603 may perform the following first process: an application effect test interface of the target application is displayed for a user, and a corresponding response result is generated and displayed by the target application according to dialogue contents input by the user in a dialogue box of the application effect test interface; and responding to the determination that the user adjusts the configuration information of the target application according to the response result, regenerating the target application according to the adjusted configuration information, and repeatedly executing the first processing based on the regenerated target application.
In addition, preferably, the effect test module 603 may issue the latest obtained target application in response to acquiring an online instruction issued by the user, where the online instruction is an instruction issued after the user determines that the configuration information of the target application does not need to be adjusted according to the response result.
The specific workflow of the embodiment of the apparatus shown in fig. 6 and fig. 7 may refer to the related description in the foregoing method embodiment, and will not be repeated.
In a word, by adopting the scheme disclosed by the disclosure, the target application meeting the business requirements of users in the vertical industry field can be simply and conveniently generated, so that the requirement of the users for efficiently building the exclusive model application meeting the self requirements of enterprises is met, moreover, an application effect test function can be provided for the generated target application, so that the users can conveniently preview the application effect in real time, the target application can be flexibly adjusted according to the application effect, and the resource cost of the user release application is reduced.
The scheme disclosed by the disclosure can be applied to the field of artificial intelligence, and particularly relates to the fields of deep learning, large language models, generated dialogue, natural language processing and the like. Artificial intelligence is the subject of studying certain thinking processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.) that make a computer simulate a person, and has technology at both hardware and software levels, and artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, etc., and artificial intelligence software technologies mainly include computer vision technologies, speech recognition technologies, natural language processing technologies, machine learning/deep learning, big data processing technologies, knowledge graph technologies, etc.
The configuration information, conversation content, etc. in the embodiments of the present disclosure are not specific to a specific user, and cannot reflect personal information of a specific user. In addition, in the technical scheme of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user all accord with the regulations of related laws and regulations, and the public order is not violated.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
Fig. 8 shows a schematic block diagram of an electronic device 800 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile apparatuses, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing apparatuses. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 8, the apparatus 800 includes a computing unit 801 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 802 or a computer program loaded from a storage unit 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to the bus 804.
Various components in device 800 are connected to I/O interface 805, including: an input unit 806 such as a keyboard, mouse, etc.; an output unit 807 such as various types of displays, speakers, and the like; a storage unit 808, such as a magnetic disk, optical disk, etc.; and a communication unit 809, such as a network card, modem, wireless communication transceiver, or the like. The communication unit 809 allows the device 800 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The computing unit 801 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of 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 the various methods and processes described above, such as the methods described in this disclosure. For example, in some embodiments, the methods described in the present disclosure may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 800 via ROM 802 and/or communication unit 809. When a computer program is loaded into RAM 803 and executed by computing unit 801, one or more steps of the methods described in the present disclosure may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the methods described in the present disclosure by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
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.
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 a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background 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 background, 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: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically 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 may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (19)
1. A target application generation method based on a large language model comprises the following steps:
acquiring configuration information of a target application to be created, which is set by a user, wherein the configuration information comprises: the target large language model and auxiliary information, wherein the auxiliary information comprises: a target plug-in matched with a specific function of the target application, wherein the target large language model is a large language model used by the target application, and the specific function comprises a function which cannot be realized by the target large language model alone;
and combining the auxiliary information with the target large language model to obtain the target application.
2. The method of claim 1, wherein,
the obtaining the configuration information of the target application to be created, which is set by the user, comprises the following steps:
responding to the obtained model selection instruction sent by the user, displaying the selectable large language model to the user, and taking the large language model selected by the user as the target large language model;
in response to obtaining a plug-in selection instruction sent by the user, displaying selectable plug-ins to the user, and taking one or all of the following plug-ins as the target plug-ins: and the user selects the plug-in from the displayed plug-ins and self-defines the plug-in.
3. The method of claim 2, further comprising:
and after the large language model selected by the user is used as the target large language model, M parameters which are corresponding to the target large language model and can be regulated are displayed, M is a positive integer, parameter values which are respectively set by the user for the parameters are obtained, and the parameters and the corresponding parameter values are added into the auxiliary information.
4. The method of claim 1, further comprising:
acquiring a knowledge base associated with the target large language model, and adding the knowledge base into the auxiliary information, wherein the knowledge base is a knowledge base corresponding to the industry field to which the target application belongs;
and/or obtaining a prompt word set by the user for the target large language model, and adding the prompt word into the auxiliary information;
and/or acquiring the opening white set by the user, adding the opening white into the auxiliary information, wherein the opening white is used for displaying the initial position of the text part in the response result generated by the target application for the input dialogue content.
5. The method of claim 4, wherein,
the obtaining a knowledge base associated with the target large language model comprises: acquiring a knowledge base selected by the user from the created knowledge bases as a knowledge base associated with the target large language model;
and/or, the step of obtaining the prompt word set by the user for the target large language model comprises the following steps: and acquiring a user-defined prompt word input by the user as the prompt word set by the user for the target large language model, or displaying an alternative prompt word template to the user, and taking the prompt word template selected by the user as the prompt word set by the user for the target large language model.
6. The method according to any one of claims 1-5, wherein,
the combining the auxiliary information with the target large language model to obtain the target application comprises the following steps: and combining the auxiliary information and the target large language model into a thinking chain, and taking the combined result as the target application.
7. The method of any of claims 1-5, further comprising:
after the target application is obtained, the following first processing is executed: displaying an application effect test interface of the target application for the user, and generating and displaying a corresponding response result by using the target application aiming at dialogue contents input by the user in a dialogue box of the application effect test interface; and responding to the determination that the user adjusts the configuration information of the target application according to the response result, regenerating the target application according to the adjusted configuration information, and repeatedly executing the first processing based on the regenerated target application.
8. The method of claim 7, further comprising:
and responding to the acquired online instruction sent by the user, and issuing the latest target application, wherein the online instruction is an instruction sent by the user after determining that the configuration information of the target application is not required to be adjusted according to the response result.
9. A large language model-based target application generation apparatus, comprising: the information acquisition module and the application generation module;
the information acquisition module is configured to acquire configuration information of a target application to be created, where the configuration information is set by a user and includes: the target large language model and auxiliary information, wherein the auxiliary information comprises: a target plug-in matched with a specific function of the target application, wherein the target large language model is a large language model used by the target application, and the specific function comprises a function which cannot be realized by the target large language model alone;
and the application generation module is used for combining the auxiliary information with the target large language model to obtain the target application.
10. The apparatus of claim 9, wherein,
the information acquisition module is used for responding to the acquisition of a model selection instruction sent by the user, displaying an alternative large language model to the user, taking the large language model selected by the user as the target large language model, responding to the acquisition of a plug-in selection instruction sent by the user, displaying an alternative plug-in to the user, and taking one or all of the following plug-ins as the target plug-in: and the user selects the plug-in from the displayed plug-ins and self-defines the plug-in.
11. The apparatus of claim 10, wherein,
the information acquisition module is further configured to display M parameters that can be adjusted and correspond to the target large language model after the large language model selected by the user is used as the target large language model, and acquire parameter values that are set by the user for each parameter respectively, and add each parameter and the corresponding parameter value to the auxiliary information.
12. The apparatus of claim 9, wherein,
the information acquisition module is further configured to acquire a knowledge base associated with the target large language model, add the knowledge base to the auxiliary information, where the knowledge base is a knowledge base corresponding to an industry field to which the target application belongs, and/or acquire a prompt word set by the user for the target large language model, add the prompt word to the auxiliary information, and/or acquire an opening white set by the user, add the opening white to the auxiliary information, where the opening white is used to display a starting position of a text part in a response result generated by the target application for input dialogue content.
13. The apparatus of claim 12, wherein,
the information acquisition module acquires a knowledge base selected by the user from the created knowledge bases as a knowledge base associated with the target large language model;
and/or the information acquisition module acquires the user-defined prompt word input by the user as the prompt word set by the user for the target big language model, or displays the alternative prompt word template to the user, and takes the prompt word template selected by the user as the prompt word set by the user for the target big language model.
14. The device according to any one of claims 9-13, wherein,
the application generation module combines the auxiliary information and the target large language model into a thinking chain, and takes the combined result as the target application.
15. The apparatus of any of claims 9-13, further comprising:
the effect testing module is used for executing the following first processing after the target application is obtained: displaying an application effect test interface of the target application for the user, and generating and displaying a corresponding response result by using the target application aiming at dialogue contents input by the user in a dialogue box of the application effect test interface; and responding to the determination that the user adjusts the configuration information of the target application according to the response result, regenerating the target application according to the adjusted configuration information, and repeatedly executing the first processing based on the regenerated target application.
16. The apparatus of claim 15, wherein,
the effect test module is further used for responding to the online instruction sent by the user, and issuing the latest target application, wherein the online instruction is an instruction sent by the user after determining that the configuration information of the target application is not required to be adjusted according to the response result.
17. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.
18. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-8.
19. A computer program product comprising computer programs/instructions which, when executed by a processor, implement the method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311322085.0A CN117492743A (en) | 2023-10-12 | 2023-10-12 | Target application generation method and device based on large language model and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311322085.0A CN117492743A (en) | 2023-10-12 | 2023-10-12 | Target application generation method and device based on large language model and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117492743A true CN117492743A (en) | 2024-02-02 |
Family
ID=89679008
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311322085.0A Pending CN117492743A (en) | 2023-10-12 | 2023-10-12 | Target application generation method and device based on large language model and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117492743A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117787668A (en) * | 2024-02-26 | 2024-03-29 | 中国科学院自动化研究所 | Target distribution method, device, electronic equipment, storage medium and program product based on large language model |
-
2023
- 2023-10-12 CN CN202311322085.0A patent/CN117492743A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117787668A (en) * | 2024-02-26 | 2024-03-29 | 中国科学院自动化研究所 | Target distribution method, device, electronic equipment, storage medium and program product based on large language model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117492743A (en) | Target application generation method and device based on large language model and storage medium | |
| WO2023142451A1 (en) | Workflow generation methods and apparatuses, and electronic device | |
| CN114036398A (en) | Content recommendation and ranking model training method, device, equipment and storage medium | |
| CN115185434A (en) | Vehicle application scene processing method, device, equipment and storage medium | |
| US20230004360A1 (en) | Methods for managing process application development and integration with bots and devices thereof | |
| CN111090740B (en) | Knowledge graph generation method for dialogue system | |
| CN116992000A (en) | Interactive information processing method, device, electronic equipment and computer readable medium | |
| CN112562043A (en) | Image processing method and device and electronic equipment | |
| CN116089739A (en) | Message pushing method, device, electronic equipment and storage medium | |
| CN114417822A (en) | Method, apparatus, device, medium and product for generating model interpretation information | |
| CN113408632A (en) | Method and device for improving image classification accuracy, electronic equipment and storage medium | |
| CN113554062A (en) | Training method, device and storage medium of multi-classification model | |
| CN114741072B (en) | Page generation method, device, equipment and storage medium | |
| CN117750050A (en) | Information processing method and device based on large language model and electronic equipment | |
| CN116561075B (en) | Method for generating dynamic link library file, method and device for calling operator | |
| CN116629810B (en) | Operation recommendation method, device, equipment and medium based on building office system | |
| CN113836291B (en) | Data processing method, device, equipment and storage medium | |
| EP4071690A2 (en) | Method and apparatus for task information management, device and storage medium | |
| CN116701571A (en) | Page display method and device, electronic equipment and storage medium | |
| CN117785165A (en) | Chart generation method and device based on large model and electronic equipment | |
| CN117806622A (en) | Application program generation method and device, electronic equipment and storage medium | |
| CN117520489A (en) | Interaction method, device, equipment and storage medium based on AIGC | |
| CN116757921A (en) | User head portrait updating method and device, electronic equipment and storage medium | |
| CN117349653A (en) | Crowd circling method and device, electronic equipment and storage medium | |
| CN117194696A (en) | Content generation method, device, equipment and storage medium based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |