CN114638221A - Business model generation method and device based on business requirements - Google Patents
Business model generation method and device based on business requirements Download PDFInfo
- Publication number
- CN114638221A CN114638221A CN202210352741.0A CN202210352741A CN114638221A CN 114638221 A CN114638221 A CN 114638221A CN 202210352741 A CN202210352741 A CN 202210352741A CN 114638221 A CN114638221 A CN 114638221A
- Authority
- CN
- China
- Prior art keywords
- word
- sentence
- participle
- standard
- model
- 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 61
- 230000011218 segmentation Effects 0.000 claims abstract description 53
- 238000006243 chemical reaction Methods 0.000 claims abstract description 35
- 230000009471 action Effects 0.000 claims abstract description 19
- 238000004590 computer program Methods 0.000 claims description 23
- 238000010276 construction Methods 0.000 claims description 8
- 230000036961 partial effect Effects 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 17
- 238000012545 processing Methods 0.000 description 13
- 230000015654 memory Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 230000009466 transformation Effects 0.000 description 5
- 230000002829 reductive effect Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000007792 addition Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/151—Transformation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Machine Translation (AREA)
Abstract
The disclosure provides a business model generation method and device based on business requirements, and relates to the fields of artificial intelligence and business architecture. The method comprises the following steps: constructing a standard conversion template for converting between the natural language and the target business model; acquiring a demand text of natural language description aiming at a target service demand; performing word segmentation on the required text to obtain a first word segmentation word sentence, a second word segmentation word sentence and a third word segmentation word sentence with parts of speech being a subject, a predicate and an object respectively; extracting a first word segmentation word and sentence, judging whether the first word segmentation word and sentence exists in a standard role database, and if so, generating a first role lane according to the first word segmentation word and sentence; extracting a second participle word and a third participle word corresponding to the first participle word and a third participle word, and placing the second participle word and the third participle word after being combined in the first character lane to generate a plurality of task boxes of the first character lane; and connecting the task frames according to the action occurrence time sequence to generate a target business model.
Description
Technical Field
The disclosure relates to the field of artificial intelligence and business architecture, which can be applied to the field of financial science and technology, in particular to a business model generation method and device based on business requirements, an electronic device, a storage medium and a program product.
Background
Under the digital transformation wave, enterprises plan the development of the enterprises by using business models. The service model is relatively abstract, and can be normally used and constructed only after special training is carried out in a short period of time. According to the situation of building a business model in the working field, huge manpower and material resources are usually invested, the consumed time is long, and the subsequent maintenance cost is extremely high. In the digital transformation process, enterprises need to respond to the market in time, and therefore, too much time is hardly provided for maintenance and use of the business model. On the other hand, if the service model cannot be maintained in time, the service model will be distorted after a period of time and cannot play a role any more.
Disclosure of Invention
In view of the foregoing technical problems, the present disclosure provides a business model generation method, apparatus, electronic device, storage medium, and program product based on business requirements that improve the work efficiency of building and maintaining business models.
According to a first aspect of the present disclosure, there is provided a business model generation method based on business requirements, including: constructing a standard conversion template for converting between a natural language and a target business model, wherein the standard conversion template comprises a standard role database; acquiring a demand text of natural language description aiming at a target service demand; performing word segmentation on the required text to obtain a first word segmentation word sentence, a second word segmentation word sentence and a third word segmentation word sentence with parts of speech being a subject, a predicate and an object respectively; extracting a first participle word and sentence, judging whether the first participle word and sentence exists in a standard role database, and if so, generating a first role lane according to the first participle word and sentence; extracting a second participle word and a third participle word corresponding to the first participle word and a third participle word, and placing the second participle word and the third participle word after being combined in the first character lane to generate a plurality of task boxes of the first character lane; and connecting the task frames according to the action occurrence time sequence to generate a target business model.
According to an embodiment of the present disclosure, the standard conversion template further includes a standard verb database and a plurality of entity databases, the standard verb database includes a preset plurality of standard verbs, and each entity database includes an entity name, an entity attribute, and a value range.
According to the embodiment of the present disclosure, the target service model further includes an entity model, which determines whether the first word-dividing word-sentence exists in the standard role database, and further includes: when the first word-dividing word sentence does not exist in the standard role database, continuously judging whether the first word-dividing word sentence is matched with the entity attribute in the entity database, if so, taking the first word-dividing word sentence as the first entity attribute; otherwise, the first word-dividing word sentence is used as the first entity name; extracting a second participle word corresponding to the first participle word, and matching the second participle word with a near word to form at least one standard verb in a standard verb database; extracting a third participle word and sentence corresponding to the second participle word and sentence, and taking the third participle word and sentence as a first value range; and generating an entity model according to the first entity attribute, the first entity name and the first value range.
According to the embodiment of the present disclosure, when the requirement text includes the conditional sentence, after the step of generating the first character swim lane according to the first participle word sentence, the method further includes: extracting condition information in the condition sentence, and generating a judgment frame of a first character lane according to the condition information; performing word segmentation on the conditional sentence to obtain a fifth word segmentation word sentence and a sixth word segmentation word sentence with parts of speech respectively being predicates and objects; the fifth participle word and sentence and the sixth participle word and sentence combination are placed in a task frame of the first character lane; and connecting a line between the task frame and the judgment frame of the first character lane according to the action occurrence time sequence so as to update the target business model.
According to the embodiment of the disclosure, the conditional sentence has a sentence tendency, the sentence tendency includes at least one of a positive tendency and a negative tendency, and the step of extracting the condition information in the conditional sentence further includes: and judging whether the sentence meaning tendency of the conditional sentence comprises a positive tendency and a negative tendency at the same time, and if so, reserving the partial conditional sentence with the positive tendency.
According to an embodiment of the present disclosure, the standard conversion template further includes a plurality of associated element databases including at least one of a customer type database, a product name database, a channel name database, and a partner name database.
According to the embodiment of the disclosure, after the step of segmenting the demand text, the method further comprises the following steps: and extracting participle words and sentences with parts of speech as nouns, recording the participle words and sentences as fourth participle words and sentences, judging whether the fourth participle words and sentences are matched with at least one associated element database, and if so, generating corresponding model labels in the target service model according to the fourth participle words and sentences.
According to the embodiment of the present disclosure, the standard conversion template further includes a model checking unit, the model checking unit is preset with at least one model quality standard, and before the step of generating the target service model, the method further includes: and adjusting the current target business model according to at least one model quality standard so as to update the target business model.
A second aspect of the present disclosure provides a business model generating apparatus based on business requirements, including: the template construction module is used for constructing a standard conversion template used for converting between the natural language and the target business model, and the standard conversion template comprises a standard role database; the system comprises a demand text acquisition module, a demand text generation module and a demand text generation module, wherein the demand text acquisition module is used for acquiring a demand text of natural language description aiming at a target service demand; the demand text word segmentation module is used for segmenting the demand text to obtain a first word segmentation word sentence, a second word segmentation word sentence and a third word segmentation word sentence, wherein the parts of speech are respectively a subject, a predicate and an object; the role lane generation module is used for extracting the first word-dividing words and sentences, judging whether the first word-dividing words and sentences exist in the standard role database, and if so, generating a first role lane according to the first word-dividing words and sentences; the task frame generation module is used for extracting a second participle word and sentence and a third participle word and sentence corresponding to the first participle word and sentence, and generating a plurality of task frames of the first character lane after the second participle word and sentence and the third participle word and sentence are combined and placed behind the first character lane; and the model generation module is used for connecting the task frames according to the action occurrence time sequence to generate a target business model.
A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the business model generation method based on business requirements described above.
The fourth aspect of the present disclosure also provides a computer-readable storage medium, on which executable instructions are stored, and when executed by a processor, the instructions cause the processor to execute the business demand-based business model generation method described above.
A fifth aspect of the present disclosure also provides a computer program product comprising a computer program which, when executed by a processor, implements the business requirement based business model generating method described above.
Compared with the prior art, the business model generation method and device based on business requirements provided by the disclosure at least have the following beneficial effects:
the standard conversion template abstracted by the incidence relation between the natural language and the business model can realize the characteristic attribute of the quick conversion of the natural language into the business model, so that the conversion of the two languages is simpler, the construction and use thresholds of the business model are effectively reduced, the investment of a large amount of manpower and resources for ensuring the authenticity and the advancement of the business model is avoided, and the use demand of the market is quickly responded.
Drawings
The foregoing and other objects, features and advantages of the disclosure will be apparent from the following description of embodiments of the disclosure, which proceeds with reference to the accompanying drawings, in which:
FIG. 1 schematically illustrates an application scenario suitable for a business model generation method and apparatus based on business requirements according to an embodiment of the present disclosure;
FIG. 2 schematically illustrates a flow chart of a business model generation method based on business requirements according to an embodiment of the disclosure;
FIG. 3 schematically illustrates a flow chart of first-participle phrase determination according to an embodiment of the present disclosure;
FIG. 4 schematically illustrates a flow chart of a business model generation method when a requirement text is a conditional sentence according to an embodiment of the present disclosure;
FIG. 5 schematically illustrates a flow chart of sentence trend determination for a conditional sentence according to an embodiment of the present disclosure;
FIG. 6 schematically shows a flow diagram of model tag generation according to an embodiment of the disclosure;
FIG. 7 schematically illustrates a block diagram of specific conversion processing logic for each piece of requirement text, according to an embodiment of the present disclosure;
FIG. 8 schematically illustrates a flow diagram of model criteria checking in accordance with an embodiment of the present disclosure;
FIG. 9 schematically illustrates a block diagram of a business model generation apparatus based on business requirements, in accordance with an embodiment of the present disclosure;
FIG. 10 schematically illustrates a block diagram of an electronic device suitable for implementing a business model generation method based on business requirements, in accordance with an embodiment of the present disclosure.
Detailed Description
Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).
Some block diagrams and/or flowcharts are shown in the figures. It will be understood that some blocks of the block diagrams and/or flowchart illustrations, or combinations thereof, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the instructions, which execute via the processor, create means for implementing the functions/acts specified in the block diagrams and/or flowchart block or blocks. The techniques of this disclosure may be implemented in hardware and/or software (including firmware, microcode, etc.). In addition, the techniques of this disclosure may take the form of a computer program product on a computer-readable storage medium having instructions stored thereon for use by or in connection with an instruction execution system.
In the technical scheme of the disclosure, the processes of collecting, storing, using, processing, transmitting, providing, disclosing and applying the personal information of the related users are all in accordance with the regulations of related laws and regulations, necessary security measures are taken, and the customs of public sequences is not violated.
In the technical scheme of the disclosure, before the personal information of the user is acquired or collected, the authorization or the consent of the user is acquired.
The embodiment of the disclosure provides a business model generation method, a business model generation device, business model generation equipment, storage media and program products based on business requirements, relates to the fields of artificial intelligence and business architecture, and can be applied to the field of financial science and technology. The method comprises the following steps: constructing a standard conversion template for converting between a natural language and a target business model, wherein the standard conversion template comprises a standard role database; acquiring a demand text of natural language description aiming at a target service demand; performing word segmentation on the required text to obtain a first word segmentation word sentence, a second word segmentation word sentence and a third word segmentation word sentence with parts of speech being a subject, a predicate and an object respectively; extracting a first word segmentation word and sentence, judging whether the first word segmentation word and sentence exists in a standard role database, and if so, generating a first role lane according to the first word segmentation word and sentence; extracting a second participle word and a third participle word corresponding to the first participle word and a third participle word, and placing the second participle word and the third participle word after being combined in the first character lane to generate a plurality of task boxes of the first character lane; and connecting the task frames according to the action occurrence time sequence to generate a target business model.
Fig. 1 schematically illustrates an application scenario 100 suitable for a business model generation method and apparatus based on business requirements according to an embodiment of the present disclosure. It should be noted that fig. 1 is only an example of an application scenario in which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, but does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.
As shown in fig. 1, the application scenario 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 105 may be a server providing various services, such as a background management server (for example only) providing support for websites browsed by users using the terminal devices 101, 102, 103. The backend management server may analyze and process the received data such as the user request, and feed back a processing result (for example, a web page, information, or data obtained or generated according to the user request) to the terminal device.
It should be noted that the business model generation method based on business requirements provided by the embodiment of the present disclosure may be generally executed by the server 105. Accordingly, the business model generation device based on business requirements provided by the embodiments of the present disclosure may be generally disposed in the server 105. The business model generation method based on business requirements provided by the embodiment of the present disclosure may also be executed by a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and/or the server 105. Accordingly, the service model generation apparatus based on service requirement provided by the embodiment of the present disclosure may also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and/or the server 105.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
The service model generation method based on service requirement according to the disclosed embodiment will be described in detail below with reference to fig. 2 to 7 based on the application scenario described in fig. 1.
FIG. 2 schematically shows a flowchart of a business model generation method based on business requirements according to an embodiment of the disclosure.
As shown in fig. 2, the business model generation method based on business requirements of this embodiment may include operations S210 to S270.
In operation S210, a standard conversion template for converting between a natural language and a target business model is constructed, the standard conversion template including a standard character database.
In operation S220, a requirement text of a natural language description for a target business requirement is acquired.
In operation S230, the demand text is participled to obtain a first participle word and sentence, a second participle word and sentence, and a third participle word and sentence, the parts of speech of which are the subject, the predicate and the object, respectively.
In operation S240, the first participle word and sentence are extracted, and it is determined whether the first participle word and sentence exist in the standard character database, and if so, a first character lane is generated according to the first participle word and sentence.
In operation S250, a second participle word and a third participle word corresponding to the first participle word and sentence are extracted, and the second participle word and sentence and the third participle word and sentence are combined and placed behind the first character lane, so as to generate a plurality of task boxes of the first character lane.
In operation S260, a plurality of task boxes are connected according to the action occurrence sequence to generate a target business model.
For example, the requirement text describes that "after an individual customer clicks on a study remittance in a mobile banking, the system pops up a page of the study remittance for the customer to fill out. "
Firstly, matching a first word segmentation word sentence 'individual client' extracted after word segmentation with 'individual client' in the existing standard role database, and generating a first role lane according to the first word segmentation word sentence 'individual client'. Then, a second participle word sentence 'click' corresponding to the first participle word sentence 'individual client' and a third participle word sentence 'study leaving remittance' are combined and placed behind a first character lane where the 'individual client' is located, and a task box of the first character lane is generated. And finally, connecting the task frame with other task frames of the first character lane according to the action occurrence time sequence to generate a target business model.
Therefore, the embodiment of the disclosure adopts the word segmentation technology to split different words and sentences from the service requirement text expressed by the natural language, and can quickly convert the natural language into the target service model by constructing the standard conversion template between the natural language and the target service model, thereby reducing a large amount of labor investment and time occupation for constructing and maintaining the target service model, and ensuring that the target service model is consistent with the latest design.
It can be understood that the standard conversion template is established according to the characteristics of the natural language and the target business model, and plays a role of intermediary, and the model elements and the incidence relation thereof are standardized and structured. The standard transformation template also needs to consider, but is not limited to, the flow of the business process, and the business rules that should be followed during the process.
In an embodiment of the present disclosure, the standard conversion template further includes a standard verb database and a plurality of entity databases, where the standard verb database includes a plurality of preset standard verbs, and each entity database includes an entity name, an entity attribute, and a value range.
Further, the standard verbs may include, for example, additions, deletions, and modifications. Therefore, for each action word expressed by the non-standardized natural language, a function of converting the action word into the standardized word can be established in the standard conversion template so as to be compatible and ensure the quality of the target business model.
Fig. 3 schematically illustrates a flow chart of first participle word judgment according to an embodiment of the present disclosure.
As shown in fig. 3, the target business model further includes an entity model, and the determining in operation S240 whether the first word segmentation sentence exists in the standard role database may specifically include operations S2401 to S2404.
In operation S2401, when the first part-word and phrase does not exist in the standard role database, continuously determining whether the first part-word and phrase matches an entity attribute in the entity database, and if so, taking the first part-word and phrase as the first entity attribute; otherwise, the first word-dividing word sentence is used as the first entity name.
In operation S2402, a second participle word corresponding to the first participle word is extracted, and the second participle word is matched as at least one standard verb in the standard verb database by a near word.
In operation S2403, a third participle word and sentence corresponding to the second participle word and sentence is extracted, and the third participle word and sentence is used as the first value range.
In operation S2404, an entity model is generated according to the first entity attribute, the first entity name, and the first value range.
For example, the requirement text describes "document type add electronic identification cards. The user can handle related business by the electronic identity card. "
Since the first segmented word and sentence certificate type extracted after word segmentation does not exist in the standard role database, at the moment, the first segmented word and sentence certificate type is judged to be capable of being matched with the entity attribute of a certain entity database, and then the first segmented word and sentence certificate type is used as the first entity attribute.
Then, a second participle word sentence "add" corresponding to the "certificate type" and having a part-of-speech of the predicate is extracted, and a corresponding code is update by matching a synonym to a standard verb "add" in a standard verb database. Then, a third participle word sentence 'electronic identity card' corresponding to the 'increase' and having the part of speech as the object is extracted, and the third participle word sentence 'electronic identity card' is used as the first value range.
And finally, generating the entity model according to the first entity attribute, the first entity name and the first value range. Therefore, the target business model finally generated by the application also comprises the entity model.
It should be noted that, the operations S210 to S270 correspond to generating a flow model, having different character lanes and processing boxes or determination boxes corresponding to the character lanes, and establishing a relationship between the processing boxes or the determination boxes, so as to obtain the target business model. Further, the embodiment of the disclosure can also obtain the entity name required for creating the entity model by searching the nouns in the requirement text, and further obtain the corresponding entity attribute and threshold. Therefore, the process model and the entity model in the target business model complement each other, and each link of target business processing is better embodied.
Fig. 4 schematically shows a flowchart of a business model generation method when a requirement text is a conditional sentence according to an embodiment of the present disclosure.
In the embodiment of the present disclosure, when the requirement text includes the conditional sentence, as shown in fig. 4, after the step of generating the first character lane according to the first participle word sentence in operation S240, operation S410 to operation S440 may be further included.
In operation S410, condition information in the condition sentence is extracted, and a determination box of the first character lane is generated according to the condition information.
In operation S420, the conditional sentence is segmented to obtain a fifth segmented word sentence and a sixth segmented word sentence having parts of speech of the predicate and the object, respectively.
In operation S430, the fifth participle word and sentence combination is placed in the task box of the first character lane.
In operation S440, a line is connected between the task frame and the decision frame of the first character lane according to the action occurrence timing, so as to update the target business model.
For the case that the requirement text is a condition sentence, the embodiment of the present disclosure puts the condition information in the condition sentence into the judgment box in the first character lane, and then considers the predicate and the object part description in the condition sentence as a new requirement text for analysis and processing until the requirement text processing is finished.
For example, the requirements text describes: when the certificate information elements are not matched, the system prompts that the certificate provided by you can not be transacted in a mobile phone bank temporarily, please transact in a website, and the client clicks 'confirm' and then returns the page to the remittance service page; when the certificate information elements are consistent, the customer can enter the name of the school. "
The requirement text is a condition sentence, and the condition information 'certificate information elements are in accordance' in the condition sentence is put into a judgment box of a role lane where the 'system' is positioned. Then, the user is prompted to go to a task box of a role lane in which the website transacts' and the system is put in, wherein the certificate provided by the user is temporarily unavailable for transacting in a mobile phone bank. And then, establishing a connection line between a judgment frame and a task frame of a role swim lane in which the 'system' is positioned according to the action occurrence time sequence. Similarly, click 'confirm' ″, put into the task frame of the role lane where the client locates, and continue to establish the connection line between the previous task frame and the task frame according to the action occurrence time sequence; and putting the 'input school name' into a task frame of a role lane where the 'client' is positioned, and continuously establishing a connecting line between a judgment frame and the task frame according to the action occurrence time sequence.
Fig. 5 schematically illustrates a flowchart of sentence trend determination for a conditional sentence according to an embodiment of the present disclosure.
In the embodiment of the disclosure, the conditional sentence has a sentence tendency, and the sentence tendency includes at least one of a positive tendency and a negative tendency. At this time, as shown in fig. 5, before the step of extracting the condition information in the condition sentence in operation S410, operation S4101 may be specifically included.
In operation S4101, it is determined whether the sentence tendencies of the condition sentences include both positive tendencies and negative tendencies, and if so, the partial condition sentences of the positive tendencies are retained.
Therefore, when the contents of the conditional sentences in the requirement text are repeated and the meanings are opposite, the partial conditional sentences with positive meanings are retained.
In the embodiment of the present disclosure, the standard conversion template further includes a plurality of associated element databases. Specifically, the associated element database may include, for example, a customer type database, a product name database, a channel name database, and a partner name database. It should be noted that, in other embodiments, the association factor database may be set according to the actual needs of the target service, and the specific invention is not limited thereto.
It can be understood that, the subject is a noun, the predicate is a verb, and the object is a noun, and the embodiments of the present disclosure perform special restrictions on all nouns related to the requirement text, so as to label or remind a special noun in the target business model.
FIG. 6 schematically shows a flow diagram of model tag generation according to an embodiment of the disclosure.
As shown in fig. 6, in the embodiment of the present disclosure, after the step of performing word segmentation on the requirement text in operation S230, operation S2301 may be specifically included.
In operation S2301, the participle words and phrases whose parts of speech are nouns are extracted and recorded as fourth participle words and phrases, and whether the fourth participle words and phrases match at least one associated element database is determined, if yes, a corresponding model tag is generated in the target service model according to the fourth participle words and phrases.
For example, when the requirement text is 'when the certificate information elements do not match, the system prompts' you can not process the certificate at the mobile phone bank temporarily and please go to a website for processing. After ' customer clicks ' confirmation ', the page returns to the remittance service page; when the credential information elements match, the customer can enter the school name ".
Extracting all participle words and sentences with parts of speech as nouns, and recording as a fourth participle word and sentence, wherein the method comprises the following steps: "certificate information element", "system", "certificate", "mobile banking", "network point", "customer", "page", "remittance service", "page" and "school name". The mobile phone bank and the website can be found in the channel name database, model labels corresponding to the mobile phone bank and the website are generated in the target business model, and the mobile phone bank and the website can be used and separated. The remittance service can be found in the product name database, and a model label corresponding to the remittance service is generated in the target service model. And other words and sentences which are not matched with the fourth participle of any one of the associated element databases do not need to be processed.
In summary, based on the technical content disclosed above, fig. 7 schematically shows a logic block diagram of a specific conversion process for each piece of requirement text according to an embodiment of the disclosure.
As shown in fig. 7, the embodiment of the present disclosure may include at least one section of requirement text, and for different contents of each section of requirement text, starting from extracting a subject, extracting condition information in a condition sentence, and extracting other terms, the process may be gradually developed according to the above disclosure.
Therefore, the word segmentation technology is adopted in the embodiment of the disclosure to split different words and sentences from the service requirement text expressed by the natural language, and the standard conversion template between the natural language and the target service model is constructed, so that the natural language can be quickly converted into the target service model, a large amount of labor investment and time occupation for constructing and maintaining the target service model are reduced, and the target service model is ensured to be consistent with the latest design.
FIG. 8 schematically shows a flow diagram of model criteria checking according to an embodiment of the disclosure.
In the embodiment of the present disclosure, the standard conversion template further includes a model checking unit, and at least one model quality standard is preset in the model checking unit. As shown in fig. 8, before the step of generating the target business model in operation S260, operation S2601 may be further included.
In operation S2601, the current target business model is adjusted according to at least one model quality criterion to update the target business model.
The preset model quality standard may be set autonomously according to actual needs of the target service, and may include, for example: in the newly added and modified entity model, when the entity attributes are less than 5, the model is considered not to meet the quality standard of the model; at least one character lane is not 'system'; at least two outlets of the judgment frame are provided; no task frame which is not related to other task frames exists; there are multiple items in the model label in the same target business model.
As for the non-compliance with the standard requirements, the service can be processed by the architect according to the actual needs of the target service.
As can be seen from the above description, the standard conversion template abstracted from the association relationship between the natural language and the service model in the embodiment of the disclosure can realize the fast conversion of the natural language into the characteristic attribute of the service model, so that the conversion between the two languages is simpler, the construction and use thresholds of the service model are effectively reduced, the investment of a large amount of manpower and resources for ensuring the authenticity and the advancement of the service model is avoided, and the use requirements of the market are quickly responded.
Based on the business model generation method based on the business requirements, the disclosure also provides a business model generation device based on the business requirements. The apparatus will be described in detail below with reference to fig. 9.
FIG. 9 schematically shows a block diagram of a business model generation apparatus based on business requirements according to an embodiment of the present disclosure.
As shown in fig. 9, the business requirement-based business model generating apparatus 900 of this embodiment includes a template building module 910, a requirement text obtaining module 920, a requirement text word segmentation module 930, a role lane generating module 940, a task box generating module 950, and a model generating module 960.
A template construction module 910, configured to construct a standard transformation template for transforming between a natural language and a target business model, where the standard transformation template includes a standard role database. In an embodiment, the template building module 910 may be configured to perform the operation S210 described above, which is not described herein again.
A requirement text obtaining module 920, configured to obtain a requirement text of the natural language description for the target service requirement. In an embodiment, the requirement text obtaining module 920 may be configured to perform the operation S220 described above, which is not described herein again.
The required text word segmentation module 930 is configured to segment the required text to obtain a first word segmentation word and sentence, a second word segmentation word and sentence, and a third word segmentation word and sentence, where the parts of speech are a subject, a predicate, and an object, respectively. In an embodiment, the requirement text segmentation module 930 may be configured to perform the operation S230 described above, which is not described herein again.
And a role lane generation module 940, configured to extract the first participle word and sentence, determine whether the first participle word and sentence exists in the standard role database, and if so, generate a first role lane according to the first participle word and sentence. In an embodiment, the character lane generation module 940 can be configured to perform the operation S240 described above, which is not described herein again.
A task box generating module 950, configured to extract a second participle word and a third participle word corresponding to the first participle word and a third participle word and a fourth participle word are combined and placed behind the first character lane, and a plurality of task boxes of the first character lane are generated. In an embodiment, the task block generating module 950 may be configured to perform the operation S250 described above, which is not described herein again.
The model generating module 960 is configured to connect the task boxes according to the action occurrence sequence to generate a target business model. In an embodiment, the model generation module 960 may be configured to perform the operation S260 described above, which is not described herein again.
According to the embodiment of the disclosure, different words and sentences are split from the service requirement text expressed by the natural language by adopting a word segmentation technology, and the natural language can be quickly converted into the target service model by constructing the standard conversion template between the natural language and the target service model, so that a large amount of labor investment and time occupation for constructing and maintaining the target service model are reduced, and the target service model is ensured to be consistent with the latest design.
According to an embodiment of the present disclosure, any multiple modules of the template building module 910, the requirement text obtaining module 920, the requirement text participle module 930, the role lane generating module 940, the task box generating module 950 and the model generating module 960 may be combined into one module to be implemented, or any one module thereof may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the template construction module 910, the requirement text obtaining module 920, the requirement text participle module 930, the role swim lane generation module 940, the task block generation module 950, and the model generation module 960 may be at least partially implemented as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented by hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or implemented by any one of three implementations of software, hardware, and firmware, or by a suitable combination of any of them. Alternatively, at least one of the template construction module 910, the requirement text acquisition module 920, the requirement text segmentation module 930, the role swimlane generation module 940, the task box generation module 950, and the model generation module 960 may be at least partially implemented as a computer program module that, when executed, may perform corresponding functions.
FIG. 10 schematically illustrates a block diagram of an electronic device suitable for implementing a business model generation method based on business requirements, in accordance with an embodiment of the present disclosure.
As shown in fig. 10, an electronic device 1000 according to an embodiment of the present disclosure includes a processor 1001 that can 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 section 1008 into a Random Access Memory (RAM) 1003. Processor 1001 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 1001 may also include onboard memory for caching purposes. The processor 1001 may comprise a single processing unit or a plurality of processing units for performing the different actions of the method flows according to embodiments of the present disclosure.
In the RAM 1003, various programs and data necessary for the operation of the electronic apparatus 1000 are stored. The processor 1001, ROM 1002, and RAM 1003 are connected to each other by a bus 1004. The processor 1001 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 1002 and/or the RAM 1003. Note that the programs may also be stored in one or more memories other than the ROM 1002 and the RAM 1003. The processor 1001 may also perform various operations of the method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.
The present disclosure also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement a business model generation method based on business requirements according to an embodiment of the present disclosure.
According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present 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. For example, according to embodiments of the present disclosure, a computer-readable storage medium may include the ROM 1002 and/or the RAM 1003 described above and/or one or more memories other than the ROM 1002 and the RAM 1003.
Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the method illustrated in the flow chart. When the computer program product runs in a computer system, the program code is used for causing the computer system to realize the business requirement-based business model generation method provided by the embodiment of the disclosure.
The computer program performs the above-described functions defined in the system/apparatus of the embodiments of the present disclosure when executed by the processor 1001. The systems, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.
In one embodiment, the computer program may be hosted on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted in the form of a signal on a network medium, distributed, downloaded and installed via the communication part 1009, and/or installed from the removable medium 1011. The computer program containing program code may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
In such an embodiment, the computer program may be downloaded and installed from a network through the communication part 1009 and/or installed from the removable medium 1011. The computer program performs the above-described functions defined in the system of the embodiment of the present disclosure when executed by the processor 1001. The above described systems, devices, apparatuses, modules, units, etc. may be implemented by computer program modules according to embodiments of the present disclosure.
In accordance with embodiments of the present disclosure, program code for executing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, these computer programs may be implemented using high level procedural and/or object oriented programming languages, and/or assembly/machine languages. The programming language includes, but is not limited to, programming languages such as Java, C + +, python, the "C" language, or the like. The program code may execute entirely on the user computing device, partly on the user device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
The flowchart 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 or flowchart illustration, and combinations of blocks in the block diagrams 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.
It will be appreciated by a person skilled in the art that various combinations or/and combinations of features recited in the various embodiments of the disclosure and/or in the claims may be made, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.
The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.
Claims (12)
1. A target business model generation method based on business requirements comprises the following steps:
constructing a standard conversion template for converting between a natural language and a target business model, wherein the standard conversion template comprises a standard role database;
acquiring a demand text of natural language description aiming at a target service demand;
performing word segmentation on the required text to obtain a first word segmentation word sentence, a second word segmentation word sentence and a third word segmentation word sentence with parts of speech being a subject, a predicate and an object respectively;
extracting the first participle word and sentence, judging whether the first participle word and sentence exists in the standard role database, and if so, generating a first role lane according to the first participle word and sentence;
extracting a second participle word and a third participle word corresponding to the first participle word and a sentence, and placing the second participle word and the third participle word and sentence combination behind the first character lane to generate a plurality of task boxes of the first character lane; and
and connecting the task frames according to the action occurrence time sequence to generate a target business model.
2. The method of claim 1, wherein the standard conversion template further comprises a standard verb database comprising a preset plurality of standard verbs and a plurality of entity databases each comprising an entity name, an entity attribute and a value field.
3. The method of claim 2, wherein the target business model further comprises an entity model, and the determining whether the first participle clause exists in the standard roles database further comprises:
when the first word-dividing word sentence does not exist in the standard role database, continuously judging whether the first word-dividing word sentence is matched with the entity attribute in the entity database, if so, taking the first word-dividing word sentence as the first entity attribute; otherwise, the first word segmentation word sentence is used as a first entity name;
extracting a second participle word corresponding to the first participle word, and matching the second participle word with a similar meaning word to form at least one standard verb in the standard verb database; and
extracting a third participle word and sentence corresponding to the second participle word and sentence, and taking the third participle word and sentence as a first value range;
and generating the entity model according to the first entity attribute, the first entity name and the first value range.
4. The method of claim 1, wherein when the requirement text includes a conditional sentence, after the step of generating a first character lane from the first participle word sentence, further comprising:
extracting condition information in the condition sentence, and generating a judgment frame of the first character lane according to the condition information;
performing word segmentation on the conditional sentence to obtain a fifth word segmentation sentence and a sixth word segmentation sentence with parts of speech being a predicate and an object respectively;
the fifth participle word and sentence and the sixth participle word and sentence are combined and placed in a task frame of the first character lane; and
and connecting a line between the task frame and the judgment frame of the first character swimlane according to the action occurrence time sequence so as to update the target business model.
5. The method of claim 4, wherein the conditional sentence carries a sentence tendency, the sentence tendency including at least one of a positive tendency and a negative tendency, and the step of extracting the condition information in the conditional sentence is preceded by:
and judging whether the sentence tendency of the conditional sentence comprises a positive tendency and a negative tendency at the same time, and if so, reserving the partial conditional sentence with the positive tendency.
6. The method of claim 1, wherein the standard conversion template further comprises a plurality of association factor databases including at least one of a customer type database, a product name database, a channel name database, and a partner name database.
7. The method of claim 6, wherein the step of tokenizing the requirement text is followed by:
and extracting participle words and sentences with part of speech being nouns, recording the participle words and sentences as fourth participle words and sentences, judging whether the fourth participle words and sentences are matched with at least one association element database, and if so, generating corresponding model labels in the target service model according to the fourth participle words and sentences.
8. The method of claim 1, wherein the standard conversion template further comprises a model checking unit, the model checking unit is preset with at least one model quality standard, and the step of generating the target business model further comprises, before:
and adjusting the current target business model according to the at least one model quality standard so as to update the target business model.
9. A business model generation apparatus based on business requirements, comprising:
the template construction module is used for constructing a standard conversion template for converting between a natural language and a target business model, and the standard conversion template comprises a standard role database;
the system comprises a demand text acquisition module, a demand text generation module and a demand text generation module, wherein the demand text acquisition module is used for acquiring a demand text of natural language description aiming at a target service demand;
the demand text word segmentation module is used for segmenting the demand text to obtain a first word segmentation word sentence, a second word segmentation word sentence and a third word segmentation word sentence, wherein the parts of speech are respectively a subject, a predicate and an object;
a role lane generation module, configured to extract the first participle word and sentence, determine whether the first participle word and sentence exists in the standard role database, and if so, generate a first role lane according to the first participle word and sentence;
a task frame generation module, configured to extract a second participle word and sentence and a third participle word and sentence corresponding to the first participle word and sentence, and place the second participle word and sentence and the third participle word and sentence combination behind the first character lane, and generate a plurality of task frames of the first character lane; and
and the model generation module is used for connecting the task frames according to the action occurrence time sequence to generate a target business model.
10. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-8.
11. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 8.
12. A computer program product comprising a computer program which, when executed by a processor, implements a method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210352741.0A CN114638221A (en) | 2022-03-31 | 2022-03-31 | Business model generation method and device based on business requirements |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210352741.0A CN114638221A (en) | 2022-03-31 | 2022-03-31 | Business model generation method and device based on business requirements |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114638221A true CN114638221A (en) | 2022-06-17 |
Family
ID=81951045
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210352741.0A Pending CN114638221A (en) | 2022-03-31 | 2022-03-31 | Business model generation method and device based on business requirements |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114638221A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117743615A (en) * | 2024-02-19 | 2024-03-22 | 精灵控(南京)智能科技有限公司 | Data processing method and processing platform based on natural language |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130006608A1 (en) * | 2011-06-28 | 2013-01-03 | International Business Machines Corporation | Generating Complex Event Processing Rules |
| CN112765974A (en) * | 2021-01-19 | 2021-05-07 | 海尔数字科技(北京)有限公司 | Service assisting method, electronic device and readable storage medium |
| CN113448848A (en) * | 2021-06-25 | 2021-09-28 | 中国工商银行股份有限公司 | Transformation method and device based on use case method, electronic equipment and storage medium |
| CN114676694A (en) * | 2022-03-25 | 2022-06-28 | 中国工商银行股份有限公司 | Method, device, equipment, medium and program product for generating business model |
-
2022
- 2022-03-31 CN CN202210352741.0A patent/CN114638221A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130006608A1 (en) * | 2011-06-28 | 2013-01-03 | International Business Machines Corporation | Generating Complex Event Processing Rules |
| CN112765974A (en) * | 2021-01-19 | 2021-05-07 | 海尔数字科技(北京)有限公司 | Service assisting method, electronic device and readable storage medium |
| CN113448848A (en) * | 2021-06-25 | 2021-09-28 | 中国工商银行股份有限公司 | Transformation method and device based on use case method, electronic equipment and storage medium |
| CN114676694A (en) * | 2022-03-25 | 2022-06-28 | 中国工商银行股份有限公司 | Method, device, equipment, medium and program product for generating business model |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117743615A (en) * | 2024-02-19 | 2024-03-22 | 精灵控(南京)智能科技有限公司 | Data processing method and processing platform based on natural language |
| CN117743615B (en) * | 2024-02-19 | 2024-04-16 | 精灵控(南京)智能科技有限公司 | Data processing method and processing platform based on natural language |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113507419B (en) | Training method of traffic distribution model, traffic distribution method and device | |
| CN113014558B (en) | Message identification method, device, computer system and readable storage medium | |
| CN110750619B (en) | Chat record keyword extraction method and device, computer equipment and storage medium | |
| CN115292352A (en) | Question query method, device, equipment, medium and program product | |
| CN118096373A (en) | Transaction data processing method, apparatus, device, storage medium, and program product | |
| CN113448848B (en) | Conversion method and device based on use case method, electronic equipment and storage medium | |
| CN110737820B (en) | Method and apparatus for generating event information | |
| CN114638221A (en) | Business model generation method and device based on business requirements | |
| CN116956891A (en) | Information extraction method, information extraction device, electronic device, and readable storage medium | |
| CN116756281A (en) | Knowledge question-answering method, device, equipment and medium | |
| CN114676694A (en) | Method, device, equipment, medium and program product for generating business model | |
| CN116048463A (en) | Intelligent recommendation method and device for content of demand item based on label management | |
| CN114461665B (en) | Method, apparatus and computer program product for generating a statement transformation model | |
| CN115759292A (en) | Model training method and device, semantic recognition method and device, and electronic device | |
| CN115862025A (en) | Product specification element extraction method, device, equipment, medium and program product | |
| CN114626370A (en) | Training method, risk early warning method, apparatus, device, medium, and program product | |
| CN115238676A (en) | Method and device for identifying hot spots of bidding demands, storage medium and electronic equipment | |
| CN113095078A (en) | Associated asset determination method and device and electronic equipment | |
| CN110879868A (en) | Consultant scheme generation method, device, system, electronic equipment and medium | |
| CN114238574B (en) | Intention recognition method based on artificial intelligence and related equipment thereof | |
| CN117077656B (en) | Demonstration relation mining method and device, medium and electronic equipment | |
| KR102685291B1 (en) | A document generation system based on real-time collection information through cloud and a document generation method for the rfp | |
| CN115034476A (en) | Project risk prediction method, device, equipment, medium and program product | |
| CN118296119A (en) | Method, device, equipment, medium and program product for generating prompt word | |
| CN117520608A (en) | Data operation method, device, equipment and medium |
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 |