CN110705280A - Technical contract approval model creation method, device, equipment and storage medium - Google Patents
Technical contract approval model creation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110705280A CN110705280A CN201910785113.XA CN201910785113A CN110705280A CN 110705280 A CN110705280 A CN 110705280A CN 201910785113 A CN201910785113 A CN 201910785113A CN 110705280 A CN110705280 A CN 110705280A
- Authority
- CN
- China
- Prior art keywords
- technical
- technical contract
- model
- contract
- word vector
- 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 52
- 239000013598 vector Substances 0.000 claims abstract description 58
- 230000011218 segmentation Effects 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000013528 artificial neural network Methods 0.000 claims abstract description 18
- 238000003062 neural network model Methods 0.000 claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims abstract description 12
- 230000015654 memory Effects 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 16
- 238000011156 evaluation Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000000605 extraction Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000001364 causal effect Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000000052 comparative effect Effects 0.000 description 3
- 239000000470 constituent Substances 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000011022 operating instruction Methods 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 238000013475 authorization Methods 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 241000894007 species Species 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000000946 synaptic effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The method, the device, the equipment and the storage medium for establishing the technical contract affirmation model provided by the application establish a word vector set by performing word segmentation and part-of-speech indexing on the acquired technical contract; converting the incidence relation among all words in the word vector model into a multi-dimensional word vector model; and taking a preset result base corresponding to the technical contract judgment result and the word vector model as the input of the neural network model, and obtaining a technical contract identification model through neural network training and learning so as to identify the technical contract and the type of the technical contract. The method and the device have the advantages that entry analysis is carried out on the technical contract, the word segmentation unit and the relevant word analysis thereof are designed by combining the specific words of the known technical contract, the extraction of the specific words in the technical contract is optimized, the intelligent model base is established by utilizing the prior technical contract and the prior knowledge condition whether the prior technical contract meets the technical contract, and the cost for manually learning the characteristics of the technical contract is saved.
Description
Technical Field
The invention relates to the technical field of text processing, in particular to a method, a device, equipment and a storage medium for creating a technical contract affirmation model.
Background
The technical contract is a special contract, the technical contract not only has technical content, but also has more technical contract fulfillment links, long performance period and diversified legal adjustment of the technical contract, the technical contract is determined by auditors, and the technicians judge according to specific requirements. . In recent years, with the development of new generation machine learning technology, and in order to improve the judgment efficiency and accuracy and reduce the cost of judgment, a judgment model for the technical contract is needed to help better analyze the technical contract and give a scheme of type judgment result, and the intelligent judgment of the technical contract with specific requirements has practical significance.
Disclosure of Invention
In view of the above-described drawbacks of the prior art, it is an object of the present application to provide a technical contract approval model creation method, apparatus, device, and storage medium to solve the problems in the prior art.
To achieve the above and other related objects, the present application provides a technical contract approval model creation method, including: performing word segmentation and part-of-speech indexing on the acquired technical contract to establish a word vector set; converting the incidence relation among all words in the word vector model into a multi-dimensional word vector model; and taking a preset result base corresponding to the technical contract judgment result and the word vector model as the input of the neural network model, and obtaining a technical contract identification model through neural network training and learning so as to identify the technical contract and the type of the technical contract.
In an embodiment of the present application, the performing word segmentation and part-of-speech indexing on the obtained technical contract to establish a word vector set includes: combining the vocabulary after the technical contract is subjected to word segmentation with words and specific words to establish a word segmentation model; and optimizing the vocabulary after the word segmentation of the word segmentation model by combining the existing vocabulary entry.
In an embodiment of the present application, the converting the association relationship between words in the word vector model into a multidimensional word vector model includes: extracting specific words in the word vector model, and establishing an association relationship in a certain association format according to the association relationship among the words; wherein the association format comprises: an entry, a keyword, and an associated/related attribute triad and/or an entry, an attribute name, and an attribute value triad.
In one embodiment of the present application, the specific words include: nouns, noun phrases, vernouns, and vernoun phrases in any one or more combinations.
In an embodiment of the application, the preset result library of the evaluation results corresponding to the technical contracts is constructed by collecting the technical contracts of the existing evaluation results and establishing a corresponding relationship between each technical contract and the corresponding evaluation result.
In an embodiment of the present application, the method further includes: taking a preset scientific and technological achievement set as the input of a neural network model; extracting the vocabulary which has an incidence relation with scientific and technological achievements from the word vector model to calculate the similarity; if the similarity exceeds a certain numerical value, acquiring a limited vocabulary associated with the achievement vocabulary in the scientific and technological achievement set for analysis; and judging whether the scientific and technological achievements corresponding to the vocabularies are abnormal or not according to the analysis result.
In an embodiment of the present application, the method for presetting the scientific and technological achievement set includes: collecting the achievement vocabularies which represent scientific and technological achievement items in the technical contract; and acquiring the limited vocabulary corresponding to the scientific and technological achievement according to the associated verb corresponding to the entry to form a scientific and technological achievement set.
To achieve the above and other related objects, the present application provides an electronic device, comprising: the processing module is used for performing word segmentation and part-of-speech indexing on the acquired technical contract to establish a word vector set; converting the incidence relation among all words in the word vector model into a multi-dimensional word vector model; and the recognition module is used for taking a preset result base corresponding to the technical contract judgment result and the word vector model as the input of the neural network model, and obtaining a technical contract recognition model through neural network training and learning so as to recognize the technical contract and the type of the technical contract.
To achieve the above and other related objects, the present application provides a computer apparatus, comprising: a memory, and a processor; the memory is to store computer instructions; the processor executes computer instructions to implement the method as described above.
To achieve the above and other related objects, the present application provides a computer readable storage medium storing computer instructions which, when executed, perform the method as described above.
In summary, the method, the device, the equipment and the storage medium for establishing the technical contract affirmation model of the application establish a word vector set by performing word segmentation and part-of-speech indexing on the acquired technical contract; converting the incidence relation among all words in the word vector model into a multi-dimensional word vector model; and taking a preset result base corresponding to the technical contract judgment result and the word vector model as the input of the neural network model, and obtaining a technical contract identification model through neural network training and learning so as to identify the technical contract and the type of the technical contract.
Has the following beneficial effects:
the method and the device have the advantages that entry analysis is carried out on the technical contract, the word segmentation unit and the relevant word analysis thereof are designed by combining the specific words of the known technical contract, the extraction of the specific words in the technical contract is optimized, the intelligent model base is established by utilizing the prior technical contract and the prior knowledge condition whether the prior technical contract meets the technical contract, and the cost for manually learning the characteristics of the technical contract is saved.
Drawings
Fig. 1 is a flow chart illustrating a method for creating a technical contract approval model according to an embodiment of the present application.
Fig. 2 is a block diagram of an electronic device according to an embodiment of the present disclosure.
Fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application is provided by way of specific examples, and other advantages and effects of the present application will be readily apparent to those skilled in the art from the disclosure herein. The present application is capable of other and different embodiments and its several details are capable of modifications and/or changes in various respects, all without departing from the spirit of the present application. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Embodiments of the present application will be described in detail below with reference to the accompanying drawings so that those skilled in the art to which the present application pertains can easily carry out the present application. The present application may be embodied in many different forms and is not limited to the embodiments described herein.
In order to clearly explain the present application, components that are not related to the description are omitted, and the same reference numerals are given to the same or similar components throughout the specification.
Throughout the specification, when a component is referred to as being "connected" to another component, this includes not only the case of being "directly connected" but also the case of being "indirectly connected" with another element interposed therebetween. In addition, when a component is referred to as "including" a certain constituent element, unless otherwise stated, it means that the component may include other constituent elements, without excluding other constituent elements.
When an element is referred to as being "on" another element, it can be directly on the other element, or intervening elements may also be present. When a component is referred to as being "directly on" another component, there are no intervening components present.
Although the terms first, second, etc. may be used herein to describe various elements in some instances, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, the first interface and the second interface, etc. are described. Also, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context indicates otherwise. It will be further understood that the terms "comprises," "comprising," "includes" and/or "including," when used in this specification, specify the presence of stated features, steps, operations, elements, components, items, species, and/or groups, but do not preclude the presence, or addition of one or more other features, steps, operations, elements, components, species, and/or groups thereof. The terms "or" and/or "as used herein are to be construed as inclusive or meaning any one or any combination. Thus, "A, B or C" or "A, B and/or C" means "any of the following: a; b; c; a and B; a and C; b and C; A. b and C ". An exception to this definition will occur only when a combination of elements, functions, steps or operations are inherently mutually exclusive in some way.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the singular forms "a", "an" and "the" include plural forms as long as the words do not expressly indicate a contrary meaning. The term "comprises/comprising" when used in this specification is taken to specify the presence of stated features, regions, integers, steps, operations, elements, and/or components, but does not exclude the presence or addition of other features, regions, integers, steps, operations, elements, and/or components.
Terms indicating "lower", "upper", and the like relative to space may be used to more easily describe a relationship of one component with respect to another component illustrated in the drawings. Such terms are intended to include not only the meanings indicated in the drawings, but also other meanings or operations of the device in use. For example, if the device in the figures is turned over, elements described as "below" other elements would then be oriented "above" the other elements. Thus, the exemplary terms "under" and "beneath" all include above and below. The device may be rotated 90 or other angles and the terminology representing relative space is also to be interpreted accordingly.
Technical contracts of enterprises generally relate to related technical achievements, and the signing of the technical contracts is more direct reflection of the conversion of the technical achievements, so that some technical contracts can obtain certain benefits or policies such as subsidies or tax exemption after being recognized by governments or organizational units.
However, in general, due to factors such as higher professional degree, more contents, and compliance of technical result transformation of a technical contract compared with other contracts, the person who determines the technical contract needs to have not only legal knowledge but also corresponding technical experience.
The invention aims to provide a technical contract affirmation model establishing method, a device, equipment and a storage medium, which can affirm whether the technical contract belongs to the technical contract or not by adopting intelligent technology and affirm the type of the technical contract.
The technical contract related to the application comprises: technical development contracts, technical transfer contracts, technical consultation contracts and technical service contracts.
Fig. 1 is a schematic flow chart of a technical contract identification method in an embodiment of the present application. As shown, the method comprises:
step S101: and performing word segmentation and part-of-speech indexing on the acquired technical contract to establish a word vector set.
Because technical contracts have more professional vocabularies, compared with text contents in the field, the technical contracts have more nouns and dynamic nouns, and less spoken words, verbs, adjectives, adverbs, conjunctions, prepositions and the like, the technical contracts can perform preliminary word segmentation through words and specific phrases and index corresponding parts of speech to achieve better word segmentation effect.
For example, the names common in technical contracts such as "contract target," "contract offer," "unit name," "party A," "party B," "parameters," and the like.
In an embodiment of the present application, the step S101 further includes:
A. combining the vocabulary after the technical contract is subjected to word segmentation with words and specific words to establish a word segmentation model;
B. and optimizing the vocabulary after the word segmentation of the word segmentation model by combining the existing vocabulary entry.
In this embodiment, the technical contract is initially segmented according to words, such as nouns or dynamic nouns, and specific phrases. The basic words in the basic word set are mostly single nouns, specific limited nouns and the like so as to obtain a series of complete names.
Of course, in some technical contracts, the vocabulary used is not standard or named according to standards, so the vocabulary after the word segmentation of the word segmentation model is optimized through the modification of the existing vocabulary entry, and the accuracy and the universality are improved.
Step S102: and converting the incidence relation among the vocabularies in the word vector model into a multi-dimensional word vector model.
In an embodiment of the present application, the step S102 further includes:
extracting specific words in the word vector model, and establishing an association relationship in a certain association format according to the association relationship among the words; wherein the association format comprises: an entry, a keyword, and an associated/related attribute triad and/or an entry, an attribute name, and an attribute value triad.
The relationship described in this application refers to the semantic (pragmatic) association of two "words" in a technical contract. In one embodiment of the present application, the specific words include, but are not limited to: nouns, noun phrases, vernouns, and vernoun phrases in any one or more combinations. For example, the vocabulary mainly includes some specific words commonly found in technical contracts, such as "contract target", "contract offer", "unit name", "party a", "party b", "parameter", and other names commonly found in technical contracts, and further, specific words such as "cost", "term", "ownership" and other specific words may be compared in the technical contracts to determine related meaning or associated semantic content.
Furthermore, the incidence relation is determined by the part of speech indexed by each vocabulary in the word vector model, and the judgment is specifically carried out by the part of speech precedence relation, namely the logical relation.
In an embodiment of the present application, the association format includes: an entry, a keyword, and an associated/related attribute triad and/or an entry, an attribute name, and an attribute value triad.
Specifically, after a specific vocabulary is found, a word association model is established according to a certain format, such as a format or a name such as < vocabulary entry associated word association/association attribute > or < vocabulary entry attribute name attribute value > to represent the association relationship of each vocabulary.
For example, the association includes: display relationships, implicit relationships, semi-display relationships, and the like. Or may further include: timing relationships (synchronous relationships or asynchronous relationships), causal relationships (direct causal relationships, indirect causal relationships or objective relationships), conditional relationships (direct conditional relationships or formal conditional relationships (hypothetical relationships)), comparative relationships (direct comparative relationships, indirect comparative relationships (turning relationships), yielding relationships), extended relationships (refinement relationships, generalization relationships, progressive relationships), parallel relationships (parallel relationships, selection relationships), carrying relationships, and the like.
For example, "pay by stage because the target amount is too large," the word vector model can be established in the form of < target amount stage causal relationship >.
In this embodiment, filtering the technical contracts and forming the word vector model is also the format required for the following neural network model input.
Step S103: and taking a preset result base corresponding to the technical contract judgment result and the word vector model as the input of the neural network model, and obtaining a technical contract identification model through neural network training and learning so as to identify the technical contract and the type of the technical contract.
The neural network is a model for simulating the functions of the human brain nervous system by modeling and connecting the basic units of the human brain, namely neurons, and develops an artificial system with intelligent information processing functions of learning, association, memory, pattern recognition and the like. An important feature of a neural network is that it is able to learn from the environment and store the results of the learning distributed among the synaptic connections of the network. The learning of the neural network is a process, under the excitation of the environment where the neural network is located, some sample patterns are input to the network in sequence, the weight matrix of each layer of the network is adjusted according to a certain rule (learning algorithm), and the learning process is ended when the weights of each layer of the network are converged to a certain value. We can then use the generated neural network to classify the real data.
In brief, the neural network inputs the result base corresponding to the technical contract judgment result and the connection weight value of the word vector model and the expected output training (the confirmation training of the technical contract) to obtain the association relationship between the word vector model and the expected output training, and accordingly the technical contract confirmation result is formed.
The input and output of the neural network, i.e. the judgment results of the corresponding technical contracts in one or more result libraries and the word vector models of the corresponding technical contracts, are required to be continuously trained or trained, and a desired technical contract identification result is expected to be obtained. Outputting the result as desired includes: if the output result is not consistent with the provided technical contract, adjusting the related threshold value or parameter, and continuing to train through the neural network model to obtain the expected output result.
Generally, the technical contracts are classified into 4 categories, i.e., technical development contracts, technical transfer contracts, technical consultation contracts, and technical service contracts.
In this embodiment, the training by the neural network through the input and the desired output may further include: training is carried out through an error back propagation algorithm based on one or more groups of word vector models, and the training is the BP algorithm.
Specifically, the error back propagation algorithm performs back propagation calculation on an output error (a difference between an expected output and an actual output) according to an original path when a signal is reversely propagated, performs inversion through a hidden layer until the signal reaches an input layer, distributes the error to each unit of each layer in the back propagation process, obtains an error signal of each unit of each layer, and uses the error signal as a basis for correcting the weight of each unit. The calculation process is completed by using a gradient descent method, and after the weight values and the threshold values of neurons in each layer are continuously adjusted, error signals are reduced to the minimum.
The process of continuously adjusting the weight and the threshold is the learning and training process of the network, and the adjustment of the weight and the threshold is repeatedly carried out through signal forward propagation and error backward propagation until the preset learning and training times or the output error is reduced to an allowable degree.
In this embodiment, the training in step 103 may obtain the connection weight and the corresponding threshold, and based on this, the machine may identify or read the corresponding different word vector models and the evaluation results more reliably, or further include the logical relationship followed between the scientific and technological achievement sets described later. And with the continuous use of the system, after a new instance is input, a new result base and a new word vector model are learned through a neural network, and a new connection weight is automatically obtained.
In one or more embodiments, the application of the technical contracts does not present any problem in the technical contracts, but there may be problems in a plurality of technical contracts, such as a patent or a technical assignment contract, which should not normally be issued by a plurality of transferees within the same time period, i.e., the situation that the technical contract is counterfeit or not compliant. The problem of technical result compliance is also a concern when the method described in the present application is applied to the approval of a technical contract.
In an embodiment of the present application, the method further includes:
A. taking a preset scientific and technological achievement set as the input of a neural network model;
B. extracting the vocabulary which has an incidence relation with scientific and technological achievements from the word vector model to calculate the similarity;
C. if the similarity exceeds a certain numerical value, acquiring a limited vocabulary associated with the achievement vocabulary in the scientific and technological achievement set for analysis;
D. and prompting whether the scientific and technological achievement corresponding to the vocabulary is abnormal or not according to an analysis result.
In the embodiment, the collected scientific and technological achievements in the technical contract are first found, wherein the scientific and technological achievements are inventions, discoveries and other scientific and technological achievements obtained by research and development. The technical achievements can be divided into patent techniques and non-patent techniques according to different degrees of entitlement. Depending on the carrier, it can be expressed as technical data, design drawings, process recipes, material recipes, computer programs, technical information and combinations thereof; can also be expressed as samples, prototypes, new products, new materials, new production lines and the like. The technical result can be an industrial result or a stage result.
In this application, through regarding preset scientific and technological achievement set as the input of neural network model to supplementary training of affirming the result output.
Specifically, the achievement vocabularies in the preset scientific and technological achievement set and the vocabularies extracted from the word vector model and having an association relationship with the scientific and technological achievements are subjected to similar pair calculation, for example, a technology is used for confirming whether the technical achievement in the technical contract to be identified corresponds to the recorded technical achievement through comparison of keywords, because some technical names are changed continuously, but key technologies or key methods are not easy to change. If the similarity exceeds a certain proportion, such as 70% or 80%, then there is a greater probability that the same technical result or different forms of the same technical result are the same technical result, then a restricted vocabulary associated with the technical result vocabulary in the scientific and technological result set is obtained for analysis, the restricted vocabulary includes, for example, a target object, the time of authorization or assignment of the technical result, right assignment conditions, etc., and whether the same technical result or different forms of the same technical result belong to the same technical result or not is further analyzed according to the information, and finally the analysis result judges whether the scientific and technological result corresponding to the vocabulary is abnormal or not, so that technical contract affirmators can further verify the abnormal scientific and technological result.
In an embodiment of the present application, the method for presetting the scientific and technological achievement set includes:
A. and collecting the result vocabularies which represent the scientific and technological result items in the technical contract.
For example, the resulting vocabulary may be looked up based on a particular vocabulary or character, such as a title number lookup, a technical noun lookup passport.
Accordingly, relevant information of the achievement vocabularies, such as provenance and detailed content, can be collected.
B. And acquiring the limited vocabulary corresponding to the scientific and technological achievement according to the associated verb corresponding to the entry to form a scientific and technological achievement set.
In this embodiment, the associated verb is mainly a verb capable of indicating an object or a condition, so as to obtain a restricted vocabulary corresponding to the scientific and technological achievement. Wherein the defined vocabulary includes, but is not limited to: defining objects, defining time, defining conditions, etc., target objects, time of technical result authorization or transfer, ownership assignment conditions, etc., and finally forming a relatively complete set of result vocabulary.
Fig. 2 is a block diagram of an electronic device according to an embodiment of the present invention. As shown, the apparatus 200 includes:
the processing module 201 is used for performing word segmentation and part-of-speech indexing on the acquired technical contract to establish a word vector set; converting the incidence relation among all words in the word vector model into a multi-dimensional word vector model;
the recognition module 202 is configured to use a preset result library corresponding to the technical contract evaluation result and the word vector model as inputs of the neural network model, and obtain a technical contract recognition model through neural network training and learning, so as to recognize the technical contract and the type of the technical contract.
It should be noted that, because the contents of information interaction, execution process, and the like between the modules/units of the apparatus are based on the same concept as the method embodiment described in the present application, the technical effect brought by the contents is the same as the method embodiment of the present application, and specific contents may refer to the description in the foregoing method embodiment of the present application, and are not described herein again.
It should be further noted that the division of the modules of the above apparatus is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these units can be implemented entirely in software, invoked by a processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, the determination processing module 201 may be a processing element separately set up, or may be implemented by being integrated into a chip of the apparatus, or may be stored in a memory of the apparatus in the form of program code, and the function of the determination processing module 201 may be called and executed by a processing element of the apparatus. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.
For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. For another example, when one of the above modules is implemented in the form of a Processing element scheduler code, the Processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
Fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present invention. As shown, the computer device 300 includes: a memory 301, and a processor 302; the memory 301 is used for storing computer instructions; the processor 302 executes computer instructions to implement the method described in fig. 1.
In some embodiments, the number of the memories 301 in the computer device 300 may be one or more, the number of the processors 302 may be one or more, the number of the communicators 303 may be one or more, and fig. 3 illustrates one example.
In an embodiment of the present application, the processor 302 in the computer device 300 loads one or more instructions corresponding to processes of an application program into the memory 301 according to the steps described in fig. 1, and the processor 302 executes the application program stored in the memory 301, thereby implementing the method described in fig. 1.
The Memory 301 may include a Random Access Memory (RAM), and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The memory 301 stores an operating system and operating instructions, executable modules or data structures, or a subset thereof, or an expanded set thereof, wherein the operating instructions may include various operating instructions for implementing various operations. The operating system may include various system programs for implementing various basic services and for handling hardware-based tasks.
The Processor 302 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
In some specific applications, the various components of the computer device 300 are coupled together by a bus system that may include a power bus, a control bus, a status signal bus, etc., in addition to a data bus. But for clarity of explanation the various buses are referred to in figure 3 as a bus system.
In an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the method described in fig. 1.
The computer-readable storage medium, as will be appreciated by one of ordinary skill in the art: the embodiment for realizing the functions of the system and each unit can be realized by hardware related to computer programs. The aforementioned computer program may be stored in a computer readable storage medium. When the program is executed, the embodiment including the functions of the system and the units is executed; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
In summary, the method, the device, the equipment and the storage medium for establishing the technical contract affirmation model provided by the application establish a word vector set by performing word segmentation and part-of-speech indexing on the acquired technical contract; converting the incidence relation among all words in the word vector model into a multi-dimensional word vector model; and taking a preset result base corresponding to the technical contract judgment result and the word vector model as the input of the neural network model, and obtaining a technical contract identification model through neural network training and learning so as to identify the technical contract and the type of the technical contract.
The application effectively overcomes various defects in the prior art and has high industrial utilization value.
The above embodiments are merely illustrative of the principles and utilities of the present application and are not intended to limit the invention. Any person skilled in the art can modify or change the above-described embodiments without departing from the spirit and scope of the present application. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present application.
Claims (10)
1. A method for creating a technical contract approval model, the method comprising:
performing word segmentation and part-of-speech indexing on the acquired technical contract to establish a word vector set;
converting the incidence relation among all words in the word vector model into a multi-dimensional word vector model;
and taking a preset result base corresponding to the technical contract judgment result and the word vector model as the input of the neural network model, and obtaining a technical contract identification model through neural network training and learning so as to identify the technical contract and the type of the technical contract.
2. The method of claim 1, wherein the tokenizing and part-of-speech indexing the obtained technical contract to establish a set of word vectors comprises:
combining the vocabulary after the technical contract is subjected to word segmentation with words and specific words to establish a word segmentation model;
and optimizing the vocabulary after the word segmentation of the word segmentation model by combining the existing vocabulary entry.
3. The method of claim 1, wherein converting the association between words in the word vector model into a multidimensional word vector model comprises:
extracting specific words in the word vector model, and establishing an association relationship in a certain association format according to the association relationship among the words; wherein the association format comprises: an entry, a keyword, and an associated/related attribute triad and/or an entry, an attribute name, and an attribute value triad.
4. The method of claim 3, wherein the particular vocabulary includes: nouns, noun phrases, vernouns, and vernoun phrases in any one or more combinations.
5. The method according to claim 1, wherein the preset result library corresponding to the technical contract evaluation results is constructed by collecting the technical contracts of the existing evaluation results and establishing a corresponding relationship between each technical contract and the corresponding evaluation result.
6. The method of claim 1, further comprising:
taking a preset scientific and technological achievement set as the input of a neural network model;
extracting the vocabulary which has an incidence relation with scientific and technological achievements from the word vector model to calculate the similarity;
if the similarity exceeds a certain numerical value, acquiring a limited vocabulary associated with the achievement vocabulary in the scientific and technological achievement set for analysis;
and judging whether the scientific and technological achievements corresponding to the vocabularies are abnormal or not according to the analysis result.
7. The method according to claim 5, wherein the method for presetting the scientific and technological achievement set comprises the following steps:
collecting the achievement vocabularies which represent scientific and technological achievement items in the technical contract;
and acquiring the limited vocabulary corresponding to the scientific and technological achievement according to the associated verb corresponding to the entry to form a scientific and technological achievement set.
8. An electronic device, the device comprising:
the processing module is used for performing word segmentation and part-of-speech indexing on the acquired technical contract to establish a word vector set; converting the incidence relation among all words in the word vector model into a multi-dimensional word vector model;
and the recognition module is used for taking a preset result base corresponding to the technical contract judgment result and the word vector model as the input of the neural network model, and obtaining a technical contract recognition model through neural network training and learning so as to recognize the technical contract and the type of the technical contract.
9. A computer device, the device comprising: a memory, and a processor; the memory is to store computer instructions; the processor executes computer instructions to implement the method of any one of claims 1 to 7.
10. A computer-readable storage medium having stored thereon computer instructions which, when executed, perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910785113.XA CN110705280A (en) | 2019-08-23 | 2019-08-23 | Technical contract approval model creation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910785113.XA CN110705280A (en) | 2019-08-23 | 2019-08-23 | Technical contract approval model creation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110705280A true CN110705280A (en) | 2020-01-17 |
Family
ID=69193570
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910785113.XA Pending CN110705280A (en) | 2019-08-23 | 2019-08-23 | Technical contract approval model creation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110705280A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112287653A (en) * | 2020-12-30 | 2021-01-29 | 南京智闪萤科技有限公司 | Method of generating electronic contract, computing apparatus, and computer storage medium |
| CN112926312A (en) * | 2021-02-24 | 2021-06-08 | 南通大学 | Method for establishing technical contract affirmation model and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104375989A (en) * | 2014-12-01 | 2015-02-25 | 国家电网公司 | Natural language text keyword association network construction system |
| WO2019105134A1 (en) * | 2017-11-30 | 2019-06-06 | 阿里巴巴集团控股有限公司 | Word vector processing method, apparatus and device |
| CN109857993A (en) * | 2019-01-02 | 2019-06-07 | 深圳市找大状法务科技有限公司 | A kind of contract text system for washing intelligently |
-
2019
- 2019-08-23 CN CN201910785113.XA patent/CN110705280A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104375989A (en) * | 2014-12-01 | 2015-02-25 | 国家电网公司 | Natural language text keyword association network construction system |
| WO2019105134A1 (en) * | 2017-11-30 | 2019-06-06 | 阿里巴巴集团控股有限公司 | Word vector processing method, apparatus and device |
| CN109857993A (en) * | 2019-01-02 | 2019-06-07 | 深圳市找大状法务科技有限公司 | A kind of contract text system for washing intelligently |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112287653A (en) * | 2020-12-30 | 2021-01-29 | 南京智闪萤科技有限公司 | Method of generating electronic contract, computing apparatus, and computer storage medium |
| CN112287653B (en) * | 2020-12-30 | 2021-05-07 | 南京智闪萤科技有限公司 | Method of generating electronic contract, computing apparatus, and computer storage medium |
| CN112926312A (en) * | 2021-02-24 | 2021-06-08 | 南通大学 | Method for establishing technical contract affirmation model and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20170330078A1 (en) | Method and system for automated model building | |
| CN112069811A (en) | Electronic text event extraction method with enhanced multi-task interaction | |
| US9111248B2 (en) | Procurement system | |
| CN109299245B (en) | Method and device for recalling knowledge points | |
| AU2020236989A1 (en) | Handling categorical field values in machine learning applications | |
| CN106649503A (en) | Query method and system based on sql | |
| CN111046187A (en) | Sample knowledge graph relation learning method and system based on confrontation type attention mechanism | |
| CN108549697A (en) | Information-pushing method, device, equipment based on semantic association and storage medium | |
| CN109409625B (en) | Method for quantitatively evaluating legal affairs | |
| CN110705280A (en) | Technical contract approval model creation method, device, equipment and storage medium | |
| CN110569289A (en) | Column data processing method, equipment and medium based on big data | |
| CN105653620A (en) | Log analysis method and device of intelligent question answering system | |
| CN116629235A (en) | Large-scale pre-training language model fine tuning method and device, electronic equipment and medium | |
| Mandvikar | Augmenting intelligent document processing (IDP) workflows with contemporary large language models (LLMs) | |
| CN110688847A (en) | Technical contract determination method, device, computer equipment and storage medium | |
| US20200387505A1 (en) | Information processing system, feature description method and feature description program | |
| WO2021217866A1 (en) | Method and apparatus for ai interview recognition, computer device and storage medium | |
| CN112817560B (en) | Computing task processing method, system and computer readable storage medium based on table function | |
| CN115329173A (en) | Method and device for determining enterprise credit based on public opinion monitoring | |
| CN111382246B (en) | Text matching method, matching device, terminal and computer readable storage medium | |
| CN114064888A (en) | Financial text classification method and system based on BERT-CNN | |
| CN116975595B (en) | Unsupervised concept extraction method and device, electronic equipment and storage medium | |
| CN113254698B (en) | Form design method and system with auxiliary filling function | |
| US20240062016A1 (en) | Systems and Methods for Textual Classification Using Natural Language Understanding Machine Learning Models for Automating Business Processes | |
| CN116306985A (en) | Predictive model training method, apparatus, computer device and storage 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200117 |