CN117473097A - Electronic product debugging process route recommendation method, device, equipment and medium - Google Patents
Electronic product debugging process route recommendation method, device, equipment and medium Download PDFInfo
- Publication number
- CN117473097A CN117473097A CN202311319139.8A CN202311319139A CN117473097A CN 117473097 A CN117473097 A CN 117473097A CN 202311319139 A CN202311319139 A CN 202311319139A CN 117473097 A CN117473097 A CN 117473097A
- Authority
- CN
- China
- Prior art keywords
- process route
- attribute
- debugging process
- electronic product
- attributes
- 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 154
- 230000008569 process Effects 0.000 title claims abstract description 117
- 239000013598 vector Substances 0.000 claims abstract description 28
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 238000011156 evaluation Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 abstract description 11
- 239000000284 extract Substances 0.000 abstract description 3
- 238000012360 testing method Methods 0.000 description 35
- 238000002360 preparation method Methods 0.000 description 13
- 230000032683 aging Effects 0.000 description 12
- 238000001514 detection method Methods 0.000 description 11
- 238000013461 design Methods 0.000 description 10
- 230000035882 stress Effects 0.000 description 10
- 238000007689 inspection Methods 0.000 description 9
- 238000012216 screening Methods 0.000 description 8
- 230000003321 amplification Effects 0.000 description 6
- 238000003199 nucleic acid amplification method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011056 performance test Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 description 1
- 206010051246 Photodermatosis Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006353 environmental stress Effects 0.000 description 1
- RKWPMPQERYDCTB-UHFFFAOYSA-N ethyl n-[4-[benzyl(2-phenylethyl)amino]-2-(4-nitrophenyl)-1h-imidazo[4,5-c]pyridin-6-yl]carbamate Chemical compound N=1C(NC(=O)OCC)=CC=2NC(C=3C=CC(=CC=3)[N+]([O-])=O)=NC=2C=1N(CC=1C=CC=CC=1)CCC1=CC=CC=C1 RKWPMPQERYDCTB-UHFFFAOYSA-N 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000008570 general process Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008845 photoaging Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000010257 thawing Methods 0.000 description 1
- 238000003878 thermal aging Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41885—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by modeling, simulation of the manufacturing system
-
- 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
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/19007—Matching; Proximity measures
- G06V30/19093—Proximity measures, i.e. similarity or distance measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Animal Behavior & Ethology (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention discloses a recommending method, a recommending device, recommending equipment and recommending media for an electronic product debugging process route, wherein the method applies ontology construction knowledge, extracts characteristic attributes of the electronic product debugging process route, constructs an ontology model of the electronic product debugging process route, divides product attributes into text type attributes, numerical value type attributes and symbol type attributes, expresses the text type attributes by low-dimensional vectors through knowledge graph embedding, calculates three attribute similarities respectively, weights and calculates global similarity, and obtains the debugging process route of the electronic product as a calculation result of the process route similarity. The invention can recommend an effective debugging process route, provides a good reference for the construction of the debugging process route of the new electronic product, and shortens the construction cost.
Description
Technical Field
The invention belongs to the technical field of electronic product debugging, and particularly relates to a method, a device, equipment and a medium for recommending an electronic product debugging process route.
Background
The design of the process route of the electronic product belongs to the most important link in the design of the debugging process, a designer of the current debugging process has to digest a plurality of product design files, including files of product specifications, test rules, debugging instructions and the like, extract the debugging requirements from the files, such as information of debugging flow, test items, test frequency points and the like, and design the debugging process route by combining with personal experience.
In the process of debugging process route design, a plurality of product design files need to be digested, the debugging process route is mostly designed by combining personal experience, the content is mainly described in a text form, and the problem of inconsistent term description exists. The electronic product debugging process route is complex in process, the process links are numerous, and the debugging process routes of different electronic products are different, but the same or similar links exist; in the face of a new electronic product, it is difficult to quickly obtain a borrowable process route scheme according to an existing process template, and determine a debugging process route of the product.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a method, a device, equipment and a medium for recommending an electronic product debugging process route, which are used for constructing an electronic product model and a debugging process route body model and defining attribute relations between the electronic product model and the debugging process route body model; embedding a knowledge graph, and representing all entities and relations by using low-dimensional vectors; dividing the product attribute into text, numerical value and symbol type attribute, respectively calculating the similarity, and weighting and fusing to obtain global similarity; and obtaining a recommended debugging process route through the global similarity.
The aim of the invention is achieved by the following technical scheme:
an electronic product debugging process route recommendation method, the method comprising:
constructing a debugging process route body according to basic element and attribute relation in the electronic product debugging process, and adding a body evaluation index;
instantiating the ontology to form a knowledge graph, and representing the knowledge graph in a vector form, wherein the vector comprises a head entity, a tail entity and a relation between the head entity and the tail entity;
dividing the attributes of the product into text type attributes, numerical type attributes and symbolic type attributes, respectively calculating the similarity of the text type attributes, the numerical type attributes and the symbolic type attributes, and calculating the global similarity by weighting and fusing the text type attributes, the numerical type attributes and the symbolic type attributes to form a knowledge base;
and calculating global similarity according to the attribute of the product to be debugged, and performing similarity matching with the knowledge base to obtain a process route recommendation result.
Further, the relationship between the head and tail entities includes:
constructing a sparse projection matrix M for each head entity and tail entity relationship r (θ r )；
Sparseness of relation is theta r ＝1-(1-θ min )N r /N r* ；
Wherein N is r Refers to the number, N, of entity pairs connected by relation r r* A value representing the most logarithmic of the connection entity;
head entity and tail entity share sparse projection matrix M r (θ r ) The scoring function is
Wherein f r (h, t) represents h p +r and t p The difference between them, h denotes the head entity, t denotes the tail entity, and p denotes the use of the Transparse model.
Further, the similarity calculation of the text type attribute includes:
wherein I is i Representing recommended attribute vectors, I j Representing other attribute vectors.
Further, the calculating of the similarity of the numerical attribute includes:
where max (i) represents the maximum value that attribute i may take, and min (i) represents the minimum value that attribute i may take.
Further, the similarity calculation of the symbolic attribute includes:
wherein,and->Representing the values of the ith attribute, respectively.
Further, the similarity calculation of the global similarity includes:
wherein omega i Weight representing the ith attribute, sim (X 0 ,X j ) Representing global similarity.
Furthermore, the method takes the product richness, the process richness, the relation richness and the attribute richness as the body evaluation index.
On the other hand, the invention also provides a device for recommending the debugging process route of the electronic product, which comprises:
the body building module builds a debugging process route body according to basic elements and attribute relations in the electronic product debugging process and adds body evaluation indexes;
the knowledge graph establishing module instantiates the ontology to form a knowledge graph and represents the knowledge graph in a vector form, wherein the vector comprises a head entity, a tail entity and a relationship between the head entity and the tail entity;
the knowledge base building module divides the attributes of the product into text type attributes, numerical type attributes and symbolic type attributes, calculates the similarity of the text type attributes, the numerical type attributes and the symbolic type attributes respectively, and calculates the global similarity by weighting and fusing the text type attributes, the numerical type attributes and the symbolic type attributes to form a knowledge base;
and the process route recommending module calculates global similarity according to the attribute of the product to be debugged and performs similarity matching with the knowledge base to obtain a process route recommending result.
On the other hand, the invention also provides a computer device, which comprises a processor and a memory, wherein the memory stores a computer program, and the computer program is loaded and executed by the processor to realize any one of the electronic product debugging process route recommendation methods.
In another aspect, the present invention further provides a computer readable storage medium, where a computer program is stored, where the computer program is loaded and executed by a processor to implement any one of the above-mentioned electronic product debugging process route recommendation methods.
The invention has the beneficial effects that:
the invention can reduce the time of debugging process designers and improve the design efficiency of the debugging process, so that the quick generation of the debugging process route can be realized under the condition of incomplete process knowledge, and the final debugging process route is standardized and normalized.
Drawings
FIG. 1 is a flow chart of a method for recommending a debugging process route of an electronic product according to an embodiment of the invention;
FIG. 2 is a block diagram of an embodiment of an ontology construction process;
fig. 3 is a block diagram of a device for recommending a debugging process route of an electronic product according to an embodiment of the invention.
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict.
All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the process of debugging process route design, a plurality of product design files are needed to be digested, and most of the debugging process route design is carried out by combining with personal experience, the content is mainly described in a text form, and the problem of inconsistent term description exists. The electronic product debugging process route is complex in process, the process links are numerous, and the debugging process routes of different electronic products are different, but the same or similar links exist; in the face of a new electronic product, it is difficult to quickly obtain a borrowable process route scheme according to an existing process template, and determine a debugging process route of the product.
In order to solve the above technical problems, the following embodiments of the method, device, equipment and medium for recommending a debugging process route of an electronic product are provided.
Example 1
Referring to fig. 1, as shown in fig. 1, a flowchart of a method for recommending a debugging process route of an electronic product according to the present embodiment is shown, and the method specifically includes the following steps:
step one: and constructing a debugging process route body according to the basic element and attribute relationship in the electronic product debugging process, and adding a body evaluation index.
Specifically, the existing ontology construction method has a seven-step method, is developed by the Stanford university and is mainly used for field ontology construction, the method is mature, is widely applied to ontology construction, and lacks links of inspection and evaluation and user feedback. When the method is applied to the field of electronic product debugging, whether the ontology model is reasonably constructed or not cannot be estimated, and application requirements are difficult to meet, so that the method is improved, evaluation indexes are added in the ontology model, and the debugging process route ontology is more reasonably constructed. The ontology evaluation index is defined as the product richness, the process richness, the relation richness and the attribute richness, as shown in table 1.
TABLE 1 body evaluation index
As an implementation, the present example uses Prot g software for ontology construction.
The product model is a model for defining and describing relevant debugging information of a debugged product, and provides a standard file for debugging process programming. The classes defining the product model are product type, interface information, product state control mode and debugging index parameters.
1) Product type. The subclasses of the product types are defined as module-level products and whole-machine-level products, wherein the module-level products are divided into a receiving class, an excitation class, a frequency synthesis class, a power-on control class, a radio frequency interface class, a power amplification class, a signal processing class, a terminal processing class and an audio processing class 9 class. The products of the whole machine level are divided into voice communication type, data link communication type, navigation type, friend or foe identification type, navigation management response type, acoustic alarm type and comprehensive management type 7.
2) Interface information. Subclasses defining interface types are interface signal types and interface signal directions. The interface signal types are divided into low-frequency signals, radio-frequency signals, mixed signals and signal ranges, and the interface signal directions are divided into input, output and input/output.
3) And (5) a product state control mode. Subclasses defining the product state control are discrete lines, data buses, address buses, control buses, expansion buses and local buses.
4) And debugging index parameters. Subclasses defining the debug index parameters are signal range, power-up current, power-up time, detection frequency, detection time, debug bandwidth, and process parameters.
The relation between the product model and the debugging process route comprises the relation between the product type and the process route, the relation between the debugging project and the tool selection, and the correlation between each subclass and the subclass of the process route. According to these relationships, the following attributes are defined, including relationship (hasRoute) of product type and process route, correlation (item-work) of debugging item and tool selection, and correlation (product-route) of each subclass of product model and each subclass of process route.
The debugging process route is divided into the main categories of preparation before debugging, power-on inspection, normal-temperature debugging, high-low-temperature debugging, environmental stress screening, electric aging and tool library 7 according to the general process sequence.
1) Preparation before debugging. The pre-commissioning preparation should account for all the preparation required before the product is commissioned. Defining subclasses of preparation before debugging for debugging file record preparation, tooling instrument preparation and tool material preparation.
2) And (5) power-up inspection. The power-up sequence should be specified according to the characteristics of the product, the test points are defined, the power-up current range of each group of voltages of the product is specified, and the voltage range of all power supply voltages of the product including important secondary voltages is specified. Subclasses of power-up checks are defined as product appearance check, static impedance check, clamp quality check, electrical quality check, power-up current, power-up test, power-up sequence, power-up voltage.
3) And (5) debugging at normal temperature. Debug items, debug steps, test items, and test methods should be specified. The sub-class of normal temperature debugging is defined as audio frequency and control unit debugging, co-location filter unit control testing, power amplification unit testing, U-section dynamic testing, power amplification module joint debugging, gain detection, AGC attenuation testing, calibration control testing, filter characteristic testing, first image suppression testing, second image suppression testing, IF2 channel detection, detection frequency, detection time, detection state and debugging bandwidth.
4) And (5) high-low temperature debugging. Instruments, equipment, tools, files and records which need to be prepared before the test are defined. The subclasses of high-low temperature debugging are defined as temperature mutation test, temperature circulation test, forced air circulation test, low-temperature environment temperature, high-temperature environment temperature, debugging duration, quality after product debugging, high-temperature debugging time, low-temperature debugging time and high-low temperature circulation temperature.
5) And (5) stress screening. The subclasses of stress screening are defined as high acceleration life test, high acceleration stress screening, vibration stress test, temperature stress test, vibration measuring device, temperature measuring device, other measuring devices, normal temperature performance test, temperature uniformity test.
6) And (5) electric aging. The subclasses of electrical aging are defined as photo aging test, thermal aging test, salt spray aging test, ozone aging test, high and low temperature cycle aging test, freeze thawing cycle aging test, and test time.
7) An instrument library. The subclasses of the tool library are defined as an LXI digital oscilloscope, a portable oscilloscope, a mixed domain oscilloscope, an oscilloscope, a digital storage oscilloscope, a digital oscilloscope, a vector signal source, a comprehensive tester, a spectrum analyzer, an attenuator, a high-power supply, a digital multimeter, a radio frequency tester, a real-time spectrum analyzer and a network analyzer.
Attributes are features or parameters that an object has, and are divided into data attributes and object attributes. The data attributes are used to represent class-to-class relationships with specific numeric types, and the object attributes are used to represent class-to-class relationships.
OWL object properties are defined in the Proteg software using OWL: topObjectProperty, OWL data properties are defined using OWL: topdata Property. The relation among the various categories of the debugging process route mainly comprises the positional relation among preparation before debugging, power-on inspection, normal temperature debugging, high-low temperature debugging, stress screening and electric aging, the relation between each level of category and the subclass thereof, the relation between the subclass of each level of category, and the relation between each process route and the tool library. From these relationships, the present embodiment defines attributes, namely, a process route location attribute (isNext), a parent class child inclusion attribute (include), and a child related attribute (associate). The sub-class related attributes include preparation related to instrument library (preparation-work), power-on inspection related to instrument library (check-work), normal temperature debugging related to instrument library (normal-work), high and low temperature debugging related to instrument library (hal-work), stress screening related to instrument library (stress-work), and electric aging related to instrument library (aging-work).
In addition to defining classes and attributes during modeling, constraints are required for the classes and attributes. OWL may define properties such as transitivity (transitive), symmetry (symmetry), and functionality (functional) of an attribute, and may define two classes of equivalence (equivalence) or disjoint (disoint), and two attributes are equivalent or reciprocal (inverse). The present embodiment performs a constraint definition on classes and attributes within the body. The preparation before debugging, power-up inspection, normal temperature debugging, high and low temperature debugging, stress screening and electric aging are subjected to disjoint constraint. The transitivity, symmetry and reciprocity of the object properties are subject to constraint constraints.
Step two: the ontology is instantiated to form a knowledge graph, and the knowledge graph is expressed in a vector form, wherein the vector comprises a head entity, a tail entity and a relation between the head entity and the tail entity.
Specifically, the knowledge graph embedding uses the idea of distributed representation, the targets are represented as dense, real-valued and low-dimensional vectors, and meanwhile, the structure and semantic information in the knowledge graph are reserved in the vectors, so that the defect of the traditional knowledge graph vector representation can be overcome.
The knowledge graph consists of knowledge triples, wherein the knowledge triples comprise a head entity h, a relation r and a tail entity t. Each triplet may be represented in the form of (h, r, t). The knowledge graph embedding is to project the entities and the relations in the knowledge graph into a low-dimensional continuous vector space, so that the semantic similarity among the entities can be calculated rapidly. The translation model aims to learn embedding by representing the relationship as a translation of a head entity to a tail entity. Aiming at the problems that the quantity of relational link entities in knowledge is inconsistent and the quantity of relational link entities in knowledge is very few, the embodiment constructs a projection matrix M for each relation r (θ r ). This projection matrix is sparse, wherein the sparsity θ r Mainly depending on the entity logarithm of the relation r connection. Let N be r Is the number of connected entity pairs, N r * Representation ofAll N r Maximum number of θ min (0≤θ min ≤1)。
1) Representing projection matrix M r (θ r ) Minimum sparsity, then the sparsity of the relationship r is defined as
θ r ＝1-(1-θ min )N r /N r*
Wherein N is r Referring to the number of entity pairs connected by relationship r, the more the number of entity pairs, the less sparsity the projection matrix, and the denser the matrix (i.e., the greater the number of non-0 elements). N (N) r Representing the most logarithmic value of the connection entity.
The head and tail entities will share a sparse matrix M r (θ r ). The scoring function is:
wherein f r (h, t) represents h p +r and t p Differences between them.
Step three: the attributes of the product are divided into text type attributes, numerical type attributes and symbolic type attributes, the similarity of the text type attributes, the numerical type attributes and the symbolic type attributes is calculated respectively, and the global similarity is calculated through weighting and fusing the text type attributes, the numerical type attributes and the symbolic type attributes, so that a knowledge base is formed.
Specifically, the most representative attribute is selected for different products to represent, and the attribute can be divided into text type attribute, numerical type attribute and symbolic type attribute. 11 attributes are selected, wherein the text type attribute has a product type, the numerical type attribute has a signal range, a power-on current, a power-on time, a detection frequency, a detection time and a debugging bandwidth, and the symbol type attribute has an interface signal type, an interface signal direction, a product state control mode and a process parameter.
Considering that different properties of a product have different roles and different degrees of influence, the properties need to be given weights. And calculating the attribute weight by adopting a rough set theory, carrying out weight assignment on the characteristic attribute according to the importance of the attribute, removing the attribute which does not play a role, improving the rationality of the result and improving the analysis precision.
For the text type attribute, the similarity cannot be directly measured by a computer, and the entity vector of the knowledge graph obtained based on vector operation can reflect the similarity among the entities. And using the distributed low-dimensional vectors of each debugging process route obtained after the knowledge graph embedding as numerical representation of each attribute, and calculating the similarity by using Euclidean distance, wherein the formula is as follows.
Wherein: i i And I j Representing the recommended attribute vector and the other attribute vector, respectively.
For the numerical type attribute, a similarity calculation method based on Hamming distance is adopted, and the formula is as follows.
Wherein: max (i), min (i) represent the maximum value and minimum value that the attribute i can take, respectively.
For the symbol type attribute, when the attributes are the same, the definition similarity is 1, and when the attribute values are different, the definition similarity is 0, and the formula is as follows.
Wherein:and->Representing the values of the i-th attributes, respectively.
Calculating global similarity, and fusing the similarity of different attributes after weighting to obtain the global similarity, wherein the formula is as follows:
wherein: omega i Weight representing the ith attribute, sim (X 0 ,X j ) Representing global similarity.
Step four: and calculating global similarity according to the attribute of the product to be debugged, and performing similarity matching with a knowledge base to obtain a process route recommendation result.
Specifically, taking a power amplifier type electronic product as an example, matching the attribute of the electronic product with the attribute in the knowledge base in a similarity manner, and verifying the method provided by the embodiment. For the electronic product, the text type attribute values are power amplification types, the numerical value type attribute values are 6GHz, 0.3A, 0.25 working hour, 2kHz, 0.5 working hour and 8MHz, and the symbol type attribute values are radio frequency signals, input, discrete lines and Fm.
The following is a partial example illustration in ontology pushing. The input text type attribute value is a power amplifier type product, and the related power amplifier type product 1, power amplifier type product 2, power amplifier type product 3, power amplifier type product 4 and power amplifier type product 5 are obtained by reasoning. And inputting the value type attribute debugging bandwidth, and reasoning to obtain relevant debugging bandwidth values of 6MHz,16MHz,4Mhz and 2Mhz. And (3) inputting a symbol type attribute value product state control mode, and reasoning to obtain related values of discrete lines, a data bus, an address bus and a local bus. The rest part of value reasoning is similar to the above, and weight and similarity calculation is performed after the related attributes are obtained.
And calculating the weight value of each attribute through the rough set theory, wherein the weight value is as follows.
After the weight is calculated, similarity matching is carried out on each attribute value and the attribute value in the knowledge base, and the case attribute value and the attribute value data in the knowledge base are as follows.
The attribute table of the product is shown in table 2:
table 2 power amplifier type electronic product attribute table
And the relation between part of the attributes and the debugging process route is described. The text attribute product type value is a power amplifier type, and the preparation of debugging records, tooling instruments and tool material items before debugging of the product with the required number of GFP is recommended; the value attribute debugging bandwidth value is 8MHz, and the normal temperature debugging project power amplifying unit test project with the required debugging bandwidth of 8MHz is recommended; the symbol attribute process parameter value is Fm, and the recommended product needs a process parameter of Fm normal temperature debugging gain detection project. The remaining properties are similar to the debug process route relationships described above.
And calculating the similarity of each attribute according to the formula, and carrying out weighted calculation to obtain the global similarity, wherein the calculation result is as follows.
Sim(X 0 ,X 1 )＝0.774
The similarity result is higher, and the calculation result recommends the process route as follows.
Preparation before debugging: GFP001 debug record, GFP001 tooling instrument, GFP001 tooling material power up check: product appearance inspection, static impedance inspection, and electrical quality inspection
And (3) debugging at normal temperature: debugging of audio frequency and control unit (1.5V, 2 kHz), testing of power amplification unit (8 MHz, 0.6A), joint debugging of power amplification module (radio frequency, 5V), gain detection (8 MHz, fm)
And (3) high-low temperature debugging: temperature cycle test (8 Mhz), forced air cycle test
Stress screening: temperature stress test (ESS), normal temperature Performance test
Electric aging: high-low temperature cycle aging test
The results show that according to the method provided by the embodiment, a debugging process route of the electronic product with higher similarity is recommended, and the debugging process route can be adjusted.
The embodiment applies ontology construction knowledge, extracts characteristic attributes of the electronic product debugging process route, and constructs an ontology model of the electronic product debugging process route. The debugging process route of the electronic product is obtained through reasoning of the knowledge graph, the attribute is divided into text type, numerical type and symbol type attribute according to the difference of the characteristic attribute, and the respective similarity calculation method is determined. And determining weight values for all the attributes through a rough set theory, and determining global similarity as a calculation result of the process route similarity. Through research and calculation verification of specific electronic product examples, the knowledge graph reasoning provided by the embodiment can recommend an effective debugging process route, provides a good reference for the construction of a debugging process route of a new electronic product, and shortens construction cost.
Example 2
Referring to fig. 3, fig. 3 is a block diagram showing a process route recommending apparatus for debugging an electronic product according to the present embodiment. The device specifically comprises the following structures:
the body building module builds a debugging process route body according to basic elements and attribute relations in the electronic product debugging process and adds body evaluation indexes;
the knowledge graph establishing module instantiates the ontology to form a knowledge graph, and represents the knowledge graph in a vector form, wherein the vector comprises a head entity, a tail entity and a relationship between the head entity and the tail entity;
the knowledge base building module divides the attributes of the product into text type attributes, numerical type attributes and symbolic type attributes, calculates the similarity of the text type attributes, the numerical type attributes and the symbolic type attributes respectively, and calculates the global similarity by weighting and fusing the text type attributes, the numerical type attributes and the symbolic type attributes to form a knowledge base;
and the process route recommending module calculates global similarity according to the attribute of the product to be debugged and performs similarity matching with the knowledge base to obtain a process route recommending result.
Example 3
The preferred embodiment provides a computer device, which can implement the steps in any embodiment of the method for recommending a debugging process route for an electronic product provided in the embodiment of the present application, so that the method for recommending a debugging process route for an electronic product provided in the embodiment of the present application can be implemented, and detailed descriptions of the foregoing embodiments are omitted herein.
Example 4
Those of ordinary skill in the art will appreciate that all or a portion of the steps of the various methods of the above embodiments may be performed by instructions, or by instructions controlling associated hardware, which may be stored in a computer-readable storage medium and loaded and executed by a processor. To this end, an embodiment of the present invention provides a storage medium having stored therein a plurality of instructions that can be loaded by a processor to perform the steps of any one of the embodiments of the method for recommending a debugging process route for an electronic product provided by the embodiment of the present invention.
Wherein the storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like.
The instructions stored in the storage medium can execute the steps in any electronic product debugging process route recommending method embodiment provided by the embodiment of the invention, so that the beneficial effects which can be achieved by any electronic product debugging process route recommending method provided by the embodiment of the invention can be achieved, and detailed descriptions of the previous embodiments are omitted.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (10)
1. The method for recommending the debugging process route of the electronic product is characterized by comprising the following steps of:
constructing a debugging process route body according to basic element and attribute relation in the electronic product debugging process, and adding a body evaluation index;
instantiating the ontology to form a knowledge graph, and representing the knowledge graph in a vector form, wherein the vector comprises a head entity, a tail entity and a relation between the head entity and the tail entity;
dividing the attributes of the product into text type attributes, numerical type attributes and symbolic type attributes, respectively calculating the similarity of the text type attributes, the numerical type attributes and the symbolic type attributes, and weighting, fusing and calculating the global similarity of the text type attributes, the numerical type attributes and the symbolic type attributes to form a knowledge base;
and calculating global similarity according to the attribute of the product to be debugged, and performing similarity matching with the knowledge base to obtain a process route recommendation result.
2. The electronic product debugging process route recommendation method of claim 1, wherein the relationship between the head and tail entities comprises:
constructing a sparse projection matrix M for each head entity and tail entity relationship r (θ r )；
Sparseness of relation is theta r ＝1-(1-θ min )N r /N r* ；
Wherein N is r Referring to the number of entity pairs connected by relationship r,a value representing the most logarithmic of the connection entity;
head entity and tail entity share sparse projection matrix M r (θ r ) The scoring function is
Wherein f r (h, t) represents h p +r and t p Differences betweenOtherwise, h denotes the head entity, t denotes the tail entity, and p denotes the use of the Transparse model.
3. The electronic product debugging process route recommendation method of claim 1, wherein the similarity calculation of text type attributes comprises:
wherein I is i Representing recommended attribute vectors, I j Representing other attribute vectors.
4. The electronic product debugging process route recommendation method of claim 3, wherein the similarity calculation of the numerical attribute comprises:
where max (i) represents the maximum value that attribute i may take, and mn (i) represents the minimum value that attribute i may take.
5. The method of claim 4, wherein the calculating the similarity of the symbolic attributes comprises:
wherein,and->Representing the values of the ith attribute, respectively.
6. The electronic product debugging process route recommendation method of claim 5, wherein the similarity calculation of global similarity comprises:
wherein omega i Weight representing the ith attribute, sim (X 0 ,X j ) Representing global similarity.
7. The method of claim 1, wherein the method uses product richness, process richness, relationship richness, and attribute richness as ontology evaluation indexes.
8. An electronic product debugging process route recommending device, characterized in that the device comprises:
the body building module builds a debugging process route body according to basic elements and attribute relations in the electronic product debugging process and adds body evaluation indexes;
the knowledge graph establishing module instantiates the ontology to form a knowledge graph and represents the knowledge graph in a vector form, wherein the vector comprises a head entity, a tail entity and a relationship between the head entity and the tail entity;
the knowledge base building module divides the attributes of the product into text type attributes, numerical type attributes and symbolic type attributes, calculates the similarity of the text type attributes, the numerical type attributes and the symbolic type attributes respectively, and calculates the global similarity by weighting and fusing the text type attributes, the numerical type attributes and the symbolic type attributes to form a knowledge base;
and the process route recommending module calculates global similarity according to the attribute of the product to be debugged and performs similarity matching with the knowledge base to obtain a process route recommending result.
9. A computer device, characterized in that it comprises a processor and a memory, in which a computer program is stored, which computer program is loaded and executed by the processor to implement the electronic product debugging process route recommendation method according to any one of claims 1-7.
10. A computer readable storage medium, wherein a computer program is stored in the storage medium, the computer program being loaded and executed by a processor to implement the electronic product debugging process route recommendation method of any one of claims 1-7.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311297286 | 2023-10-09 | ||
| CN202311297286X | 2023-10-09 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117473097A true CN117473097A (en) | 2024-01-30 |
Family
ID=89624722
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311319139.8A Pending CN117473097A (en) | 2023-10-09 | 2023-10-12 | Electronic product debugging process route recommendation method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117473097A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117884816A (en) * | 2024-03-18 | 2024-04-16 | 苏芯物联技术(南京)有限公司 | Rapid process recommendation method based on historical welding current process interval |
-
2023
- 2023-10-12 CN CN202311319139.8A patent/CN117473097A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117884816A (en) * | 2024-03-18 | 2024-04-16 | 苏芯物联技术(南京)有限公司 | Rapid process recommendation method based on historical welding current process interval |
| CN117884816B (en) * | 2024-03-18 | 2024-05-17 | 苏芯物联技术(南京)有限公司 | Rapid process recommendation method based on historical welding current process interval |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Variyam et al. | Specification-driven test generation for analog circuits | |
| CN117473097A (en) | Electronic product debugging process route recommendation method, device, equipment and medium | |
| Yang et al. | Complex field fault modeling-based optimal frequency selection in linear analog circuit fault diagnosis | |
| CN112052172B (en) | Rapid test method and device for third-party channel and electronic equipment | |
| CN112528458A (en) | Metering master station alarm analysis model construction method based on FP-Growth algorithm | |
| CN101614799B (en) | Signal separation and selection method applied in current sensor angular difference on-line monitoring system | |
| CN109829051B (en) | Method and device for screening similar sentences of database | |
| CN110674315B (en) | Auxiliary power supply debugging method based on knowledge graph technology | |
| Cilici et al. | Assisted test design for non-intrusive machine learning indirect test of millimeter-wave circuits | |
| CN116203920A (en) | Fault diagnosis design method and system based on adjustment and measurement experience knowledge | |
| Bourelly et al. | Ga-based features selection for electro-chemical impedance spectroscopy on lithium iron phosphate batteries | |
| CN115345106A (en) | Verilog-A model construction method, system and equipment of electronic device | |
| CN111696523B (en) | Accuracy testing method and device of voice recognition engine and electronic equipment | |
| US20100131143A1 (en) | Method and system for automatic test data generation for lookup tables | |
| CN117453924A (en) | Automatic recommending method, device, equipment and medium for debugging process resources of electronic product | |
| Akkouche et al. | Minimization of functional tests by statistical modelling of analogue circuits | |
| Cole et al. | Tools for validation and calibration of very large power system models | |
| Gomes et al. | Modular fault simulation of mixed signal circuits with fault ranking by severity | |
| Drozd et al. | Development of next generation FSV tools and standards | |
| CN113358930B (en) | Harmonic wave test system, device and method based on signal deviation | |
| Hou et al. | What Has Been Enhanced in my Knowledge-Enhanced Language Model? | |
| Maidon et al. | An analog circuit fault characterization methodology | |
| Kincl | Methods for testing of analog circuits | |
| CN116625493A (en) | Noise testing method and system and electronic equipment | |
| Ross et al. | Improving Monte Carlo Analysis of Power Systems With Data Clustering and Vector Fitting |
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 |