Method and device for counting total vehicle evaluation score based on node network model

Abstract

The embodiment of the invention relates to a method and a device for counting a total vehicle evaluation score based on a node network model. The method comprises the following steps: constructing the node network model; receiving a vehicle evaluation item implementation detailed rule input by a user and a corresponding vehicle evaluation data set; performing instance configuration on the node network model based on vehicle evaluation project implementation rules to obtain a corresponding first model instance; and inputting the vehicle evaluation data set into the first model instance for calculation to obtain a corresponding first evaluation total score, and feeding back the first evaluation total score to a user. According to the method, the upgrading period of the total score evaluation calculation tool can be shortened to the maximum extent, and the purposes of shortening the evaluation period and improving the evaluation efficiency are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and device for counting vehicle evaluation total scores based on a node network model. Background Art

[0002] Before conducting the evaluation, the performance evaluation organization of automatic / unmanned vehicles will formulate a corresponding vehicle evaluation project implementation rules. Under normal circumstances, the vehicle evaluation project implementation rules will regard all actual evaluation projects as a third-level project, and classify and aggregate all third-level projects based on the set second-level clustering rules to obtain multiple second-level projects (each second-level project is aggregated from one or more third-level projects), and classify and aggregate all second-level projects based on the set first-level clustering rules to obtain multiple first-level projects (each first-level project is aggregated from one or more second-level projects); the rules will also use the actual evaluation score of each third-level project as the project score of the current project, and configure a corresponding second-level score calculation function for each second-level project, and the function will calculate the corresponding second-level project score based on the scores of all the third-level projects under it, and configure a corresponding first-level score calculation function for each first-level project, and the function will calculate the corresponding first-level project score based on the scores of all the second-level projects under it, and configure a sum function to calculate the total score based on all the first-level project scores obtained.

[0003] After the above rules are formulated, the performance evaluation agency staff's evaluation work is roughly divided into two steps: first, based on the evaluation requirements of all three-level items in the rules, the vehicle is comprehensively evaluated and each three-level item is scored, and then the calculation tool is used to calculate the scores of all three-level items and the final calculated total score is used as the total score of the current vehicle. The calculation tool here is a software and / or hardware module custom-developed based on the statistical principles of the scores at each level of the above rules.

[0004] We found a problem with this calculation tool in actual application: most performance evaluation agencies currently use such tools that are software / hardware modules with fixed processing steps. Once the implementation details of the vehicle evaluation items need to be adjusted (such as adding items to the third-level items, replacing the first / second-level score calculation functions, etc.), it is necessary to redevelop the module functions and replace the old and new versions. This will result in the staff having to wait for a while after each adjustment to the details before calculating the total score based on the new version of the calculation tool, which will undoubtedly prolong the staff's evaluation cycle and reduce the evaluation efficiency. Summary of the invention

[0005] The purpose of the present invention is to provide a method, device, electronic device and computer-readable storage medium for calculating the total score of vehicle evaluation based on a node network model in view of the defects of the prior art. The present invention constructs a node network model with reference to the hierarchical node network of the tree structure, and designs the node value calculation function of the transmission node in the model as an optional dynamic configuration function, and provides a function library as the optional range; the node hierarchy of this model, the number of nodes at each level and the transmission node value calculation function can be dynamically adjusted, so that different model instances can be configured based on different vehicle evaluation project implementation details without changing the software program code or hardware processing components; the specific model use steps are: after receiving the vehicle evaluation project implementation details input by the user and the three-level project score set (i.e., vehicle evaluation data set) completed based on the details, firstly configure the node network model based on the details to obtain a corresponding model instance, and then input the vehicle evaluation data set into the model instance to calculate the corresponding evaluation total score. The evaluation total score calculation tool implemented based on the present invention does not need to be redeveloped or replaced with the old version each time the implementation details of the vehicle evaluation project are adjusted. It only needs to configure the node network model once based on the latest details to generate a new model instance for total score calculation. The present invention can shorten the tool upgrade cycle to the maximum extent, thereby achieving the purpose of shortening the evaluation cycle and improving the evaluation efficiency.

[0006] To achieve the above object, a first aspect of an embodiment of the present invention provides a method for calculating the total score of vehicle evaluation based on a node network model, the method comprising:

[0007] Build a node network model;

[0008] Receive vehicle evaluation project implementation details and corresponding vehicle evaluation data sets input by users;

[0009] Based on the vehicle evaluation project implementation rules, the node network model is configured to obtain a corresponding first model instance;

[0010] The vehicle evaluation data set is input into the first model instance to calculate and obtain a corresponding first evaluation total score which is fed back to the user.

[0011] Preferably, the maximum hierarchical depth of the node network model is denoted as M, which is composed of a plurality of nodes N and a plurality of node edges E; M is a positive integer;

[0012] Each of the nodes N corresponds to a set of node attributes; the node attributes include node level, node identifier, parent node identifier and node value calculation function; the node level is the level number of the current node, 0≤node level≤M; the node identifier is the unique identifier of the current node; the parent node identifier is the parent node identifier of the current node;

[0013] Each of the node edges E corresponds to a set of edge attributes; the edge attributes include edge identifiers and edge weights; each of the node edges E is a directed edge, starting from a child node and connected to its corresponding parent node; the edge identifier is the unique identifier of the current node edge; the edge weight is the child node value weight corresponding to the current node edge;

[0014] The node N with a node level of 0 in the node network model is recorded as a root node, and the number of root nodes is unique; each node N in the node network model except the root node is connected to a corresponding upper parent node through a directed node edge E, and serves as a child node of the current upper parent node, and the level difference between any child node and its corresponding upper parent node is 1; each node N in the node network model except the root node that is not connected to any child node is recorded as an input node, and the node N that is neither the root node nor the input node is recorded as a transmission node;

[0015] Each of the input nodes is used to receive a corresponding input value x; the node value calculation function of each of the input nodes is fixed to an assignment function: y in =x,y in is the node value of the current input node;

[0016] Each of the transmission nodes is used to calculate the node value of the current node using the weighted node values ​​of all child nodes of the current node as input; the node value calculation function of each of the transmission nodes is y tr =F tr ({x a}), x a =y a × a ; 1≤a≤A, A is the total number of child nodes of the current transmission node; y tr is the node value of the current transmission node; x a is the weighted node value of the a-th child node of the current transmission node, specifically the node value y of the a-th child node a and the corresponding edge weight w a The product of tr is the calculation function formula of the current transmission node; the calculation function formula F of each transmission node tr Dynamic configuration is performed based on a preset function library; the function library at least includes a multi-class summation function, a multi-class normalization function, and a multi-class activation function;

[0017] The root node is used to sum the weighted node values ​​of all child nodes and output the corresponding node value; the node value calculation function of the root node is fixed as a summation function: x b =y b × b ; 1≤b≤B, B is the total number of child nodes of the root node; y root is the node value of the root node; b is the weighted node value of the bth child node of the root node, specifically the node value y of the bth child node b and the corresponding edge weight w b The product of .

[0018] Preferably, the vehicle evaluation project implementation rules include a vehicle evaluation total score calculation function and G0 first-class evaluation items P i , G0 is a positive integer, 1≤i≤G0; each of the evaluation items P i Including G i Category II evaluation items P i,j , each G i are all positive integers, 1≤j≤G i Each of the two evaluation items P i,j Including G i,j Three types of evaluation items P i,j,q , each G i,j are all positive integers, 1≤q≤G i,j ;

[0019] The vehicle evaluation total score calculation function is matched with the summation function of the root node of the node network model, and is used to calculate the total score of the vehicle evaluation items P of the first category. i The weighted scores of a category of items are summed up and the calculation result is used as the corresponding vehicle evaluation total score; the weighted score of a category of items is the corresponding category of evaluation items P i The product of the score of a category of items and the weight of a category of items;

[0020] Each of the evaluation items P i The project attributes include a type of project identification, a type of project name, the type of project score, the type of project weight and a type of score calculation function; the input of the type of score calculation function is the G corresponding to the current type of evaluation project i The second category evaluation items P i,j The weighted scores of the second-category items are output as the corresponding scores of the first-category items; the function types of the first-category score calculation function at least include summation function, normalization function and activation function; the weighted scores of the second-category items are the corresponding second-category evaluation items P i,j The product of the second-category project score and the second-category project weight;

[0021] Each of the two evaluation items P i,jThe project attributes include the second-class project identification, the second-class project name, the second-class project score, the second-class project weight and the second-class score calculation function; the input of the second-class score calculation function is the G corresponding to the current second-class evaluation project i,j The three types of evaluation items P i,j,q The weighted scores of the three types of items are output as the corresponding scores of the two types of items; the function types of the two-type score calculation function at least include summation function, normalization function and activation function; the weighted scores of the three types of items are the corresponding three types of evaluation items P i,j,q The product of the scores of the three categories of projects and the weights of the three categories of projects;

[0022] Each of the three evaluation items P i,j,q The project attributes include three types of project identifications, three types of project names, the three types of project scores and the three types of project weights; the three types of project scores are specific scores obtained by evaluators or evaluation equipment based on the evaluation requirements of the current three types of evaluation projects.

[0023] Preferably, the maximum level depth M of the first model instance is 3;

[0024] The total number of nodes in the first model instance is n sumall , the node set consists of a first root node, n sum1 First-level transmission nodes, n sum2 Secondary transmission nodes and n sum3 It consists of three-level input nodes; n sumall 、n sum1 、n sum2 、n sum3 are all positive integers;

[0025] Among them, n sumall =1+n sum1 +n sum2 +n sum3 ,

[0026]

[0027] The first root node corresponds to the total score of the vehicle evaluation in the vehicle evaluation project implementation rules; the node level of the first root node is 0, the node identifier is a unique root node identifier, the upper node identifier is empty, and the node value calculation function matches the summation function of the root node of the node network model;

[0028] The first-level transmission node and the first type of evaluation item P iOne-to-one correspondence; the node level of the first-level transmission node is 1, the node identifier is a unique first-level node identifier, the upper-level node identifier is the root node identifier, the node value calculation function is the corresponding first-class evaluation item P i There is a corresponding first-level directed edge from each of the first-level transmission nodes to the first root node; the first-level directed edges correspond to the first-level transmission nodes one by one; the edge identifier of the first-level directed edge is a unique first-level edge identifier, and the edge weight is the same as the corresponding first-level evaluation item P i The weight of the said type of project is matched;

[0029] The secondary transmission node and the second type of evaluation item P i,j One-to-one correspondence; the node level of the secondary transmission node is 2, the node identifier is a unique secondary node identifier, the upper node identifier is a corresponding primary node identifier of the primary transmission node, the node value calculation function and the corresponding second-class evaluation item P i,j The second-class score calculation function matches; there is a corresponding second-class directed edge from each of the second-class transmission nodes to a corresponding first-class transmission node; the second-class directed edges correspond to the second-class transmission nodes one by one; the edge identifier of the second-class directed edge is a unique second-class edge identifier, and the edge weight is the same as the corresponding second-class evaluation item P i,j The weights of the two types of items are matched;

[0030] The three-level input nodes and the three types of evaluation items P i,j,q One-to-one correspondence; the node level of the three-level input node is 3, the node identifier is a unique three-level node identifier, the upper node identifier is the secondary node identifier of a corresponding secondary transmission node, and the node value calculation function matches the assignment function of the input node of the node network model; there is a corresponding three-level directed edge from each of the three-level transmission nodes to a corresponding secondary transmission node; the three-level directed edges correspond to the three-level transmission nodes one-to-one; the edge identifier of the three-level directed edges is a unique three-level edge identifier, and the edge weights are the same as the corresponding three types of evaluation items P i,j,q The weights of the three categories of projects are matched.

[0031] Preferably, the vehicle evaluation data set includes n sum3 Rating value x u , 1≤u≤n sum3 ; The score value x u There is a one-to-one correspondence with the third-level input nodes of the first model instance.

[0032] Preferably, the step of inputting the vehicle evaluation data set into the first model instance to calculate and obtain a corresponding first evaluation total score and feeding it back to the user specifically includes:

[0033] The score values ​​x of the vehicle evaluation data set are u Input the corresponding third-level input node in the first model instance;

[0034] The first model instance calculates the corresponding first root node value according to the input data;

[0035] The obtained first root node value is fed back to the user as the corresponding first evaluation total score.

[0036] Furthermore, the first model instance calculates the corresponding first root node value according to the current input data, specifically including:

[0037] Each of the third-level input nodes of the first model instance converts the score value x input this time into u Bring in the corresponding node value calculation function to calculate and obtain the corresponding third-level node value, and transmit the third-level node value to the second-level transmission node of the parent through the corresponding third-level directed edge;

[0038] Each of the second-level transmission nodes of the first model instance uses the product of the edge weight corresponding to each of the third-level directed edges and the third-level node value as the corresponding third-level node weighted value, and brings the third-level node weighted values ​​of all child levels into the corresponding node value calculation function to calculate and obtain the corresponding second-level node value, and transmits the second-level node value to the first-level transmission node of the parent level through the corresponding second-level directed edge;

[0039] Each of the first-level transmission nodes of the first model instance uses the product of the edge weight corresponding to each of the second-level directed edges and the second-level node value as the corresponding second-level node weighted value, and brings the second-level node weighted values ​​of all child levels into the corresponding node value calculation function to calculate and obtain the corresponding first-level node value, and transmits the first-level node value to the first root node of the parent level through the corresponding first-level directed edge;

[0040] The first root node of the first model instance takes the product of the edge weight corresponding to each of the first-level directed edges and the first-level node value as the corresponding first-level node weighted value, and brings the first-level node weighted values ​​of all child levels into the corresponding node value calculation function to calculate and obtain the corresponding first root node value.

[0041] A second aspect of an embodiment of the present invention provides a device for implementing the method for calculating the total score of vehicle evaluation based on a node network model as described in the first aspect, the device comprising: a model building module, a data receiving module, a model instantiation module and a model application module;

[0042] The model building module is used to build a node network model;

[0043] The data receiving module is used to receive the vehicle evaluation project implementation details and the corresponding vehicle evaluation data set input by the user;

[0044] The model instantiation module is used to configure the node network model based on the vehicle evaluation project implementation rules to obtain a corresponding first model instance;

[0045] The model application module is used to input the vehicle evaluation data set into the first model instance to calculate and obtain the corresponding first evaluation total score and feed it back to the user.

[0046] A third aspect of an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a transceiver;

[0047] The processor is used to be coupled to the memory, read and execute instructions in the memory, so as to implement the method steps described in the first aspect above;

[0048] The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

[0049] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions. When the computer instructions are executed by a computer, the computer executes the instructions of the method described in the first aspect above.

[0050] The embodiment of the present invention provides a method, device, electronic device and computer-readable storage medium for counting the total score of vehicle evaluation based on a node network model. It can be seen from the above invention content that the embodiment of the present invention constructs a node network model with reference to the hierarchical node network of the tree structure, and designs the node value calculation function of the transmission node in the model as an optional dynamic configuration function, and provides a function library as the optional range; the node level, the number of nodes at each level and the transmission node value calculation function of this model can be dynamically adjusted, so that different model instances can be configured based on different vehicle evaluation project implementation details without changing the software program code or hardware processing components; the specific model use steps are: after receiving the vehicle evaluation project implementation details input by the user and the three-level project score set (i.e., vehicle evaluation data set) completed based on the details, firstly configure the node network model based on the details to obtain a corresponding model instance, and then input the vehicle evaluation data set into the model instance to calculate the corresponding evaluation total score. The evaluation total score calculation tool implemented based on the embodiment of the present invention does not need to be redeveloped or replaced with the old version each time the implementation details of the vehicle evaluation project are adjusted. It only needs to configure the node network model once based on the latest details to generate a new model instance for total score calculation. The embodiment of the present invention shortens the tool upgrade cycle to the maximum extent, and at the same time shortens the evaluation cycle and improves the evaluation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A schematic diagram of a method for calculating the total score of vehicle evaluation based on a node network model provided in the first embodiment of the present invention;

[0052] Figure 2 A schematic diagram of a node network model according to a first embodiment of the present invention;

[0053] Figure 3 A schematic diagram of a first model example of the first embodiment of the present invention;

[0054] Figure 4 A module structure diagram of a device for calculating vehicle evaluation total scores based on a node network model provided in Embodiment 2 of the present invention;

[0055] Figure 5 A schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] A method for calculating the total score of vehicle evaluation based on a node network model is provided in the first embodiment of the present invention. Figure 1 A schematic diagram of a method for calculating the total score of vehicle evaluation based on a node network model provided in the first embodiment of the present invention includes the following main steps:

[0058] Step 1: Build a node network model.

[0059] Here, the node network model of the embodiment of the present invention is a hierarchical node network with a tree structure; the maximum hierarchical depth of the node network model is denoted as M, and is composed of multiple nodes N and multiple node edges E; the maximum hierarchical depth M here is a positive integer and can be configured based on actual needs; the number of nodes N and node edges E can also be configured based on actual needs.

[0060] Each node N corresponds to a set of node attributes; the node attributes include node level, node identifier, parent node identifier and node value calculation function; among them, the node level is the level number of the current node, 0≤node level≤M; the node identifier is the unique identifier of the current node; the parent node identifier is the parent node identifier connected to the current node.

[0061] Each node edge E corresponds to a set of edge attributes; the edge attributes include edge identifier and edge weight; each node edge E is a directed edge, starting from a child node and connecting to its corresponding parent node; the edge identifier is the unique identifier of the current node edge; the edge weight is the weight of the child node value corresponding to the current node edge.

[0062] It should be noted that the node N with a node level of 0 in the node network model is recorded as a root node, and the number of root nodes is unique; each node N except the root node in the node network model is connected to a corresponding upper parent node through a directed node edge E, and serves as a child node of the current upper parent node, and the level difference between any child node and its corresponding upper parent node is 1; each node N in the node network model except the root node that is not connected to any child node is recorded as an input node, and the node N that is neither a root node nor an input node is recorded as a transmission node.

[0063] Each input node of the node network model is used to receive a corresponding input value x; the node value calculation function of each input node is fixed to an assignment function: y in=x,y in The node value of the current input node.

[0064] Each transmission node in the node network model is used to calculate the node value of the current node using the weighted node values ​​of all child nodes of the current node as input; and the expression of the node value calculation function that realizes this calculation function is y tr =F tr ({x a}), x a =y a × a ; Where 1≤a≤A, A is the total number of child nodes of the current transmission node; y tr is the node value of the current transmission node; x a is the weighted node value of the a-th child node of the current transmission node, specifically the node value y of the a-th child node a and the corresponding edge weight w a The product of tr is the calculation function formula of the current transmission node; it should be noted that the calculation function formula F of each transmission node in the node network model tr All can be dynamically configured based on a preset function library; the function library at least includes a multi-class summation function, a multi-class normalization function and a multi-class activation function.

[0065] The root node of the node network model is used to sum the weighted node values ​​of all child nodes and output the corresponding node values; the node value calculation function of the root node is fixed as a summation function: x b =y b × b ; Where 1≤b≤B, B is the total number of child nodes of the root node; y root is the node value of the root node; x b is the weighted node value of the b-th child node of the root node, specifically the node value y of the b-th child node b and the corresponding edge weight w b The product of .

[0066] Figure 2 The schematic diagram of the node network model of the first embodiment of the present invention provides a model example with a maximum layer depth M=3, which can be referred to Figure 2 Understand the technical details of the node network model.

[0067] Step 2: Receive the vehicle evaluation project implementation details and the corresponding vehicle evaluation data set input by the user.

[0068] Here, the implementation rules of the vehicle evaluation items in the embodiment of the present invention include a vehicle evaluation total score calculation function and G0 first-class evaluation items Pi , each category of evaluation items P i Including G i Category II evaluation items P i,j , each second-category evaluation item P i,j Including G i,j Three types of evaluation items P i,j,q ; Where G0 is a positive integer, 1≤i≤G0; each G i are all positive integers, 1≤j≤G i ; Each G i,j are all positive integers, 1≤q≤G i,j .

[0069] The vehicle evaluation total score calculation function in the rules matches the summation function of the root node of the node network model, which is used to calculate the G0 first-class evaluation items P i The weighted scores of the first category of items are summed up and the calculation result is used as the corresponding vehicle evaluation total score; among which, the weighted score of the first category of items is the corresponding first category of evaluation items P i The product of the score of a category of items and the weight of a category of items.

[0070] Each category of evaluation item P in the detailed rules i The project attributes include a type of project identification, a type of project name, a type of project score, a type of project weight and a type of score calculation function; wherein the type of project identification is the unique identification of the current type of evaluation project, the type of project name is the name of the first-level category corresponding to the current type of evaluation project, and the input of the type of score calculation function is the G corresponding to the current type of evaluation project. i Category II evaluation items P i,j The weighted scores of the second-category items are output as the corresponding scores of the first-category items; the function types of the first-category score calculation function at least include summation function, normalization function and activation function; the weighted scores of the second-category items are the corresponding second-category evaluation items P i,j The product of the second-category project score and the second-category project weight.

[0071] Each Category II evaluation item P in the detailed rules i,j The project attributes include the second-class project identifier, the second-class project name, the second-class project score, the second-class project weight and the second-class score calculation function; among them, the second-class project identifier is the unique identifier of the current second-class evaluation project, the second-class project name is the secondary class name corresponding to the current second-class evaluation project, and the input of the second-class score calculation function is the G corresponding to the current second-class evaluation project. i,j Three types of evaluation items P i,j,q The weighted scores of the three types of items are output as the corresponding scores of the two types of items; the function types of the two-type score calculation function at least include summation function, normalization function and activation function; the weighted scores of the three types of items are the corresponding three types of evaluation items Pi,j,q The product of the scores of the three categories of projects and the weights of the three categories of projects.

[0072] Each of the three evaluation items in the detailed rules i,j,q The project attributes include three types of project identification, three types of project names, three types of project scores and three types of project weights; among them, the three types of project identification is the unique identification of the current three types of evaluation projects, the three types of project names are the name information of the single evaluation project corresponding to the current three types of evaluation projects, and the three types of project scores are the specific scores obtained by the evaluators or evaluation equipment based on the evaluation requirements of the current three types of evaluation projects.

[0073] Step 3: Based on the vehicle evaluation project implementation rules, the node network model is configured to obtain a corresponding first model instance.

[0074] Here, the specific information of the first model instance obtained by configuration in the embodiment of the present invention is as follows:

[0075] 1) The maximum level depth M of the first model instance is 3;

[0076] 2) The total number of nodes in the first model instance is n sumall , the node set consists of a first root node, n sum1 First-level transmission nodes, n sum2 Secondary transmission nodes and n sum3 It consists of three-level input nodes; n sumall 、n sum1 、n sum2 、n sum3 are all positive integers;

[0077] Among them, n sumall =1+n sum1 +n sum2 +n sum3 ,

[0078]

[0079] 3) The first root node of the first model instance corresponds to the total vehicle evaluation score of the vehicle evaluation project implementation rules; the node level of the first root node is 0, the node identifier is a unique root node identifier, the upper node identifier is empty, and the node value calculation function matches the summation function of the root node of the node network model; here, the above-mentioned root node identifier can be configured based on the detailed version of the vehicle evaluation project implementation rules, and can also be configured based on a preset unique identifier generation rule;

[0080] 4) Class I evaluation item P of the first model instance's first-level transmission node and vehicle evaluation item implementation details iOne-to-one correspondence; the node level of the first-level transmission node is 1, the node identifier is the unique first-level node identifier, the upper node identifier is the root node identifier, and the node value calculation function corresponds to the first-class evaluation item P i There is a corresponding first-level directed edge from each first-level transmission node to the first root node; the first-level directed edge corresponds to the first-level transmission node one by one; the edge identifier of the first-level directed edge is a unique first-level edge identifier, and the edge weight is the same as the corresponding first-level evaluation item P i Here, the above-mentioned first-level node identification can be based on the corresponding first-class evaluation project P i The above-mentioned first-level edge identifier can be configured based on the parent-child node identifier of the current edge connection, or based on the preset unique identifier generation rule;

[0081] 5) Secondary transmission node and vehicle evaluation project implementation details of the first model instance, Category II evaluation project P i,j One-to-one correspondence; the node level of the secondary transmission node is 2, the node identifier is a unique secondary node identifier, the upper node identifier is a corresponding primary node identifier of the primary transmission node, the node value calculation function and the corresponding second-class evaluation item P i,j The second-class score calculation function matches; there is a corresponding second-class directed edge from each second-class transmission node to a corresponding first-class transmission node; the second-class directed edge corresponds to the second-class transmission node one by one; the edge identifier of the second-class directed edge is a unique second-class edge identifier, and the edge weight is the same as the corresponding second-class evaluation item P i,j Here, the above-mentioned secondary node identification can be based on the corresponding second-class evaluation project P i,j The secondary edge identifier can be configured based on the parent-child node identifier of the current edge connection, or based on the preset unique identifier generation rule;

[0082] 6) The three-level input nodes of the first model instance and the three types of evaluation items P in the implementation rules of the vehicle evaluation items i,j,q One-to-one correspondence; the node level of the third-level input node is 3, the node identifier is a unique third-level node identifier, the upper node identifier is a corresponding second-level node identifier of the second-level transmission node, and the node value calculation function matches the assignment function of the input node of the node network model; there is a corresponding third-level directed edge from each third-level transmission node to a corresponding second-level transmission node; the third-level directed edge corresponds to the third-level transmission node one-to-one; the edge identifier of the third-level directed edge is a unique third-level edge identifier, and the edge weight is the same as the corresponding three types of evaluation items P i,j,q Here, the above three-level node identification can be based on the corresponding three types of evaluation items Pi,j,q The above-mentioned three-level edge identifier can be configured based on the parent-child node identifier of the current edge connection, or based on the preset unique identifier generation rule.

[0083] Figure 3 The schematic diagram of the first model example of the first embodiment of the present invention provides an example of the first model example, which can be referred to as Figure 3 Understand the technical details of the first model instance.

[0084] In addition, if Figure 3 As shown, the data composition of the vehicle evaluation data set of the embodiment of the present invention is related to all the three-level input nodes of the first model instance. Specifically: the vehicle evaluation data set includes n sum3 Rating value x u , 1≤u≤n sum3 ; Rating value x u There is a one-to-one correspondence with the third-level input nodes of the first model instance.

[0085] Step 4: input the vehicle evaluation data set into the first model instance to calculate and obtain the corresponding first evaluation total score and provide feedback to the user;

[0086] Specifically, step 41 includes: u Input the corresponding third-level input node in the first model instance;

[0087] Step 42, the first model instance calculates the corresponding first root node value according to the input data;

[0088] Specifically, step 421 includes: each third-level input node of the first model instance converts the score value x input this time into u The corresponding node value calculation function is brought in to calculate the corresponding third-level node value, and the third-level node value is transmitted to the parent's second-level transmission node through the corresponding third-level directed edge;

[0089] Step 422, each secondary transmission node of the first model instance uses the product of the edge weight corresponding to each third-level directed edge and the third-level node value as the corresponding third-level node weighted value, and brings the third-level node weighted values ​​of all child levels into the corresponding node value calculation function to calculate the corresponding second-level node value, and transmits the second-level node value to the first-level transmission node of the parent level through the corresponding second-level directed edge;

[0090] Step 423, each first-level transmission node of the first model instance uses the product of the edge weight corresponding to each second-level directed edge and the second-level node value as the corresponding second-level node weighted value, and brings the second-level node weighted values ​​of all child levels into the corresponding node value calculation function to calculate the corresponding first-level node value, and transmits the first-level node value to the first root node of the parent level through the corresponding first-level directed edge;

[0091] Step 424: The first root node of the first model instance uses the product of the edge weight corresponding to each first-level directed edge and the first-level node value as the corresponding first-level node weight value, and brings the first-level node weight values ​​of all sub-levels into the corresponding node value calculation function to calculate and obtain the corresponding first root node value;

[0092] Step 43: Feedback the obtained first root node value to the user as the corresponding first evaluation total score.

[0093] Figure 4 The module structure diagram of a device for calculating the total score of vehicle evaluation based on a node network model provided in the second embodiment of the present invention, the device is a terminal device or server that implements the aforementioned method embodiment, and can also be a device that enables the aforementioned terminal device or server to implement the aforementioned method embodiment, for example, the device can be a device or chip system of the aforementioned terminal device or server. Figure 4 As shown, the device for calculating the total score of vehicle evaluation based on the node network model provided in the second embodiment of the present invention includes: a model construction module 201, a data receiving module 202, a model instantiation module 203 and a model application module 204.

[0094] The model building module 201 is used to build a node network model.

[0095] The data receiving module 202 is used to receive the vehicle evaluation item implementation details and the corresponding vehicle evaluation data set input by the user.

[0096] The model instantiation module 203 is used to configure the node network model based on the vehicle evaluation project implementation rules to obtain the corresponding first model instance.

[0097] The model application module 204 is used to input the vehicle evaluation data set into the first model instance to calculate and obtain the corresponding first evaluation total score and provide feedback to the user.

[0098] An embodiment of the present invention provides a device for counting the total score of vehicle evaluation based on a node network model, which can execute the method steps in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here.

[0099] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the model building module can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The function of the above-mentioned module is determined. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0100] 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 (ASIC), or one or more digital signal processors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module above is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0101] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the above method embodiments are generated. The above computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The above-mentioned computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the above-mentioned computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, Bluetooth, microwave, etc.) methods. The above-mentioned computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The above-mentioned available medium can be a magnetic medium (such as a floppy disk, a hard disk, a tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0102] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. The electronic device may be a terminal device or a server for implementing the method of the aforementioned embodiment, or may be a terminal device or a server for implementing the method of the aforementioned embodiment connected to the aforementioned terminal device or server. Figure 5 As shown, the electronic device may include: a processor 301 (such as a CPU), a memory 302, and a transceiver 303; the transceiver 303 is coupled to the processor 301, and the processor 301 controls the transceiver 303. Various instructions may be stored in the memory 302 to complete various processing functions and implement the processing steps described in the aforementioned embodiment method. Preferably, the electronic device involved in the embodiment of the present invention also includes: a power supply 304, a system bus 305 and a communication port 306. The system bus 305 is used to realize the communication connection between components. The above-mentioned communication port 306 is used for connecting and communicating between the electronic device and other peripherals.

[0103] exist Figure 5The system bus 305 mentioned in the figure can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The communication interface is used to realize the communication between the database access device and other devices (such as clients, read-write libraries, and read-only libraries). The memory may include random access memory (RAM), and may also include non-volatile memory (Non-Volatile Memory), such as at least one disk storage.

[0104] The above-mentioned processor can be a general-purpose processor, including a central processing unit CPU, a network processor (Network Processor, NP), a graphics processing unit (Graphics Processing Unit, GPU), etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0105] It should be noted that an embodiment of the present invention further provides a computer-readable storage medium, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the method and processing process provided in the above embodiments.

[0106] The embodiment of the present invention provides a method, device, electronic device and computer-readable storage medium for counting the total score of vehicle evaluation based on a node network model. It can be seen from the above invention content that the embodiment of the present invention constructs a node network model with reference to the hierarchical node network of the tree structure, and designs the node value calculation function of the transmission node in the model as an optional dynamic configuration function, and provides a function library as the optional range; the node level, the number of nodes at each level and the transmission node value calculation function of this model can be dynamically adjusted, so that different model instances can be configured based on different vehicle evaluation project implementation details without changing the software program code or hardware processing components; the specific model use steps are: after receiving the vehicle evaluation project implementation details input by the user and the three-level project score set (i.e., vehicle evaluation data set) completed based on the details, firstly configure the node network model based on the details to obtain a corresponding model instance, and then input the vehicle evaluation data set into the model instance to calculate the corresponding evaluation total score. The evaluation total score calculation tool implemented based on the embodiment of the present invention does not need to be redeveloped or replaced with the old version each time the implementation details of the vehicle evaluation project are adjusted. It only needs to configure the node network model once based on the latest details to generate a new model instance for total score calculation. The embodiment of the present invention shortens the tool upgrade cycle to the maximum extent, and at the same time shortens the evaluation cycle and improves the evaluation efficiency.

[0107] The professionals should further realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0108] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0109] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for calculating the total score of vehicle evaluation based on a node network model, characterized in that: The method comprises: Build a node network model; Receive vehicle evaluation project implementation details and corresponding vehicle evaluation data sets input by users; Based on the vehicle evaluation project implementation rules, the node network model is configured to obtain a corresponding first model instance; The vehicle evaluation data set is input into the first model instance to calculate and obtain a corresponding first evaluation total score which is fed back to the user.

2. The method for calculating the total score of vehicle evaluation based on a node network model according to claim 1, characterized in that: The maximum hierarchical depth of the node network model is denoted as M, which is composed of multiple nodes N and multiple node edges E; M is a positive integer; Each of the nodes N corresponds to a set of node attributes; the node attributes include node level, node identifier, parent node identifier and node value calculation function; the node level is the level number of the current node, 0≤node level≤M; the node identifier is the unique identifier of the current node; the parent node identifier is the parent node identifier of the current node; Each of the node edges E corresponds to a set of edge attributes; the edge attributes include edge identifiers and edge weights; each of the node edges E is a directed edge, starting from a child node and connected to its corresponding parent node; the edge identifier is the unique identifier of the current node edge; the edge weight is the child node value weight corresponding to the current node edge; The node N with the node level 0 in the node network model is recorded as a root node, and the number of the root nodes is unique; Each of the nodes N except the root node in the node network model is connected to a corresponding upper parent node through a directed node edge E and serves as a child node of the current upper parent node, and the level difference between any child node and its corresponding upper parent node is 1; In the node network model, each node N that is not connected to any child node except the root node is recorded as an input node, and the node N that is neither the root node nor the input node is recorded as a transmission node; Each of the input nodes is used to receive a corresponding input value x; the node value calculation function of each of the input nodes is fixed to an assignment function: y in =x,y in is the node value of the current input node; Each of the transmission nodes is used to calculate the node value of the current node using the weighted node values ​​of all child nodes of the current node as input; the node value calculation function of each of the transmission nodes is y tr =F tr ({x a }), x a =y a × a ; 1≤a≤A, A is the total number of child nodes of the current transmission node; y tr is the node value of the current transmission node; x a is the weighted node value of the a-th child node of the current transmission node, specifically the node value y of the a-th child node a and the corresponding edge weight w a The product of tr is the calculation function formula of the current transmission node; the calculation function formula F of each transmission node tr Dynamic configuration is performed based on a preset function library; the function library at least includes a multi-class summation function, a multi-class normalization function, and a multi-class activation function; The root node is used to sum the weighted node values ​​of all child nodes and output the corresponding node value; the node value calculation function of the root node is fixed as a summation function: x b =y b × b ; 1≤b≤B, B is the total number of child nodes of the root node; y root is the node value of the root node; b is the weighted node value of the bth child node of the root node, specifically the node value y of the bth child node b and the corresponding edge weight w b The product of .

3. The method for calculating the total vehicle evaluation score based on the node network model according to claim 2 is characterized in that: The vehicle evaluation project implementation rules include a vehicle evaluation total score calculation function and G0 first-class evaluation items P i , G0 is a positive integer, 1≤i≤G0; each of the evaluation items P i Including G i Second-class evaluation items P i,j , each G i are all positive integers, 1≤j≤G i Each of the two evaluation items P i,j Including G i,j Three types of evaluation items P i,j,q , each G i,j are all positive integers, 1≤q≤G i,j ; The vehicle evaluation total score calculation function is matched with the summation function of the root node of the node network model, and is used to calculate the total score of the vehicle evaluation items P of the first category. i The weighted scores of a category of items are summed up and the calculation result is used as the corresponding vehicle evaluation total score; the weighted score of a category of items is the corresponding category of evaluation items P i The product of the score of a category of items and the weight of a category of items; Each of the evaluation items P i The project attributes include a type of project identification, a type of project name, the type of project score, the type of project weight and a type of score calculation function; the input of the type of score calculation function is the G corresponding to the current type of evaluation project i The second category evaluation items P i,j The weighted scores of the second-category items are output as the corresponding scores of the first-category items; the function types of the first-category score calculation function at least include summation function, normalization function and activation function; the weighted scores of the second-category items are the corresponding second-category evaluation items P i,j The product of the second-category project score and the second-category project weight; Each of the two evaluation items P i,j The project attributes include the second-class project identification, the second-class project name, the second-class project score, the second-class project weight and the second-class score calculation function; the input of the second-class score calculation function is the G corresponding to the current second-class evaluation project i,j The three types of evaluation items P i,j,q The weighted scores of the three types of items are output as the corresponding scores of the two types of items; the function types of the two-type score calculation function at least include summation function, normalization function and activation function; the weighted scores of the three types of items are the corresponding three types of evaluation items P i,j,q The product of the scores of the three categories of projects and the weights of the three categories of projects; Each of the three evaluation items P i,j,q The project attributes include three types of project identifications, three types of project names, the three types of project scores and the three types of project weights; the three types of project scores are specific scores obtained by evaluators or evaluation equipment based on the evaluation requirements of the current three types of evaluation projects.

4. The method for calculating the total vehicle evaluation score based on the node network model according to claim 3 is characterized in that: The maximum level depth M of the first model instance is 3; The total number of nodes in the first model instance is n sumall , the node set consists of a first root node, n sum1 First-level transmission nodes, n sum2 Secondary transmission nodes and n sum3 It consists of three-level input nodes; n sumall 、n sum1 、n sum2 、n sum3 are all positive integers; Among them, n sumall =1+n sum1 +n sum2 +n sum3 , The first root node corresponds to the total score of the vehicle evaluation in the vehicle evaluation project implementation rules; the node level of the first root node is 0, the node identifier is a unique root node identifier, the upper node identifier is empty, and the node value calculation function matches the summation function of the root node of the node network model; The first-level transmission node and the first type of evaluation item P i One-to-one correspondence; the node level of the first-level transmission node is 1, the node identifier is a unique first-level node identifier, the upper-level node identifier is the root node identifier, the node value calculation function is the corresponding first-class evaluation item P i There is a corresponding first-level directed edge from each of the first-level transmission nodes to the first root node; the first-level directed edges correspond to the first-level transmission nodes one by one; the edge identifier of the first-level directed edge is a unique first-level edge identifier, and the edge weight is the same as the corresponding first-level evaluation item P i The weight of the said type of project is matched; The secondary transmission node and the second type of evaluation item P i,j One-to-one correspondence; the node level of the secondary transmission node is 2, the node identifier is a unique secondary node identifier, the upper node identifier is a corresponding primary node identifier of the primary transmission node, the node value calculation function and the corresponding second-class evaluation item P i,j The second-class score calculation function matches; there is a corresponding second-class directed edge from each of the second-class transmission nodes to a corresponding first-class transmission node; the second-class directed edges correspond to the second-class transmission nodes one by one; the edge identifier of the second-class directed edge is a unique second-class edge identifier, and the edge weight is the same as the corresponding second-class evaluation item P i,j The weights of the two types of items are matched; The three-level input nodes and the three types of evaluation items P i,j,q One-to-one correspondence; the node level of the three-level input node is 3, the node identifier is a unique three-level node identifier, the upper node identifier is the secondary node identifier of a corresponding secondary transmission node, and the node value calculation function matches the assignment function of the input node of the node network model; there is a corresponding three-level directed edge from each of the three-level transmission nodes to a corresponding secondary transmission node; the three-level directed edges correspond to the three-level transmission nodes one-to-one; the edge identifier of the three-level directed edges is a unique three-level edge identifier, and the edge weights are the same as the corresponding three types of evaluation items P i,j,q The weights of the three categories of projects are matched.

5. The method for calculating the total score of vehicle evaluation based on a node network model according to claim 4, characterized in that: The vehicle evaluation dataset includes n sum3 Rating value x u , 1≤u≤n sum3 ; The score value x u There is a one-to-one correspondence with the third-level input nodes of the first model instance.

6. The method for calculating the total vehicle evaluation score based on the node network model according to claim 5, characterized in that: The step of inputting the vehicle evaluation data set into the first model instance to calculate and obtain a corresponding first evaluation total score and feeding it back to the user specifically includes: The score values ​​x of the vehicle evaluation data set are u Input the corresponding third-level input node in the first model instance; The first model instance calculates the corresponding first root node value according to the input data; The obtained first root node value is fed back to the user as the corresponding first evaluation total score.

7. The method for calculating the total vehicle evaluation score based on the node network model according to claim 6, characterized in that: The first model instance calculates the corresponding first root node value according to the current input data, specifically including: Each of the third-level input nodes of the first model instance converts the score value x input this time into u Bring in the corresponding node value calculation function to calculate and obtain the corresponding third-level node value, and transmit the third-level node value to the second-level transmission node of the parent through the corresponding third-level directed edge; Each of the second-level transmission nodes of the first model instance uses the product of the edge weight corresponding to each of the third-level directed edges and the third-level node value as the corresponding third-level node weighted value, and brings the third-level node weighted values ​​of all child levels into the corresponding node value calculation function to calculate and obtain the corresponding second-level node value, and transmits the second-level node value to the first-level transmission node of the parent level through the corresponding second-level directed edge; Each of the first-level transmission nodes of the first model instance uses the product of the edge weight corresponding to each of the second-level directed edges and the second-level node value as the corresponding second-level node weighted value, and brings the second-level node weighted values ​​of all child levels into the corresponding node value calculation function to calculate and obtain the corresponding first-level node value, and transmits the first-level node value to the first root node of the parent level through the corresponding first-level directed edge; The first root node of the first model instance takes the product of the edge weight corresponding to each of the first-level directed edges and the first-level node value as the corresponding first-level node weighted value, and brings the first-level node weighted values ​​of all child levels into the corresponding node value calculation function to calculate and obtain the corresponding first root node value.

8. A device for executing the method for calculating the total vehicle evaluation score based on a node network model according to any one of claims 1 to 7, characterized in that: The device comprises: a model building module, a data receiving module, a model instantiation module and a model application module; The model building module is used to build a node network model; The data receiving module is used to receive the vehicle evaluation project implementation details and the corresponding vehicle evaluation data set input by the user; The model instantiation module is used to configure the node network model based on the vehicle evaluation project implementation rules to obtain a corresponding first model instance; The model application module is used to input the vehicle evaluation data set into the first model instance to calculate and obtain the corresponding first evaluation total score and feed it back to the user.

9. An electronic device, characterized in that: include: memory, processors, and transceivers; The processor is used to couple with the memory, read and execute instructions in the memory, so as to implement the method according to any one of claims 1 to 7; The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a computer, the computer is enabled to execute the method according to any one of claims 1 to 7.

Images