Performance dynamic evaluation method and device, equipment, storage medium and program product
By collecting and analyzing employee sales and behavioral data, and combining various algorithms and blockchain technology, a dynamic weight table is generated, which solves the problem of inaccurate performance evaluation results and achieves a fairer and more accurate performance evaluation.
Patent Information
- Application Number
- CN202511266105.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-05
- Publication Date
- 2026-01-30
AI Technical Summary
Existing performance appraisal methods are too simplistic, resulting in inaccurate evaluation results, high error rates, and an inability to reasonably reflect the performance of employees or departments.
By collecting sales and behavioral data through a customer relationship management system, extracting semantic features by combining a pre-trained language model and encoder, calculating dynamic weight vectors using ELO scoring and PageRank algorithms, and verifying them with Shapley values and a blockchain system, a dynamic weight table is generated and hashed to achieve multi-dimensional performance evaluation.
It improves the accuracy and fairness of performance evaluation, can adapt to the rapidly changing market environment, reduces the risk of data tampering, and ensures the transparency and credibility of evaluation results.
Smart Images
Figure CN121436736A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to a method, apparatus, device, storage medium, and program product for dynamic performance evaluation. Background Technology
[0002] To measure whether employees or departments have achieved their sales targets and to transform their efforts and results into quantifiable data, companies, especially those designing and selling technology products, need to evaluate the performance of their employees or departments. This is to incentivize high-performing employees and motivate low-performing employees, encourage continuous improvement, and ensure that employees' work aligns with the company's overall sales strategy and business objectives.
[0003] However, the relevant performance evaluation methods are too simplistic in terms of evaluation dimensions, such as only covering sales revenue, which leads to inaccurate evaluation results, a high error rate, and is not reasonable for the performance evaluation of employees or departments. Summary of the Invention
[0004] This disclosure is made in view of the above-mentioned problems and provides a method, apparatus, device, storage medium and program product for dynamic performance evaluation.
[0005] According to one aspect of this disclosure, a dynamic performance evaluation method is provided, comprising: Sales data of employees is collected through a customer relationship management system, and behavioral data of employees is collected through external data collection devices. The behavioral data includes the communication process and completion rate of employees providing technical services to customers. Obtain the historical score data of the employee's sales behavior and its innovation value in the current market, and calculate the innovation parameters corresponding to the sales behavior based on the historical score data and innovation value; Based on the innovation parameters, calculate the weight ratio of each evaluation indicator in the performance evaluation, and obtain the dynamic weight vector corresponding to each evaluation indicator. Based on the sales data and the behavioral data, obtain the data corresponding to each of the evaluation indicators; The performance evaluation results of the employees are obtained by weighting the data corresponding to each evaluation indicator using the dynamic weight vector.
[0006] By assessing the innovation value of a sales activity in the current market, we can determine the importance of current market changes and historical experience to that activity. For example, when the innovation value exceeds a certain threshold, it indicates that the sales activity is highly innovative, and current market changes may be more important. In this case, we can appropriately increase the innovation parameter corresponding to the sales activity to take a more balanced view of "history" and "present," making the final performance evaluation results fairer, more accurate, and more adaptable to a rapidly changing environment, and rewarding innovation.
[0007] By setting multiple evaluation indicators, it is possible to go beyond just sales revenue and assign different dynamic weight vectors to each evaluation indicator by calculating dynamic weight vectors. This can improve the accuracy of performance evaluation results and provide a more reasonable and accurate evaluation method.
[0008] Furthermore, according to a dynamic performance evaluation method of one aspect of this disclosure, based on the historical scoring data and innovation value, innovation parameters corresponding to the sales behavior are calculated, including: If the innovation value is less than or equal to a preset threshold, then based on the historical scoring data, the innovation parameter corresponding to the sales behavior is confirmed as the first value; If the innovation value is greater than a preset threshold, the proportion of the historical scoring data is reduced, and the innovation parameter corresponding to the sales behavior is a second value, which is greater than the first value. Furthermore, according to one aspect of the performance dynamic evaluation method of this disclosure, it also includes: The historical scoring data is cleaned; Obtain unstructured data from the cleaned historical scoring data, and preprocess the unstructured data; Semantic features of the pre-processed unstructured data are extracted using a pre-trained language model, and the dimensionality of the semantic features is compressed using an encoder.
[0009] Extracting semantic features and compressing dimensionality using a pre-trained language model can improve the accuracy of dynamic weight vector calculation. For example, the pre-trained language model achieves an F1 score of 0.89 for extracting semantic features from work orders, and the Transformer encoder can compress the feature dimension to 32 dimensions, improving the accuracy of multidimensional association analysis by 42%.
[0010] Furthermore, according to one aspect of the performance dynamic evaluation method of this disclosure, based on the innovation parameters, the weight ratio of each evaluation indicator in the performance evaluation is calculated, and the dynamic weight vector corresponding to each evaluation indicator is obtained, including: Based on the innovation parameters, confirm the weight of the historical scoring data and the current market in calculating the dynamic weight vector; By combining the ELO scoring algorithm and the PageRank algorithm, and based on the historical scoring data and the current market share, the weight of each evaluation indicator in the performance evaluation is calculated, and the dynamic weight vector corresponding to each evaluation indicator is obtained.
[0011] By combining the ELO scoring algorithm and the PageRank algorithm, the static calculation deficiency of the PageRank algorithm is overcome, and the dynamic weight vector is updated in real time, which helps to improve the evaluation accuracy.
[0012] Furthermore, according to one aspect of the performance dynamic evaluation method disclosed herein, it also includes: Keywords in the strategic framework are extracted using a pre-trained language model, and the priority of each keyword is calculated using the entropy method. Based on the keywords and their priorities, a strategic decoding engine is used to calculate strategic objectives and corresponding performance indicators. The contribution weight of each department to each of the aforementioned performance indicators is calculated using the Shapley value, and a dynamic weight table is generated. The dynamic weight table includes the strategic objectives, the performance indicators corresponding to each of the aforementioned strategic objectives, and the contribution weight of each department to each of the aforementioned performance indicators. The dynamic weight table is verified through the consensus verification mechanism of the blockchain system to confirm the accuracy of the contribution weight allocation.
[0013] Using Shapley values to calculate the contribution weight of each department to each performance indicator can shorten the response time of the strategic decoding engine and improve data processing efficiency.
[0014] Furthermore, according to one aspect of the performance dynamic evaluation method disclosed herein, it also includes: If the dynamic weight table passes verification, hash the dynamic weight table and the performance evaluation result to generate a hash value. The hash value is verified using the consensus verification mechanism of the blockchain system; If the hash value passes verification, the dynamic weight table and the performance evaluation result are stored in the blockchain system, and blockchain storage information is generated.
[0015] By using hash-based sharding for storage, with each shard not exceeding 1KB in size, and generating hash values for evidence storage, the risk of data tampering can be reduced, and the data recovery integrity rate can be guaranteed.
[0016] According to another aspect of this disclosure, a dynamic performance evaluation device is provided, comprising: The data collection module is used to collect sales data from employees through the customer relationship management system and to collect behavioral data from employees through external data collection devices. The behavioral data includes the communication process and completion rate of employees providing technical services to customers. The innovation parameter calculation module is used to obtain the historical score data of the employee's sales behavior and the innovation value in the current market, and calculate the innovation parameters corresponding to the sales behavior based on the historical score data and the innovation value. The weight calculation module is used to calculate the weight ratio of each evaluation indicator in the performance evaluation based on the innovation parameters, and to obtain the dynamic weight vector corresponding to each evaluation indicator. The acquisition module is used to acquire data corresponding to each of the evaluation indicators based on the sales data and the behavioral data; The evaluation module is used to perform weighted calculations on the data corresponding to each evaluation indicator using the dynamic weight vector to obtain the performance evaluation results of the employee.
[0017] According to another aspect of this disclosure, a computer device is provided, including a memory, a processor, and a computer program stored in the memory, the processor executing the computer program to implement the method of one aspect above.
[0018] According to another aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the method of one aspect above.
[0019] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method of the above-described aspect.
[0020] It should be understood that both the foregoing general description and the following detailed description are exemplary and intended to provide further illustration of the claimed technology. Attached Figure Description
[0021] The above and other objects, features, and advantages of this disclosure will become more apparent from the more detailed description of the embodiments thereof in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this disclosure and form part of the specification. They are used together with the embodiments of this disclosure to explain the disclosure and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.
[0022] Figure 1 This is a flowchart illustrating a dynamic performance evaluation method according to an embodiment of this disclosure.
[0023] Figure 2This is a system architecture diagram illustrating a dynamic performance evaluation method applied according to an embodiment of this disclosure.
[0024] Figure 3 This is a flowchart illustrating an application example according to an embodiment of this disclosure.
[0025] Figure 4 This is a schematic diagram of the structure of a performance dynamic evaluation device according to an embodiment of the present disclosure.
[0026] Figure 5 This is a schematic diagram illustrating the structure of a computer device according to an embodiment of the present disclosure.
[0027] Figure 6 This is a schematic diagram illustrating a computer program product according to an embodiment of the present disclosure. Detailed Implementation
[0028] To make the objectives, technical solutions, and advantages of this disclosure more apparent, exemplary embodiments according to this disclosure will now be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this disclosure, and not all embodiments of this disclosure. It should be understood that this disclosure is not limited to the exemplary embodiments described herein.
[0029] To measure whether employees or departments have achieved their sales targets and to transform their efforts and results into quantifiable data, companies, especially those designing and selling technology products, need to evaluate the performance of their employees or departments. This is to incentivize high-performing employees and motivate low-performing employees, encourage continuous improvement, and ensure that employees' work aligns with the company's overall sales strategy and business objectives.
[0030] However, the relevant performance evaluation methods are too simplistic in terms of evaluation dimensions, such as only covering sales revenue, which leads to inaccurate evaluation results, a high error rate, and is not reasonable for the performance evaluation of employees or departments.
[0031] In addition, there is the problem of data silos: the allocation of KPI weights across departments relies on human experience, which has a high error rate.
[0032] The above description, with reference to the accompanying drawings, illustrates a dynamic performance evaluation method, apparatus, device, storage medium, and program product according to embodiments of the present disclosure. By analyzing the innovation value of a sales activity in the current market, the importance of current market changes and historical experience to the sales activity can be determined. For example, when the innovation value exceeds a certain threshold, it indicates that the sales activity is highly innovative, and the changes in the current market may be more important. In this case, the innovation parameter corresponding to the sales activity can be appropriately increased to more balance the "history" and "present," making the final calculated performance evaluation result fairer, more accurate, and more adaptable to a rapidly changing environment, while also rewarding innovation.
[0033] By setting multiple evaluation indicators, it is possible to go beyond just sales revenue and assign different dynamic weight vectors to each evaluation indicator by calculating dynamic weight vectors. This can improve the accuracy of performance evaluation results and provide a more reasonable and accurate evaluation method.
[0034] Extracting semantic features and compressing dimensionality using a pre-trained language model can improve the accuracy of dynamic weight vector calculation. For example, the pre-trained language model achieves an F1 score of 0.89 for extracting semantic features from work orders, and the Transformer encoder can compress the feature dimension to 32 dimensions, improving the accuracy of multidimensional association analysis by 42%.
[0035] By combining the ELO scoring algorithm and the PageRank algorithm, the static calculation deficiency of the PageRank algorithm is overcome, and real-time dynamic updates of the dynamic weight vector are achieved, which helps improve the evaluation accuracy. Verification shows that the error rate of weight allocation does not exceed 3%, which is beneficial to improving evaluation accuracy.
[0036] Using Shapley values to calculate the contribution weight of each department to each performance indicator can shorten the response time of the strategic decoding engine and improve data processing efficiency.
[0037] By using hash-based sharding storage, with each shard not exceeding 1KB in size, a hash value for evidence storage is generated, which reduces the risk of data tampering (verified to reduce the risk of data tampering by 99%) and ensures a high data recovery integrity rate.
[0038] To facilitate understanding of this embodiment, a detailed description of the dynamic performance evaluation method disclosed in this disclosure is provided first. The execution entity of the dynamic performance evaluation method provided in this disclosure is generally a computer device with a certain computing capability. This computer device may include, for example, a terminal device, a server, or other processing devices. The terminal device may be a user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, in-vehicle device, wearable device, etc. In some possible implementations, this dynamic performance evaluation method can be implemented by a processor calling computer-readable instructions stored in memory.
[0039] like Figure 1 The diagram shows a flowchart of a dynamic performance evaluation method provided in this embodiment of the present disclosure, the method comprising S101-S105: S101: Collect employee sales data through the customer relationship management system and employee behavior data through external data collection devices.
[0040] Sales data is collected through a Customer Relationship Management (CRM) system, including data such as sales orders and customer profiles. This data is synchronized in real-time (T+1) via a RESTful API interface to ensure its timeliness and accuracy. Behavioral data is collected through external devices, such as customer visit videos. This data includes the interaction process and completion rate of employees providing technical services to customers. It is primarily used to record key information about technical services, completion rates, and interactions with customers. External collection devices can be AR glasses, cameras, etc., and the collection frequency can be set, such as 5 seconds per frame.
[0041] S102: Obtain historical score data of employees' sales behavior and innovation value in the current market, and calculate the innovation parameters corresponding to the sales behavior based on the historical score data and innovation value.
[0042] By assessing the innovation value of a sales activity in the current market, we can determine the importance of current market changes and historical experience to that activity. For example, when the innovation value exceeds a certain threshold, it indicates that the sales activity is highly innovative, and current market changes may be more important. In this case, we can appropriately increase the innovation parameter corresponding to the sales activity to take a more balanced view of "history" and "present," making the final performance evaluation results fairer, more accurate, and more adaptable to a rapidly changing environment, and rewarding innovation.
[0043] In one or more embodiments, S102 further includes: If the innovation value is less than or equal to the preset threshold, the innovation parameter corresponding to the sales behavior is confirmed as the first value based on historical scoring data; if the innovation value is greater than the preset threshold, the proportion of historical scoring data is reduced, and the innovation parameter corresponding to the sales behavior is the second value, which is greater than the first value.
[0044] Specifically, the preset threshold can be selected according to actual needs. For example, in this embodiment, the preset threshold is set to 0.8. If the innovation value is greater than 0.8, then the innovation parameter λ = 0.02 (weight penalty coefficient); otherwise, the innovation parameter λ = 0.01. The calculated dynamic weight vector is applied to the sales performance evaluation system, including multiple evaluation indicators such as sales revenue, customer conversion rate, and order response time, to achieve dynamic weight allocation of multi-dimensional performance evaluation indicators.
[0045] S103: Based on the innovation parameters, calculate the weight ratio of each evaluation indicator in the performance evaluation, and obtain the dynamic weight vector corresponding to each evaluation indicator.
[0046] In one or more embodiments, S103 further includes: Based on the innovation parameters, confirm the weight of historical scoring data and the current market when calculating the dynamic weight vector; By combining the ELO scoring algorithm and the PageRank algorithm, and based on historical scoring data and the current market share, the weight of each evaluation indicator in the performance evaluation is calculated, and the dynamic weight vector corresponding to each evaluation indicator is obtained.
[0047] By combining the ELO scoring algorithm and the PageRank algorithm, the static calculation deficiency of the PageRank algorithm is overcome, and real-time dynamic updates of the dynamic weight vector are achieved, which helps improve the evaluation accuracy. Verification shows that the error rate of weight allocation does not exceed 3%, which is beneficial to improving evaluation accuracy.
[0048] S104: Based on sales data and behavioral data, obtain the data corresponding to each evaluation indicator.
[0049] S105: Use dynamic weight vectors to weight the data corresponding to each evaluation indicator to obtain the employee's performance evaluation results.
[0050] In one or more embodiments, it further includes: The historical scoring data is cleaned; Obtain unstructured data from the cleaned historical scoring data, and preprocess the unstructured data; The semantic features of the pre-trained unstructured data are extracted using a pre-trained language (Bidirectional Encoder Representations from Transformers, BERT) model, and the dimension of the semantic features is compressed using an encoder.
[0051] Compressing the dimensions of semantic features includes: processing unstructured data (such as work order descriptions), extracting semantic features using the BERT model, and then compressing the feature dimensions of semantic features through Transformer encoding. For example, the feature dimensions can be compressed to 32 dimensions to improve the accuracy of multidimensional association analysis.
[0052] In one or more embodiments, it further includes: Keywords in the strategic framework are extracted using a pre-trained language (BERT) model, and the priority of each keyword is calculated using the entropy method. Based on keywords and their priorities, the strategic decoding engine is used to calculate strategic objectives and corresponding performance indicators. The Shapley value is used to calculate the contribution weight of each department to each performance indicator and generate a dynamic weight table. The dynamic weight table includes strategic objectives, the performance indicators corresponding to each strategic objective, and the contribution weight of each department to each performance indicator. The consensus verification mechanism of the blockchain system is used to verify the dynamic weight table and confirm the accuracy of the contribution weight allocation.
[0053] The strategic framework can be in XML format. Keyword extraction is performed using the BERT model, and the priority of each keyword is calculated using the entropy method to parse the strategic framework. Shapley values are used to calculate the contribution weight of each department to each performance indicator, which can shorten the response time of the strategic decoding engine and improve data processing efficiency. The dynamic weight table is verified through the consensus verification mechanism of the blockchain system, ensuring the rationality and fairness of the contribution weight allocation.
[0054] In one or more embodiments, it further includes: If the dynamic weight table passes verification, hash the dynamic weight table and the performance evaluation results to generate a hash value. The hash value is verified using the consensus verification mechanism of the blockchain system; If the hash value passes verification, the dynamic weight table and performance evaluation results are stored in the blockchain system, and blockchain storage information is generated.
[0055] The CID-1024 hash shards are generated and stored using the IPFS (InterPlanetary File System) distributed storage system to ensure the security and traceability of the hash values. A consensus verification mechanism is used to verify the hash values, ensuring the immutability of the data on the blockchain. Furthermore, the performance evaluation results generated from the blockchain-based evidence storage can be fed back to relevant personnel, facilitating transparent and trustworthy management of sales performance evaluation results.
[0056] The performance improvement of the evaluation method in this embodiment compared with other technologies is shown in Table 1: Table 1 Performance Improvement Status
[0057] like Figure 2 The diagram shown is a system architecture diagram of the dynamic performance evaluation method provided in this embodiment of the disclosure, including a data acquisition layer 1, an intelligent analysis layer 2, a decision-making layer 3, and an evidence storage layer 4. Specifically: Data Acquisition Layer 1: (1) Collect sales data from the CRM system's data interface (RESTful API); Data types: sales orders, customer profiles, etc.; Update frequency: T+1 real-time synchronization; (2) Collect behavioral data from external data acquisition devices (AR glasses); Data type: Customer visit video (MP4 / H.265); Acquisition frequency: 5 seconds / frame; Intelligent Analysis Layer 2: (3) ELO scoring algorithm module Input data: Historical rating data (CSV / IPFS); Output data: Dynamic weight vector and performance evaluation results (JSON format); (4) BERT+Transformer hybrid model Input data: Unstructured data (such as work order descriptions); Output data: semantic features (DIM=32); Decision-making level 3: (5) Strategic Decoding Engine Input data: OKR strategic framework (XML format) Output data: Dynamic weight table (Excel format) Evidence layer 4: (6) IPFS+PBFT Evidence Storage System Evidence storage format: CID-1024 hash value; Consensus verification: 3-node PBFT network, specifically: Node 1: Weight Calculation (TF-IDF Algorithm); Node 2: Result Validation (Shapley Value Analysis); Node 3: Final signature (ECDSA encryption).
[0058] Based on the above embodiments, this embodiment also provides an application example, specifically applied to equipment manufacturing enterprises. The flowchart of the application example is as follows. Figure 3 As shown, including S301~S305: S301: Clean the collected historical scoring data.
[0059] Specifically, cleaning can be done using a missing value filling algorithm.
[0060] S302: Standardize historical scoring data.
[0061] Specifically, unstructured data is preprocessed, semantic features are extracted using the BERT model, and then feature compression is performed using the Transformer encoder. Structured data includes sales figures and customer conversion rates, while unstructured data includes video summaries of customer visit videos.
[0062] Tests showed that in the equipment manufacturing industry, BERT achieved an F1 score of 0.89 for extracting semantic features, and the dimensionality was compressed to 32 after Transformer encoding, improving the accuracy of multidimensional association analysis by 42%.
[0063] S303: Innovative parameter λ is dynamically adjusted.
[0064] Specifically, if the innovation value is greater than 0.8, then λ = 0.02, which is the weight penalty coefficient of the ELO scoring algorithm; otherwise, λ = 0.01, which is the default value of the ELO scoring algorithm.
[0065] S304: Input structured and unstructured data into the dynamic weight engine and output a dynamic weight vector in JSON format.
[0066] The structured data consists of sales data such as sales revenue and customer conversion rate, while the unstructured data consists of video summaries of customer visit videos. The dynamic weight engine is a fusion architecture formed by combining the ELO scoring algorithm and the PageRank improved model.
[0067] The dynamic weighting engine uses the formula: R_new = R_old + K×(S - E) to calculate the new ELO score, where K is the adjustment factor, S is the actual score, and E is the expected score. Specifically: Basic weighting: Sales revenue 30% + Conversion rate 40% + Response time 30%; Strategic adjustment: During the new product promotion period, the weight of conversion rate is increased to 50%.
[0068] The existing PageRank algorithm has the defect of static calculation of node importance. This embodiment introduces the ELO scoring algorithm, and realizes the real-time update of dynamic weight vector through the formula R_new=R_old+K×(SE), where K is the adjustment coefficient.
[0069] S305: Blockchain Evidence Storage: The SHA-256 hash value of the performance evaluation result is uploaded to the blockchain, and the PBFT consensus verification pass rate is 100%.
[0070] The storage uses CID-1024 hash shards, each ≤1KB. After the 3-node PBFT network reaches consensus, it generates SHA-256 evidence hash, and the data recovery integrity rate is ≥99.99%.
[0071] According to another aspect of the embodiments of this disclosure, a dynamic performance evaluation device is provided, such as... Figure 4 As shown, the device includes: The data acquisition module 401 is used to collect sales data of employees through the customer relationship management system and to collect behavioral data of employees through external data acquisition devices. The behavioral data includes the communication process and completion rate of employees providing technical services to customers. The innovation parameter calculation module 402 is used to obtain the historical score data of the employee's sales behavior and the innovation value in the current market, and calculate the innovation parameters corresponding to the sales behavior based on the historical score data and the innovation value. The weight calculation module 403 is used to calculate the weight ratio of each evaluation indicator in the performance evaluation based on the innovation parameters, and to obtain the dynamic weight vector corresponding to each evaluation indicator. The acquisition module 404 is used to acquire data corresponding to each of the evaluation indicators based on the sales data and the behavioral data; The evaluation module 405 is used to perform weighted calculations on the data corresponding to each evaluation indicator using the dynamic weight vector to obtain the performance evaluation results of the employee.
[0072] In one or more embodiments, the innovation parameter calculation module 402 includes: If the innovation value is less than or equal to a preset threshold, then based on the historical scoring data, the innovation parameter corresponding to the sales behavior is confirmed as the first value; If the innovation value is greater than a preset threshold, the proportion of the historical scoring data is reduced, and the innovation parameter corresponding to the sales behavior is a second value, which is greater than the first value.
[0073] The dynamic performance evaluation device is also used for: The historical scoring data is cleaned; Obtain unstructured data from the cleaned historical scoring data, and preprocess the unstructured data; Semantic features of the pre-processed unstructured data are extracted using a pre-trained language model, and the dimensionality of the semantic features is compressed using an encoder.
[0074] In one or more embodiments, the weight calculation module 403 includes: Based on the innovation parameters, confirm the weight of the historical scoring data and the current market in calculating the dynamic weight vector; By combining the ELO scoring algorithm and the PageRank algorithm, and based on the historical scoring data and the current market share, the weight of each evaluation indicator in the performance evaluation is calculated, and the dynamic weight vector corresponding to each evaluation indicator is obtained.
[0075] The dynamic performance evaluation device is also used for: Keywords in the strategic framework are extracted using a pre-trained language model, and the priority of each keyword is calculated using the entropy method. Based on the keywords and their priorities, a strategic decoding engine is used to calculate strategic objectives and corresponding performance indicators. The contribution weight of each department to each of the aforementioned performance indicators is calculated using the Shapley value, and a dynamic weight table is generated. The dynamic weight table includes the strategic objectives, the performance indicators corresponding to each of the aforementioned strategic objectives, and the contribution weight of each department to each of the aforementioned performance indicators. The dynamic weight table is verified through the consensus verification mechanism of the blockchain system to confirm the accuracy of the contribution weight allocation.
[0076] In one or more embodiments, the dynamic performance evaluation device is further used for: If the dynamic weight table passes verification, hash the dynamic weight table and the performance evaluation result to generate a hash value. The hash value is verified using the consensus verification mechanism of the blockchain system; If the hash value passes verification, the dynamic weight table and the performance evaluation result are stored in the blockchain system, and blockchain storage information is generated.
[0077] The performance dynamic evaluation device and the performance dynamic evaluation method provided in this disclosure are based on the same inventive concept and have the same beneficial effects as the methods they adopt, operate or implement.
[0078] This disclosure also provides a computer device for performing the above-described dynamic performance evaluation method. Please refer to... Figure 5 It illustrates a schematic diagram of a computer device provided by some embodiments of this disclosure. For example... Figure 5 As shown, the computer device 50 includes: a processor 500, a memory 501, a bus 502, and a communication interface 503. The processor 500, the communication interface 503, and the memory 501 are connected via the bus 502. The memory 501 stores a computer program that can run on the processor 500. When the processor 500 runs the computer program, it executes the dynamic performance evaluation method provided in any of the foregoing embodiments of this disclosure.
[0079] The memory 501 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this device network element and at least one other network element is achieved through at least one communication interface 503 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc.
[0080] Bus 502 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory 501 is used to store programs. After receiving an execution instruction, the processor 500 executes the program. The dynamic performance evaluation method disclosed in any of the foregoing embodiments of this disclosure can be applied to the processor 500, or implemented by the processor 500.
[0081] The processor 500 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 500 or by instructions in software form. The processor 500 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPTA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this disclosure. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this disclosure can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 501. The processor 500 reads the information in memory 501 and, in conjunction with its hardware, completes the steps of the above method.
[0082] The computer device and the performance dynamic evaluation method provided in this disclosure are based on the same inventive concept and have the same beneficial effects as the methods they adopt, operate or implement.
[0083] This disclosure also provides a computer-readable storage medium corresponding to the performance dynamic evaluation method provided in the foregoing embodiments. The computer-readable storage medium is an optical disc, on which a computer program (i.e., a computer program product) is stored. When the computer program is run by a processor, it executes the performance dynamic evaluation method provided in any of the foregoing embodiments.
[0084] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here.
[0085] The computer-readable storage medium provided in the above embodiments of this disclosure and the performance dynamic evaluation method provided in the embodiments of this disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the applications stored therein.
[0086] This disclosure also provides a computer program product; please refer to [link / reference]. Figure 6 The computer program product 600 carries program code, namely computer program 601. The instructions included in the computer program 601 can be used to execute the steps of the dynamic performance evaluation method described in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.
[0087] The aforementioned computer program product can be implemented through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied in a computer storage medium; in another optional embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.
[0088] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.
[0089] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.
[0090] Additionally, as used herein, the "or" used in a list of items beginning with "at least one" indicates a separate list, such that a list of, for example, "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not imply that the described example is preferred or better than other examples.
[0091] It should also be noted that in the systems and methods of this disclosure, the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions to this disclosure.
[0092] Various changes, substitutions, and modifications can be made to the technology described herein without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, events, means, methods, and actions described above. Currently existing or later-developed processes, machines, manufactures, events, means, methods, or actions that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein can be utilized. Therefore, the appended claims include such processes, machines, manufactures, events, means, methods, or actions within their scope.
[0093] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.
[0094] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.
Claims
1. A method of dynamically assessing performance, characterized by, The method comprises the following steps: Collecting sales data of employees through a customer relationship management system, and collecting behavior data of employees through an external collection device, wherein the behavior data includes communication process and completion degree of employees providing technical services for customers; Obtaining historical score data of sales behavior of the employees and innovation value in the current market, and calculating an innovation parameter corresponding to the sales behavior based on the historical score data and the innovation value; According to the innovation parameter, calculating the weight proportion of each evaluation index in performance evaluation, and obtaining a dynamic weight vector corresponding to each evaluation index; Based on the sales data and the behavior data, obtaining data corresponding to each evaluation index; Using the dynamic weight vector to perform weighted calculation on the data corresponding to each evaluation index, and obtaining a performance evaluation result of the employees.
2. The performance dynamic assessment method of claim 1, wherein, Based on the historical score data and the innovation value, the innovation parameter corresponding to the sales behavior is calculated, which comprises: If the innovation value is less than or equal to a preset threshold, the innovation parameter corresponding to the sales behavior is determined as a first value according to the historical score data; If the innovation value is greater than the preset threshold, the proportion of the historical score data is reduced, the innovation parameter corresponding to the sales behavior is a second value, and the second value is greater than the first value.
3. The performance dynamic assessment method of claim 1, wherein, Further comprising: Cleaning the historical score data; Obtaining unstructured data in the cleaned historical score data, and preprocessing the unstructured data; Using a pre-trained language model to extract semantic features of the preprocessed unstructured data, and compressing the dimensions of the semantic features through an encoder.
4. The performance dynamic assessment method of claim 1, wherein, According to the innovation parameter, the weight proportion of each evaluation index in performance evaluation is calculated, and a dynamic weight vector corresponding to each evaluation index is obtained, which comprises: According to the innovation parameter, the proportion of the historical score data and the current market in calculating the dynamic weight vector is determined; Combining the ELO score algorithm and the PageRank algorithm, the weight proportion of each evaluation index in performance evaluation is calculated according to the proportion of the historical score data and the current market, and a dynamic weight vector corresponding to each evaluation index is obtained.
5. The performance dynamic assessment method of claim 1, wherein, Further comprising: Extracting keywords in a strategic framework through a pre-trained language model, and calculating the priority of each keyword using an entropy method; Based on the keywords and the priority of each keyword, a strategic decoding engine is used to calculate strategic objectives and performance indicators corresponding to each strategic objective; Using Shapley value to calculate the contribution weight of each department to each performance indicator, and generating a dynamic weight table, wherein the dynamic weight table comprises the strategic objectives, performance indicators corresponding to each strategic objective, and the contribution weight of each department to each performance indicator; The dynamic weight table is verified through a consensus verification mechanism of a blockchain system to confirm the accuracy of the contribution weight distribution.
6. The performance dynamic assessment method of claim 5, wherein, Further comprising: If the dynamic weight table passes the verification, the dynamic weight table and the performance evaluation result are subjected to hash processing to generate a hash value; The hash value is verified by using a consensus verification mechanism of a blockchain system. If the hash value is verified, the dynamic weight table and the performance evaluation result are notarized to the blockchain system, and blockchain notarization information is generated.
7. A performance dynamic evaluation device, characterized by, Comprise: The acquisition module is used for acquiring the sales data of the employee through a customer relationship management system and acquiring the behavior data of the employee through an external acquisition device, the behavior data including an exchange process and completion degree of the employee in providing technical services for a customer; The innovation parameter calculation module is used for acquiring historical score data of the sales behavior of the employee and an innovation value in a current market, and calculating an innovation parameter corresponding to the sales behavior based on the historical score data and the innovation value; The weight calculation module is used for calculating a weight proportion of each evaluation index in performance evaluation according to the innovation parameter, and obtaining a dynamic weight vector corresponding to each evaluation index; The acquisition module is used for acquiring data corresponding to each evaluation index based on the sales data and the behavior data; The evaluation module is used for performing weighted calculation on the data corresponding to each evaluation index by using the dynamic weight vector, and obtaining a performance evaluation result of the employee.
8. A computer-embedded device comprising a memory, a processor and a computer program stored on the memory, characterized in that, The processor executes the computer program to implement the method of any one of claims 1-6.
9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the method of any one of claims 1-6.
10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the method of any one of claims 1-6.