A semantic analysis-driven customer requirements mining method for product conceptual design.

Precise customer requirements acquisition is the primary stage of product conceptual design, which plays a decisive role in product quality and innovation. However, existing customer requirements mining approaches pay attention to the offline or online customer comment feedback and there has been little quantitative analysis of customer requirements in the analogical reasoning environment. Latent and innovative customer requirements can be expressed by analogical inspiration distinctly. In response, this paper proposes a semantic analysis-driven customer requirements mining method for product conceptual design based on deep transfer learning and improved latent Dirichlet allocation (ILDA). Initially, an analogy-inspired verbal protocol analysis experiment is implemented to obtain detailed customer requirements descriptions of elevator. Then, full connection layers and a softmax layer are added to the output-end of Chinese bidirectional encoder representations from Transformers (BERT) pre-training language model. The above deep transfer model is utilized to realize the customer requirements classification among functional domain, behavioral domain and structural domain in the customer requirement descriptions of elevator by fine-tuning training. Moreover, the ILDA is adopted to mine the functional customer requirements that can represent customer intention maximally. Finally, an effective accuracy of customer requirements classification is acquired by using the BERT deep transfer model. Meanwhile, five kinds of customer requirements of elevator and corresponding keywords as well as their weight coefficients in the topic-word distribution are extracted. This work can provide a novel research perspective on customer requirements mining for product conceptual design through natural language processing.

[Clinical efficacy of posterior percutaneous endoscopic cervical discectomy for single level cervical spondylopathy with intraspinal ossification].

OBJECTIVE: To evaluate the effectiveness and security of posterior percutaneous endoscopic cervical discectomy (PPECD) in the treatment of single level cervical spondylopathy with intraspinal ossification. METHODS: Twenty three patients with single level cervical spondylopathy with intraspinal ossification were treated by posterior percutaneous endoscopic cervical discectomy between August 2017 and July 2019. There were 16 males and 7 females, aged from 29 to 74 years old with an average of (50±13) years.The disease duration were 3 to 120 months with a median of 6 months. There were 9 cases of cervical spondylotic radiculopathy, 6 cases of cervical spondylotic myelopathy, and 8 cases of mixed cervical spondylopathy. According to the characteristics of ossification, 17 cases were osteophytes on the posterior edge of the vertebral body;3 cases were protrusion ossification;3 cases were posterior longitudinal ligament ossification. According to the position of ossification in spinal canal, 14 cases were medial and lateral type, 5 cases were central type, and 4 cases were mixed type. Posterior percutaneous cervical endoscopic cervical discectomy in patients performed by the same surgeon. Japanese Orthopaedic Association (JOA) score and visual analogue scale(VAS) were compared separately before and after operation. At 3 months after operation, clinical effect was assessed according to modified Macnab standard. RESULTS: All operations were successful. The operative time was 30 to 155 (69.1±27.2) min. The bedridden time was 2 to 3(3.0±0.9) h, length of postoperative hospitalization was 2 to 7(4.1± 1.5) d. Three dimensional CT reconstruction of the cervical spine at 3 days after operation showed that ossified tissue of 13 cases were completely removed, and 10 cases were left after operation, and the residual was located at the posterior edge and/or center of the upper vertebral body. VAS score at discharge from hospital was significantly lower than that before operation (t=9.35, P<0.001), and 21 cases had a score of 0 to 3. Postoperative JOA score was significantly higher (t=7.29, P<0.001). At 3 months after operation, according to modified Macnab standard to evaluate clinical effect, 18 cases got exellent results, 4 good and 1 fair, with an excellent and good rate of 95.6%(22/23). CONCLUSION: For an experienced surgeon, percutaneous posterior cervical endoscopic discectomy is safe and reliable in treating single level cervical spondylopathy with intraspinal ossification, and can obtain good clinical results.