摘要：【中文】一种超声波诊断装置，具有在超声波图像数据和超声波以外的医用图像数据之间进行配准处理的功能，其具备：图像生成部，对于在第一超声波图像数据和第一医用图像数据之间进行配准处理所需的第一配准参数，利用在所述第一超声波图像数据和第二超声波图像数据之间进行配准处理所需的第二配准参数，生成与所述第二超声波图像配准的第二医用图像数据；以及图像配准部，对上述第二超声波图像数据和上述第二医用图像数据进行配准处理，生成结合图像。 【EN】An ultrasonic diagnostic apparatus having a function of performing registration processing between ultrasonic image data and medical image data other than ultrasonic waves, comprising: an image generation unit that generates second medical image data registered with a second ultrasound image by using a first registration parameter required for performing registration processing between first ultrasound image data and second ultrasound image data, the first registration parameter being required for performing registration processing between the first ultrasound image data and the first medical image data; and an image registration unit configured to perform registration processing on the second ultrasound image data and the second medical image data to generate a combined image.

摘要：【中文】本申请实施例公开了一种基于对抗样本增强模型抗攻击能力的方法和系统。所述方法包括：获取第一样本和第二样本，其中，所述第一样本与所述第二样本的相似度大于相似度阈值；将所述第一样本和所述第二样本输入第一模型，得到与所述第一样本对应的第一输出，以及与所述第二样本对应的第二输出；基于所述第一输出与所述第二输出的差异程度，调整所述第二样本，以增大所述差异程度，并在所述差异程度满足预设条件时，将调整后的所述第二样本作为对抗样本；基于该对抗样本，调整第二模型，以增强所述第二模型的抗攻击能力。其中，第二模型可以为用于对理赔证据图片进行识别的神经网络模型，理赔证据图片包括理赔者的个人信息图片。 【EN】The embodiment of the application discloses a method and a system for enhancing the anti-attack capability of a model based on a confrontation sample. The method comprises the following steps: acquiring a first sample and a second sample, wherein the similarity of the first sample and the second sample is greater than a similarity threshold; inputting the first sample and the second sample into a first model to obtain a first output corresponding to the first sample and a second output corresponding to the second sample; adjusting the second sample based on the difference degree of the first output and the second output to increase the difference degree, and taking the adjusted second sample as a confrontation sample when the difference degree meets a preset condition; based on the challenge samples, the second model is adjusted to enhance the challenge resistance of the second model. The second model can be a neural network model for identifying the claim evidence picture, and the claim evidence picture comprises a personal information picture of a claim.

摘要：【中文】本发明提供用于图像配准的医用图像诊断装置、医用图像诊断方法及超声波诊断装置。本发明的医用图像诊断装置，进行被检体的医用图像数据间的图像配准，其特征在于，具有：提取部，提取上述医用图像数据中包括的被检体的构造物；尺度设定部，将上述构造物的显示尺度设定为规定值；以及图像配准部，在上述规定值的显示尺度下进行上述医用图像数据间的图像配准。 【EN】The invention provides a medical image diagnosis apparatus, a medical image diagnosis method and an ultrasonic diagnosis apparatus for image registration. A medical image diagnostic apparatus according to the present invention performs image registration between medical image data of a subject, and includes: an extraction unit that extracts a structure of a subject included in the medical image data; a dimension setting unit that sets a display dimension of the structure to a predetermined value; and an image registration unit that performs image registration between the medical image data at the display scale of the predetermined value.

摘要：【中文】本申请实施例公开了一种基于对抗样本增强模型抗攻击能力的方法和系统。所述方法包括：获取目标样本；将所述目标样本输入第一模型，得到对应于所述目标样本的输出；调整所述目标样本，以降低所述目标样本的所述输出中的前N个最大的输出值，其中，所述N是正整数，所述输出值用于表征所述目标样本属于所述输出值对应类别的概率；在所述输出满足预设条件时，将调整后的所述目标样本作为对抗样本；基于该对抗样本，调整第二模型，以增强所述第二模型的抗攻击能力。其中，第二模型可以为用于对理赔证据图片进行识别的神经网络模型，理赔证据图片包括理赔者的个人信息图片以及理赔商品的图片。 【EN】The embodiment of the application discloses a method and a system for enhancing the anti-attack capability of a model based on a confrontation sample. The method comprises the following steps: obtaining a target sample; inputting the target sample into a first model, resulting in an output corresponding to the target sample; adjusting the target sample to reduce the first N largest output values in the output of the target sample, wherein N is a positive integer, and the output values are used for representing the probability that the target sample belongs to the corresponding class of the output values; when the output meets a preset condition, taking the adjusted target sample as a confrontation sample; based on the challenge samples, the second model is adjusted to enhance the challenge resistance of the second model. The second model can be a neural network model for identifying the claim evidence picture, and the claim evidence picture comprises a personal information picture of a claim and a picture of a claim commodity.

摘要：【中文】本说明书实施例公开了一种基于对抗样本增强模型抗攻击能力的方法和系统，所述方法包括：获取目标样本的集合；将所述集合中的每一所述目标样本输入目标模型，得到与所述目标样本对应的第一输出；在所述第一输出大于或等于输出阈值时，将所述目标模型的所述第一输出对应的标签作为所述目标样本的目标标签；利用所述目标样本的集合和所述目标样本对应的所述目标标签训练替代模型；将候选样本输入所述替代模型，得到对应于所述候选样本的第二输出，并基于该第二输出调整所述候选样本以得到对抗样本；基于该对抗样本，调整所述目标模型。其中，目标模型可以为用于对图片进行识别的神经网络模型，所述图片包括个人信息图片。 【EN】The embodiment of the specification discloses a method and a system for enhancing the attack resistance of a model based on a confrontation sample, wherein the method comprises the following steps: acquiring a set of target samples; inputting each target sample in the set into a target model to obtain a first output corresponding to the target sample; when the first output is greater than or equal to an output threshold value, taking a label corresponding to the first output of the target model as a target label of the target sample; training a substitution model by using the set of target samples and the target labels corresponding to the target samples; inputting the candidate sample into the surrogate model to obtain a second output corresponding to the candidate sample, and adjusting the candidate sample based on the second output to obtain a confrontation sample; based on the confrontation samples, the target model is adjusted. The target model may be a neural network model for identifying pictures, including personal information pictures.

摘要：【中文】本申请实施例提供一种镜片检测装置，涉及光学检测技术领域。该镜片检测装置包括固定机构和激光检测机构：所述固定机构用于固定所述镜片；所述镜片设置有调节器，所述调节器用于调节所述镜片的偏转角度；所述激光检测机构设置于所述固定机构的前方，用于检测所述镜片偏转时的角度数据。该镜片检测装置可以实现提高检测精度和检测效率，以及降低生产成本的技术效果。 【EN】The embodiment of the application provides a lens detection device, and relates to the technical field of optical detection. This lens detection device includes fixed establishment and laser detection mechanism: the fixing mechanism is used for fixing the lens; the lens is provided with an adjuster which is used for adjusting the deflection angle of the lens; the laser detection mechanism is arranged in front of the fixing mechanism and used for detecting angle data of the lens during deflection. The lens detection device can achieve the technical effects of improving detection precision and detection efficiency and reducing production cost.

摘要：【中文】本发明公开一种含乳双歧杆菌BL‑99的固体饮料及其应用。具体而言，本发明提供了一种固体饮料组合物，以固体饮料的总重量为100％计，其原料组成中包括：保藏编号CGMCC No.15650的乳双歧杆菌(Bifidobacterium lactis)或其活性物质0.1％～50％；麦芽糊精10％～20％。本发明的固体饮料具有促进肠道消化、通便的功效。 【EN】The invention discloses a solid beverage containing bifidobacterium lactis BL-99 and application thereof. Specifically, the invention provides a solid beverage composition, which comprises the following raw materials by weight percent based on 100 percent of the total weight of the solid beverage: bifidobacterium lactis (Bifidobacterium lactis) with the preservation number of CGMCC No.15650 or 0.1-50% of active substances thereof; 10 to 20 percent of maltodextrin. The solid beverage has the effects of promoting intestinal digestion and relaxing bowels.

摘要：【中文】本发明实施例提供自移动售货机器人、控制方法及交互方法。其中，自移动售货机器人，包括：放置架，用于放置陈列品；盖板，设置在所述放置架上部；可移动底座，设置在所述放置架底部，驱动所述自移动售货机器人移动；所述放置架设有活动件，所述活动件执行动作防止所述陈列品倾倒。本发明实施例提供的技术方案，在自移动售货机器人移动时，通过活动件可有效防止陈列品倾倒。 【EN】The embodiment of the invention provides a self-moving vending robot, a control method and an interaction method. Wherein, from removing vending machine people includes: the placing rack is used for placing the exhibit; the cover plate is arranged on the upper part of the placing rack; the movable base is arranged at the bottom of the placing rack and drives the self-moving vending robot to move; the placing rack is provided with a moving part, and the moving part executes actions to prevent the display from toppling. According to the technical scheme provided by the embodiment of the invention, when the self-moving vending robot moves, the display can be effectively prevented from toppling over through the movable part.

摘要：【中文】本发明一种复合材料用鳞形密齿金刚石涂层铣刀，刀体上周向设置若干周刃，周刃相互之间形成右螺旋排屑槽，右螺旋排屑槽上设有浅槽形结构的保护刀棱，刀体上通过右螺旋排屑槽形成周刃刃背，周刃刃背上设有左旋的左螺旋排屑槽，刀体前端端部设置若干端刃，端刃相互之间形成容屑槽。本发明提供的复合材料用鳞形密齿金刚石涂层铣刀，采用左、右螺旋交叉鳞形结构，左、右螺旋排屑槽槽底均呈圆弧状，增大排屑空间，增加切屑的流动速度，通过右旋锋利面与左旋倒钝面实现切屑的切除与挤削，保证被加工表面的平整，无毛刺和分层现象，减小每齿材料去除量，涂覆多层金刚石涂层，增强刀具表面的硬度，降低刀具磨损，提高加工切削速度和材料去除效率。 【EN】The invention relates to a scale-shaped dense-tooth diamond coating milling cutter for a composite material, wherein a plurality of peripheral blades are circumferentially arranged on a cutter body, right spiral chip grooves are formed among the peripheral blades, protective edges of a shallow groove structure are arranged on the right spiral chip grooves, peripheral blade back bodies are formed on the cutter body through the right spiral chip grooves, left-handed left spiral chip grooves are arranged on the peripheral blade back bodies, a plurality of end blades are arranged at the front end of the cutter body, and chip grooves are formed among the end blades. The scale-shaped dense-tooth diamond coating milling cutter for the composite material adopts a left and right spiral crossed scale-shaped structure, the bottoms of the left and right spiral chip removal grooves are arc-shaped, the chip removal space is enlarged, the flow speed of chips is increased, the cutting and the extrusion of the chips are realized through a right-handed sharp surface and a left-handed inverted blunt surface, the smoothness of the processed surface is ensured, no burr and layering phenomenon exist, the removal amount of materials of each tooth is reduced, a plurality of layers of diamond coatings are coated, the hardness of the surface of a cutter is enhanced, the abrasion of the cutter is reduced, and the processing cutting speed and the material removal efficiency are improved.

摘要：【中文】本发明涉及激光加工领域，尤其涉及一种激光头空移控制方法及控制系统，所述控制方法包括以下步骤：确定激光头空移的起点以及终点；在激光头空移抬起到下降过程中，通过激光头的X轴、Y轴进行插补运动，使激光头的抬起轨迹和下降轨迹均呈现为弧形轨迹；确定激光头基于空移时间段的路径。在激光头抬起到下降的过程中，通过控制激光头的X轴、Y轴进行插补运动，即可缩短激光头的运动路径，从而减少的激光头空移的时间，提高生产效率。 【EN】The invention relates to the field of laser processing, in particular to a laser head idle movement control method and a control system, wherein the control method comprises the following steps: determining the starting point and the end point of the laser head idle movement; in the process of lifting and descending the laser head in the idle movement mode, interpolation motion is carried out through an X axis and a Y axis of the laser head, so that the lifting track and the descending track of the laser head are both arc tracks; determining a path of the laser head based on the idle time period. In the process that the laser head is lifted to descend, the X axis and the Y axis of the laser head are controlled to perform interpolation motion, so that the motion path of the laser head can be shortened, the idle moving time of the laser head is shortened, and the production efficiency is improved.